summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c1
-rw-r--r--net/8021q/vlan_dev.c52
-rw-r--r--net/batman-adv/bat_iv_ogm.c2
-rw-r--r--net/batman-adv/distributed-arp-table.c3
-rw-r--r--net/batman-adv/fragmentation.c11
-rw-r--r--net/batman-adv/gateway_client.c11
-rw-r--r--net/batman-adv/hard-interface.c2
-rw-r--r--net/batman-adv/multicast.c6
-rw-r--r--net/batman-adv/originator.c62
-rw-r--r--net/bluetooth/hci_conn.c9
-rw-r--r--net/bluetooth/hci_event.c6
-rw-r--r--net/bluetooth/l2cap_core.c4
-rw-r--r--net/bridge/br_fdb.c8
-rw-r--r--net/bridge/br_input.c4
-rw-r--r--net/bridge/br_netfilter.c4
-rw-r--r--net/bridge/br_netlink.c15
-rw-r--r--net/bridge/br_private.h7
-rw-r--r--net/bridge/br_vlan.c28
-rw-r--r--net/can/gw.c4
-rw-r--r--net/ceph/messenger.c20
-rw-r--r--net/ceph/osdmap.c14
-rw-r--r--net/core/dev.c133
-rw-r--r--net/core/filter.c23
-rw-r--r--net/core/neighbour.c4
-rw-r--r--net/core/net_namespace.c2
-rw-r--r--net/core/rtnetlink.c86
-rw-r--r--net/core/skbuff.c4
-rw-r--r--net/core/sock.c49
-rw-r--r--net/core/sock_diag.c4
-rw-r--r--net/core/utils.c8
-rw-r--r--net/dcb/dcbnl.c2
-rw-r--r--net/decnet/dn_dev.c4
-rw-r--r--net/decnet/dn_fib.c4
-rw-r--r--net/decnet/netfilter/dn_rtmsg.c2
-rw-r--r--net/dsa/dsa.c3
-rw-r--r--net/ipv4/af_inet.c36
-rw-r--r--net/ipv4/fib_semantics.c2
-rw-r--r--net/ipv4/inet_connection_sock.c8
-rw-r--r--net/ipv4/ip_forward.c54
-rw-r--r--net/ipv4/ip_fragment.c5
-rw-r--r--net/ipv4/ip_output.c51
-rw-r--r--net/ipv4/ip_tunnel.c6
-rw-r--r--net/ipv4/ip_vti.c5
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c5
-rw-r--r--net/ipv4/ping.c6
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c42
-rw-r--r--net/ipv4/tcp_cubic.c2
-rw-r--r--net/ipv4/tcp_input.c11
-rw-r--r--net/ipv4/tcp_output.c14
-rw-r--r--net/ipv4/xfrm4_output.c32
-rw-r--r--net/ipv4/xfrm4_protocol.c19
-rw-r--r--net/ipv6/ip6_fib.c3
-rw-r--r--net/ipv6/ip6_offload.c6
-rw-r--r--net/ipv6/ip6_output.c8
-rw-r--r--net/ipv6/ip6_tunnel.c2
-rw-r--r--net/ipv6/ip6_vti.c8
-rw-r--r--net/ipv6/ip6mr.c2
-rw-r--r--net/ipv6/ndisc.c7
-rw-r--r--net/ipv6/netfilter.c6
-rw-r--r--net/ipv6/netfilter/ip6t_rpfilter.c1
-rw-r--r--net/ipv6/output_core.c11
-rw-r--r--net/ipv6/route.c26
-rw-r--r--net/ipv6/tcpv6_offload.c2
-rw-r--r--net/ipv6/xfrm6_output.c22
-rw-r--r--net/ipv6/xfrm6_protocol.c11
-rw-r--r--net/iucv/af_iucv.c2
-rw-r--r--net/mac80211/ieee80211_i.h1
-rw-r--r--net/mac80211/mlme.c20
-rw-r--r--net/mac80211/offchannel.c27
-rw-r--r--net/mac80211/rx.c3
-rw-r--r--net/mac80211/sta_info.c3
-rw-r--r--net/mac80211/status.c5
-rw-r--r--net/mac80211/trace.h4
-rw-r--r--net/mac80211/util.c2
-rw-r--r--net/mac80211/vht.c9
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c15
-rw-r--r--net/netfilter/nf_conntrack_netlink.c3
-rw-r--r--net/netfilter/nf_tables_core.c49
-rw-r--r--net/netfilter/nfnetlink.c11
-rw-r--r--net/netlink/af_netlink.c80
-rw-r--r--net/netlink/genetlink.c2
-rw-r--r--net/packet/diag.c7
-rw-r--r--net/phonet/pn_netlink.c8
-rw-r--r--net/rxrpc/ar-key.c2
-rw-r--r--net/sched/act_api.c2
-rw-r--r--net/sched/cls_api.c2
-rw-r--r--net/sched/cls_tcindex.c30
-rw-r--r--net/sched/sch_api.c6
-rw-r--r--net/sched/sch_hhf.c11
-rw-r--r--net/sctp/protocol.c7
-rw-r--r--net/sctp/sm_sideeffect.c7
-rw-r--r--net/tipc/netlink.c2
-rw-r--r--net/vmw_vsock/af_vsock.c47
-rw-r--r--net/wireless/scan.c12
-rw-r--r--net/wireless/sme.c2
-rw-r--r--net/xfrm/xfrm_user.c2
97 files changed, 956 insertions, 443 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 175273f38cb..44ebd5c2cd4 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -169,6 +169,7 @@ int register_vlan_dev(struct net_device *dev)
if (err < 0)
goto out_uninit_mvrp;
+ vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1;
err = register_netdevice(dev);
if (err < 0)
goto out_uninit_mvrp;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 733ec283ed1..019efb79708 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -493,48 +493,10 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
}
}
-static int vlan_calculate_locking_subclass(struct net_device *real_dev)
-{
- int subclass = 0;
-
- while (is_vlan_dev(real_dev)) {
- subclass++;
- real_dev = vlan_dev_priv(real_dev)->real_dev;
- }
-
- return subclass;
-}
-
-static void vlan_dev_mc_sync(struct net_device *to, struct net_device *from)
-{
- int err = 0, subclass;
-
- subclass = vlan_calculate_locking_subclass(to);
-
- spin_lock_nested(&to->addr_list_lock, subclass);
- err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
- if (!err)
- __dev_set_rx_mode(to);
- spin_unlock(&to->addr_list_lock);
-}
-
-static void vlan_dev_uc_sync(struct net_device *to, struct net_device *from)
-{
- int err = 0, subclass;
-
- subclass = vlan_calculate_locking_subclass(to);
-
- spin_lock_nested(&to->addr_list_lock, subclass);
- err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
- if (!err)
- __dev_set_rx_mode(to);
- spin_unlock(&to->addr_list_lock);
-}
-
static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
{
- vlan_dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
- vlan_dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+ dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+ dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
}
/*
@@ -562,6 +524,11 @@ static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass)
netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass);
}
+static int vlan_dev_get_lock_subclass(struct net_device *dev)
+{
+ return vlan_dev_priv(dev)->nest_level;
+}
+
static const struct header_ops vlan_header_ops = {
.create = vlan_dev_hard_header,
.rebuild = vlan_dev_rebuild_header,
@@ -597,7 +564,6 @@ static const struct net_device_ops vlan_netdev_ops;
static int vlan_dev_init(struct net_device *dev)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
- int subclass = 0;
netif_carrier_off(dev);
@@ -646,8 +612,7 @@ static int vlan_dev_init(struct net_device *dev)
SET_NETDEV_DEVTYPE(dev, &vlan_type);
- subclass = vlan_calculate_locking_subclass(dev);
- vlan_dev_set_lockdep_class(dev, subclass);
+ vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev));
vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
@@ -819,6 +784,7 @@ static const struct net_device_ops vlan_netdev_ops = {
.ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup,
#endif
.ndo_fix_features = vlan_dev_fix_features,
+ .ndo_get_lock_subclass = vlan_dev_get_lock_subclass,
};
void vlan_setup(struct net_device *dev)
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index b3bd4ec3fd9..f04224c3200 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -1545,6 +1545,8 @@ out_neigh:
if ((orig_neigh_node) && (!is_single_hop_neigh))
batadv_orig_node_free_ref(orig_neigh_node);
out:
+ if (router_ifinfo)
+ batadv_neigh_ifinfo_free_ref(router_ifinfo);
if (router)
batadv_neigh_node_free_ref(router);
if (router_router)
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index b25fd64d727..aa5d4946d0d 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -940,8 +940,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
* additional DAT answer may trigger kernel warnings about
* a packet coming from the wrong port.
*/
- if (batadv_is_my_client(bat_priv, dat_entry->mac_addr,
- BATADV_NO_FLAGS)) {
+ if (batadv_is_my_client(bat_priv, dat_entry->mac_addr, vid)) {
ret = true;
goto out;
}
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index bcc4bea632f..f14e54a0569 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -418,12 +418,13 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
struct batadv_neigh_node *neigh_node)
{
struct batadv_priv *bat_priv;
- struct batadv_hard_iface *primary_if;
+ struct batadv_hard_iface *primary_if = NULL;
struct batadv_frag_packet frag_header;
struct sk_buff *skb_fragment;
unsigned mtu = neigh_node->if_incoming->net_dev->mtu;
unsigned header_size = sizeof(frag_header);
unsigned max_fragment_size, max_packet_size;
+ bool ret = false;
/* To avoid merge and refragmentation at next-hops we never send
* fragments larger than BATADV_FRAG_MAX_FRAG_SIZE
@@ -483,7 +484,11 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
skb->len + ETH_HLEN);
batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
- return true;
+ ret = true;
+
out_err:
- return false;
+ if (primary_if)
+ batadv_hardif_free_ref(primary_if);
+
+ return ret;
}
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index c835e137423..90cff585b37 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -42,8 +42,10 @@
static void batadv_gw_node_free_ref(struct batadv_gw_node *gw_node)
{
- if (atomic_dec_and_test(&gw_node->refcount))
+ if (atomic_dec_and_test(&gw_node->refcount)) {
+ batadv_orig_node_free_ref(gw_node->orig_node);
kfree_rcu(gw_node, rcu);
+ }
}
static struct batadv_gw_node *
@@ -406,9 +408,14 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv,
if (gateway->bandwidth_down == 0)
return;
+ if (!atomic_inc_not_zero(&orig_node->refcount))
+ return;
+
gw_node = kzalloc(sizeof(*gw_node), GFP_ATOMIC);
- if (!gw_node)
+ if (!gw_node) {
+ batadv_orig_node_free_ref(orig_node);
return;
+ }
INIT_HLIST_NODE(&gw_node->list);
gw_node->orig_node = orig_node;
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index b851cc58085..fbda6b54baf 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -83,7 +83,7 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
return true;
/* no more parents..stop recursion */
- if (net_dev->iflink == net_dev->ifindex)
+ if (net_dev->iflink == 0 || net_dev->iflink == net_dev->ifindex)
return false;
/* recurse over the parent device */
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 8c7ca811de6..96b66fd30f9 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -415,7 +415,7 @@ batadv_mcast_forw_ipv4_node_get(struct batadv_priv *bat_priv)
hlist_for_each_entry_rcu(tmp_orig_node,
&bat_priv->mcast.want_all_ipv4_list,
mcast_want_all_ipv4_node) {
- if (!atomic_inc_not_zero(&orig_node->refcount))
+ if (!atomic_inc_not_zero(&tmp_orig_node->refcount))
continue;
orig_node = tmp_orig_node;
@@ -442,7 +442,7 @@ batadv_mcast_forw_ipv6_node_get(struct batadv_priv *bat_priv)
hlist_for_each_entry_rcu(tmp_orig_node,
&bat_priv->mcast.want_all_ipv6_list,
mcast_want_all_ipv6_node) {
- if (!atomic_inc_not_zero(&orig_node->refcount))
+ if (!atomic_inc_not_zero(&tmp_orig_node->refcount))
continue;
orig_node = tmp_orig_node;
@@ -493,7 +493,7 @@ batadv_mcast_forw_unsnoop_node_get(struct batadv_priv *bat_priv)
hlist_for_each_entry_rcu(tmp_orig_node,
&bat_priv->mcast.want_all_unsnoopables_list,
mcast_want_all_unsnoopables_node) {
- if (!atomic_inc_not_zero(&orig_node->refcount))
+ if (!atomic_inc_not_zero(&tmp_orig_node->refcount))
continue;
orig_node = tmp_orig_node;
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index ffd9dfbd9b0..6a484514cd3 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -501,12 +501,17 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
{
struct batadv_orig_ifinfo *orig_ifinfo;
+ struct batadv_neigh_node *router;
orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu);
if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing);
+ /* this is the last reference to this object */
+ router = rcu_dereference_protected(orig_ifinfo->router, true);
+ if (router)
+ batadv_neigh_node_free_ref_now(router);
kfree(orig_ifinfo);
}
@@ -702,6 +707,47 @@ free_orig_node:
}
/**
+ * batadv_purge_neigh_ifinfo - purge obsolete ifinfo entries from neighbor
+ * @bat_priv: the bat priv with all the soft interface information
+ * @neigh: orig node which is to be checked
+ */
+static void
+batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv,
+ struct batadv_neigh_node *neigh)
+{
+ struct batadv_neigh_ifinfo *neigh_ifinfo;
+ struct batadv_hard_iface *if_outgoing;
+ struct hlist_node *node_tmp;
+
+ spin_lock_bh(&neigh->ifinfo_lock);
+
+ /* for all ifinfo objects for this neighinator */
+ hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
+ &neigh->ifinfo_list, list) {
+ if_outgoing = neigh_ifinfo->if_outgoing;
+
+ /* always keep the default interface */
+ if (if_outgoing == BATADV_IF_DEFAULT)
+ continue;
+
+ /* don't purge if the interface is not (going) down */
+ if ((if_outgoing->if_status != BATADV_IF_INACTIVE) &&
+ (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) &&
+ (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED))
+ continue;
+
+ batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+ "neighbor/ifinfo purge: neighbor %pM, iface: %s\n",
+ neigh->addr, if_outgoing->net_dev->name);
+
+ hlist_del_rcu(&neigh_ifinfo->list);
+ batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
+ }
+
+ spin_unlock_bh(&neigh->ifinfo_lock);
+}
+
+/**
* batadv_purge_orig_ifinfo - purge obsolete ifinfo entries from originator
* @bat_priv: the bat priv with all the soft interface information
* @orig_node: orig node which is to be checked
@@ -800,6 +846,11 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
hlist_del_rcu(&neigh_node->list);
batadv_neigh_node_free_ref(neigh_node);
+ } else {
+ /* only necessary if not the whole neighbor is to be
+ * deleted, but some interface has been removed.
+ */
+ batadv_purge_neigh_ifinfo(bat_priv, neigh_node);
}
}
@@ -857,7 +908,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
{
struct batadv_neigh_node *best_neigh_node;
struct batadv_hard_iface *hard_iface;
- bool changed;
+ bool changed_ifinfo, changed_neigh;
if (batadv_has_timed_out(orig_node->last_seen,
2 * BATADV_PURGE_TIMEOUT)) {
@@ -867,10 +918,10 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
jiffies_to_msecs(orig_node->last_seen));
return true;
}
- changed = batadv_purge_orig_ifinfo(bat_priv, orig_node);
- changed = changed || batadv_purge_orig_neighbors(bat_priv, orig_node);
+ changed_ifinfo = batadv_purge_orig_ifinfo(bat_priv, orig_node);
+ changed_neigh = batadv_purge_orig_neighbors(bat_priv, orig_node);
- if (!changed)
+ if (!changed_ifinfo && !changed_neigh)
return false;
/* first for NULL ... */
@@ -1028,7 +1079,8 @@ int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface);
out:
- batadv_hardif_free_ref(hard_iface);
+ if (hard_iface)
+ batadv_hardif_free_ref(hard_iface);
return 0;
}
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index d958e2dca52..521fd4f3985 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -819,14 +819,17 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
struct hci_cp_auth_requested cp;
- /* encrypt must be pending if auth is also pending */
- set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
-
cp.handle = cpu_to_le16(conn->handle);
hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED,
sizeof(cp), &cp);
+
+ /* If we're already encrypted set the REAUTH_PEND flag,
+ * otherwise set the ENCRYPT_PEND.
+ */
if (conn->key_type != 0xff)
set_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
+ else
+ set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
}
return 0;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 49774912cb0..15010a230b6 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3330,6 +3330,12 @@ static void hci_key_refresh_complete_evt(struct hci_dev *hdev,
if (!conn)
goto unlock;
+ /* For BR/EDR the necessary steps are taken through the
+ * auth_complete event.
+ */
+ if (conn->type != LE_LINK)
+ goto unlock;
+
if (!ev->status)
conn->sec_level = conn->pending_sec_level;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index a1e5bb7d06e..dc4d301d3a7 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -7519,9 +7519,9 @@ int __init l2cap_init(void)
l2cap_debugfs = debugfs_create_file("l2cap", 0444, bt_debugfs,
NULL, &l2cap_debugfs_fops);
- debugfs_create_u16("l2cap_le_max_credits", 0466, bt_debugfs,
+ debugfs_create_u16("l2cap_le_max_credits", 0644, bt_debugfs,
&le_max_credits);
- debugfs_create_u16("l2cap_le_default_mps", 0466, bt_debugfs,
+ debugfs_create_u16("l2cap_le_default_mps", 0644, bt_debugfs,
&le_default_mps);
bt_6lowpan_init();
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 9203d5a1943..474d36f9334 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -487,6 +487,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
{
struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
struct net_bridge_fdb_entry *fdb;
+ bool fdb_modified = false;
/* some users want to always flood. */
if (hold_time(br) == 0)
@@ -507,10 +508,15 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
source->dev->name);
} else {
/* fastpath: update of existing entry */
- fdb->dst = source;
+ if (unlikely(source != fdb->dst)) {
+ fdb->dst = source;
+ fdb_modified = true;
+ }
fdb->updated = jiffies;
if (unlikely(added_by_user))
fdb->added_by_user = 1;
+ if (unlikely(fdb_modified))
+ fdb_notify(br, fdb, RTM_NEWNEIGH);
}
} else {
spin_lock(&br->hash_lock);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 7985deaff52..04d6348fd53 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -147,8 +147,8 @@ static int br_handle_local_finish(struct sk_buff *skb)
struct net_bridge_port *p = br_port_get_rcu(skb->dev);
u16 vid = 0;
- br_vlan_get_tag(skb, &vid);
- if (p->flags & BR_LEARNING)
+ /* check if vlan is allowed, to avoid spoofing */
+ if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid))
br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
return 0; /* process further */
}
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 80e1b0f60a3..2acf7fa1fec 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -859,12 +859,12 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
return NF_STOLEN;
}
-#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4)
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
static int br_nf_dev_queue_xmit(struct sk_buff *skb)
{
int ret;
- if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) &&
+ if (skb->protocol == htons(ETH_P_IP) &&
skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu &&
!skb_is_gso(skb)) {
if (br_parse_ip_options(skb))
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index e74b6d530cb..e8844d975b3 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -445,6 +445,20 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
return 0;
}
+static int br_dev_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ struct net_bridge *br = netdev_priv(dev);
+
+ if (tb[IFLA_ADDRESS]) {
+ spin_lock_bh(&br->lock);
+ br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
+ spin_unlock_bh(&br->lock);
+ }
+
+ return register_netdevice(dev);
+}
+
static size_t br_get_link_af_size(const struct net_device *dev)
{
struct net_port_vlans *pv;
@@ -473,6 +487,7 @@ struct rtnl_link_ops br_link_ops __read_mostly = {
.priv_size = sizeof(struct net_bridge),
.setup = br_dev_setup,
.validate = br_validate,
+ .newlink = br_dev_newlink,
.dellink = br_dev_delete,
};
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 06811d79f89..59d3a85c587 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -581,6 +581,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
struct sk_buff *skb, u16 *vid);
bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v,
const struct sk_buff *skb);
+bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid);
struct sk_buff *br_handle_vlan(struct net_bridge *br,
const struct net_port_vlans *v,
struct sk_buff *skb);
@@ -648,6 +649,12 @@ static inline bool br_allowed_egress(struct net_bridge *br,
return true;
}
+static inline bool br_should_learn(struct net_bridge_port *p,
+ struct sk_buff *skb, u16 *vid)
+{
+ return true;
+}
+
static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
const struct net_port_vlans *v,
struct sk_buff *skb)
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 4a371610278..5fee2feaf29 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -241,6 +241,34 @@ bool br_allowed_egress(struct net_bridge *br,
return false;
}
+/* Called under RCU */
+bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
+{
+ struct net_bridge *br = p->br;
+ struct net_port_vlans *v;
+
+ if (!br->vlan_enabled)
+ return true;
+
+ v = rcu_dereference(p->vlan_info);
+ if (!v)
+ return false;
+
+ br_vlan_get_tag(skb, vid);
+ if (!*vid) {
+ *vid = br_get_pvid(v);
+ if (*vid == VLAN_N_VID)
+ return false;
+
+ return true;
+ }
+
+ if (test_bit(*vid, v->vlan_bitmap))
+ return true;
+
+ return false;
+}
+
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
*/
diff --git a/net/can/gw.c b/net/can/gw.c
index ac31891967d..050a2110d43 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -804,7 +804,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh)
u8 limhops = 0;
int err = 0;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (nlmsg_len(nlh) < sizeof(*r))
@@ -893,7 +893,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh)
u8 limhops = 0;
int err = 0;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (nlmsg_len(nlh) < sizeof(*r))
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index dac7f9b9868..1948d592aa5 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -557,7 +557,7 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
return r;
}
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+static int __ceph_tcp_sendpage(struct socket *sock, struct page *page,
int offset, size_t size, bool more)
{
int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR);
@@ -570,6 +570,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
return ret;
}
+static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+ int offset, size_t size, bool more)
+{
+ int ret;
+ struct kvec iov;
+
+ /* sendpage cannot properly handle pages with page_count == 0,
+ * we need to fallback to sendmsg if that's the case */
+ if (page_count(page) >= 1)
+ return __ceph_tcp_sendpage(sock, page, offset, size, more);
+
+ iov.iov_base = kmap(page) + offset;
+ iov.iov_len = size;
+ ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more);
+ kunmap(page);
+
+ return ret;
+}
/*
* Shutdown/close the socket for the given connection.
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index e632b5a52f5..c547e46084d 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -329,6 +329,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
dout("crush decode tunable chooseleaf_descend_once = %d",
c->chooseleaf_descend_once);
+ ceph_decode_need(p, end, sizeof(u8), done);
+ c->chooseleaf_vary_r = ceph_decode_8(p);
+ dout("crush decode tunable chooseleaf_vary_r = %d",
+ c->chooseleaf_vary_r);
+
done:
dout("crush_decode success\n");
return c;
@@ -1548,8 +1553,10 @@ static void apply_primary_affinity(struct ceph_osdmap *osdmap, u32 pps,
return;
for (i = 0; i < len; i++) {
- if (osds[i] != CRUSH_ITEM_NONE &&
- osdmap->osd_primary_affinity[i] !=
+ int osd = osds[i];
+
+ if (osd != CRUSH_ITEM_NONE &&
+ osdmap->osd_primary_affinity[osd] !=
CEPH_OSD_DEFAULT_PRIMARY_AFFINITY) {
break;
}
@@ -1563,10 +1570,9 @@ static void apply_primary_affinity(struct ceph_osdmap *osdmap, u32 pps,
* osd's pgs get rejected as primary.
*/
for (i = 0; i < len; i++) {
- int osd;
+ int osd = osds[i];
u32 aff;
- osd = osds[i];
if (osd == CRUSH_ITEM_NONE)
continue;
diff --git a/net/core/dev.c b/net/core/dev.c
index d2c8a06b3a9..fb8b0546485 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2283,8 +2283,8 @@ EXPORT_SYMBOL(skb_checksum_help);
__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
{
+ unsigned int vlan_depth = skb->mac_len;
__be16 type = skb->protocol;
- int vlan_depth = skb->mac_len;
/* Tunnel gso handlers can set protocol to ethernet. */
if (type == htons(ETH_P_TEB)) {
@@ -2297,15 +2297,30 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
type = eth->h_proto;
}
- while (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
- struct vlan_hdr *vh;
+ /* if skb->protocol is 802.1Q/AD then the header should already be
+ * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
+ * ETH_HLEN otherwise
+ */
+ if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
+ if (vlan_depth) {
+ if (unlikely(WARN_ON(vlan_depth < VLAN_HLEN)))
+ return 0;
+ vlan_depth -= VLAN_HLEN;
+ } else {
+ vlan_depth = ETH_HLEN;
+ }
+ do {
+ struct vlan_hdr *vh;
- if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN)))
- return 0;
+ if (unlikely(!pskb_may_pull(skb,
+ vlan_depth + VLAN_HLEN)))
+ return 0;
- vh = (struct vlan_hdr *)(skb->data + vlan_depth);
- type = vh->h_vlan_encapsulated_proto;
- vlan_depth += VLAN_HLEN;
+ vh = (struct vlan_hdr *)(skb->data + vlan_depth);
+ type = vh->h_vlan_encapsulated_proto;
+ vlan_depth += VLAN_HLEN;
+ } while (type == htons(ETH_P_8021Q) ||
+ type == htons(ETH_P_8021AD));
}
*depth = vlan_depth;
@@ -2418,7 +2433,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault);
* 2. No high memory really exists on this machine.
*/
-static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_HIGHMEM
int i;
@@ -2493,38 +2508,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
}
static netdev_features_t harmonize_features(struct sk_buff *skb,
- const struct net_device *dev,
- netdev_features_t features)
+ netdev_features_t features)
{
int tmp;
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
features &= ~NETIF_F_ALL_CSUM;
- } else if (illegal_highdma(dev, skb)) {
+ } else if (illegal_highdma(skb->dev, skb)) {
features &= ~NETIF_F_SG;
}
return features;
}
-netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
- const struct net_device *dev)
+netdev_features_t netif_skb_features(struct sk_buff *skb)
{
__be16 protocol = skb->protocol;
- netdev_features_t features = dev->features;
+ netdev_features_t features = skb->dev->features;
- if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
+ if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
features &= ~NETIF_F_GSO_MASK;
if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
} else if (!vlan_tx_tag_present(skb)) {
- return harmonize_features(skb, dev, features);
+ return harmonize_features(skb, features);
}
- features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+ features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX);
if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
@@ -2532,9 +2545,9 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
- return harmonize_features(skb, dev, features);
+ return harmonize_features(skb, features);
}
-EXPORT_SYMBOL(netif_skb_dev_features);
+EXPORT_SYMBOL(netif_skb_features);
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
@@ -3953,6 +3966,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
}
NAPI_GRO_CB(skb)->count = 1;
NAPI_GRO_CB(skb)->age = jiffies;
+ NAPI_GRO_CB(skb)->last = skb;
skb_shinfo(skb)->gso_size = skb_gro_len(skb);
skb->next = napi->gro_list;
napi->gro_list = skb;
@@ -4543,6 +4557,32 @@ void *netdev_adjacent_get_private(struct list_head *adj_list)
EXPORT_SYMBOL(netdev_adjacent_get_private);
/**
+ * netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next device from the dev's upper list, starting from iter
+ * position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *upper;
+
+ WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
+
+ upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+ if (&upper->list == &dev->adj_list.upper)
+ return NULL;
+
+ *iter = &upper->list;
+
+ return upper->dev;
+}
+EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+
+/**
* netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
* @dev: device
* @iter: list_head ** of the current position
@@ -4624,6 +4664,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
/**
+ * netdev_lower_get_next - Get the next device from the lower neighbour
+ * list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ *iter = &lower->list;
+
+ return lower->dev;
+}
+EXPORT_SYMBOL(netdev_lower_get_next);
+
+/**
* netdev_lower_get_first_private_rcu - Get the first ->private from the
* lower neighbour list, RCU
* variant
@@ -5073,6 +5139,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_lower_dev_get_private);
+
+int dev_get_nest_level(struct net_device *dev,
+ bool (*type_check)(struct net_device *dev))
+{
+ struct net_device *lower = NULL;
+ struct list_head *iter;
+ int max_nest = -1;
+ int nest;
+
+ ASSERT_RTNL();
+
+ netdev_for_each_lower_dev(dev, lower, iter) {
+ nest = dev_get_nest_level(lower, type_check);
+ if (max_nest < nest)
+ max_nest = nest;
+ }
+
+ if (type_check(dev))
+ max_nest++;
+
+ return max_nest;
+}
+EXPORT_SYMBOL(dev_get_nest_level);
+
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
const struct net_device_ops *ops = dev->netdev_ops;
@@ -5238,7 +5328,6 @@ void __dev_set_rx_mode(struct net_device *dev)
if (ops->ndo_set_rx_mode)
ops->ndo_set_rx_mode(dev);
}
-EXPORT_SYMBOL(__dev_set_rx_mode);
void dev_set_rx_mode(struct net_device *dev)
{
@@ -5543,7 +5632,7 @@ static int dev_new_index(struct net *net)
/* Delayed registration/unregisteration */
static LIST_HEAD(net_todo_list);
-static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
+DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
static void net_set_todo(struct net_device *dev)
{
diff --git a/net/core/filter.c b/net/core/filter.c
index cd58614660c..4aec7b93f1a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -122,6 +122,13 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
return 0;
}
+/* Register mappings for user programs. */
+#define A_REG 0
+#define X_REG 7
+#define TMP_REG 8
+#define ARG2_REG 2
+#define ARG3_REG 3
+
/**
* __sk_run_filter - run a filter on a given context
* @ctx: buffer to run the filter on
@@ -242,6 +249,8 @@ unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
regs[FP_REG] = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
regs[ARG1_REG] = (u64) (unsigned long) ctx;
+ regs[A_REG] = 0;
+ regs[X_REG] = 0;
select_insn:
goto *jumptable[insn->code];
@@ -643,13 +652,6 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
return raw_smp_processor_id();
}
-/* Register mappings for user programs. */
-#define A_REG 0
-#define X_REG 7
-#define TMP_REG 8
-#define ARG2_REG 2
-#define ARG3_REG 3
-
static bool convert_bpf_extensions(struct sock_filter *fp,
struct sock_filter_int **insnp)
{
@@ -1557,8 +1559,13 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
fp->jited = 0;
err = sk_chk_filter(fp->insns, fp->len);
- if (err)
+ if (err) {
+ if (sk != NULL)
+ sk_filter_uncharge(sk, fp);
+ else
+ kfree(fp);
return ERR_PTR(err);
+ }
/* Probe if we can JIT compile the filter and if so, do
* the compilation of the filter.
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8f8a96ef9f3..32d872eec7f 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1248,8 +1248,8 @@ void __neigh_set_probe_once(struct neighbour *neigh)
neigh->updated = jiffies;
if (!(neigh->nud_state & NUD_FAILED))
return;
- neigh->nud_state = NUD_PROBE;
- atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES));
+ neigh->nud_state = NUD_INCOMPLETE;
+ atomic_set(&neigh->probes, neigh_max_probes(neigh));
neigh_add_timer(neigh,
jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME));
}
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 81d3a9a0845..7c8ffd97496 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -24,7 +24,7 @@
static LIST_HEAD(pernet_list);
static struct list_head *first_device = &pernet_list;
-static DEFINE_MUTEX(net_mutex);
+DEFINE_MUTEX(net_mutex);
LIST_HEAD(net_namespace_list);
EXPORT_SYMBOL_GPL(net_namespace_list);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d4ff41739b0..2d8d8fcfa06 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops)
}
EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
+/* Return with the rtnl_lock held when there are no network
+ * devices unregistering in any network namespace.
+ */
+static void rtnl_lock_unregistering_all(void)
+{
+ struct net *net;
+ bool unregistering;
+ DEFINE_WAIT(wait);
+
+ for (;;) {
+ prepare_to_wait(&netdev_unregistering_wq, &wait,
+ TASK_UNINTERRUPTIBLE);
+ unregistering = false;
+ rtnl_lock();
+ for_each_net(net) {
+ if (net->dev_unreg_count > 0) {
+ unregistering = true;
+ break;
+ }
+ }
+ if (!unregistering)
+ break;
+ __rtnl_unlock();
+ schedule();
+ }
+ finish_wait(&netdev_unregistering_wq, &wait);
+}
+
/**
* rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
* @ops: struct rtnl_link_ops * to unregister
*/
void rtnl_link_unregister(struct rtnl_link_ops *ops)
{
- rtnl_lock();
+ /* Close the race with cleanup_net() */
+ mutex_lock(&net_mutex);
+ rtnl_lock_unregistering_all();
__rtnl_link_unregister(ops);
rtnl_unlock();
+ mutex_unlock(&net_mutex);
}
EXPORT_SYMBOL_GPL(rtnl_link_unregister);
@@ -774,7 +805,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
return 0;
}
-static size_t rtnl_port_size(const struct net_device *dev)
+static size_t rtnl_port_size(const struct net_device *dev,
+ u32 ext_filter_mask)
{
size_t port_size = nla_total_size(4) /* PORT_VF */
+ nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */
@@ -790,7 +822,8 @@ static size_t rtnl_port_size(const struct net_device *dev)
size_t port_self_size = nla_total_size(sizeof(struct nlattr))
+ port_size;
- if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
+ if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
+ !(ext_filter_mask & RTEXT_FILTER_VF))
return 0;
if (dev_num_vf(dev->dev.parent))
return port_self_size + vf_ports_size +
@@ -826,7 +859,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(ext_filter_mask
& RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
+ rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
- + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ rtnl_link_get_size(dev) /* IFLA_LINKINFO */
+ rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
+ nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */
@@ -888,11 +921,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
return 0;
}
-static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev)
+static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
+ u32 ext_filter_mask)
{
int err;
- if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
+ if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
+ !(ext_filter_mask & RTEXT_FILTER_VF))
return 0;
err = rtnl_port_self_fill(skb, dev);
@@ -1079,7 +1114,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
nla_nest_end(skb, vfinfo);
}
- if (rtnl_port_fill(skb, dev))
+ if (rtnl_port_fill(skb, dev, ext_filter_mask))
goto nla_put_failure;
if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) {
@@ -1198,6 +1233,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
struct hlist_head *head;
struct nlattr *tb[IFLA_MAX+1];
u32 ext_filter_mask = 0;
+ int err;
s_h = cb->args[0];
s_idx = cb->args[1];
@@ -1218,11 +1254,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
hlist_for_each_entry_rcu(dev, head, index_hlist) {
if (idx < s_idx)
goto cont;
- if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, 0,
- NLM_F_MULTI,
- ext_filter_mask) <= 0)
+ err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, 0,
+ NLM_F_MULTI,
+ ext_filter_mask);
+ /* If we ran out of room on the first message,
+ * we're in trouble
+ */
+ WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
+
+ if (err <= 0)
goto out;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
@@ -1395,7 +1437,8 @@ static int do_set_master(struct net_device *dev, int ifindex)
return 0;
}
-static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
+static int do_setlink(const struct sk_buff *skb,
+ struct net_device *dev, struct ifinfomsg *ifm,
struct nlattr **tb, char *ifname, int modified)
{
const struct net_device_ops *ops = dev->netdev_ops;
@@ -1407,7 +1450,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
err = PTR_ERR(net);
goto errout;
}
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+ if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
err = -EPERM;
goto errout;
}
@@ -1661,7 +1704,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
if (err < 0)
goto errout;
- err = do_setlink(dev, ifm, tb, ifname, 0);
+ err = do_setlink(skb, dev, ifm, tb, ifname, 0);
errout:
return err;
}
@@ -1778,7 +1821,8 @@ err:
}
EXPORT_SYMBOL(rtnl_create_link);
-static int rtnl_group_changelink(struct net *net, int group,
+static int rtnl_group_changelink(const struct sk_buff *skb,
+ struct net *net, int group,
struct ifinfomsg *ifm,
struct nlattr **tb)
{
@@ -1787,7 +1831,7 @@ static int rtnl_group_changelink(struct net *net, int group,
for_each_netdev(net, dev) {
if (dev->group == group) {
- err = do_setlink(dev, ifm, tb, NULL, 0);
+ err = do_setlink(skb, dev, ifm, tb, NULL, 0);
if (err < 0)
return err;
}
@@ -1929,12 +1973,12 @@ replay:
modified = 1;
}
- return do_setlink(dev, ifm, tb, ifname, modified);
+ return do_setlink(skb, dev, ifm, tb, ifname, modified);
}
if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
- return rtnl_group_changelink(net,
+ return rtnl_group_changelink(skb, net,
nla_get_u32(tb[IFLA_GROUP]),
ifm, tb);
return -ENODEV;
@@ -2321,7 +2365,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
int err = -EINVAL;
__u8 *addr;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
@@ -2773,7 +2817,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
sz_idx = type>>2;
kind = type&3;
- if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN))
+ if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1b62343f583..8383b2bddeb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3076,7 +3076,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
if (unlikely(p->len + len >= 65536))
return -E2BIG;
- lp = NAPI_GRO_CB(p)->last ?: p;
+ lp = NAPI_GRO_CB(p)->last;
pinfo = skb_shinfo(lp);
if (headlen <= offset) {
@@ -3192,7 +3192,7 @@ merge:
__skb_pull(skb, offset);
- if (!NAPI_GRO_CB(p)->last)
+ if (NAPI_GRO_CB(p)->last == p)
skb_shinfo(p)->frag_list = skb;
else
NAPI_GRO_CB(p)->last->next = skb;
diff --git a/net/core/sock.c b/net/core/sock.c
index b4fff008136..664ee4295b6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -145,6 +145,55 @@
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
+/**
+ * sk_ns_capable - General socket capability test
+ * @sk: Socket to use a capability on or through
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket had when the socket was
+ * created and the current process has the capability @cap in the user
+ * namespace @user_ns.
+ */
+bool sk_ns_capable(const struct sock *sk,
+ struct user_namespace *user_ns, int cap)
+{
+ return file_ns_capable(sk->sk_socket->file, user_ns, cap) &&
+ ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(sk_ns_capable);
+
+/**
+ * sk_capable - Socket global capability test
+ * @sk: Socket to use a capability on or through
+ * @cap: The global capbility to use
+ *
+ * Test to see if the opener of the socket had when the socket was
+ * created and the current process has the capability @cap in all user
+ * namespaces.
+ */
+bool sk_capable(const struct sock *sk, int cap)
+{
+ return sk_ns_capable(sk, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(sk_capable);
+
+/**
+ * sk_net_capable - Network namespace socket capability test
+ * @sk: Socket to use a capability on or through
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket had when the socke was created
+ * and the current process has the capability @cap over the network namespace
+ * the socket is a member of.
+ */
+bool sk_net_capable(const struct sock *sk, int cap)
+{
+ return sk_ns_capable(sk, sock_net(sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(sk_net_capable);
+
+
#ifdef CONFIG_MEMCG_KMEM
int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index d7af1885932..a4216a4c957 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
}
EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
-int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
struct sk_buff *skb, int attrtype)
{
struct sock_fprog_kern *fprog;
@@ -58,7 +58,7 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
unsigned int flen;
int err = 0;
- if (!ns_capable(user_ns, CAP_NET_ADMIN)) {
+ if (!may_report_filterinfo) {
nla_reserve(skb, attrtype, 0);
return 0;
}
diff --git a/net/core/utils.c b/net/core/utils.c
index 2f737bf90b3..eed34338736 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w)
{
struct __net_random_once_work *work =
container_of(w, struct __net_random_once_work, work);
- if (!static_key_enabled(work->key))
- static_key_slow_inc(work->key);
+ BUG_ON(!static_key_enabled(work->key));
+ static_key_slow_dec(work->key);
kfree(work);
}
@@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key)
}
bool __net_get_random_once(void *buf, int nbytes, bool *done,
- struct static_key *done_key)
+ struct static_key *once_key)
{
static DEFINE_SPINLOCK(lock);
unsigned long flags;
@@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done,
*done = true;
spin_unlock_irqrestore(&lock, flags);
- __net_random_once_disable_jump(done_key);
+ __net_random_once_disable_jump(once_key);
return true;
}
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 55364440267..f8b98d89c28 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1669,7 +1669,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
struct nlmsghdr *reply_nlh = NULL;
const struct reply_func *fn;
- if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN))
+ if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX,
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index a603823a3e2..3b726f31c64 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -574,7 +574,7 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
struct dn_ifaddr __rcu **ifap;
int err = -EINVAL;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (!net_eq(net, &init_net))
@@ -618,7 +618,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
struct dn_ifaddr *ifa;
int err;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (!net_eq(net, &init_net))
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 57dc159245e..d332aefb084 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -505,7 +505,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
struct nlattr *attrs[RTA_MAX+1];
int err;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (!net_eq(net, &init_net))
@@ -530,7 +530,7 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
struct nlattr *attrs[RTA_MAX+1];
int err;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (!net_eq(net, &init_net))
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index e83015cecfa..e4d9560a910 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -107,7 +107,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
return;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
RCV_SKB_FAIL(-EPERM);
/* Eventually we might send routing messages too */
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 0eb5d5e76df..5db37cef50a 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -406,8 +406,9 @@ static int dsa_of_probe(struct platform_device *pdev)
goto out_free;
}
- chip_index = 0;
+ chip_index = -1;
for_each_available_child_of_node(np, child) {
+ chip_index++;
cd = &pd->chip[chip_index];
cd->mii_bus = &mdio_bus->dev;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8c54870db79..6d6dd345bc4 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1650,6 +1650,39 @@ static int __init init_ipv4_mibs(void)
return register_pernet_subsys(&ipv4_mib_ops);
}
+static __net_init int inet_init_net(struct net *net)
+{
+ /*
+ * Set defaults for local port range
+ */
+ seqlock_init(&net->ipv4.ip_local_ports.lock);
+ net->ipv4.ip_local_ports.range[0] = 32768;
+ net->ipv4.ip_local_ports.range[1] = 61000;
+
+ seqlock_init(&net->ipv4.ping_group_range.lock);
+ /*
+ * Sane defaults - nobody may create ping sockets.
+ * Boot scripts should set this to distro-specific group.
+ */
+ net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1);
+ net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0);
+ return 0;
+}
+
+static __net_exit void inet_exit_net(struct net *net)
+{
+}
+
+static __net_initdata struct pernet_operations af_inet_ops = {
+ .init = inet_init_net,
+ .exit = inet_exit_net,
+};
+
+static int __init init_inet_pernet_ops(void)
+{
+ return register_pernet_subsys(&af_inet_ops);
+}
+
static int ipv4_proc_init(void);
/*
@@ -1794,6 +1827,9 @@ static int __init inet_init(void)
if (ip_mr_init())
pr_crit("%s: Cannot init ipv4 mroute\n", __func__);
#endif
+
+ if (init_inet_pernet_ops())
+ pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
/*
* Initialise per-cpu ipv4 mibs
*/
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 8a043f03c88..b10cd43a472 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -821,13 +821,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
if (fi == NULL)
goto failure;
+ fib_info_cnt++;
if (cfg->fc_mx) {
fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
if (!fi->fib_metrics)
goto failure;
} else
fi->fib_metrics = (u32 *) dst_default_metrics;
- fib_info_cnt++;
fi->fib_net = hold_net(net);
fi->fib_protocol = cfg->fc_protocol;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 0d1e2cb877e..a56b8e6e866 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -37,11 +37,11 @@ void inet_get_local_port_range(struct net *net, int *low, int *high)
unsigned int seq;
do {
- seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
- *low = net->ipv4.sysctl_local_ports.range[0];
- *high = net->ipv4.sysctl_local_ports.range[1];
- } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+ *low = net->ipv4.ip_local_ports.range[0];
+ *high = net->ipv4.ip_local_ports.range[1];
+ } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
}
EXPORT_SYMBOL(inet_get_local_port_range);
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index be8abe73bb9..6f111e48e11 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -42,12 +42,12 @@
static bool ip_may_fragment(const struct sk_buff *skb)
{
return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
- !skb->local_df;
+ skb->local_df;
}
static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
{
- if (skb->len <= mtu || skb->local_df)
+ if (skb->len <= mtu)
return false;
if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
@@ -56,53 +56,6 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
return true;
}
-static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
-{
- unsigned int mtu;
-
- if (skb->local_df || !skb_is_gso(skb))
- return false;
-
- mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
-
- /* if seglen > mtu, do software segmentation for IP fragmentation on
- * output. DF bit cannot be set since ip_forward would have sent
- * icmp error.
- */
- return skb_gso_network_seglen(skb) > mtu;
-}
-
-/* called if GSO skb needs to be fragmented on forward */
-static int ip_forward_finish_gso(struct sk_buff *skb)
-{
- struct dst_entry *dst = skb_dst(skb);
- netdev_features_t features;
- struct sk_buff *segs;
- int ret = 0;
-
- features = netif_skb_dev_features(skb, dst->dev);
- segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
- if (IS_ERR(segs)) {
- kfree_skb(skb);
- return -ENOMEM;
- }
-
- consume_skb(skb);
-
- do {
- struct sk_buff *nskb = segs->next;
- int err;
-
- segs->next = NULL;
- err = dst_output(segs);
-
- if (err && ret == 0)
- ret = err;
- segs = nskb;
- } while (segs);
-
- return ret;
-}
static int ip_forward_finish(struct sk_buff *skb)
{
@@ -114,9 +67,6 @@ static int ip_forward_finish(struct sk_buff *skb)
if (unlikely(opt->optlen))
ip_forward_options(skb);
- if (ip_gso_exceeds_dst_mtu(skb))
- return ip_forward_finish_gso(skb);
-
return dst_output(skb);
}
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index c10a3ce5cbf..ed32313e307 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -232,8 +232,9 @@ static void ip_expire(unsigned long arg)
* "Fragment Reassembly Timeout" message, per RFC792.
*/
if (qp->user == IP_DEFRAG_AF_PACKET ||
- (qp->user == IP_DEFRAG_CONNTRACK_IN &&
- skb_rtable(head)->rt_type != RTN_LOCAL))
+ ((qp->user >= IP_DEFRAG_CONNTRACK_IN) &&
+ (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) &&
+ (skb_rtable(head)->rt_type != RTN_LOCAL)))
goto out_rcu_unlock;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 1cbeba5edff..a52f50187b5 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -211,6 +211,48 @@ static inline int ip_finish_output2(struct sk_buff *skb)
return -EINVAL;
}
+static int ip_finish_output_gso(struct sk_buff *skb)
+{
+ netdev_features_t features;
+ struct sk_buff *segs;
+ int ret = 0;
+
+ /* common case: locally created skb or seglen is <= mtu */
+ if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
+ skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
+ return ip_finish_output2(skb);
+
+ /* Slowpath - GSO segment length is exceeding the dst MTU.
+ *
+ * This can happen in two cases:
+ * 1) TCP GRO packet, DF bit not set
+ * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
+ * from host network stack.
+ */
+ features = netif_skb_features(skb);
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+ if (IS_ERR(segs)) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ consume_skb(skb);
+
+ do {
+ struct sk_buff *nskb = segs->next;
+ int err;
+
+ segs->next = NULL;
+ err = ip_fragment(segs, ip_finish_output2);
+
+ if (err && ret == 0)
+ ret = err;
+ segs = nskb;
+ } while (segs);
+
+ return ret;
+}
+
static int ip_finish_output(struct sk_buff *skb)
{
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
@@ -220,10 +262,13 @@ static int ip_finish_output(struct sk_buff *skb)
return dst_output(skb);
}
#endif
- if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
+ if (skb_is_gso(skb))
+ return ip_finish_output_gso(skb);
+
+ if (skb->len > ip_skb_dst_mtu(skb))
return ip_fragment(skb, ip_finish_output2);
- else
- return ip_finish_output2(skb);
+
+ return ip_finish_output2(skb);
}
int ip_mc_output(struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index fa5b7519765..2acc2337d38 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -442,6 +442,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
tunnel->i_seqno = ntohl(tpi->seq) + 1;
}
+ skb_reset_network_header(skb);
+
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
if (log_ecn_error)
@@ -538,9 +540,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
unsigned int max_headroom; /* The extra header space needed */
__be32 dst;
int err;
- bool connected = true;
+ bool connected;
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+ connected = (tunnel->parms.iph.daddr != 0);
dst = tnl_params->daddr;
if (dst == 0) {
@@ -880,6 +883,7 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
*/
if (!IS_ERR(itn->fb_tunnel_dev)) {
itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+ itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
}
rtnl_unlock();
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index afcee51b90e..13ef00f1e17 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -239,6 +239,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
static int vti4_err(struct sk_buff *skb, u32 info)
{
__be32 spi;
+ __u32 mark;
struct xfrm_state *x;
struct ip_tunnel *tunnel;
struct ip_esp_hdr *esph;
@@ -254,6 +255,8 @@ static int vti4_err(struct sk_buff *skb, u32 info)
if (!tunnel)
return -1;
+ mark = be32_to_cpu(tunnel->parms.o_key);
+
switch (protocol) {
case IPPROTO_ESP:
esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
@@ -281,7 +284,7 @@ static int vti4_err(struct sk_buff *skb, u32 info)
return 0;
}
- x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+ x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
spi, protocol, AF_INET);
if (!x)
return 0;
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 12e13bd82b5..f40f321b41f 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -22,7 +22,6 @@
#endif
#include <net/netfilter/nf_conntrack_zones.h>
-/* Returns new sk_buff, or NULL */
static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
{
int err;
@@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
err = ip_defrag(skb, user);
local_bh_enable();
- if (!err)
+ if (!err) {
ip_send_check(ip_hdr(skb));
+ skb->local_df = 1;
+ }
return err;
}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 8210964a9f1..044a0ddf6a7 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -236,15 +236,15 @@ exit:
static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
kgid_t *high)
{
- kgid_t *data = net->ipv4.sysctl_ping_group_range;
+ kgid_t *data = net->ipv4.ping_group_range.range;
unsigned int seq;
do {
- seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
*low = data[0];
*high = data[1];
- } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+ } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index db1e0da871f..5e676be3dae 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1519,7 +1519,7 @@ static int __mkroute_input(struct sk_buff *skb,
struct in_device *out_dev;
unsigned int flags = 0;
bool do_cache;
- u32 itag;
+ u32 itag = 0;
/* get a working reference to the output device */
out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 44eba052b43..5cde8f263d4 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
/* Update system visible IP port range */
static void set_local_port_range(struct net *net, int range[2])
{
- write_seqlock(&net->ipv4.sysctl_local_ports.lock);
- net->ipv4.sysctl_local_ports.range[0] = range[0];
- net->ipv4.sysctl_local_ports.range[1] = range[1];
- write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
+ write_seqlock(&net->ipv4.ip_local_ports.lock);
+ net->ipv4.ip_local_ports.range[0] = range[0];
+ net->ipv4.ip_local_ports.range[1] = range[1];
+ write_sequnlock(&net->ipv4.ip_local_ports.lock);
}
/* Validate changes from /proc interface. */
@@ -57,7 +57,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
size_t *lenp, loff_t *ppos)
{
struct net *net =
- container_of(table->data, struct net, ipv4.sysctl_local_ports.range);
+ container_of(table->data, struct net, ipv4.ip_local_ports.range);
int ret;
int range[2];
struct ctl_table tmp = {
@@ -87,14 +87,14 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
{
kgid_t *data = table->data;
struct net *net =
- container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
+ container_of(table->data, struct net, ipv4.ping_group_range.range);
unsigned int seq;
do {
- seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
*low = data[0];
*high = data[1];
- } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+ } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
}
/* Update system visible IP port range */
@@ -102,11 +102,11 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
{
kgid_t *data = table->data;
struct net *net =
- container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
- write_seqlock(&net->ipv4.sysctl_local_ports.lock);
+ container_of(table->data, struct net, ipv4.ping_group_range.range);
+ write_seqlock(&net->ipv4.ip_local_ports.lock);
data[0] = low;
data[1] = high;
- write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
+ write_sequnlock(&net->ipv4.ip_local_ports.lock);
}
/* Validate changes from /proc interface. */
@@ -805,7 +805,7 @@ static struct ctl_table ipv4_net_table[] = {
},
{
.procname = "ping_group_range",
- .data = &init_net.ipv4.sysctl_ping_group_range,
+ .data = &init_net.ipv4.ping_group_range.range,
.maxlen = sizeof(gid_t)*2,
.mode = 0644,
.proc_handler = ipv4_ping_group_range,
@@ -819,8 +819,8 @@ static struct ctl_table ipv4_net_table[] = {
},
{
.procname = "ip_local_port_range",
- .maxlen = sizeof(init_net.ipv4.sysctl_local_ports.range),
- .data = &init_net.ipv4.sysctl_local_ports.range,
+ .maxlen = sizeof(init_net.ipv4.ip_local_ports.range),
+ .data = &init_net.ipv4.ip_local_ports.range,
.mode = 0644,
.proc_handler = ipv4_local_port_range,
},
@@ -858,20 +858,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
table[i].data += (void *)net - (void *)&init_net;
}
- /*
- * Sane defaults - nobody may create ping sockets.
- * Boot scripts should set this to distro-specific group.
- */
- net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
- net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
-
- /*
- * Set defaults for local port range
- */
- seqlock_init(&net->ipv4.sysctl_local_ports.lock);
- net->ipv4.sysctl_local_ports.range[0] = 32768;
- net->ipv4.sysctl_local_ports.range[1] = 61000;
-
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
if (net->ipv4.ipv4_hdr == NULL)
goto err_reg;
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 8bf224516ba..b4f1b29b08b 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -409,7 +409,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
ratio += cnt;
- ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT);
+ ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
}
/* Some calls are for duplicates without timetamps */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d6b46eb2f94..3a26b3b23f1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2684,13 +2684,12 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
bool recovered = !before(tp->snd_una, tp->high_seq);
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
- if (flag & FLAG_ORIG_SACK_ACKED) {
- /* Step 3.b. A timeout is spurious if not all data are
- * lost, i.e., never-retransmitted data are (s)acked.
- */
- tcp_try_undo_loss(sk, true);
+ /* Step 3.b. A timeout is spurious if not all data are
+ * lost, i.e., never-retransmitted data are (s)acked.
+ */
+ if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
return;
- }
+
if (after(tp->snd_nxt, tp->high_seq) &&
(flag & FLAG_DATA_SACKED || is_dupack)) {
tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 025e2509398..12d6016bdd9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2441,8 +2441,14 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
- if (likely(!err))
+ if (likely(!err)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+ /* Update global TCP statistics. */
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+ tp->total_retrans++;
+ }
return err;
}
@@ -2452,12 +2458,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
int err = __tcp_retransmit_skb(sk, skb);
if (err == 0) {
- /* Update global TCP statistics. */
- TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
- if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
- tp->total_retrans++;
-
#if FASTRETRANS_DEBUG > 0
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
net_dbg_ratelimited("retrans_out leaked\n");
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 40e701f2e1e..186a8ecf92f 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -62,10 +62,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
if (err)
return err;
- memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED;
-
- skb->protocol = htons(ETH_P_IP);
+ IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
return x->outer_mode->output2(x, skb);
}
@@ -73,27 +70,34 @@ EXPORT_SYMBOL(xfrm4_prepare_output);
int xfrm4_output_finish(struct sk_buff *skb)
{
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ skb->protocol = htons(ETH_P_IP);
+
+#ifdef CONFIG_NETFILTER
+ IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
+#endif
+
+ return xfrm_output(skb);
+}
+
+static int __xfrm4_output(struct sk_buff *skb)
+{
+ struct xfrm_state *x = skb_dst(skb)->xfrm;
+
#ifdef CONFIG_NETFILTER
- if (!skb_dst(skb)->xfrm) {
+ if (!x) {
IPCB(skb)->flags |= IPSKB_REROUTED;
return dst_output(skb);
}
-
- IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
#endif
- skb->protocol = htons(ETH_P_IP);
- return xfrm_output(skb);
+ return x->outer_mode->afinfo->output_finish(skb);
}
int xfrm4_output(struct sock *sk, struct sk_buff *skb)
{
- struct dst_entry *dst = skb_dst(skb);
- struct xfrm_state *x = dst->xfrm;
-
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb,
- NULL, dst->dev,
- x->outer_mode->afinfo->output_finish,
+ NULL, skb_dst(skb)->dev, __xfrm4_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index 7f7b243e813..a2ce0101eaa 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/net/ipv4/xfrm4_protocol.c
@@ -50,8 +50,12 @@ int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
{
int ret;
struct xfrm4_protocol *handler;
+ struct xfrm4_protocol __rcu **head = proto_handlers(protocol);
- for_each_protocol_rcu(*proto_handlers(protocol), handler)
+ if (!head)
+ return 0;
+
+ for_each_protocol_rcu(*head, handler)
if ((ret = handler->cb_handler(skb, err)) <= 0)
return ret;
@@ -64,15 +68,20 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
{
int ret;
struct xfrm4_protocol *handler;
+ struct xfrm4_protocol __rcu **head = proto_handlers(nexthdr);
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
- for_each_protocol_rcu(*proto_handlers(nexthdr), handler)
+ if (!head)
+ goto out;
+
+ for_each_protocol_rcu(*head, handler)
if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
return ret;
+out:
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
kfree_skb(skb);
@@ -208,6 +217,9 @@ int xfrm4_protocol_register(struct xfrm4_protocol *handler,
int ret = -EEXIST;
int priority = handler->priority;
+ if (!proto_handlers(protocol) || !netproto(protocol))
+ return -EINVAL;
+
mutex_lock(&xfrm4_protocol_mutex);
if (!rcu_dereference_protected(*proto_handlers(protocol),
@@ -250,6 +262,9 @@ int xfrm4_protocol_deregister(struct xfrm4_protocol *handler,
struct xfrm4_protocol *t;
int ret = -ENOENT;
+ if (!proto_handlers(protocol) || !netproto(protocol))
+ return -EINVAL;
+
mutex_lock(&xfrm4_protocol_mutex);
for (pprev = proto_handlers(protocol);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 34e0ded5c14..87891f5f57b 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1459,7 +1459,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
if (w->skip) {
w->skip--;
- continue;
+ goto skip;
}
err = w->func(w);
@@ -1469,6 +1469,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
w->count++;
continue;
}
+skip:
w->state = FWS_U;
case FWS_U:
if (fn == w->root)
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 59f95affceb..b2f091566f8 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -196,7 +196,6 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
unsigned int off;
u16 flush = 1;
int proto;
- __wsum csum;
off = skb_gro_offset(skb);
hlen = off + sizeof(*iph);
@@ -264,13 +263,10 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
NAPI_GRO_CB(skb)->flush |= flush;
- csum = skb->csum;
- skb_postpull_rcsum(skb, iph, skb_network_header_len(skb));
+ skb_gro_postpull_rcsum(skb, iph, nlen);
pp = ops->callbacks.gro_receive(head, skb);
- skb->csum = csum;
-
out_unlock:
rcu_read_unlock();
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 40e7581374f..fbf11562b54 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -344,12 +344,16 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
{
- if (skb->len <= mtu || skb->local_df)
+ if (skb->len <= mtu)
return false;
+ /* ipv6 conntrack defrag sets max_frag_size + local_df */
if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
return true;
+ if (skb->local_df)
+ return false;
+
if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
return false;
@@ -1225,7 +1229,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
unsigned int maxnonfragsize, headersize;
headersize = sizeof(struct ipv6hdr) +
- (opt ? opt->tot_len : 0) +
+ (opt ? opt->opt_flen + opt->opt_nflen : 0) +
(dst_allfrag(&rt->dst) ?
sizeof(struct frag_hdr) : 0) +
rt->rt6i_nfheader_len;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b05b609f69d..f6a66bb4114 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1557,7 +1557,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[])
{
u8 proto;
- if (!data)
+ if (!data || !data[IFLA_IPTUN_PROTO])
return 0;
proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index b7c0f827140..6cc9f9371cc 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -511,6 +511,7 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
__be32 spi;
+ __u32 mark;
struct xfrm_state *x;
struct ip6_tnl *t;
struct ip_esp_hdr *esph;
@@ -524,6 +525,8 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!t)
return -1;
+ mark = be32_to_cpu(t->parms.o_key);
+
switch (protocol) {
case IPPROTO_ESP:
esph = (struct ip_esp_hdr *)(skb->data + offset);
@@ -545,7 +548,7 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
type != NDISC_REDIRECT)
return 0;
- x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+ x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
spi, protocol, AF_INET6);
if (!x)
return 0;
@@ -1097,7 +1100,6 @@ static int __init vti6_tunnel_init(void)
err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP);
if (err < 0) {
- unregister_pernet_device(&vti6_net_ops);
pr_err("%s: can't register vti6 protocol\n", __func__);
goto out;
@@ -1106,7 +1108,6 @@ static int __init vti6_tunnel_init(void)
err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH);
if (err < 0) {
xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
- unregister_pernet_device(&vti6_net_ops);
pr_err("%s: can't register vti6 protocol\n", __func__);
goto out;
@@ -1116,7 +1117,6 @@ static int __init vti6_tunnel_init(void)
if (err < 0) {
xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
- unregister_pernet_device(&vti6_net_ops);
pr_err("%s: can't register vti6 protocol\n", __func__);
goto out;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 8659067da28..8250474ab7d 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1633,7 +1633,7 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb)
{
struct mr6_table *mrt;
struct flowi6 fl6 = {
- .flowi6_iif = skb->skb_iif,
+ .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX,
.flowi6_oif = skb->dev->ifindex,
.flowi6_mark = skb->mark,
};
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 09a22f4f36c..ca8d4ea48a5 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -851,7 +851,7 @@ out:
static void ndisc_recv_na(struct sk_buff *skb)
{
struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
- const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
+ struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
u8 *lladdr = NULL;
u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
@@ -944,10 +944,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
/*
* Change: router to host
*/
- struct rt6_info *rt;
- rt = rt6_get_dflt_router(saddr, dev);
- if (rt)
- ip6_del_rt(rt);
+ rt6_clean_tohost(dev_net(dev), saddr);
}
out:
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 95f3f1da0d7..d38e6a8d8b9 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb)
.daddr = iph->daddr,
.saddr = iph->saddr,
};
+ int err;
dst = ip6_route_output(net, skb->sk, &fl6);
- if (dst->error) {
+ err = dst->error;
+ if (err) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
dst_release(dst);
- return dst->error;
+ return err;
}
/* Drop old route. */
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index e0983f3648a..790e0c6b19e 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -33,6 +33,7 @@ static bool rpfilter_lookup_reverse6(const struct sk_buff *skb,
struct ipv6hdr *iph = ipv6_hdr(skb);
bool ret = false;
struct flowi6 fl6 = {
+ .flowi6_iif = LOOPBACK_IFINDEX,
.flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK,
.flowi6_proto = iph->nexthdr,
.daddr = iph->saddr,
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 6313abd53c9..56596ce390a 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -12,7 +12,7 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
{
static atomic_t ipv6_fragmentation_id;
struct in6_addr addr;
- int old, new;
+ int ident;
#if IS_ENABLED(CONFIG_IPV6)
struct inet_peer *peer;
@@ -26,15 +26,10 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
return;
}
#endif
- do {
- old = atomic_read(&ipv6_fragmentation_id);
- new = old + 1;
- if (!new)
- new = 1;
- } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old);
+ ident = atomic_inc_return(&ipv6_fragmentation_id);
addr = rt->rt6i_dst.addr;
- addr.s6_addr32[0] ^= (__force __be32)new;
+ addr.s6_addr32[0] ^= (__force __be32)ident;
fhdr->identification = htonl(secure_ipv6_id(addr.s6_addr32));
}
EXPORT_SYMBOL(ipv6_select_ident);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4011617cca6..6ebdb7b6744 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1273,6 +1273,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_iif = LOOPBACK_IFINDEX;
fl6.flowi6_oif = oif;
fl6.flowi6_mark = mark;
fl6.daddr = iph->daddr;
@@ -1294,6 +1295,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_iif = LOOPBACK_IFINDEX;
fl6.flowi6_oif = oif;
fl6.flowi6_mark = mark;
fl6.daddr = msg->dest;
@@ -2232,6 +2234,27 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
fib6_clean_all(net, fib6_remove_prefsrc, &adni);
}
+#define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
+#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE)
+
+/* Remove routers and update dst entries when gateway turn into host. */
+static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
+{
+ struct in6_addr *gateway = (struct in6_addr *)arg;
+
+ if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) ||
+ ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) &&
+ ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
+ return -1;
+ }
+ return 0;
+}
+
+void rt6_clean_tohost(struct net *net, struct in6_addr *gateway)
+{
+ fib6_clean_all(net, fib6_clean_tohost, gateway);
+}
+
struct arg_dev_net {
struct net_device *dev;
struct net *net;
@@ -2707,6 +2730,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh)
if (tb[RTA_OIF])
oif = nla_get_u32(tb[RTA_OIF]);
+ if (tb[RTA_MARK])
+ fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+
if (iif) {
struct net_device *dev;
int flags = 0;
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 0d78132ff18..8517d3cd1ae 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -42,7 +42,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
if (NAPI_GRO_CB(skb)->flush)
goto skip_csum;
- wsum = skb->csum;
+ wsum = NAPI_GRO_CB(skb)->csum;
switch (skb->ip_summed) {
case CHECKSUM_NONE:
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 19ef329bdbf..b930d080c66 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -114,12 +114,6 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
if (err)
return err;
- memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
-#ifdef CONFIG_NETFILTER
- IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
-#endif
-
- skb->protocol = htons(ETH_P_IPV6);
skb->local_df = 1;
return x->outer_mode->output2(x, skb);
@@ -128,11 +122,13 @@ EXPORT_SYMBOL(xfrm6_prepare_output);
int xfrm6_output_finish(struct sk_buff *skb)
{
+ memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ skb->protocol = htons(ETH_P_IPV6);
+
#ifdef CONFIG_NETFILTER
IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
#endif
- skb->protocol = htons(ETH_P_IPV6);
return xfrm_output(skb);
}
@@ -142,6 +138,13 @@ static int __xfrm6_output(struct sk_buff *skb)
struct xfrm_state *x = dst->xfrm;
int mtu;
+#ifdef CONFIG_NETFILTER
+ if (!x) {
+ IP6CB(skb)->flags |= IP6SKB_REROUTED;
+ return dst_output(skb);
+ }
+#endif
+
if (skb->protocol == htons(ETH_P_IPV6))
mtu = ip6_skb_dst_mtu(skb);
else
@@ -165,6 +168,7 @@ static int __xfrm6_output(struct sk_buff *skb)
int xfrm6_output(struct sock *sk, struct sk_buff *skb)
{
- return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL,
- skb_dst(skb)->dev, __xfrm6_output);
+ return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb,
+ NULL, skb_dst(skb)->dev, __xfrm6_output,
+ !(IP6CB(skb)->flags & IP6SKB_REROUTED));
}
diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c
index 6ab989c486f..54d13f8dbba 100644
--- a/net/ipv6/xfrm6_protocol.c
+++ b/net/ipv6/xfrm6_protocol.c
@@ -50,6 +50,10 @@ int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
{
int ret;
struct xfrm6_protocol *handler;
+ struct xfrm6_protocol __rcu **head = proto_handlers(protocol);
+
+ if (!head)
+ return 0;
for_each_protocol_rcu(*proto_handlers(protocol), handler)
if ((ret = handler->cb_handler(skb, err)) <= 0)
@@ -184,10 +188,12 @@ int xfrm6_protocol_register(struct xfrm6_protocol *handler,
struct xfrm6_protocol __rcu **pprev;
struct xfrm6_protocol *t;
bool add_netproto = false;
-
int ret = -EEXIST;
int priority = handler->priority;
+ if (!proto_handlers(protocol) || !netproto(protocol))
+ return -EINVAL;
+
mutex_lock(&xfrm6_protocol_mutex);
if (!rcu_dereference_protected(*proto_handlers(protocol),
@@ -230,6 +236,9 @@ int xfrm6_protocol_deregister(struct xfrm6_protocol *handler,
struct xfrm6_protocol *t;
int ret = -ENOENT;
+ if (!proto_handlers(protocol) || !netproto(protocol))
+ return -EINVAL;
+
mutex_lock(&xfrm6_protocol_mutex);
for (pprev = proto_handlers(protocol);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 01e77b0ae07..8c9d7302c84 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1830,7 +1830,7 @@ static void iucv_callback_txdone(struct iucv_path *path,
spin_lock_irqsave(&list->lock, flags);
while (list_skb != (struct sk_buff *)list) {
- if (msg->tag != IUCV_SKB_CB(list_skb)->tag) {
+ if (msg->tag == IUCV_SKB_CB(list_skb)->tag) {
this = list_skb;
break;
}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 222c28b7531..f169b6ee94e 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -317,6 +317,7 @@ struct ieee80211_roc_work {
bool started, abort, hw_begun, notified;
bool to_be_freed;
+ bool on_channel;
unsigned long hw_start_time;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index dee50aefd6e..27600a9808b 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3598,18 +3598,24 @@ void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
sdata_lock(sdata);
- if (ifmgd->auth_data) {
+ if (ifmgd->auth_data || ifmgd->assoc_data) {
+ const u8 *bssid = ifmgd->auth_data ?
+ ifmgd->auth_data->bss->bssid :
+ ifmgd->assoc_data->bss->bssid;
+
/*
- * If we are trying to authenticate while suspending, cfg80211
- * won't know and won't actually abort those attempts, thus we
- * need to do that ourselves.
+ * If we are trying to authenticate / associate while suspending,
+ * cfg80211 won't know and won't actually abort those attempts,
+ * thus we need to do that ourselves.
*/
- ieee80211_send_deauth_disassoc(sdata,
- ifmgd->auth_data->bss->bssid,
+ ieee80211_send_deauth_disassoc(sdata, bssid,
IEEE80211_STYPE_DEAUTH,
WLAN_REASON_DEAUTH_LEAVING,
false, frame_buf);
- ieee80211_destroy_auth_data(sdata, false);
+ if (ifmgd->assoc_data)
+ ieee80211_destroy_assoc_data(sdata, false);
+ if (ifmgd->auth_data)
+ ieee80211_destroy_auth_data(sdata, false);
cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
IEEE80211_DEAUTH_FRAME_LEN);
}
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 6fb38558a5e..7a17decd27f 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -333,7 +333,7 @@ void ieee80211_sw_roc_work(struct work_struct *work)
container_of(work, struct ieee80211_roc_work, work.work);
struct ieee80211_sub_if_data *sdata = roc->sdata;
struct ieee80211_local *local = sdata->local;
- bool started;
+ bool started, on_channel;
mutex_lock(&local->mtx);
@@ -354,14 +354,26 @@ void ieee80211_sw_roc_work(struct work_struct *work)
if (!roc->started) {
struct ieee80211_roc_work *dep;
- /* start this ROC */
- ieee80211_offchannel_stop_vifs(local);
+ WARN_ON(local->use_chanctx);
+
+ /* If actually operating on the desired channel (with at least
+ * 20 MHz channel width) don't stop all the operations but still
+ * treat it as though the ROC operation started properly, so
+ * other ROC operations won't interfere with this one.
+ */
+ roc->on_channel = roc->chan == local->_oper_chandef.chan &&
+ local->_oper_chandef.width != NL80211_CHAN_WIDTH_5 &&
+ local->_oper_chandef.width != NL80211_CHAN_WIDTH_10;
- /* switch channel etc */
+ /* start this ROC */
ieee80211_recalc_idle(local);
- local->tmp_channel = roc->chan;
- ieee80211_hw_config(local, 0);
+ if (!roc->on_channel) {
+ ieee80211_offchannel_stop_vifs(local);
+
+ local->tmp_channel = roc->chan;
+ ieee80211_hw_config(local, 0);
+ }
/* tell userspace or send frame */
ieee80211_handle_roc_started(roc);
@@ -380,9 +392,10 @@ void ieee80211_sw_roc_work(struct work_struct *work)
finish:
list_del(&roc->list);
started = roc->started;
+ on_channel = roc->on_channel;
ieee80211_roc_notify_destroy(roc, !roc->abort);
- if (started) {
+ if (started && !on_channel) {
ieee80211_flush_queues(local, NULL);
local->tmp_channel = NULL;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 216c45b949e..2b608b2b70e 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1231,7 +1231,8 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
if (ether_addr_equal(bssid, rx->sdata->u.ibss.bssid) &&
test_sta_flag(sta, WLAN_STA_AUTHORIZED)) {
sta->last_rx = jiffies;
- if (ieee80211_is_data(hdr->frame_control)) {
+ if (ieee80211_is_data(hdr->frame_control) &&
+ !is_multicast_ether_addr(hdr->addr1)) {
sta->last_rx_rate_idx = status->rate_idx;
sta->last_rx_rate_flag = status->flag;
sta->last_rx_rate_vht_flag = status->vht_flag;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 137a192e64b..847d92f6bef 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1148,7 +1148,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
atomic_dec(&ps->num_sta_ps);
/* This station just woke up and isn't aware of our SMPS state */
- if (!ieee80211_smps_is_restrictive(sta->known_smps_mode,
+ if (!ieee80211_vif_is_mesh(&sdata->vif) &&
+ !ieee80211_smps_is_restrictive(sta->known_smps_mode,
sdata->smps_mode) &&
sta->known_smps_mode != sdata->bss->req_smps &&
sta_info_tx_streams(sta) != 1) {
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 00ba90b02ab..60cb7a66597 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -314,10 +314,9 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local,
!is_multicast_ether_addr(hdr->addr1))
txflags |= IEEE80211_RADIOTAP_F_TX_FAIL;
- if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) ||
- (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT))
+ if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)
txflags |= IEEE80211_RADIOTAP_F_TX_CTS;
- else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS)
+ if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS)
txflags |= IEEE80211_RADIOTAP_F_TX_RTS;
put_unaligned_le16(txflags, pos);
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index a0b0aea7652..cec5b60487a 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -21,10 +21,10 @@
#define VIF_ENTRY __field(enum nl80211_iftype, vif_type) __field(void *, sdata) \
__field(bool, p2p) \
- __string(vif_name, sdata->dev ? sdata->dev->name : "<nodev>")
+ __string(vif_name, sdata->name)
#define VIF_ASSIGN __entry->vif_type = sdata->vif.type; __entry->sdata = sdata; \
__entry->p2p = sdata->vif.p2p; \
- __assign_str(vif_name, sdata->dev ? sdata->dev->name : sdata->name)
+ __assign_str(vif_name, sdata->name)
#define VIF_PR_FMT " vif:%s(%d%s)"
#define VIF_PR_ARG __get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : ""
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 275c94f995f..3c365837e91 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1780,7 +1780,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
mutex_unlock(&local->mtx);
if (sched_scan_stopped)
- cfg80211_sched_scan_stopped(local->hw.wiphy);
+ cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy);
/*
* If this is for hw restart things are still running.
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index e9e36a25616..9265adfdabf 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -129,9 +129,12 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
if (!vht_cap_ie || !sband->vht_cap.vht_supported)
return;
- /* A VHT STA must support 40 MHz */
- if (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40))
- return;
+ /*
+ * A VHT STA must support 40 MHz, but if we verify that here
+ * then we break a few things - some APs (e.g. Netgear R6300v2
+ * and others based on the BCM4360 chipset) will unset this
+ * capability bit when operating in 20 MHz.
+ */
vht_cap->vht_supported = true;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 4f26ee46b51..3d2d2c8108c 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1392,15 +1392,19 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
if (ipip) {
__be32 info = ic->un.gateway;
+ __u8 type = ic->type;
+ __u8 code = ic->code;
/* Update the MTU */
if (ic->type == ICMP_DEST_UNREACH &&
ic->code == ICMP_FRAG_NEEDED) {
struct ip_vs_dest *dest = cp->dest;
u32 mtu = ntohs(ic->un.frag.mtu);
+ __be16 frag_off = cih->frag_off;
/* Strip outer IP and ICMP, go to IPIP header */
- __skb_pull(skb, ihl + sizeof(_icmph));
+ if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL)
+ goto ignore_ipip;
offset2 -= ihl + sizeof(_icmph);
skb_reset_network_header(skb);
IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
@@ -1408,7 +1412,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
ipv4_update_pmtu(skb, dev_net(skb->dev),
mtu, 0, 0, 0, 0);
/* Client uses PMTUD? */
- if (!(cih->frag_off & htons(IP_DF)))
+ if (!(frag_off & htons(IP_DF)))
goto ignore_ipip;
/* Prefer the resulting PMTU */
if (dest) {
@@ -1427,12 +1431,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
/* Strip outer IP, ICMP and IPIP, go to IP header of
* original request.
*/
- __skb_pull(skb, offset2);
+ if (pskb_pull(skb, offset2) == NULL)
+ goto ignore_ipip;
skb_reset_network_header(skb);
IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
- ic->type, ic->code, ntohl(info));
- icmp_send(skb, ic->type, ic->code, info);
+ type, code, ntohl(info));
+ icmp_send(skb, type, code, info);
/* ICMP can be shorter but anyways, account it */
ip_vs_out_stats(cp, skb);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index ccc46fa5edb..58579634427 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1336,6 +1336,9 @@ ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
#ifdef CONFIG_NF_NAT_NEEDED
int ret;
+ if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
+ return 0;
+
ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST,
cda[CTA_NAT_DST]);
if (ret < 0)
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 804105391b9..345acfb1720 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -66,20 +66,6 @@ struct nft_jumpstack {
int rulenum;
};
-static inline void
-nft_chain_stats(const struct nft_chain *this, const struct nft_pktinfo *pkt,
- struct nft_jumpstack *jumpstack, unsigned int stackptr)
-{
- struct nft_stats __percpu *stats;
- const struct nft_chain *chain = stackptr ? jumpstack[0].chain : this;
-
- rcu_read_lock_bh();
- stats = rcu_dereference(nft_base_chain(chain)->stats);
- __this_cpu_inc(stats->pkts);
- __this_cpu_add(stats->bytes, pkt->skb->len);
- rcu_read_unlock_bh();
-}
-
enum nft_trace {
NFT_TRACE_RULE,
NFT_TRACE_RETURN,
@@ -117,13 +103,14 @@ static void nft_trace_packet(const struct nft_pktinfo *pkt,
unsigned int
nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
{
- const struct nft_chain *chain = ops->priv;
+ const struct nft_chain *chain = ops->priv, *basechain = chain;
const struct nft_rule *rule;
const struct nft_expr *expr, *last;
struct nft_data data[NFT_REG_MAX + 1];
unsigned int stackptr = 0;
struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
- int rulenum = 0;
+ struct nft_stats __percpu *stats;
+ int rulenum;
/*
* Cache cursor to avoid problems in case that the cursor is updated
* while traversing the ruleset.
@@ -131,6 +118,7 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
unsigned int gencursor = ACCESS_ONCE(chain->net->nft.gencursor);
do_chain:
+ rulenum = 0;
rule = list_entry(&chain->rules, struct nft_rule, list);
next_rule:
data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
@@ -156,8 +144,10 @@ next_rule:
switch (data[NFT_REG_VERDICT].verdict) {
case NFT_BREAK:
data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
- /* fall through */
+ continue;
case NFT_CONTINUE:
+ if (unlikely(pkt->skb->nf_trace))
+ nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
continue;
}
break;
@@ -183,37 +173,44 @@ next_rule:
jumpstack[stackptr].rule = rule;
jumpstack[stackptr].rulenum = rulenum;
stackptr++;
- /* fall through */
+ chain = data[NFT_REG_VERDICT].chain;
+ goto do_chain;
case NFT_GOTO:
+ if (unlikely(pkt->skb->nf_trace))
+ nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+
chain = data[NFT_REG_VERDICT].chain;
goto do_chain;
case NFT_RETURN:
if (unlikely(pkt->skb->nf_trace))
nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN);
-
- /* fall through */
+ break;
case NFT_CONTINUE:
+ if (unlikely(pkt->skb->nf_trace && !(chain->flags & NFT_BASE_CHAIN)))
+ nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN);
break;
default:
WARN_ON(1);
}
if (stackptr > 0) {
- if (unlikely(pkt->skb->nf_trace))
- nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN);
-
stackptr--;
chain = jumpstack[stackptr].chain;
rule = jumpstack[stackptr].rule;
rulenum = jumpstack[stackptr].rulenum;
goto next_rule;
}
- nft_chain_stats(chain, pkt, jumpstack, stackptr);
if (unlikely(pkt->skb->nf_trace))
- nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_POLICY);
+ nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY);
+
+ rcu_read_lock_bh();
+ stats = rcu_dereference(nft_base_chain(basechain)->stats);
+ __this_cpu_inc(stats->pkts);
+ __this_cpu_add(stats->bytes, pkt->skb->len);
+ rcu_read_unlock_bh();
- return nft_base_chain(chain)->policy;
+ return nft_base_chain(basechain)->policy;
}
EXPORT_SYMBOL_GPL(nft_do_chain);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index e8138da4c14..23ef77c60ff 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -256,15 +256,15 @@ replay:
#endif
{
nfnl_unlock(subsys_id);
- kfree_skb(nskb);
- return netlink_ack(skb, nlh, -EOPNOTSUPP);
+ netlink_ack(skb, nlh, -EOPNOTSUPP);
+ return kfree_skb(nskb);
}
}
if (!ss->commit || !ss->abort) {
nfnl_unlock(subsys_id);
- kfree_skb(nskb);
- return netlink_ack(skb, nlh, -EOPNOTSUPP);
+ netlink_ack(skb, nlh, -EOPNOTSUPP);
+ return kfree_skb(skb);
}
while (skb->len >= nlmsg_total_size(0)) {
@@ -368,14 +368,13 @@ done:
static void nfnetlink_rcv(struct sk_buff *skb)
{
struct nlmsghdr *nlh = nlmsg_hdr(skb);
- struct net *net = sock_net(skb->sk);
int msglen;
if (nlh->nlmsg_len < NLMSG_HDRLEN ||
skb->len < nlh->nlmsg_len)
return;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+ if (!netlink_net_capable(skb, CAP_NET_ADMIN)) {
netlink_ack(skb, nlh, -EPERM);
return;
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 894cda0206b..f22757a29cd 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1360,7 +1360,74 @@ retry:
return err;
}
-static inline int netlink_capable(const struct socket *sock, unsigned int flag)
+/**
+ * __netlink_ns_capable - General netlink message capability test
+ * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace.
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+ struct user_namespace *user_ns, int cap)
+{
+ return ((nsp->flags & NETLINK_SKB_DST) ||
+ file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
+ ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(__netlink_ns_capable);
+
+/**
+ * netlink_ns_capable - General netlink message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool netlink_ns_capable(const struct sk_buff *skb,
+ struct user_namespace *user_ns, int cap)
+{
+ return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_ns_capable);
+
+/**
+ * netlink_capable - Netlink global message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in all user namespaces.
+ */
+bool netlink_capable(const struct sk_buff *skb, int cap)
+{
+ return netlink_ns_capable(skb, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_capable);
+
+/**
+ * netlink_net_capable - Netlink network namespace message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap over the network namespace of
+ * the socket we received the message from.
+ */
+bool netlink_net_capable(const struct sk_buff *skb, int cap)
+{
+ return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_net_capable);
+
+static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
{
return (nl_table[sock->sk->sk_protocol].flags & flag) ||
ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
@@ -1428,7 +1495,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
/* Only superuser is allowed to listen multicasts */
if (nladdr->nl_groups) {
- if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+ if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
return -EPERM;
err = netlink_realloc_groups(sk);
if (err)
@@ -1490,7 +1557,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
return -EINVAL;
if ((nladdr->nl_groups || nladdr->nl_pid) &&
- !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+ !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
return -EPERM;
if (!nlk->portid)
@@ -2096,7 +2163,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
break;
case NETLINK_ADD_MEMBERSHIP:
case NETLINK_DROP_MEMBERSHIP: {
- if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+ if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
return -EPERM;
err = netlink_realloc_groups(sk);
if (err)
@@ -2228,6 +2295,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
struct sk_buff *skb;
int err;
struct scm_cookie scm;
+ u32 netlink_skb_flags = 0;
if (msg->msg_flags&MSG_OOB)
return -EOPNOTSUPP;
@@ -2247,8 +2315,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
dst_group = ffs(addr->nl_groups);
err = -EPERM;
if ((dst_group || dst_portid) &&
- !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+ !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
goto out;
+ netlink_skb_flags |= NETLINK_SKB_DST;
} else {
dst_portid = nlk->dst_portid;
dst_group = nlk->dst_group;
@@ -2278,6 +2347,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
NETLINK_CB(skb).portid = nlk->portid;
NETLINK_CB(skb).dst_group = dst_group;
NETLINK_CB(skb).creds = siocb->scm->creds;
+ NETLINK_CB(skb).flags = netlink_skb_flags;
err = -EFAULT;
if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index b1dcdb932a8..a3ba3ca0ff9 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -561,7 +561,7 @@ static int genl_family_rcv_msg(struct genl_family *family,
return -EOPNOTSUPP;
if ((ops->flags & GENL_ADMIN_PERM) &&
- !capable(CAP_NET_ADMIN))
+ !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) {
diff --git a/net/packet/diag.c b/net/packet/diag.c
index 533ce4ff108..92f2c7107ee 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -128,6 +128,7 @@ static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb)
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
struct packet_diag_req *req,
+ bool may_report_filterinfo,
struct user_namespace *user_ns,
u32 portid, u32 seq, u32 flags, int sk_ino)
{
@@ -172,7 +173,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
goto out_nlmsg_trim;
if ((req->pdiag_show & PACKET_SHOW_FILTER) &&
- sock_diag_put_filterinfo(user_ns, sk, skb, PACKET_DIAG_FILTER))
+ sock_diag_put_filterinfo(may_report_filterinfo, sk, skb,
+ PACKET_DIAG_FILTER))
goto out_nlmsg_trim;
return nlmsg_end(skb, nlh);
@@ -188,9 +190,11 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
struct packet_diag_req *req;
struct net *net;
struct sock *sk;
+ bool may_report_filterinfo;
net = sock_net(skb->sk);
req = nlmsg_data(cb->nlh);
+ may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
mutex_lock(&net->packet.sklist_lock);
sk_for_each(sk, &net->packet.sklist) {
@@ -200,6 +204,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
goto next;
if (sk_diag_fill(sk, skb, req,
+ may_report_filterinfo,
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index dc15f430080..b64151ade6b 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -70,10 +70,10 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
int err;
u8 pnaddr;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
- if (!capable(CAP_SYS_ADMIN))
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
return -EPERM;
ASSERT_RTNL();
@@ -233,10 +233,10 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
int err;
u8 dst;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
- if (!capable(CAP_SYS_ADMIN))
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
return -EPERM;
ASSERT_RTNL();
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index 7633a752c65..0ad080790a3 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -99,7 +99,7 @@ static int rxrpc_instantiate_xdr_rxkad(struct key *key, const __be32 *xdr,
_debug("tktlen: %x", tktlen);
if (tktlen > AFSTOKEN_RK_TIX_MAX)
return -EKEYREJECTED;
- if (8 * 4 + tktlen != toklen)
+ if (toklen < 8 * 4 + tktlen)
return -EKEYREJECTED;
plen = sizeof(*token) + sizeof(*token->kad) + tktlen;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 8a5ba5add4b..648778aef1a 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -948,7 +948,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n)
u32 portid = skb ? NETLINK_CB(skb).portid : 0;
int ret = 0, ovr = 0;
- if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN))
+ if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 29a30a14c31..bdbdb1a7920 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -134,7 +134,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
int err;
int tp_created = 0;
- if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN))
+ if ((n->nlmsg_type != RTM_GETTFILTER) && !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
replay:
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index eed8404443d..f435a88d899 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -188,6 +188,12 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
[TCA_TCINDEX_CLASSID] = { .type = NLA_U32 },
};
+static void tcindex_filter_result_init(struct tcindex_filter_result *r)
+{
+ memset(r, 0, sizeof(*r));
+ tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+}
+
static int
tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
u32 handle, struct tcindex_data *p,
@@ -207,15 +213,11 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
return err;
memcpy(&cp, p, sizeof(cp));
- memset(&new_filter_result, 0, sizeof(new_filter_result));
- tcf_exts_init(&new_filter_result.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+ tcindex_filter_result_init(&new_filter_result);
+ tcindex_filter_result_init(&cr);
if (old_r)
- memcpy(&cr, r, sizeof(cr));
- else {
- memset(&cr, 0, sizeof(cr));
- tcf_exts_init(&cr.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
- }
+ cr.res = r->res;
if (tb[TCA_TCINDEX_HASH])
cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -267,9 +269,14 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
err = -ENOMEM;
if (!cp.perfect && !cp.h) {
if (valid_perfect_hash(&cp)) {
+ int i;
+
cp.perfect = kcalloc(cp.hash, sizeof(*r), GFP_KERNEL);
if (!cp.perfect)
goto errout;
+ for (i = 0; i < cp.hash; i++)
+ tcf_exts_init(&cp.perfect[i].exts, TCA_TCINDEX_ACT,
+ TCA_TCINDEX_POLICE);
balloc = 1;
} else {
cp.h = kcalloc(cp.hash, sizeof(f), GFP_KERNEL);
@@ -295,14 +302,17 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
tcf_bind_filter(tp, &cr.res, base);
}
- tcf_exts_change(tp, &cr.exts, &e);
+ if (old_r)
+ tcf_exts_change(tp, &r->exts, &e);
+ else
+ tcf_exts_change(tp, &cr.exts, &e);
tcf_tree_lock(tp);
if (old_r && old_r != r)
- memset(old_r, 0, sizeof(*old_r));
+ tcindex_filter_result_init(old_r);
memcpy(p, &cp, sizeof(cp));
- memcpy(r, &cr, sizeof(cr));
+ r->res = cr.res;
if (r == &new_filter_result) {
struct tcindex_filter **fp;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index a0b84e0e22d..400769014bb 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1084,7 +1084,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
struct Qdisc *p = NULL;
int err;
- if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN))
+ if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
@@ -1151,7 +1151,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
struct Qdisc *q, *p;
int err;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
replay:
@@ -1490,7 +1490,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n)
u32 qid;
int err;
- if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN))
+ if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index edee03d922e..6e957c3b985 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -553,11 +553,6 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
if (err < 0)
return err;
- sch_tree_lock(sch);
-
- if (tb[TCA_HHF_BACKLOG_LIMIT])
- sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]);
-
if (tb[TCA_HHF_QUANTUM])
new_quantum = nla_get_u32(tb[TCA_HHF_QUANTUM]);
@@ -567,6 +562,12 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight;
if (non_hh_quantum > INT_MAX)
return -EINVAL;
+
+ sch_tree_lock(sch);
+
+ if (tb[TCA_HHF_BACKLOG_LIMIT])
+ sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]);
+
q->quantum = new_quantum;
q->hhf_non_hh_weight = new_hhf_non_hh_weight;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index c09757fbf80..44cbb54c857 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -491,8 +491,13 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
continue;
if ((laddr->state == SCTP_ADDR_SRC) &&
(AF_INET == laddr->a.sa.sa_family)) {
- fl4->saddr = laddr->a.v4.sin_addr.s_addr;
fl4->fl4_sport = laddr->a.v4.sin_port;
+ flowi4_update_output(fl4,
+ asoc->base.sk->sk_bound_dev_if,
+ RT_CONN_FLAGS(asoc->base.sk),
+ daddr->v4.sin_addr.s_addr,
+ laddr->a.v4.sin_addr.s_addr);
+
rt = ip_route_output_key(sock_net(sk), fl4);
if (!IS_ERR(rt)) {
dst = &rt->dst;
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 5d6883ff00c..fef2acdf4a2 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -496,11 +496,10 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands,
/* If the transport error count is greater than the pf_retrans
* threshold, and less than pathmaxrtx, and if the current state
- * is not SCTP_UNCONFIRMED, then mark this transport as Partially
- * Failed, see SCTP Quick Failover Draft, section 5.1
+ * is SCTP_ACTIVE, then mark this transport as Partially Failed,
+ * see SCTP Quick Failover Draft, section 5.1
*/
- if ((transport->state != SCTP_PF) &&
- (transport->state != SCTP_UNCONFIRMED) &&
+ if ((transport->state == SCTP_ACTIVE) &&
(asoc->pf_retrans < transport->pathmaxrxt) &&
(transport->error_count > asoc->pf_retrans)) {
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 3aaf73de9e2..ad844d36534 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -47,7 +47,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
u16 cmd;
- if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN)))
+ if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN)))
cmd = TIPC_CMD_NOT_NET_ADMIN;
else
cmd = req_userhdr->cmd;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 5adfd94c5b8..85d232bed87 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1925,9 +1925,23 @@ static struct miscdevice vsock_device = {
.fops = &vsock_device_ops,
};
-static int __vsock_core_init(void)
+int __vsock_core_init(const struct vsock_transport *t, struct module *owner)
{
- int err;
+ int err = mutex_lock_interruptible(&vsock_register_mutex);
+
+ if (err)
+ return err;
+
+ if (transport) {
+ err = -EBUSY;
+ goto err_busy;
+ }
+
+ /* Transport must be the owner of the protocol so that it can't
+ * unload while there are open sockets.
+ */
+ vsock_proto.owner = owner;
+ transport = t;
vsock_init_tables();
@@ -1951,36 +1965,19 @@ static int __vsock_core_init(void)
goto err_unregister_proto;
}
+ mutex_unlock(&vsock_register_mutex);
return 0;
err_unregister_proto:
proto_unregister(&vsock_proto);
err_misc_deregister:
misc_deregister(&vsock_device);
- return err;
-}
-
-int vsock_core_init(const struct vsock_transport *t)
-{
- int retval = mutex_lock_interruptible(&vsock_register_mutex);
- if (retval)
- return retval;
-
- if (transport) {
- retval = -EBUSY;
- goto out;
- }
-
- transport = t;
- retval = __vsock_core_init();
- if (retval)
- transport = NULL;
-
-out:
+ transport = NULL;
+err_busy:
mutex_unlock(&vsock_register_mutex);
- return retval;
+ return err;
}
-EXPORT_SYMBOL_GPL(vsock_core_init);
+EXPORT_SYMBOL_GPL(__vsock_core_init);
void vsock_core_exit(void)
{
@@ -2000,5 +1997,5 @@ EXPORT_SYMBOL_GPL(vsock_core_exit);
MODULE_AUTHOR("VMware, Inc.");
MODULE_DESCRIPTION("VMware Virtual Socket Family");
-MODULE_VERSION("1.0.0.0-k");
+MODULE_VERSION("1.0.1.0-k");
MODULE_LICENSE("GPL v2");
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 7d09a712cb1..88f108edfb5 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -284,14 +284,22 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy)
}
EXPORT_SYMBOL(cfg80211_sched_scan_results);
-void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy)
{
struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+ ASSERT_RTNL();
+
trace_cfg80211_sched_scan_stopped(wiphy);
- rtnl_lock();
__cfg80211_stop_sched_scan(rdev, true);
+}
+EXPORT_SYMBOL(cfg80211_sched_scan_stopped_rtnl);
+
+void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+{
+ rtnl_lock();
+ cfg80211_sched_scan_stopped_rtnl(wiphy);
rtnl_unlock();
}
EXPORT_SYMBOL(cfg80211_sched_scan_stopped);
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index acdcb4a8181..3546a77033d 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -234,7 +234,6 @@ void cfg80211_conn_work(struct work_struct *work)
NULL, 0, NULL, 0,
WLAN_STATUS_UNSPECIFIED_FAILURE,
false, NULL);
- cfg80211_sme_free(wdev);
}
wdev_unlock(wdev);
}
@@ -648,6 +647,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
cfg80211_unhold_bss(bss_from_pub(bss));
cfg80211_put_bss(wdev->wiphy, bss);
}
+ cfg80211_sme_free(wdev);
return;
}
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 8f131c10a6f..51398ae6cda 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2377,7 +2377,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
link = &xfrm_dispatch[type];
/* All operations require privileges, even GET */
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ if (!netlink_net_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||