aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c96
-rw-r--r--net/Kconfig3
-rw-r--r--net/appletalk/ddp.c2
-rw-r--r--net/atm/common.c4
-rw-r--r--net/atm/common.h2
-rw-r--r--net/atm/pvc.c2
-rw-r--r--net/atm/svc.c2
-rw-r--r--net/ax25/af_ax25.c4
-rw-r--r--net/batman-adv/Makefile6
-rw-r--r--net/batman-adv/bat_algo.h2
-rw-r--r--net/batman-adv/bat_iv_ogm.c210
-rw-r--r--net/batman-adv/bitarray.c6
-rw-r--r--net/batman-adv/bitarray.h8
-rw-r--r--net/batman-adv/bridge_loop_avoidance.c56
-rw-r--r--net/batman-adv/bridge_loop_avoidance.h12
-rw-r--r--net/batman-adv/debugfs.c47
-rw-r--r--net/batman-adv/debugfs.h43
-rw-r--r--net/batman-adv/distributed-arp-table.c47
-rw-r--r--net/batman-adv/distributed-arp-table.h15
-rw-r--r--net/batman-adv/fragmentation.c44
-rw-r--r--net/batman-adv/fragmentation.h11
-rw-r--r--net/batman-adv/gateway_client.c41
-rw-r--r--net/batman-adv/gateway_client.h10
-rw-r--r--net/batman-adv/gateway_common.c13
-rw-r--r--net/batman-adv/gateway_common.h9
-rw-r--r--net/batman-adv/hard-interface.c40
-rw-r--r--net/batman-adv/hard-interface.h13
-rw-r--r--net/batman-adv/hash.c8
-rw-r--r--net/batman-adv/hash.h33
-rw-r--r--net/batman-adv/icmp_socket.c35
-rw-r--r--net/batman-adv/icmp_socket.h9
-rw-r--r--net/batman-adv/main.c103
-rw-r--r--net/batman-adv/main.h40
-rw-r--r--net/batman-adv/multicast.c31
-rw-r--r--net/batman-adv/multicast.h8
-rw-r--r--net/batman-adv/network-coding.c53
-rw-r--r--net/batman-adv/network-coding.h15
-rw-r--r--net/batman-adv/originator.c36
-rw-r--r--net/batman-adv/originator.h28
-rw-r--r--net/batman-adv/packet.h5
-rw-r--r--net/batman-adv/routing.c38
-rw-r--r--net/batman-adv/routing.h12
-rw-r--r--net/batman-adv/send.c40
-rw-r--r--net/batman-adv/send.h15
-rw-r--r--net/batman-adv/soft-interface.c72
-rw-r--r--net/batman-adv/soft-interface.h13
-rw-r--r--net/batman-adv/sysfs.c62
-rw-r--r--net/batman-adv/sysfs.h12
-rw-r--r--net/batman-adv/translation-table.c91
-rw-r--r--net/batman-adv/translation-table.h11
-rw-r--r--net/batman-adv/types.h33
-rw-r--r--net/bluetooth/6lowpan.c2
-rw-r--r--net/bluetooth/bnep/sock.c2
-rw-r--r--net/bluetooth/cmtp/sock.c2
-rw-r--r--net/bluetooth/hci_core.c5
-rw-r--r--net/bluetooth/hci_sock.c2
-rw-r--r--net/bluetooth/hidp/sock.c2
-rw-r--r--net/bluetooth/l2cap_sock.c10
-rw-r--r--net/bluetooth/mgmt.c6
-rw-r--r--net/bluetooth/rfcomm/core.c2
-rw-r--r--net/bluetooth/rfcomm/sock.c8
-rw-r--r--net/bluetooth/sco.c8
-rw-r--r--net/bluetooth/smp.c20
-rw-r--r--net/bridge/br.c22
-rw-r--r--net/bridge/br_fdb.c14
-rw-r--r--net/bridge/br_multicast.c262
-rw-r--r--net/bridge/br_netfilter.c40
-rw-r--r--net/bridge/br_netlink.c24
-rw-r--r--net/bridge/br_private.h4
-rw-r--r--net/bridge/br_stp.c6
-rw-r--r--net/bridge/netfilter/ebt_stp.c6
-rw-r--r--net/bridge/netfilter/ebtables.c2
-rw-r--r--net/caif/caif_socket.c2
-rw-r--r--net/can/af_can.c2
-rw-r--r--net/can/gw.c68
-rw-r--r--net/ceph/messenger.c4
-rw-r--r--net/core/dev.c220
-rw-r--r--net/core/ethtool.c13
-rw-r--r--net/core/filter.c259
-rw-r--r--net/core/flow_dissector.c656
-rw-r--r--net/core/neighbour.c3
-rw-r--r--net/core/net-sysfs.c10
-rw-r--r--net/core/net_namespace.c133
-rw-r--r--net/core/netevent.c5
-rw-r--r--net/core/pktgen.c110
-rw-r--r--net/core/rtnetlink.c12
-rw-r--r--net/core/secure_seq.c2
-rw-r--r--net/core/skbuff.c387
-rw-r--r--net/core/sock.c44
-rw-r--r--net/core/stream.c6
-rw-r--r--net/core/utils.c12
-rw-r--r--net/decnet/af_decnet.c8
-rw-r--r--net/dsa/slave.c54
-rw-r--r--net/ethernet/eth.c15
-rw-r--r--net/ieee802154/6lowpan/core.c28
-rw-r--r--net/ieee802154/6lowpan/tx.c2
-rw-r--r--net/ieee802154/core.c2
-rw-r--r--net/ieee802154/nl-mac.c39
-rw-r--r--net/ieee802154/nl-phy.c10
-rw-r--r--net/ieee802154/nl802154.c276
-rw-r--r--net/ieee802154/rdev-ops.h23
-rw-r--r--net/ieee802154/socket.c22
-rw-r--r--net/ieee802154/trace.h32
-rw-r--r--net/ipv4/Kconfig24
-rw-r--r--net/ipv4/Makefile3
-rw-r--r--net/ipv4/af_inet.c11
-rw-r--r--net/ipv4/fib_semantics.c4
-rw-r--r--net/ipv4/fib_trie.c62
-rw-r--r--net/ipv4/geneve_core.c (renamed from net/ipv4/geneve.c)10
-rw-r--r--net/ipv4/igmp.c162
-rw-r--r--net/ipv4/inet_connection_sock.c19
-rw-r--r--net/ipv4/inet_hashtables.c57
-rw-r--r--net/ipv4/inet_timewait_sock.c2
-rw-r--r--net/ipv4/ip_forward.c18
-rw-r--r--net/ipv4/ip_fragment.c46
-rw-r--r--net/ipv4/ip_output.c84
-rw-r--r--net/ipv4/ip_sockglue.c7
-rw-r--r--net/ipv4/ip_tunnel_core.c20
-rw-r--r--net/ipv4/ipip.c3
-rw-r--r--net/ipv4/netfilter/ip_tables.c4
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c5
-rw-r--r--net/ipv4/netfilter/ipt_SYNPROXY.c4
-rw-r--r--net/ipv4/proc.c2
-rw-r--r--net/ipv4/route.c23
-rw-r--r--net/ipv4/syncookies.c10
-rw-r--r--net/ipv4/sysctl_net_ipv4.c25
-rw-r--r--net/ipv4/tcp.c89
-rw-r--r--net/ipv4/tcp_cdg.c433
-rw-r--r--net/ipv4/tcp_dctcp.c26
-rw-r--r--net/ipv4/tcp_input.c139
-rw-r--r--net/ipv4/tcp_ipv4.c15
-rw-r--r--net/ipv4/tcp_minisocks.c4
-rw-r--r--net/ipv4/tcp_offload.c4
-rw-r--r--net/ipv4/tcp_output.c106
-rw-r--r--net/ipv4/tcp_timer.c4
-rw-r--r--net/ipv4/udp_tunnel.c8
-rw-r--r--net/ipv6/Makefile1
-rw-r--r--net/ipv6/addrconf.c2
-rw-r--r--net/ipv6/af_inet6.c6
-rw-r--r--net/ipv6/icmp.c6
-rw-r--r--net/ipv6/inet6_hashtables.c8
-rw-r--r--net/ipv6/ip6_fib.c25
-rw-r--r--net/ipv6/ip6_flowlabel.c4
-rw-r--r--net/ipv6/ip6_output.c60
-rw-r--r--net/ipv6/ip6_tunnel.c2
-rw-r--r--net/ipv6/ip6_udp_tunnel.c6
-rw-r--r--net/ipv6/mcast_snoop.c213
-rw-r--r--net/ipv6/ndisc.c2
-rw-r--r--net/ipv6/netfilter/ip6_tables.c4
-rw-r--r--net/ipv6/output_core.c13
-rw-r--r--net/ipv6/raw.c11
-rw-r--r--net/ipv6/route.c561
-rw-r--r--net/ipv6/syncookies.c19
-rw-r--r--net/ipv6/sysctl_net_ipv6.c8
-rw-r--r--net/ipv6/tcp_ipv6.c16
-rw-r--r--net/ipv6/xfrm6_policy.c20
-rw-r--r--net/ipx/af_ipx.c2
-rw-r--r--net/irda/af_irda.c2
-rw-r--r--net/irda/timer.c4
-rw-r--r--net/iucv/af_iucv.c10
-rw-r--r--net/key/af_key.c2
-rw-r--r--net/l2tp/l2tp_core.c15
-rw-r--r--net/l2tp/l2tp_ppp.c4
-rw-r--r--net/llc/af_llc.c2
-rw-r--r--net/llc/llc_conn.c6
-rw-r--r--net/mac80211/Kconfig16
-rw-r--r--net/mac80211/agg-tx.c4
-rw-r--r--net/mac80211/cfg.c214
-rw-r--r--net/mac80211/chan.c10
-rw-r--r--net/mac80211/debugfs.c177
-rw-r--r--net/mac80211/debugfs_key.c17
-rw-r--r--net/mac80211/debugfs_sta.c85
-rw-r--r--net/mac80211/driver-ops.h13
-rw-r--r--net/mac80211/ethtool.c3
-rw-r--r--net/mac80211/ibss.c6
-rw-r--r--net/mac80211/ieee80211_i.h36
-rw-r--r--net/mac80211/iface.c74
-rw-r--r--net/mac80211/key.c96
-rw-r--r--net/mac80211/key.h7
-rw-r--r--net/mac80211/led.c268
-rw-r--r--net/mac80211/led.h44
-rw-r--r--net/mac80211/main.c34
-rw-r--r--net/mac80211/mesh.c1
-rw-r--r--net/mac80211/mesh_hwmp.c35
-rw-r--r--net/mac80211/mesh_plink.c44
-rw-r--r--net/mac80211/mlme.c247
-rw-r--r--net/mac80211/offchannel.c2
-rw-r--r--net/mac80211/pm.c4
-rw-r--r--net/mac80211/rate.c14
-rw-r--r--net/mac80211/rate.h14
-rw-r--r--net/mac80211/rc80211_minstrel_ht.c2
-rw-r--r--net/mac80211/rx.c227
-rw-r--r--net/mac80211/scan.c18
-rw-r--r--net/mac80211/sta_info.c24
-rw-r--r--net/mac80211/sta_info.h44
-rw-r--r--net/mac80211/status.c163
-rw-r--r--net/mac80211/tdls.c52
-rw-r--r--net/mac80211/trace.h42
-rw-r--r--net/mac80211/tx.c549
-rw-r--r--net/mac80211/util.c6
-rw-r--r--net/mac80211/wpa.c10
-rw-r--r--net/mac802154/Kconfig1
-rw-r--r--net/mac802154/cfg.c101
-rw-r--r--net/mac802154/driver-ops.h8
-rw-r--r--net/mac802154/ieee802154_i.h7
-rw-r--r--net/mac802154/iface.c30
-rw-r--r--net/mac802154/mac_cmd.c42
-rw-r--r--net/mac802154/main.c32
-rw-r--r--net/mac802154/mib.c63
-rw-r--r--net/mac802154/rx.c5
-rw-r--r--net/mac802154/util.c5
-rw-r--r--net/mpls/mpls_gso.c2
-rw-r--r--net/netfilter/Kconfig13
-rw-r--r--net/netfilter/Makefile1
-rw-r--r--net/netfilter/core.c37
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_ip.c17
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_ipmac.c13
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_port.c3
-rw-r--r--net/netfilter/ipset/ip_set_core.c49
-rw-r--r--net/netfilter/ipset/ip_set_getport.c6
-rw-r--r--net/netfilter/ipset/ip_set_hash_gen.h22
-rw-r--r--net/netfilter/ipset/ip_set_hash_ip.c33
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipmark.c43
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipport.c49
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportip.c40
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportnet.c40
-rw-r--r--net/netfilter/ipset/ip_set_hash_mac.c11
-rw-r--r--net/netfilter/ipset/ip_set_hash_net.c28
-rw-r--r--net/netfilter/ipset/ip_set_hash_netiface.c29
-rw-r--r--net/netfilter/ipset/ip_set_hash_netnet.c30
-rw-r--r--net/netfilter/ipset/ip_set_hash_netport.c38
-rw-r--r--net/netfilter/ipset/ip_set_hash_netportnet.c52
-rw-r--r--net/netfilter/ipset/ip_set_list_set.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c30
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c19
-rw-r--r--net/netfilter/nf_conntrack_h323_main.c4
-rw-r--r--net/netfilter/nf_tables_api.c46
-rw-r--r--net/netfilter/nf_tables_netdev.c183
-rw-r--r--net/netfilter/nfnetlink_queue_core.c2
-rw-r--r--net/netfilter/nft_compat.c2
-rw-r--r--net/netfilter/x_tables.c18
-rw-r--r--net/netfilter/xt_TCPMSS.c6
-rw-r--r--net/netfilter/xt_TEE.c1
-rw-r--r--net/netfilter/xt_addrtype.c2
-rw-r--r--net/netfilter/xt_mark.c1
-rw-r--r--net/netfilter/xt_set.c3
-rw-r--r--net/netlink/af_netlink.c148
-rw-r--r--net/netrom/af_netrom.c4
-rw-r--r--net/nfc/af_nfc.c2
-rw-r--r--net/nfc/llcp.h2
-rw-r--r--net/nfc/llcp_core.c2
-rw-r--r--net/nfc/llcp_sock.c8
-rw-r--r--net/nfc/nfc.h2
-rw-r--r--net/nfc/rawsock.c4
-rw-r--r--net/openvswitch/Kconfig2
-rw-r--r--net/openvswitch/actions.c23
-rw-r--r--net/openvswitch/datapath.c20
-rw-r--r--net/openvswitch/datapath.h2
-rw-r--r--net/openvswitch/flow.c4
-rw-r--r--net/openvswitch/flow_netlink.c2
-rw-r--r--net/openvswitch/vport-geneve.c5
-rw-r--r--net/packet/af_packet.c173
-rw-r--r--net/packet/internal.h12
-rw-r--r--net/phonet/af_phonet.c2
-rw-r--r--net/phonet/pep.c2
-rw-r--r--net/rds/af_rds.c43
-rw-r--r--net/rds/bind.c4
-rw-r--r--net/rds/rds.h6
-rw-r--r--net/rds/transport.c21
-rw-r--r--net/rfkill/core.c12
-rw-r--r--net/rfkill/rfkill-gpio.c24
-rw-r--r--net/rose/af_rose.c4
-rw-r--r--net/rxrpc/af_rxrpc.c2
-rw-r--r--net/rxrpc/ar-local.c4
-rw-r--r--net/sched/Kconfig11
-rw-r--r--net/sched/Makefile1
-rw-r--r--net/sched/act_api.c5
-rw-r--r--net/sched/act_bpf.c9
-rw-r--r--net/sched/act_mirred.c2
-rw-r--r--net/sched/act_pedit.c5
-rw-r--r--net/sched/cls_bpf.c16
-rw-r--r--net/sched/cls_flow.c28
-rw-r--r--net/sched/cls_flower.c691
-rw-r--r--net/sched/sch_api.c12
-rw-r--r--net/sched/sch_choke.c20
-rw-r--r--net/sched/sch_codel.c15
-rw-r--r--net/sched/sch_fq_codel.c26
-rw-r--r--net/sched/sch_gred.c28
-rw-r--r--net/sched/sch_hhf.c19
-rw-r--r--net/sched/sch_ingress.c59
-rw-r--r--net/sched/sch_netem.c4
-rw-r--r--net/sched/sch_sfb.c24
-rw-r--r--net/sched/sch_sfq.c27
-rw-r--r--net/sctp/ipv6.c7
-rw-r--r--net/sctp/protocol.c2
-rw-r--r--net/socket.c7
-rw-r--r--net/switchdev/switchdev.c835
-rw-r--r--net/tipc/addr.c7
-rw-r--r--net/tipc/addr.h8
-rw-r--r--net/tipc/bcast.c41
-rw-r--r--net/tipc/bcast.h1
-rw-r--r--net/tipc/bearer.c20
-rw-r--r--net/tipc/bearer.h2
-rw-r--r--net/tipc/core.c4
-rw-r--r--net/tipc/core.h37
-rw-r--r--net/tipc/link.c311
-rw-r--r--net/tipc/link.h59
-rw-r--r--net/tipc/msg.c51
-rw-r--r--net/tipc/msg.h37
-rw-r--r--net/tipc/name_table.c34
-rw-r--r--net/tipc/net.c1
-rw-r--r--net/tipc/netlink_compat.c137
-rw-r--r--net/tipc/node.c3
-rw-r--r--net/tipc/node.h2
-rw-r--r--net/tipc/server.c6
-rw-r--r--net/tipc/socket.c10
-rw-r--r--net/tipc/subscr.c242
-rw-r--r--net/tipc/subscr.h18
-rw-r--r--net/unix/af_unix.c267
-rw-r--r--net/vmw_vsock/af_vsock.c7
-rw-r--r--net/vmw_vsock/vmci_transport.c2
-rw-r--r--net/wireless/chan.c65
-rw-r--r--net/wireless/core.h1
-rw-r--r--net/wireless/nl80211.c7
-rw-r--r--net/wireless/reg.c4
-rw-r--r--net/wireless/sme.c4
-rw-r--r--net/wireless/sysfs.c14
-rw-r--r--net/wireless/util.c5
-rw-r--r--net/x25/af_x25.c8
-rw-r--r--net/xfrm/xfrm_input.c12
-rw-r--r--net/xfrm/xfrm_output.c12
-rw-r--r--net/xfrm/xfrm_policy.c42
-rw-r--r--net/xfrm/xfrm_state.c4
333 files changed, 10036 insertions, 4539 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 59555f0f8fc8..d2cd9de4b724 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -618,6 +618,92 @@ out:
return err;
}
+static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
+ struct sk_buff *skb)
+{
+ struct sk_buff *p, **pp = NULL;
+ struct vlan_hdr *vhdr;
+ unsigned int hlen, off_vlan;
+ const struct packet_offload *ptype;
+ __be16 type;
+ int flush = 1;
+
+ off_vlan = skb_gro_offset(skb);
+ hlen = off_vlan + sizeof(*vhdr);
+ vhdr = skb_gro_header_fast(skb, off_vlan);
+ if (skb_gro_header_hard(skb, hlen)) {
+ vhdr = skb_gro_header_slow(skb, hlen, off_vlan);
+ if (unlikely(!vhdr))
+ goto out;
+ }
+
+ type = vhdr->h_vlan_encapsulated_proto;
+
+ rcu_read_lock();
+ ptype = gro_find_receive_by_type(type);
+ if (!ptype)
+ goto out_unlock;
+
+ flush = 0;
+
+ for (p = *head; p; p = p->next) {
+ struct vlan_hdr *vhdr2;
+
+ if (!NAPI_GRO_CB(p)->same_flow)
+ continue;
+
+ vhdr2 = (struct vlan_hdr *)(p->data + off_vlan);
+ if (compare_vlan_header(vhdr, vhdr2))
+ NAPI_GRO_CB(p)->same_flow = 0;
+ }
+
+ skb_gro_pull(skb, sizeof(*vhdr));
+ skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
+ pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+ rcu_read_unlock();
+out:
+ NAPI_GRO_CB(skb)->flush |= flush;
+
+ return pp;
+}
+
+static int vlan_gro_complete(struct sk_buff *skb, int nhoff)
+{
+ struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + nhoff);
+ __be16 type = vhdr->h_vlan_encapsulated_proto;
+ struct packet_offload *ptype;
+ int err = -ENOENT;
+
+ rcu_read_lock();
+ ptype = gro_find_complete_by_type(type);
+ if (ptype)
+ err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(*vhdr));
+
+ rcu_read_unlock();
+ return err;
+}
+
+static struct packet_offload vlan_packet_offloads[] __read_mostly = {
+ {
+ .type = cpu_to_be16(ETH_P_8021Q),
+ .priority = 10,
+ .callbacks = {
+ .gro_receive = vlan_gro_receive,
+ .gro_complete = vlan_gro_complete,
+ },
+ },
+ {
+ .type = cpu_to_be16(ETH_P_8021AD),
+ .priority = 10,
+ .callbacks = {
+ .gro_receive = vlan_gro_receive,
+ .gro_complete = vlan_gro_complete,
+ },
+ },
+};
+
static int __net_init vlan_init_net(struct net *net)
{
struct vlan_net *vn = net_generic(net, vlan_net_id);
@@ -645,6 +731,7 @@ static struct pernet_operations vlan_net_ops = {
static int __init vlan_proto_init(void)
{
int err;
+ unsigned int i;
pr_info("%s v%s\n", vlan_fullname, vlan_version);
@@ -668,6 +755,9 @@ static int __init vlan_proto_init(void)
if (err < 0)
goto err5;
+ for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++)
+ dev_add_offload(&vlan_packet_offloads[i]);
+
vlan_ioctl_set(vlan_ioctl_handler);
return 0;
@@ -685,7 +775,13 @@ err0:
static void __exit vlan_cleanup_module(void)
{
+ unsigned int i;
+
vlan_ioctl_set(NULL);
+
+ for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++)
+ dev_remove_offload(&vlan_packet_offloads[i]);
+
vlan_netlink_fini();
unregister_netdevice_notifier(&vlan_notifier_block);
diff --git a/net/Kconfig b/net/Kconfig
index 44dd5786ee91..57a7c5af3175 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -45,6 +45,9 @@ config COMPAT_NETLINK_MESSAGES
Newly written code should NEVER need this option but do
compat-independent messages instead!
+config NET_INGRESS
+ bool
+
menu "Networking options"
source "net/packet/Kconfig"
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 3b7ad43c7dad..d5871ac493eb 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1030,7 +1030,7 @@ static int atalk_create(struct net *net, struct socket *sock, int protocol,
if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
goto out;
rc = -ENOMEM;
- sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto);
+ sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto, kern);
if (!sk)
goto out;
rc = 0;
diff --git a/net/atm/common.c b/net/atm/common.c
index ed0466637e13..49a872db7e42 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -141,7 +141,7 @@ static struct proto vcc_proto = {
.release_cb = vcc_release_cb,
};
-int vcc_create(struct net *net, struct socket *sock, int protocol, int family)
+int vcc_create(struct net *net, struct socket *sock, int protocol, int family, int kern)
{
struct sock *sk;
struct atm_vcc *vcc;
@@ -149,7 +149,7 @@ int vcc_create(struct net *net, struct socket *sock, int protocol, int family)
sock->sk = NULL;
if (sock->type == SOCK_STREAM)
return -EINVAL;
- sk = sk_alloc(net, family, GFP_KERNEL, &vcc_proto);
+ sk = sk_alloc(net, family, GFP_KERNEL, &vcc_proto, kern);
if (!sk)
return -ENOMEM;
sock_init_data(sock, sk);
diff --git a/net/atm/common.h b/net/atm/common.h
index 4d6f5b2068ac..959436b87182 100644
--- a/net/atm/common.h
+++ b/net/atm/common.h
@@ -10,7 +10,7 @@
#include <linux/poll.h> /* for poll_table */
-int vcc_create(struct net *net, struct socket *sock, int protocol, int family);
+int vcc_create(struct net *net, struct socket *sock, int protocol, int family, int kern);
int vcc_release(struct socket *sock);
int vcc_connect(struct socket *sock, int itf, short vpi, int vci);
int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index ae0324021407..040207ec399f 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -136,7 +136,7 @@ static int pvc_create(struct net *net, struct socket *sock, int protocol,
return -EAFNOSUPPORT;
sock->ops = &pvc_proto_ops;
- return vcc_create(net, sock, protocol, PF_ATMPVC);
+ return vcc_create(net, sock, protocol, PF_ATMPVC, kern);
}
static const struct net_proto_family pvc_family_ops = {
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 1ba23f5018e7..3fa0a9ee98d1 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -660,7 +660,7 @@ static int svc_create(struct net *net, struct socket *sock, int protocol,
return -EAFNOSUPPORT;
sock->ops = &svc_proto_ops;
- error = vcc_create(net, sock, protocol, AF_ATMSVC);
+ error = vcc_create(net, sock, protocol, AF_ATMSVC, kern);
if (error)
return error;
ATM_SD(sock)->local.sas_family = AF_ATMSVC;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 330c1f4a5a0b..4273533d22b1 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -855,7 +855,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol,
return -ESOCKTNOSUPPORT;
}
- sk = sk_alloc(net, PF_AX25, GFP_ATOMIC, &ax25_proto);
+ sk = sk_alloc(net, PF_AX25, GFP_ATOMIC, &ax25_proto, kern);
if (sk == NULL)
return -ENOMEM;
@@ -881,7 +881,7 @@ struct sock *ax25_make_new(struct sock *osk, struct ax25_dev *ax25_dev)
struct sock *sk;
ax25_cb *ax25, *oax25;
- sk = sk_alloc(sock_net(osk), PF_AX25, GFP_ATOMIC, osk->sk_prot);
+ sk = sk_alloc(sock_net(osk), PF_AX25, GFP_ATOMIC, osk->sk_prot, 0);
if (sk == NULL)
return NULL;
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index eb7d8c0388e4..21434ab79d2c 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -1,5 +1,5 @@
#
-# Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+# Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
#
# Marek Lindner, Simon Wunderlich
#
@@ -20,7 +20,7 @@ obj-$(CONFIG_BATMAN_ADV) += batman-adv.o
batman-adv-y += bat_iv_ogm.o
batman-adv-y += bitarray.o
batman-adv-$(CONFIG_BATMAN_ADV_BLA) += bridge_loop_avoidance.o
-batman-adv-y += debugfs.o
+batman-adv-$(CONFIG_DEBUG_FS) += debugfs.o
batman-adv-$(CONFIG_BATMAN_ADV_DAT) += distributed-arp-table.o
batman-adv-y += fragmentation.o
batman-adv-y += gateway_client.o
@@ -29,6 +29,7 @@ batman-adv-y += hard-interface.o
batman-adv-y += hash.o
batman-adv-y += icmp_socket.o
batman-adv-y += main.o
+batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o
batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o
batman-adv-y += originator.o
batman-adv-y += routing.o
@@ -36,4 +37,3 @@ batman-adv-y += send.o
batman-adv-y += soft-interface.o
batman-adv-y += sysfs.o
batman-adv-y += translation-table.o
-batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o
diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h
index 4e49666f8c65..4e59cf3eb079 100644
--- a/net/batman-adv/bat_algo.h
+++ b/net/batman-adv/bat_algo.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 00e00e09b000..753383c2215c 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -15,20 +15,50 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
+#include "bat_algo.h"
#include "main.h"
-#include "translation-table.h"
+
+#include <linux/atomic.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/bug.h>
+#include <linux/byteorder/generic.h>
+#include <linux/cache.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/pkt_sched.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#include "bitarray.h"
+#include "hard-interface.h"
+#include "hash.h"
+#include "network-coding.h"
#include "originator.h"
+#include "packet.h"
#include "routing.h"
-#include "gateway_common.h"
-#include "gateway_client.h"
-#include "hard-interface.h"
#include "send.h"
-#include "bat_algo.h"
-#include "network-coding.h"
+#include "translation-table.h"
/**
* enum batadv_dup_status - duplicate status
- * @BATADV_NO_DUP: the packet is a duplicate
+ * @BATADV_NO_DUP: the packet is no duplicate
* @BATADV_ORIG_DUP: OGM is a duplicate in the originator (but not for the
* neighbor)
* @BATADV_NEIGH_DUP: OGM is a duplicate for the neighbor
@@ -55,7 +85,7 @@ static void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index,
}
/**
- * batadv_ring_buffer_set - compute the average of all non-zero values stored
+ * batadv_ring_buffer_avg - compute the average of all non-zero values stored
* in the given ring buffer
* @lq_recv: pointer to the ring buffer
*
@@ -64,7 +94,9 @@ static void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index,
static uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[])
{
const uint8_t *ptr;
- uint16_t count = 0, i = 0, sum = 0;
+ uint16_t count = 0;
+ uint16_t i = 0;
+ uint16_t sum = 0;
ptr = lq_recv;
@@ -308,7 +340,6 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
struct batadv_ogm_packet *batadv_ogm_packet;
unsigned char *ogm_buff;
uint32_t random_seqno;
- int res = -ENOMEM;
/* randomize initial seqno to avoid collision */
get_random_bytes(&random_seqno, sizeof(random_seqno));
@@ -317,7 +348,7 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
hard_iface->bat_iv.ogm_buff_len = BATADV_OGM_HLEN;
ogm_buff = kmalloc(hard_iface->bat_iv.ogm_buff_len, GFP_ATOMIC);
if (!ogm_buff)
- goto out;
+ return -ENOMEM;
hard_iface->bat_iv.ogm_buff = ogm_buff;
@@ -329,10 +360,7 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
batadv_ogm_packet->reserved = 0;
batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE;
- res = 0;
-
-out:
- return res;
+ return 0;
}
static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface)
@@ -396,8 +424,8 @@ static uint8_t batadv_hop_penalty(uint8_t tq,
}
/* is there another aggregated packet here? */
-static int batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
- __be16 tvlv_len)
+static bool batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
+ __be16 tvlv_len)
{
int next_buff_pos = 0;
@@ -413,7 +441,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet,
struct batadv_hard_iface *hard_iface)
{
struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
- char *fwd_str;
+ const char *fwd_str;
uint8_t packet_num;
int16_t buff_pos;
struct batadv_ogm_packet *batadv_ogm_packet;
@@ -451,7 +479,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet,
batadv_ogm_packet->orig,
ntohl(batadv_ogm_packet->seqno),
batadv_ogm_packet->tq, batadv_ogm_packet->ttl,
- (batadv_ogm_packet->flags & BATADV_DIRECTLINK ?
+ ((batadv_ogm_packet->flags & BATADV_DIRECTLINK) ?
"on" : "off"),
hard_iface->net_dev->name,
hard_iface->net_dev->dev_addr);
@@ -548,58 +576,62 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
* - the send time is within our MAX_AGGREGATION_MS time
* - the resulting packet wont be bigger than
* MAX_AGGREGATION_BYTES
+ * otherwise aggregation is not possible
*/
- if (time_before(send_time, forw_packet->send_time) &&
- time_after_eq(aggregation_end_time, forw_packet->send_time) &&
- (aggregated_bytes <= BATADV_MAX_AGGREGATION_BYTES)) {
- /* check aggregation compatibility
- * -> direct link packets are broadcasted on
- * their interface only
- * -> aggregate packet if the current packet is
- * a "global" packet as well as the base
- * packet
- */
- primary_if = batadv_primary_if_get_selected(bat_priv);
- if (!primary_if)
- goto out;
-
- /* packet is not leaving on the same interface. */
- if (forw_packet->if_outgoing != if_outgoing)
- goto out;
+ if (!time_before(send_time, forw_packet->send_time) ||
+ !time_after_eq(aggregation_end_time, forw_packet->send_time))
+ return false;
+
+ if (aggregated_bytes > BATADV_MAX_AGGREGATION_BYTES)
+ return false;
+
+ /* packet is not leaving on the same interface. */
+ if (forw_packet->if_outgoing != if_outgoing)
+ return false;
+
+ /* check aggregation compatibility
+ * -> direct link packets are broadcasted on
+ * their interface only
+ * -> aggregate packet if the current packet is
+ * a "global" packet as well as the base
+ * packet
+ */
+ primary_if = batadv_primary_if_get_selected(bat_priv);
+ if (!primary_if)
+ return false;
- /* packets without direct link flag and high TTL
- * are flooded through the net
- */
- if ((!directlink) &&
- (!(batadv_ogm_packet->flags & BATADV_DIRECTLINK)) &&
- (batadv_ogm_packet->ttl != 1) &&
-
- /* own packets originating non-primary
- * interfaces leave only that interface
- */
- ((!forw_packet->own) ||
- (forw_packet->if_incoming == primary_if))) {
- res = true;
- goto out;
- }
+ /* packets without direct link flag and high TTL
+ * are flooded through the net
+ */
+ if (!directlink &&
+ !(batadv_ogm_packet->flags & BATADV_DIRECTLINK) &&
+ batadv_ogm_packet->ttl != 1 &&
+
+ /* own packets originating non-primary
+ * interfaces leave only that interface
+ */
+ (!forw_packet->own ||
+ forw_packet->if_incoming == primary_if)) {
+ res = true;
+ goto out;
+ }
- /* if the incoming packet is sent via this one
- * interface only - we still can aggregate
- */
- if ((directlink) &&
- (new_bat_ogm_packet->ttl == 1) &&
- (forw_packet->if_incoming == if_incoming) &&
-
- /* packets from direct neighbors or
- * own secondary interface packets
- * (= secondary interface packets in general)
- */
- (batadv_ogm_packet->flags & BATADV_DIRECTLINK ||
- (forw_packet->own &&
- forw_packet->if_incoming != primary_if))) {
- res = true;
- goto out;
- }
+ /* if the incoming packet is sent via this one
+ * interface only - we still can aggregate
+ */
+ if (directlink &&
+ new_bat_ogm_packet->ttl == 1 &&
+ forw_packet->if_incoming == if_incoming &&
+
+ /* packets from direct neighbors or
+ * own secondary interface packets
+ * (= secondary interface packets in general)
+ */
+ (batadv_ogm_packet->flags & BATADV_DIRECTLINK ||
+ (forw_packet->own &&
+ forw_packet->if_incoming != primary_if))) {
+ res = true;
+ goto out;
}
out:
@@ -642,19 +674,16 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
if (!batadv_atomic_dec_not_zero(&bat_priv->batman_queue_left)) {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"batman packet queue full\n");
- goto out;
+ goto out_free_outgoing;
}
}
forw_packet_aggr = kmalloc(sizeof(*forw_packet_aggr), GFP_ATOMIC);
- if (!forw_packet_aggr) {
- if (!own_packet)
- atomic_inc(&bat_priv->batman_queue_left);
- goto out;
- }
+ if (!forw_packet_aggr)
+ goto out_nomem;
- if ((atomic_read(&bat_priv->aggregated_ogms)) &&
- (packet_len < BATADV_MAX_AGGREGATION_BYTES))
+ if (atomic_read(&bat_priv->aggregated_ogms) &&
+ packet_len < BATADV_MAX_AGGREGATION_BYTES)
skb_size = BATADV_MAX_AGGREGATION_BYTES;
else
skb_size = packet_len;
@@ -662,12 +691,8 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
skb_size += ETH_HLEN;
forw_packet_aggr->skb = netdev_alloc_skb_ip_align(NULL, skb_size);
- if (!forw_packet_aggr->skb) {
- if (!own_packet)
- atomic_inc(&bat_priv->batman_queue_left);
- kfree(forw_packet_aggr);
- goto out;
- }
+ if (!forw_packet_aggr->skb)
+ goto out_free_forw_packet;
forw_packet_aggr->skb->priority = TC_PRIO_CONTROL;
skb_reserve(forw_packet_aggr->skb, ETH_HLEN);
@@ -699,7 +724,12 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
send_time - jiffies);
return;
-out:
+out_free_forw_packet:
+ kfree(forw_packet_aggr);
+out_nomem:
+ if (!own_packet)
+ atomic_inc(&bat_priv->batman_queue_left);
+out_free_outgoing:
batadv_hardif_free_ref(if_outgoing);
out_free_incoming:
batadv_hardif_free_ref(if_incoming);
@@ -752,13 +782,13 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv,
unsigned long max_aggregation_jiffies;
batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff;
- direct_link = batadv_ogm_packet->flags & BATADV_DIRECTLINK ? 1 : 0;
+ direct_link = !!(batadv_ogm_packet->flags & BATADV_DIRECTLINK);
max_aggregation_jiffies = msecs_to_jiffies(BATADV_MAX_AGGREGATION_MS);
/* find position for the packet in the forward queue */
spin_lock_bh(&bat_priv->forw_bat_list_lock);
/* own packets are not to be aggregated */
- if ((atomic_read(&bat_priv->aggregated_ogms)) && (!own_packet)) {
+ if (atomic_read(&bat_priv->aggregated_ogms) && !own_packet) {
hlist_for_each_entry(forw_packet_pos,
&bat_priv->forw_bat_list, list) {
if (batadv_iv_ogm_can_aggregate(batadv_ogm_packet,
@@ -1034,9 +1064,10 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
batadv_orig_node_free_ref(orig_tmp);
if (!neigh_node)
goto unlock;
- } else
+ } else {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"Updating existing last-hop neighbor of originator\n");
+ }
rcu_read_unlock();
neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing);
@@ -1081,7 +1112,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
* won't consider it either
*/
if (router_ifinfo &&
- (neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg)) {
+ neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg) {
orig_node_tmp = router->orig_node;
spin_lock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock);
if_num = router->if_incoming->if_num;
@@ -1356,8 +1387,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr,
out:
spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock);
batadv_orig_node_free_ref(orig_node);
- if (orig_ifinfo)
- batadv_orig_ifinfo_free_ref(orig_ifinfo);
+ batadv_orig_ifinfo_free_ref(orig_ifinfo);
return ret;
}
diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c
index e3da07a64026..cf68c328345e 100644
--- a/net/batman-adv/bitarray.c
+++ b/net/batman-adv/bitarray.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*
@@ -15,10 +15,10 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
#include "bitarray.h"
+#include "main.h"
-#include <linux/bitops.h>
+#include <linux/bitmap.h>
/* shift the packet array by n places. */
static void batadv_bitmap_shift_left(unsigned long *seq_bits, int32_t n)
diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h
index 2acaafe60188..0c2456225fae 100644
--- a/net/batman-adv/bitarray.h
+++ b/net/batman-adv/bitarray.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*
@@ -18,6 +18,12 @@
#ifndef _NET_BATMAN_ADV_BITARRAY_H_
#define _NET_BATMAN_ADV_BITARRAY_H_
+#include "main.h"
+
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+
/* Returns 1 if the corresponding bit in the given seq_bits indicates true
* and curr_seqno is within range of last_seqno. Otherwise returns 0.
*/
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index ac4b96eccade..ba0609292ae7 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich
*
@@ -15,19 +15,41 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
-#include "hash.h"
-#include "hard-interface.h"
-#include "originator.h"
#include "bridge_loop_avoidance.h"
-#include "translation-table.h"
-#include "send.h"
+#include "main.h"
-#include <linux/etherdevice.h>
+#include <linux/atomic.h>
+#include <linux/byteorder/generic.h>
+#include <linux/compiler.h>
#include <linux/crc16.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
#include <linux/if_arp.h>
-#include <net/arp.h>
+#include <linux/if_ether.h>
#include <linux/if_vlan.h>
+#include <linux/jhash.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/workqueue.h>
+#include <net/arp.h>
+
+#include "hard-interface.h"
+#include "hash.h"
+#include "originator.h"
+#include "packet.h"
+#include "translation-table.h"
static const uint8_t batadv_announce_mac[4] = {0x43, 0x05, 0x43, 0x05};
@@ -42,12 +64,8 @@ static inline uint32_t batadv_choose_claim(const void *data, uint32_t size)
struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data;
uint32_t hash = 0;
- hash = batadv_hash_bytes(hash, &claim->addr, sizeof(claim->addr));
- hash = batadv_hash_bytes(hash, &claim->vid, sizeof(claim->vid));
-
- hash += (hash << 3);
- hash ^= (hash >> 11);
- hash += (hash << 15);
+ hash = jhash(&claim->addr, sizeof(claim->addr), hash);
+ hash = jhash(&claim->vid, sizeof(claim->vid), hash);
return hash % size;
}
@@ -59,12 +77,8 @@ static inline uint32_t batadv_choose_backbone_gw(const void *data,
const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data;
uint32_t hash = 0;
- hash = batadv_hash_bytes(hash, &claim->addr, sizeof(claim->addr));
- hash = batadv_hash_bytes(hash, &claim->vid, sizeof(claim->vid));
-
- hash += (hash << 3);
- hash ^= (hash >> 11);
- hash += (hash << 15);
+ hash = jhash(&claim->addr, sizeof(claim->addr), hash);
+ hash = jhash(&claim->vid, sizeof(claim->vid), hash);
return hash % size;
}
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index 43c985d92c3e..0282690389ac 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich
*
@@ -18,6 +18,16 @@
#ifndef _NET_BATMAN_ADV_BLA_H_
#define _NET_BATMAN_ADV_BLA_H_
+#include "main.h"
+
+#include <linux/types.h>
+
+struct batadv_hard_iface;
+struct batadv_orig_node;
+struct batadv_priv;
+struct seq_file;
+struct sk_buff;
+
#ifdef CONFIG_BATMAN_ADV_BLA
int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
unsigned short vid, bool is_bcast);
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index a4972874c056..c4c1e8030ba0 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -15,21 +15,42 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
+#include "debugfs.h"
#include "main.h"
+#include <linux/compiler.h>
#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/fcntl.h>
+#include <linux/fs.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/poll.h>
+#include <linux/printk.h>
+#include <linux/sched.h> /* for linux/wait.h */
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/stddef.h>
+#include <linux/stringify.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/wait.h>
+#include <stdarg.h>
-#include "debugfs.h"
-#include "translation-table.h"
-#include "originator.h"
-#include "hard-interface.h"
-#include "gateway_common.h"
-#include "gateway_client.h"
-#include "soft-interface.h"
-#include "icmp_socket.h"
#include "bridge_loop_avoidance.h"
#include "distributed-arp-table.h"
+#include "gateway_client.h"
+#include "icmp_socket.h"
#include "network-coding.h"
+#include "originator.h"
+#include "translation-table.h"
static struct dentry *batadv_debugfs;
@@ -482,11 +503,7 @@ rem_attr:
debugfs_remove_recursive(hard_iface->debug_dir);
hard_iface->debug_dir = NULL;
out:
-#ifdef CONFIG_DEBUG_FS
return -ENOMEM;
-#else
- return 0;
-#endif /* CONFIG_DEBUG_FS */
}
/**
@@ -541,11 +558,7 @@ rem_attr:
debugfs_remove_recursive(bat_priv->debug_dir);
bat_priv->debug_dir = NULL;
out:
-#ifdef CONFIG_DEBUG_FS
return -ENOMEM;
-#else
- return 0;
-#endif /* CONFIG_DEBUG_FS */
}
void batadv_debugfs_del_meshif(struct net_device *dev)
diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h
index 37c4d6ddd04d..187acdc85dfa 100644
--- a/net/batman-adv/debugfs.h
+++ b/net/batman-adv/debugfs.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -18,8 +18,17 @@
#ifndef _NET_BATMAN_ADV_DEBUGFS_H_
#define _NET_BATMAN_ADV_DEBUGFS_H_
+#include "main.h"
+
+#include <linux/kconfig.h>
+
+struct batadv_hard_iface;
+struct net_device;
+
#define BATADV_DEBUGFS_SUBDIR "batman_adv"
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+
void batadv_debugfs_init(void);
void batadv_debugfs_destroy(void);
int batadv_debugfs_add_meshif(struct net_device *dev);
@@ -27,4 +36,36 @@ void batadv_debugfs_del_meshif(struct net_device *dev);
int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface);
void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface);
+#else
+
+static inline void batadv_debugfs_init(void)
+{
+}
+
+static inline void batadv_debugfs_destroy(void)
+{
+}
+
+static inline int batadv_debugfs_add_meshif(struct net_device *dev)
+{
+ return 0;
+}
+
+static inline void batadv_debugfs_del_meshif(struct net_device *dev)
+{
+}
+
+static inline
+int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
+{
+ return 0;
+}
+
+static inline
+void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface)
+{
+}
+
+#endif
+
#endif /* _NET_BATMAN_ADV_DEBUGFS_H_ */
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index aad022dd15df..fb54e6aed096 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors:
*
* Antonio Quartulli
*
@@ -15,18 +15,36 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include <linux/if_ether.h>
+#include "distributed-arp-table.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/byteorder/generic.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
#include <linux/if_arp.h>
+#include <linux/if_ether.h>
#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/workqueue.h>
#include <net/arp.h>
-#include "main.h"
-#include "hash.h"
-#include "distributed-arp-table.h"
#include "hard-interface.h"
+#include "hash.h"
#include "originator.h"
#include "send.h"
-#include "types.h"
#include "translation-table.h"
static void batadv_dat_purge(struct work_struct *work);
@@ -206,9 +224,22 @@ static uint32_t batadv_hash_dat(const void *data, uint32_t size)
{
uint32_t hash = 0;
const struct batadv_dat_entry *dat = data;
+ const unsigned char *key;
+ uint32_t i;
- hash = batadv_hash_bytes(hash, &dat->ip, sizeof(dat->ip));
- hash = batadv_hash_bytes(hash, &dat->vid, sizeof(dat->vid));
+ key = (const unsigned char *)&dat->ip;
+ for (i = 0; i < sizeof(dat->ip); i++) {
+ hash += key[i];
+ hash += (hash << 10);
+ hash ^= (hash >> 6);
+ }
+
+ key = (const unsigned char *)&dat->vid;
+ for (i = 0; i < sizeof(dat->vid); i++) {
+ hash += key[i];
+ hash += (hash << 10);
+ hash ^= (hash >> 6);
+ }
hash += (hash << 3);
hash ^= (hash >> 11);
diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h
index 2fe0764c64be..3181507ebc14 100644
--- a/net/batman-adv/distributed-arp-table.h
+++ b/net/batman-adv/distributed-arp-table.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors:
*
* Antonio Quartulli
*
@@ -18,12 +18,19 @@
#ifndef _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_
#define _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_
-#ifdef CONFIG_BATMAN_ADV_DAT
+#include "main.h"
+
+#include <linux/compiler.h>
+#include <linux/netdevice.h>
+#include <linux/types.h>
-#include "types.h"
#include "originator.h"
+#include "packet.h"
-#include <linux/if_arp.h>
+struct seq_file;
+struct sk_buff;
+
+#ifdef CONFIG_BATMAN_ADV_DAT
/* BATADV_DAT_ADDR_MAX - maximum address value in the DHT space */
#define BATADV_DAT_ADDR_MAX ((batadv_dat_addr_t)~(batadv_dat_addr_t)0)
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 3d1dcaa3e8b5..c0f0d01ab244 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2015 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll <martin@hundeboll.net>
*
@@ -15,12 +15,28 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
#include "fragmentation.h"
-#include "send.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/byteorder/generic.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/pkt_sched.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+
+#include "hard-interface.h"
#include "originator.h"
+#include "packet.h"
#include "routing.h"
-#include "hard-interface.h"
+#include "send.h"
#include "soft-interface.h"
/**
@@ -161,6 +177,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node,
hlist_add_head(&frag_entry_new->list, &chain->head);
chain->size = skb->len - hdr_size;
chain->timestamp = jiffies;
+ chain->total_size = ntohs(frag_packet->total_size);
ret = true;
goto out;
}
@@ -195,9 +212,11 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node,
out:
if (chain->size > batadv_frag_size_limit() ||
- ntohs(frag_packet->total_size) > batadv_frag_size_limit()) {
+ chain->total_size != ntohs(frag_packet->total_size) ||
+ chain->total_size > batadv_frag_size_limit()) {
/* Clear chain if total size of either the list or the packet
- * exceeds the maximum size of one merged packet.
+ * exceeds the maximum size of one merged packet. Don't allow
+ * packets to have different total_size.
*/
batadv_frag_clear_chain(&chain->head);
chain->size = 0;
@@ -228,19 +247,13 @@ err:
* Returns the merged skb or NULL on error.
*/
static struct sk_buff *
-batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb)
+batadv_frag_merge_packets(struct hlist_head *chain)
{
struct batadv_frag_packet *packet;
struct batadv_frag_list_entry *entry;
struct sk_buff *skb_out = NULL;
int size, hdr_size = sizeof(struct batadv_frag_packet);
- /* Make sure incoming skb has non-bogus data. */
- packet = (struct batadv_frag_packet *)skb->data;
- size = ntohs(packet->total_size);
- if (size > batadv_frag_size_limit())
- goto free;
-
/* Remove first entry, as this is the destination for the rest of the
* fragments.
*/
@@ -249,6 +262,9 @@ batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb)
skb_out = entry->skb;
kfree(entry);
+ packet = (struct batadv_frag_packet *)skb_out->data;
+ size = ntohs(packet->total_size);
+
/* Make room for the rest of the fragments. */
if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) {
kfree_skb(skb_out);
@@ -304,7 +320,7 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb,
if (hlist_empty(&head))
goto out;
- skb_out = batadv_frag_merge_packets(&head, *skb);
+ skb_out = batadv_frag_merge_packets(&head);
if (!skb_out)
goto out_err;
diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h
index d848cf6676a2..8b9877e70b95 100644
--- a/net/batman-adv/fragmentation.h
+++ b/net/batman-adv/fragmentation.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2015 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll <martin@hundeboll.net>
*
@@ -18,6 +18,15 @@
#ifndef _NET_BATMAN_ADV_FRAGMENTATION_H_
#define _NET_BATMAN_ADV_FRAGMENTATION_H_
+#include "main.h"
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+struct sk_buff;
+
void batadv_frag_purge_orig(struct batadv_orig_node *orig,
bool (*check_cb)(struct batadv_frag_table_entry *));
bool batadv_frag_skb_fwd(struct sk_buff *skb,
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 090828cf1fa7..bb0158620628 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -15,18 +15,38 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
-#include "sysfs.h"
#include "gateway_client.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/byteorder/generic.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/udp.h>
+
#include "gateway_common.h"
#include "hard-interface.h"
#include "originator.h"
-#include "translation-table.h"
+#include "packet.h"
#include "routing.h"
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/udp.h>
-#include <linux/if_vlan.h>
+#include "sysfs.h"
+#include "translation-table.h"
/* These are the offsets of the "hw type" and "hw address length" in the dhcp
* packet starting at the beginning of the dhcp header
@@ -733,11 +753,6 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len,
if (!pskb_may_pull(skb, *header_len + sizeof(*udphdr)))
return BATADV_DHCP_NO;
- /* skb->data might have been reallocated by pskb_may_pull() */
- ethhdr = eth_hdr(skb);
- if (ntohs(ethhdr->h_proto) == ETH_P_8021Q)
- ethhdr = (struct ethhdr *)(skb->data + VLAN_HLEN);
-
udphdr = (struct udphdr *)(skb->data + *header_len);
*header_len += sizeof(*udphdr);
diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h
index 7ee53bb7d50f..89565b451c18 100644
--- a/net/batman-adv/gateway_client.h
+++ b/net/batman-adv/gateway_client.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -18,6 +18,14 @@
#ifndef _NET_BATMAN_ADV_GATEWAY_CLIENT_H_
#define _NET_BATMAN_ADV_GATEWAY_CLIENT_H_
+#include "main.h"
+
+#include <linux/types.h>
+
+struct batadv_tvlv_gateway_data;
+struct seq_file;
+struct sk_buff;
+
void batadv_gw_check_client_stop(struct batadv_priv *bat_priv);
void batadv_gw_reselect(struct batadv_priv *bat_priv);
void batadv_gw_election(struct batadv_priv *bat_priv);
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 88a1bc3804d1..39cf44ccebd4 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -15,9 +15,18 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
#include "gateway_common.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/byteorder/generic.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+
#include "gateway_client.h"
+#include "packet.h"
/**
* batadv_parse_gw_bandwidth - parse supplied string buffer to extract download
diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h
index aa5116561947..bd5c812cebf4 100644
--- a/net/batman-adv/gateway_common.h
+++ b/net/batman-adv/gateway_common.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -18,6 +18,13 @@
#ifndef _NET_BATMAN_ADV_GATEWAY_COMMON_H_
#define _NET_BATMAN_ADV_GATEWAY_COMMON_H_
+#include "main.h"
+
+#include <linux/types.h>
+
+struct batadv_priv;
+struct net_device;
+
enum batadv_gw_modes {
BATADV_GW_MODE_OFF,
BATADV_GW_MODE_CLIENT,
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index baf1f9843f2c..f4a15d2e5eaf 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -15,22 +15,36 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
-#include "distributed-arp-table.h"
#include "hard-interface.h"
-#include "soft-interface.h"
-#include "send.h"
-#include "translation-table.h"
-#include "routing.h"
-#include "sysfs.h"
-#include "debugfs.h"
-#include "originator.h"
-#include "hash.h"
-#include "bridge_loop_avoidance.h"
-#include "gateway_client.h"
+#include "main.h"
+#include <linux/bug.h>
+#include <linux/byteorder/generic.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
#include <linux/if_arp.h>
#include <linux/if_ether.h>
+#include <linux/if.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/printk.h>
+#include <linux/rculist.h>
+#include <linux/rtnetlink.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <net/net_namespace.h>
+
+#include "bridge_loop_avoidance.h"
+#include "debugfs.h"
+#include "distributed-arp-table.h"
+#include "gateway_client.h"
+#include "originator.h"
+#include "packet.h"
+#include "send.h"
+#include "soft-interface.h"
+#include "sysfs.h"
+#include "translation-table.h"
void batadv_hardif_free_rcu(struct rcu_head *rcu)
{
diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index 1918cd50b62e..5a31420513e1 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -18,6 +18,17 @@
#ifndef _NET_BATMAN_ADV_HARD_INTERFACE_H_
#define _NET_BATMAN_ADV_HARD_INTERFACE_H_
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <linux/notifier.h>
+#include <linux/rcupdate.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+struct net_device;
+
enum batadv_hard_if_state {
BATADV_IF_NOT_IN_USE,
BATADV_IF_TO_BE_REMOVED,
diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c
index 7c1c63080e20..e89f3146b092 100644
--- a/net/batman-adv/hash.c
+++ b/net/batman-adv/hash.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*
@@ -15,8 +15,12 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
#include "hash.h"
+#include "main.h"
+
+#include <linux/fs.h>
+#include <linux/lockdep.h>
+#include <linux/slab.h>
/* clears the hash */
static void batadv_hash_init(struct batadv_hashtable *hash)
diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h
index 539fc1266793..5065f50c9c3c 100644
--- a/net/batman-adv/hash.h
+++ b/net/batman-adv/hash.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*
@@ -18,7 +18,16 @@
#ifndef _NET_BATMAN_ADV_HASH_H_
#define _NET_BATMAN_ADV_HASH_H_
+#include "main.h"
+
+#include <linux/compiler.h>
#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+struct lock_class_key;
/* callback to a compare function. should compare 2 element datas for their
* keys, return 0 if same and not 0 if not same
@@ -80,28 +89,6 @@ static inline void batadv_hash_delete(struct batadv_hashtable *hash,
}
/**
- * batadv_hash_bytes - hash some bytes and add them to the previous hash
- * @hash: previous hash value
- * @data: data to be hashed
- * @size: number of bytes to be hashed
- *
- * Returns the new hash value.
- */
-static inline uint32_t batadv_hash_bytes(uint32_t hash, const void *data,
- uint32_t size)
-{
- const unsigned char *key = data;
- int i;
-
- for (i = 0; i < size; i++) {
- hash += key[i];
- hash += (hash << 10);
- hash ^= (hash >> 6);
- }
- return hash;
-}
-
-/**
* batadv_hash_add - adds data to the hashtable
* @hash: storage hash table
* @compare: callback to determine if 2 hash elements are identical
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 161ef8f17d2e..07061bcbaa04 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -15,14 +15,39 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
+#include "icmp_socket.h"
#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
#include <linux/debugfs.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/export.h>
+#include <linux/fcntl.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/pkt_sched.h>
+#include <linux/poll.h>
+#include <linux/printk.h>
+#include <linux/sched.h> /* for linux/wait.h */
+#include <linux/skbuff.h>
#include <linux/slab.h>
-#include "icmp_socket.h"
-#include "send.h"
-#include "hash.h"
-#include "originator.h"
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/wait.h>
+
#include "hard-interface.h"
+#include "originator.h"
+#include "packet.h"
+#include "send.h"
static struct batadv_socket_client *batadv_socket_client_hash[256];
diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h
index 0c33950aa4aa..7de7fce4b48c 100644
--- a/net/batman-adv/icmp_socket.h
+++ b/net/batman-adv/icmp_socket.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -18,6 +18,13 @@
#ifndef _NET_BATMAN_ADV_ICMP_SOCKET_H_
#define _NET_BATMAN_ADV_ICMP_SOCKET_H_
+#include "main.h"
+
+#include <linux/types.h>
+
+struct batadv_icmp_header;
+struct batadv_priv;
+
#define BATADV_ICMP_SOCKET "socket"
void batadv_socket_init(void);
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 12fc77bef23f..8457097f1643 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -15,31 +15,53 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/byteorder/generic.h>
#include <linux/crc32c.h>
-#include <linux/highmem.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
#include <linux/if_vlan.h>
-#include <net/ip.h>
-#include <net/ipv6.h>
+#include <linux/init.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/netdevice.h>
+#include <linux/pkt_sched.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/workqueue.h>
#include <net/dsfield.h>
-#include "main.h"
-#include "sysfs.h"
+#include <net/rtnetlink.h>
+
+#include "bat_algo.h"
+#include "bridge_loop_avoidance.h"
#include "debugfs.h"
+#include "distributed-arp-table.h"
+#include "gateway_client.h"
+#include "gateway_common.h"
+#include "hard-interface.h"
+#include "icmp_socket.h"
+#include "multicast.h"
+#include "network-coding.h"
+#include "originator.h"
+#include "packet.h"
#include "routing.h"
#include "send.h"
-#include "originator.h"
#include "soft-interface.h"
-#include "icmp_socket.h"
#include "translation-table.h"
-#include "hard-interface.h"
-#include "gateway_client.h"
-#include "bridge_loop_avoidance.h"
-#include "distributed-arp-table.h"
-#include "multicast.h"
-#include "gateway_common.h"
-#include "hash.h"
-#include "bat_algo.h"
-#include "network-coding.h"
-#include "fragmentation.h"
/* List manipulations on hardif_list have to be rtnl_lock()'ed,
* list traversals just rcu-locked
@@ -209,10 +231,13 @@ void batadv_mesh_free(struct net_device *soft_iface)
* interfaces in the current mesh
* @bat_priv: the bat priv with all the soft interface information
* @addr: the address to check
+ *
+ * Returns 'true' if the mac address was found, false otherwise.
*/
-int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr)
+bool batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr)
{
const struct batadv_hard_iface *hard_iface;
+ bool is_my_mac = false;
rcu_read_lock();
list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
@@ -223,12 +248,12 @@ int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr)
continue;
if (batadv_compare_eth(hard_iface->net_dev->dev_addr, addr)) {
- rcu_read_unlock();
- return 1;
+ is_my_mac = true;
+ break;
}
}
rcu_read_unlock();
- return 0;
+ return is_my_mac;
}
/**
@@ -510,14 +535,12 @@ static struct batadv_algo_ops *batadv_algo_get(char *name)
int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops)
{
struct batadv_algo_ops *bat_algo_ops_tmp;
- int ret;
bat_algo_ops_tmp = batadv_algo_get(bat_algo_ops->name);
if (bat_algo_ops_tmp) {
pr_info("Trying to register already registered routing algorithm: %s\n",
bat_algo_ops->name);
- ret = -EEXIST;
- goto out;
+ return -EEXIST;
}
/* all algorithms must implement all ops (for now) */
@@ -531,32 +554,26 @@ int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops)
!bat_algo_ops->bat_neigh_is_equiv_or_better) {
pr_info("Routing algo '%s' does not implement required ops\n",
bat_algo_ops->name);
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
INIT_HLIST_NODE(&bat_algo_ops->list);
hlist_add_head(&bat_algo_ops->list, &batadv_algo_list);
- ret = 0;
-out:
- return ret;
+ return 0;
}
int batadv_algo_select(struct batadv_priv *bat_priv, char *name)
{
struct batadv_algo_ops *bat_algo_ops;
- int ret = -EINVAL;
bat_algo_ops = batadv_algo_get(name);
if (!bat_algo_ops)
- goto out;
+ return -EINVAL;
bat_priv->bat_algo_ops = bat_algo_ops;
- ret = 0;
-out:
- return ret;
+ return 0;
}
int batadv_algo_seq_print_text(struct seq_file *seq, void *offset)
@@ -819,15 +836,15 @@ static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff,
new_buff = kmalloc(min_packet_len + additional_packet_len, GFP_ATOMIC);
/* keep old buffer if kmalloc should fail */
- if (new_buff) {
- memcpy(new_buff, *packet_buff, min_packet_len);
- kfree(*packet_buff);
- *packet_buff = new_buff;
- *packet_buff_len = min_packet_len + additional_packet_len;
- return true;
- }
+ if (!new_buff)
+ return false;
+
+ memcpy(new_buff, *packet_buff, min_packet_len);
+ kfree(*packet_buff);
+ *packet_buff = new_buff;
+ *packet_buff_len = min_packet_len + additional_packet_len;
- return false;
+ return true;
}
/**
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 4d2318829a34..41d27c7872b9 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -24,7 +24,7 @@
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2015.0"
+#define BATADV_SOURCE_VERSION "2015.1"
#endif
/* B.A.T.M.A.N. parameters */
@@ -44,7 +44,7 @@
#define BATADV_TT_CLIENT_TEMP_TIMEOUT 600000 /* in milliseconds */
#define BATADV_TT_WORK_PERIOD 5000 /* 5 seconds */
#define BATADV_ORIG_WORK_PERIOD 1000 /* 1 second */
-#define BATADV_DAT_ENTRY_TIMEOUT (5*60000) /* 5 mins in milliseconds */
+#define BATADV_DAT_ENTRY_TIMEOUT (5 * 60000) /* 5 mins in milliseconds */
/* sliding packet range of received originator messages in sequence numbers
* (should be a multiple of our word size)
*/
@@ -163,28 +163,26 @@ enum batadv_uev_type {
/* Kernel headers */
-#include <linux/mutex.h> /* mutex */
-#include <linux/module.h> /* needed by all modules */
-#include <linux/netdevice.h> /* netdevice */
-#include <linux/etherdevice.h> /* ethernet address classification */
-#include <linux/if_ether.h> /* ethernet header */
-#include <linux/poll.h> /* poll_table */
-#include <linux/kthread.h> /* kernel threads */
-#include <linux/pkt_sched.h> /* schedule types */
-#include <linux/workqueue.h> /* workqueue */
+#include <linux/atomic.h>
+#include <linux/bitops.h> /* for packet.h */
+#include <linux/compiler.h>
+#include <linux/cpumask.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h> /* for packet.h */
+#include <linux/netdevice.h>
+#include <linux/printk.h>
+#include <linux/types.h>
#include <linux/percpu.h>
-#include <linux/slab.h>
-#include <net/sock.h> /* struct sock */
-#include <net/addrconf.h> /* ipv6 address stuff */
-#include <linux/ip.h>
-#include <net/rtnetlink.h>
#include <linux/jiffies.h>
-#include <linux/seq_file.h>
#include <linux/if_vlan.h>
#include "types.h"
-#define BATADV_PRINT_VID(vid) (vid & BATADV_VLAN_HAS_TAG ? \
+struct batadv_ogm_packet;
+struct seq_file;
+struct sk_buff;
+
+#define BATADV_PRINT_VID(vid) ((vid & BATADV_VLAN_HAS_TAG) ? \
(int)(vid & VLAN_VID_MASK) : -1)
extern char batadv_routing_algo[];
@@ -195,7 +193,7 @@ extern struct workqueue_struct *batadv_event_workqueue;
int batadv_mesh_init(struct net_device *soft_iface);
void batadv_mesh_free(struct net_device *soft_iface);
-int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr);
+bool batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr);
struct batadv_hard_iface *
batadv_seq_print_text_primary_if_get(struct seq_file *seq);
int batadv_max_header_len(void);
@@ -279,7 +277,7 @@ static inline void _batadv_dbg(int type __always_unused,
*
* note: can't use ether_addr_equal() as it requires aligned memory
*/
-static inline int batadv_compare_eth(const void *data1, const void *data2)
+static inline bool batadv_compare_eth(const void *data1, const void *data2)
{
return ether_addr_equal_unaligned(data1, data2);
}
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index b24e4bb64fb5..7aa480b7edd0 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2014-2015 B.A.T.M.A.N. contributors:
*
* Linus Lüssing
*
@@ -15,10 +15,33 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
#include "multicast.h"
-#include "originator.h"
-#include "hard-interface.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/byteorder/generic.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+
+#include "packet.h"
#include "translation-table.h"
/**
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index 3a44ebdb43cb..beb6e56c624a 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2014-2015 B.A.T.M.A.N. contributors:
*
* Linus Lüssing
*
@@ -18,6 +18,12 @@
#ifndef _NET_BATMAN_ADV_MULTICAST_H_
#define _NET_BATMAN_ADV_MULTICAST_H_
+#include "main.h"
+
+struct batadv_orig_node;
+struct batadv_priv;
+struct sk_buff;
+
/**
* batadv_forw_mode - the way a packet should be forwarded as
* @BATADV_FORW_ALL: forward the packet to all nodes (currently via classic
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 127cc4d7380a..f0a50f31d822 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2012-2015 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll, Jeppe Ledet-Pedersen
*
@@ -15,15 +15,44 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
+#include "network-coding.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/byteorder/generic.h>
+#include <linux/compiler.h>
#include <linux/debugfs.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/init.h>
+#include <linux/jhash.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/workqueue.h>
-#include "main.h"
+#include "hard-interface.h"
#include "hash.h"
-#include "network-coding.h"
-#include "send.h"
#include "originator.h"
-#include "hard-interface.h"
+#include "packet.h"
#include "routing.h"
+#include "send.h"
static struct lock_class_key batadv_nc_coding_hash_lock_class_key;
static struct lock_class_key batadv_nc_decoding_hash_lock_class_key;
@@ -155,7 +184,7 @@ err:
*/
void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv)
{
- atomic_set(&bat_priv->network_coding, 1);
+ atomic_set(&bat_priv->network_coding, 0);
bat_priv->nc.min_tq = 200;
bat_priv->nc.max_fwd_delay = 10;
bat_priv->nc.max_buffer_time = 200;
@@ -275,7 +304,7 @@ static bool batadv_nc_to_purge_nc_path_decoding(struct batadv_priv *bat_priv,
* max_buffer time
*/
return batadv_has_timed_out(nc_path->last_valid,
- bat_priv->nc.max_buffer_time*10);
+ bat_priv->nc.max_buffer_time * 10);
}
/**
@@ -453,14 +482,8 @@ static uint32_t batadv_nc_hash_choose(const void *data, uint32_t size)
const struct batadv_nc_path *nc_path = data;
uint32_t hash = 0;
- hash = batadv_hash_bytes(hash, &nc_path->prev_hop,
- sizeof(nc_path->prev_hop));
- hash = batadv_hash_bytes(hash, &nc_path->next_hop,
- sizeof(nc_path->next_hop));
-
- hash += (hash << 3);
- hash ^= (hash >> 11);
- hash += (hash << 15);
+ hash = jhash(&nc_path->prev_hop, sizeof(nc_path->prev_hop), hash);
+ hash = jhash(&nc_path->next_hop, sizeof(nc_path->next_hop), hash);
return hash % size;
}
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
index 358c0d686ab0..5b79aa8c64c1 100644
--- a/net/batman-adv/network-coding.h
+++ b/net/batman-adv/network-coding.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2012-2015 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll, Jeppe Ledet-Pedersen
*
@@ -18,6 +18,19 @@
#ifndef _NET_BATMAN_ADV_NETWORK_CODING_H_
#define _NET_BATMAN_ADV_NETWORK_CODING_H_
+#include "main.h"
+
+#include <linux/types.h>
+
+struct batadv_nc_node;
+struct batadv_neigh_node;
+struct batadv_ogm_packet;
+struct batadv_orig_node;
+struct batadv_priv;
+struct net_device;
+struct seq_file;
+struct sk_buff;
+
#ifdef CONFIG_BATMAN_ADV_NC
void batadv_nc_status_update(struct net_device *net_dev);
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 90e805aba379..018b7495ad84 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -15,19 +15,31 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
+#include "originator.h"
#include "main.h"
+
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+
#include "distributed-arp-table.h"
-#include "originator.h"
-#include "hash.h"
-#include "translation-table.h"
-#include "routing.h"
+#include "fragmentation.h"
#include "gateway_client.h"
#include "hard-interface.h"
-#include "soft-interface.h"
-#include "bridge_loop_avoidance.h"
-#include "network-coding.h"
-#include "fragmentation.h"
+#include "hash.h"
#include "multicast.h"
+#include "network-coding.h"
+#include "routing.h"
+#include "translation-table.h"
/* hash class keys */
static struct lock_class_key batadv_orig_hash_lock_class_key;
@@ -197,13 +209,19 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
struct hlist_node *node_tmp;
struct batadv_neigh_node *neigh_node;
struct batadv_neigh_ifinfo *neigh_ifinfo;
+ struct batadv_algo_ops *bao;
neigh_node = container_of(rcu, struct batadv_neigh_node, rcu);
+ bao = neigh_node->orig_node->bat_priv->bat_algo_ops;
hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
&neigh_node->ifinfo_list, list) {
batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo);
}
+
+ if (bao->bat_neigh_free)
+ bao->bat_neigh_free(neigh_node);
+
batadv_hardif_free_ref_now(neigh_node->if_incoming);
kfree(neigh_node);
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index aa4a43696295..79734d302010 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -18,8 +18,21 @@
#ifndef _NET_BATMAN_ADV_ORIGINATOR_H_
#define _NET_BATMAN_ADV_ORIGINATOR_H_
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <linux/if_ether.h>
+#include <linux/jhash.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
#include "hash.h"
+struct seq_file;
+
int batadv_compare_orig(const struct hlist_node *node, const void *data2);
int batadv_originator_init(struct batadv_priv *bat_priv);
void batadv_originator_free(struct batadv_priv *bat_priv);
@@ -75,20 +88,9 @@ void batadv_orig_node_vlan_free_ref(struct batadv_orig_node_vlan *orig_vlan);
*/
static inline uint32_t batadv_choose_orig(const void *data, uint32_t size)
{
- const unsigned char *key = data;
uint32_t hash = 0;
- size_t i;
-
- for (i = 0; i < 6; i++) {
- hash += key[i];
- hash += (hash << 10);
- hash ^= (hash >> 6);
- }
-
- hash += (hash << 3);
- hash ^= (hash >> 11);
- hash += (hash << 15);
+ hash = jhash(data, ETH_ALEN, hash);
return hash % size;
}
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index b81fbbf21a63..9e747c08d0bc 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -18,6 +18,9 @@
#ifndef _NET_BATMAN_ADV_PACKET_H_
#define _NET_BATMAN_ADV_PACKET_H_
+#include <asm/byteorder.h>
+#include <linux/types.h>
+
/**
* enum batadv_packettype - types for batman-adv encapsulated packets
* @BATADV_IV_OGM: originator messages for B.A.T.M.A.N. IV
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index da83982bf974..c360c0cd19c2 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -15,20 +15,36 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
#include "routing.h"
-#include "send.h"
-#include "soft-interface.h"
-#include "hard-interface.h"
-#include "icmp_socket.h"
-#include "translation-table.h"
-#include "originator.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/byteorder/generic.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/jiffies.h>
+#include <linux/netdevice.h>
+#include <linux/printk.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+
+#include "bitarray.h"
#include "bridge_loop_avoidance.h"
#include "distributed-arp-table.h"
-#include "network-coding.h"
#include "fragmentation.h"
-
-#include <linux/if_vlan.h>
+#include "hard-interface.h"
+#include "icmp_socket.h"
+#include "network-coding.h"
+#include "originator.h"
+#include "packet.h"
+#include "send.h"
+#include "soft-interface.h"
+#include "translation-table.h"
static int batadv_route_unicast_packet(struct sk_buff *skb,
struct batadv_hard_iface *recv_if);
diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h
index 557d3d12a9ab..6bc29d33abc1 100644
--- a/net/batman-adv/routing.h
+++ b/net/batman-adv/routing.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -18,6 +18,16 @@
#ifndef _NET_BATMAN_ADV_ROUTING_H_
#define _NET_BATMAN_ADV_ROUTING_H_
+#include "main.h"
+
+#include <linux/types.h>
+
+struct batadv_hard_iface;
+struct batadv_neigh_node;
+struct batadv_orig_node;
+struct batadv_priv;
+struct sk_buff;
+
bool batadv_check_management_packet(struct sk_buff *skb,
struct batadv_hard_iface *hard_iface,
int header_len);
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 3d64ed20c393..0a01992e65ab 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -15,19 +15,37 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
+#include "send.h"
#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/byteorder/generic.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/if.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/printk.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/workqueue.h>
+
#include "distributed-arp-table.h"
-#include "send.h"
-#include "routing.h"
-#include "translation-table.h"
-#include "soft-interface.h"
-#include "hard-interface.h"
-#include "gateway_common.h"
+#include "fragmentation.h"
#include "gateway_client.h"
-#include "originator.h"
+#include "hard-interface.h"
#include "network-coding.h"
-#include "fragmentation.h"
-#include "multicast.h"
+#include "originator.h"
+#include "routing.h"
+#include "soft-interface.h"
+#include "translation-table.h"
static void batadv_send_outstanding_bcast_packet(struct work_struct *work);
@@ -255,8 +273,8 @@ int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
unsigned short vid)
{
- struct ethhdr *ethhdr;
struct batadv_unicast_packet *unicast_packet;
+ struct ethhdr *ethhdr;
int ret = NET_XMIT_DROP;
if (!orig_node)
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index 38d0ec1833ae..0536835fe503 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -18,6 +18,19 @@
#ifndef _NET_BATMAN_ADV_SEND_H_
#define _NET_BATMAN_ADV_SEND_H_
+#include "main.h"
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#include "packet.h"
+
+struct batadv_hard_iface;
+struct batadv_orig_node;
+struct batadv_priv;
+struct sk_buff;
+struct work_struct;
+
int batadv_send_skb_packet(struct sk_buff *skb,
struct batadv_hard_iface *hard_iface,
const uint8_t *dst_addr);
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 5ec31d7de24f..c002961da75d 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -15,26 +15,50 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
#include "soft-interface.h"
-#include "hard-interface.h"
-#include "distributed-arp-table.h"
-#include "routing.h"
-#include "send.h"
-#include "debugfs.h"
-#include "translation-table.h"
-#include "hash.h"
-#include "gateway_common.h"
-#include "gateway_client.h"
-#include "sysfs.h"
-#include "originator.h"
-#include <linux/slab.h>
-#include <linux/ethtool.h>
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/byteorder/generic.h>
+#include <linux/cache.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
#include <linux/if_vlan.h>
-#include "multicast.h"
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+#include <linux/percpu.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
#include "bridge_loop_avoidance.h"
+#include "debugfs.h"
+#include "distributed-arp-table.h"
+#include "gateway_client.h"
+#include "gateway_common.h"
+#include "hard-interface.h"
+#include "multicast.h"
#include "network-coding.h"
+#include "packet.h"
+#include "send.h"
+#include "sysfs.h"
+#include "translation-table.h"
static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd);
static void batadv_get_drvinfo(struct net_device *dev,
@@ -105,6 +129,7 @@ static struct net_device_stats *batadv_interface_stats(struct net_device *dev)
static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)
{
struct batadv_priv *bat_priv = netdev_priv(dev);
+ struct batadv_softif_vlan *vlan;
struct sockaddr *addr = p;
uint8_t old_addr[ETH_ALEN];
@@ -115,12 +140,17 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)
ether_addr_copy(dev->dev_addr, addr->sa_data);
/* only modify transtable if it has been initialized before */
- if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE) {
- batadv_tt_local_remove(bat_priv, old_addr, BATADV_NO_FLAGS,
+ if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
+ return 0;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) {
+ batadv_tt_local_remove(bat_priv, old_addr, vlan->vid,
"mac address changed", false);
- batadv_tt_local_add(dev, addr->sa_data, BATADV_NO_FLAGS,
+ batadv_tt_local_add(dev, addr->sa_data, vlan->vid,
BATADV_NULL_IFINDEX, BATADV_NO_MARK);
}
+ rcu_read_unlock();
return 0;
}
@@ -732,7 +762,7 @@ static int batadv_softif_init_late(struct net_device *dev)
atomic_set(&bat_priv->aggregated_ogms, 1);
atomic_set(&bat_priv->bonding, 0);
#ifdef CONFIG_BATMAN_ADV_BLA
- atomic_set(&bat_priv->bridge_loop_avoidance, 0);
+ atomic_set(&bat_priv->bridge_loop_avoidance, 1);
#endif
#ifdef CONFIG_BATMAN_ADV_DAT
atomic_set(&bat_priv->distributed_arp_table, 1);
@@ -818,7 +848,7 @@ static int batadv_softif_slave_add(struct net_device *dev,
int ret = -EINVAL;
hard_iface = batadv_hardif_get_by_netdev(slave_dev);
- if (!hard_iface || hard_iface->soft_iface != NULL)
+ if (!hard_iface || hard_iface->soft_iface)
goto out;
ret = batadv_hardif_enable_interface(hard_iface, dev->name);
diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h
index dbab22fd89a5..578e8a663c30 100644
--- a/net/batman-adv/soft-interface.h
+++ b/net/batman-adv/soft-interface.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -18,6 +18,17 @@
#ifndef _NET_BATMAN_ADV_SOFT_INTERFACE_H_
#define _NET_BATMAN_ADV_SOFT_INTERFACE_H_
+#include "main.h"
+
+#include <net/rtnetlink.h>
+
+struct batadv_hard_iface;
+struct batadv_orig_node;
+struct batadv_priv;
+struct batadv_softif_vlan;
+struct net_device;
+struct sk_buff;
+
int batadv_skb_head_push(struct sk_buff *skb, unsigned int len);
void batadv_interface_rx(struct net_device *soft_iface,
struct sk_buff *skb, struct batadv_hard_iface *recv_if,
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index a75dc12f96f8..d6a312a82c03 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -15,16 +15,35 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
#include "sysfs.h"
-#include "translation-table.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/if.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/printk.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/rtnetlink.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/stringify.h>
+
#include "distributed-arp-table.h"
-#include "network-coding.h"
-#include "originator.h"
+#include "gateway_client.h"
+#include "gateway_common.h"
#include "hard-interface.h"
+#include "network-coding.h"
+#include "packet.h"
#include "soft-interface.h"
-#include "gateway_common.h"
-#include "gateway_client.h"
static struct net_device *batadv_kobj_to_netdev(struct kobject *obj)
{
@@ -151,7 +170,7 @@ ssize_t batadv_show_##_name(struct kobject *kobj, \
static BATADV_ATTR(_name, _mode, batadv_show_##_name, \
batadv_store_##_name)
-#define BATADV_ATTR_SIF_STORE_UINT(_name, _min, _max, _post_func) \
+#define BATADV_ATTR_SIF_STORE_UINT(_name, _var, _min, _max, _post_func) \
ssize_t batadv_store_##_name(struct kobject *kobj, \
struct attribute *attr, char *buff, \
size_t count) \
@@ -161,24 +180,24 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \
\
return __batadv_store_uint_attr(buff, count, _min, _max, \
_post_func, attr, \
- &bat_priv->_name, net_dev); \
+ &bat_priv->_var, net_dev); \
}
-#define BATADV_ATTR_SIF_SHOW_UINT(_name) \
+#define BATADV_ATTR_SIF_SHOW_UINT(_name, _var) \
ssize_t batadv_show_##_name(struct kobject *kobj, \
struct attribute *attr, char *buff) \
{ \
struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); \
\
- return sprintf(buff, "%i\n", atomic_read(&bat_priv->_name)); \
+ return sprintf(buff, "%i\n", atomic_read(&bat_priv->_var)); \
} \
/* Use this, if you are going to set [name] in the soft-interface
* (bat_priv) to an unsigned integer value
*/
-#define BATADV_ATTR_SIF_UINT(_name, _mode, _min, _max, _post_func) \
- static BATADV_ATTR_SIF_STORE_UINT(_name, _min, _max, _post_func)\
- static BATADV_ATTR_SIF_SHOW_UINT(_name) \
+#define BATADV_ATTR_SIF_UINT(_name, _var, _mode, _min, _max, _post_func)\
+ static BATADV_ATTR_SIF_STORE_UINT(_name, _var, _min, _max, _post_func)\
+ static BATADV_ATTR_SIF_SHOW_UINT(_name, _var) \
static BATADV_ATTR(_name, _mode, batadv_show_##_name, \
batadv_store_##_name)
@@ -540,19 +559,20 @@ BATADV_ATTR_SIF_BOOL(fragmentation, S_IRUGO | S_IWUSR, batadv_update_min_mtu);
static BATADV_ATTR(routing_algo, S_IRUGO, batadv_show_bat_algo, NULL);
static BATADV_ATTR(gw_mode, S_IRUGO | S_IWUSR, batadv_show_gw_mode,
batadv_store_gw_mode);
-BATADV_ATTR_SIF_UINT(orig_interval, S_IRUGO | S_IWUSR, 2 * BATADV_JITTER,
- INT_MAX, NULL);
-BATADV_ATTR_SIF_UINT(hop_penalty, S_IRUGO | S_IWUSR, 0, BATADV_TQ_MAX_VALUE,
- NULL);
-BATADV_ATTR_SIF_UINT(gw_sel_class, S_IRUGO | S_IWUSR, 1, BATADV_TQ_MAX_VALUE,
- batadv_post_gw_reselect);
+BATADV_ATTR_SIF_UINT(orig_interval, orig_interval, S_IRUGO | S_IWUSR,
+ 2 * BATADV_JITTER, INT_MAX, NULL);
+BATADV_ATTR_SIF_UINT(hop_penalty, hop_penalty, S_IRUGO | S_IWUSR, 0,
+ BATADV_TQ_MAX_VALUE, NULL);
+BATADV_ATTR_SIF_UINT(gw_sel_class, gw_sel_class, S_IRUGO | S_IWUSR, 1,
+ BATADV_TQ_MAX_VALUE, batadv_post_gw_reselect);
static BATADV_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, batadv_show_gw_bwidth,
batadv_store_gw_bwidth);
#ifdef CONFIG_BATMAN_ADV_MCAST
BATADV_ATTR_SIF_BOOL(multicast_mode, S_IRUGO | S_IWUSR, NULL);
#endif
#ifdef CONFIG_BATMAN_ADV_DEBUG
-BATADV_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, BATADV_DBG_ALL, NULL);
+BATADV_ATTR_SIF_UINT(log_level, log_level, S_IRUGO | S_IWUSR, 0,
+ BATADV_DBG_ALL, NULL);
#endif
#ifdef CONFIG_BATMAN_ADV_NC
BATADV_ATTR_SIF_BOOL(network_coding, S_IRUGO | S_IWUSR,
diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h
index b715b60db7cd..2294583f7cf9 100644
--- a/net/batman-adv/sysfs.h
+++ b/net/batman-adv/sysfs.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
@@ -18,6 +18,16 @@
#ifndef _NET_BATMAN_ADV_SYSFS_H_
#define _NET_BATMAN_ADV_SYSFS_H_
+#include "main.h"
+
+#include <linux/sysfs.h>
+#include <linux/types.h>
+
+struct batadv_priv;
+struct batadv_softif_vlan;
+struct kobject;
+struct net_device;
+
#define BATADV_SYSFS_IF_MESH_SUBDIR "mesh"
#define BATADV_SYSFS_IF_BAT_SUBDIR "batman_adv"
/**
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 07b263a437d1..b4824951010b 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich, Antonio Quartulli
*
@@ -15,18 +15,41 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
#include "translation-table.h"
-#include "soft-interface.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/byteorder/generic.h>
+#include <linux/compiler.h>
+#include <linux/crc32c.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/jhash.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/workqueue.h>
+#include <net/net_namespace.h>
+
+#include "bridge_loop_avoidance.h"
#include "hard-interface.h"
-#include "send.h"
#include "hash.h"
-#include "originator.h"
-#include "routing.h"
-#include "bridge_loop_avoidance.h"
#include "multicast.h"
-
-#include <linux/crc32c.h>
+#include "originator.h"
+#include "packet.h"
+#include "soft-interface.h"
/* hash class keys */
static struct lock_class_key batadv_tt_local_hash_lock_class_key;
@@ -67,12 +90,8 @@ static inline uint32_t batadv_choose_tt(const void *data, uint32_t size)
uint32_t hash = 0;
tt = (struct batadv_tt_common_entry *)data;
- hash = batadv_hash_bytes(hash, &tt->addr, ETH_ALEN);
- hash = batadv_hash_bytes(hash, &tt->vid, sizeof(tt->vid));
-
- hash += (hash << 3);
- hash ^= (hash >> 11);
- hash += (hash << 15);
+ hash = jhash(&tt->addr, ETH_ALEN, hash);
+ hash = jhash(&tt->vid, sizeof(tt->vid), hash);
return hash % size;
}
@@ -954,17 +973,17 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
" * %pM %4i [%c%c%c%c%c%c] %3u.%03u (%#.8x)\n",
tt_common_entry->addr,
BATADV_PRINT_VID(tt_common_entry->vid),
- (tt_common_entry->flags &
- BATADV_TT_CLIENT_ROAM ? 'R' : '.'),
+ ((tt_common_entry->flags &
+ BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
no_purge ? 'P' : '.',
- (tt_common_entry->flags &
- BATADV_TT_CLIENT_NEW ? 'N' : '.'),
- (tt_common_entry->flags &
- BATADV_TT_CLIENT_PENDING ? 'X' : '.'),
- (tt_common_entry->flags &
- BATADV_TT_CLIENT_WIFI ? 'W' : '.'),
- (tt_common_entry->flags &
- BATADV_TT_CLIENT_ISOLA ? 'I' : '.'),
+ ((tt_common_entry->flags &
+ BATADV_TT_CLIENT_NEW) ? 'N' : '.'),
+ ((tt_common_entry->flags &
+ BATADV_TT_CLIENT_PENDING) ? 'X' : '.'),
+ ((tt_common_entry->flags &
+ BATADV_TT_CLIENT_WIFI) ? 'W' : '.'),
+ ((tt_common_entry->flags &
+ BATADV_TT_CLIENT_ISOLA) ? 'I' : '.'),
no_purge ? 0 : last_seen_secs,
no_purge ? 0 : last_seen_msecs,
vlan->tt.crc);
@@ -1528,10 +1547,10 @@ batadv_tt_global_print_entry(struct batadv_priv *bat_priv,
BATADV_PRINT_VID(tt_global_entry->common.vid),
best_entry->ttvn, best_entry->orig_node->orig,
last_ttvn, vlan->tt.crc,
- (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'),
- (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'),
- (flags & BATADV_TT_CLIENT_ISOLA ? 'I' : '.'),
- (flags & BATADV_TT_CLIENT_TEMP ? 'T' : '.'));
+ ((flags & BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
+ ((flags & BATADV_TT_CLIENT_WIFI) ? 'W' : '.'),
+ ((flags & BATADV_TT_CLIENT_ISOLA) ? 'I' : '.'),
+ ((flags & BATADV_TT_CLIENT_TEMP) ? 'T' : '.'));
batadv_orig_node_vlan_free_ref(vlan);
}
@@ -1560,10 +1579,10 @@ print_list:
BATADV_PRINT_VID(tt_global_entry->common.vid),
orig_entry->ttvn, orig_entry->orig_node->orig,
last_ttvn, vlan->tt.crc,
- (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'),
- (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'),
- (flags & BATADV_TT_CLIENT_ISOLA ? 'I' : '.'),
- (flags & BATADV_TT_CLIENT_TEMP ? 'T' : '.'));
+ ((flags & BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
+ ((flags & BATADV_TT_CLIENT_WIFI) ? 'W' : '.'),
+ ((flags & BATADV_TT_CLIENT_ISOLA) ? 'I' : '.'),
+ ((flags & BATADV_TT_CLIENT_TEMP) ? 'T' : '.'));
batadv_orig_node_vlan_free_ref(vlan);
}
@@ -2529,7 +2548,7 @@ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Received TT_REQUEST from %pM for ttvn: %u (%pM) [%c]\n",
req_src, tt_data->ttvn, req_dst,
- (tt_data->flags & BATADV_TT_FULL_TABLE ? 'F' : '.'));
+ ((tt_data->flags & BATADV_TT_FULL_TABLE) ? 'F' : '.'));
/* Let's get the orig node of the REAL destination */
req_dst_orig_node = batadv_orig_hash_find(bat_priv, req_dst);
@@ -2660,7 +2679,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Received TT_REQUEST from %pM for ttvn: %u (me) [%c]\n",
req_src, tt_data->ttvn,
- (tt_data->flags & BATADV_TT_FULL_TABLE ? 'F' : '.'));
+ ((tt_data->flags & BATADV_TT_FULL_TABLE) ? 'F' : '.'));
spin_lock_bh(&bat_priv->tt.commit_lock);
@@ -2899,7 +2918,7 @@ static void batadv_handle_tt_response(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Received TT_RESPONSE from %pM for ttvn %d t_size: %d [%c]\n",
resp_src, tt_data->ttvn, num_entries,
- (tt_data->flags & BATADV_TT_FULL_TABLE ? 'F' : '.'));
+ ((tt_data->flags & BATADV_TT_FULL_TABLE) ? 'F' : '.'));
orig_node = batadv_orig_hash_find(bat_priv, resp_src);
if (!orig_node)
diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h
index ad84d7b89e39..6acc25d3a925 100644
--- a/net/batman-adv/translation-table.h
+++ b/net/batman-adv/translation-table.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich, Antonio Quartulli
*
@@ -18,6 +18,15 @@
#ifndef _NET_BATMAN_ADV_TRANSLATION_TABLE_H_
#define _NET_BATMAN_ADV_TRANSLATION_TABLE_H_
+#include "main.h"
+
+#include <linux/types.h>
+
+struct batadv_orig_node;
+struct batadv_priv;
+struct net_device;
+struct seq_file;
+
int batadv_tt_init(struct batadv_priv *bat_priv);
bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
unsigned short vid, int ifindex, uint32_t mark);
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 9398c3fb4174..67d63483618e 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
@@ -18,9 +18,23 @@
#ifndef _NET_BATMAN_ADV_TYPES_H_
#define _NET_BATMAN_ADV_TYPES_H_
+#ifndef _NET_BATMAN_ADV_MAIN_H_
+#error only "main.h" can be included directly
+#endif
+
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/if_ether.h>
+#include <linux/netdevice.h>
+#include <linux/sched.h> /* for linux/wait.h */
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+
#include "packet.h"
-#include "bitarray.h"
-#include <linux/kernel.h>
+
+struct seq_file;
#ifdef CONFIG_BATMAN_ADV_DAT
@@ -132,6 +146,7 @@ struct batadv_orig_ifinfo {
* @timestamp: time (jiffie) of last received fragment
* @seqno: sequence number of the fragments in the list
* @size: accumulated size of packets in list
+ * @total_size: expected size of the assembled packet
*/
struct batadv_frag_table_entry {
struct hlist_head head;
@@ -139,6 +154,7 @@ struct batadv_frag_table_entry {
unsigned long timestamp;
uint16_t seqno;
uint16_t size;
+ uint16_t total_size;
};
/**
@@ -181,9 +197,10 @@ struct batadv_orig_node_vlan {
/**
* struct batadv_orig_bat_iv - B.A.T.M.A.N. IV private orig_node members
- * @bcast_own: bitfield containing the number of our OGMs this orig_node
- * rebroadcasted "back" to us (relative to last_real_seqno)
- * @bcast_own_sum: counted result of bcast_own
+ * @bcast_own: set of bitfields (one per hard interface) where each one counts
+ * the number of our OGMs this orig_node rebroadcasted "back" to us (relative
+ * to last_real_seqno). Every bitfield is BATADV_TQ_LOCAL_WINDOW_SIZE bits long.
+ * @bcast_own_sum: sum of bcast_own
* @ogm_cnt_lock: lock protecting bcast_own, bcast_own_sum,
* neigh_node->bat_iv.real_bits & neigh_node->bat_iv.real_packet_count
*/
@@ -1118,6 +1135,8 @@ struct batadv_forw_packet {
* @bat_neigh_is_equiv_or_better: check if neigh1 is equally good or better
* than neigh2 for their respective outgoing interface from the metric
* prospective
+ * @bat_neigh_free: free the resources allocated by the routing algorithm for a
+ * neigh_node object
* @bat_orig_print: print the originator table (optional)
* @bat_orig_free: free the resources allocated by the routing algorithm for an
* orig_node object
@@ -1135,6 +1154,7 @@ struct batadv_algo_ops {
void (*bat_primary_iface_set)(struct batadv_hard_iface *hard_iface);
void (*bat_ogm_schedule)(struct batadv_hard_iface *hard_iface);
void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet);
+ /* neigh_node handling API */
int (*bat_neigh_cmp)(struct batadv_neigh_node *neigh1,
struct batadv_hard_iface *if_outgoing1,
struct batadv_neigh_node *neigh2,
@@ -1144,6 +1164,7 @@ struct batadv_algo_ops {
struct batadv_hard_iface *if_outgoing1,
struct batadv_neigh_node *neigh2,
struct batadv_hard_iface *if_outgoing2);
+ void (*bat_neigh_free)(struct batadv_neigh_node *neigh);
/* orig_node handling API */
void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq,
struct batadv_hard_iface *hard_iface);
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 1742b849fcff..f3d6046c8ee7 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -192,7 +192,7 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_dev *dev,
if (ipv6_addr_any(nexthop))
return NULL;
} else {
- nexthop = rt6_nexthop(rt);
+ nexthop = rt6_nexthop(rt, daddr);
/* We need to remember the address because it is needed
* by bt_xmit() when sending the packet. In bt_xmit(), the
diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c
index bde2bdd9e929..b5116fa9835e 100644
--- a/net/bluetooth/bnep/sock.c
+++ b/net/bluetooth/bnep/sock.c
@@ -202,7 +202,7 @@ static int bnep_sock_create(struct net *net, struct socket *sock, int protocol,
if (sock->type != SOCK_RAW)
return -ESOCKTNOSUPPORT;
- sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &bnep_proto);
+ sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &bnep_proto, kern);
if (!sk)
return -ENOMEM;
diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c
index d82787d417bd..ce86a7bae844 100644
--- a/net/bluetooth/cmtp/sock.c
+++ b/net/bluetooth/cmtp/sock.c
@@ -205,7 +205,7 @@ static int cmtp_sock_create(struct net *net, struct socket *sock, int protocol,
if (sock->type != SOCK_RAW)
return -ESOCKTNOSUPPORT;
- sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &cmtp_proto);
+ sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &cmtp_proto, kern);
if (!sk)
return -ENOMEM;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index c4802f3bd4c5..f6c99098959f 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -94,7 +94,6 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf,
char buf[32];
size_t buf_size = min(count, (sizeof(buf)-1));
bool enable;
- int err;
if (!test_bit(HCI_UP, &hdev->flags))
return -ENETDOWN;
@@ -121,12 +120,8 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf,
if (IS_ERR(skb))
return PTR_ERR(skb);
- err = -bt_to_errno(skb->data[0]);
kfree_skb(skb);
- if (err < 0)
- return err;
-
hci_dev_change_flag(hdev, HCI_DUT_MODE);
return count;
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 56f9edbf3d05..5b14dcafcd08 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1377,7 +1377,7 @@ static int hci_sock_create(struct net *net, struct socket *sock, int protocol,
sock->ops = &hci_sock_ops;
- sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hci_sk_proto);
+ sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hci_sk_proto, kern);
if (!sk)
return -ENOMEM;
diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c
index cb3fdde1968a..008ba439bd62 100644
--- a/net/bluetooth/hidp/sock.c
+++ b/net/bluetooth/hidp/sock.c
@@ -235,7 +235,7 @@ static int hidp_sock_create(struct net *net, struct socket *sock, int protocol,
if (sock->type != SOCK_RAW)
return -ESOCKTNOSUPPORT;
- sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hidp_proto);
+ sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hidp_proto, kern);
if (!sk)
return -ENOMEM;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index a7278f05eafb..244287706f91 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -43,7 +43,7 @@ static struct bt_sock_list l2cap_sk_list = {
static const struct proto_ops l2cap_sock_ops;
static void l2cap_sock_init(struct sock *sk, struct sock *parent);
static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
- int proto, gfp_t prio);
+ int proto, gfp_t prio, int kern);
bool l2cap_is_socket(struct socket *sock)
{
@@ -1193,7 +1193,7 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan)
}
sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP,
- GFP_ATOMIC);
+ GFP_ATOMIC, 0);
if (!sk) {
release_sock(parent);
return NULL;
@@ -1523,12 +1523,12 @@ static struct proto l2cap_proto = {
};
static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
- int proto, gfp_t prio)
+ int proto, gfp_t prio, int kern)
{
struct sock *sk;
struct l2cap_chan *chan;
- sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto);
+ sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto, kern);
if (!sk)
return NULL;
@@ -1574,7 +1574,7 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol,
sock->ops = &l2cap_sock_ops;
- sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC);
+ sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern);
if (!sk)
return -ENOMEM;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 7fd87e7135b5..a6f21f8c2f98 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -7577,7 +7577,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent)
memset(&ev, 0, sizeof(ev));
/* Devices using resolvable or non-resolvable random addresses
- * without providing an indentity resolving key don't require
+ * without providing an identity resolving key don't require
* to store long term keys. Their addresses will change the
* next time around.
*
@@ -7617,7 +7617,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk)
/* For identity resolving keys from devices that are already
* using a public address or static random address, do not
* ask for storing this key. The identity resolving key really
- * is only mandatory for devices using resovlable random
+ * is only mandatory for devices using resolvable random
* addresses.
*
* Storing all identity resolving keys has the downside that
@@ -7646,7 +7646,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk,
memset(&ev, 0, sizeof(ev));
/* Devices using resolvable or non-resolvable random addresses
- * without providing an indentity resolving key don't require
+ * without providing an identity resolving key don't require
* to store signature resolving keys. Their addresses will change
* the next time around.
*
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index 4fea24275b17..29709fbfd1f5 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -200,7 +200,7 @@ static int rfcomm_l2sock_create(struct socket **sock)
BT_DBG("");
- err = sock_create_kern(PF_BLUETOOTH, SOCK_SEQPACKET, BTPROTO_L2CAP, sock);
+ err = sock_create_kern(&init_net, PF_BLUETOOTH, SOCK_SEQPACKET, BTPROTO_L2CAP, sock);
if (!err) {
struct sock *sk = (*sock)->sk;
sk->sk_data_ready = rfcomm_l2data_ready;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 825e8fb5114b..b2338e971b33 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -269,12 +269,12 @@ static struct proto rfcomm_proto = {
.obj_size = sizeof(struct rfcomm_pinfo)
};
-static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio)
+static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern)
{
struct rfcomm_dlc *d;
struct sock *sk;
- sk = sk_alloc(net, PF_BLUETOOTH, prio, &rfcomm_proto);
+ sk = sk_alloc(net, PF_BLUETOOTH, prio, &rfcomm_proto, kern);
if (!sk)
return NULL;
@@ -324,7 +324,7 @@ static int rfcomm_sock_create(struct net *net, struct socket *sock,
sock->ops = &rfcomm_sock_ops;
- sk = rfcomm_sock_alloc(net, sock, protocol, GFP_ATOMIC);
+ sk = rfcomm_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern);
if (!sk)
return -ENOMEM;
@@ -969,7 +969,7 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc *
goto done;
}
- sk = rfcomm_sock_alloc(sock_net(parent), NULL, BTPROTO_RFCOMM, GFP_ATOMIC);
+ sk = rfcomm_sock_alloc(sock_net(parent), NULL, BTPROTO_RFCOMM, GFP_ATOMIC, 0);
if (!sk)
goto done;
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 4322c833e748..6b6e59dc54cf 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -460,11 +460,11 @@ static struct proto sco_proto = {
.obj_size = sizeof(struct sco_pinfo)
};
-static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio)
+static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern)
{
struct sock *sk;
- sk = sk_alloc(net, PF_BLUETOOTH, prio, &sco_proto);
+ sk = sk_alloc(net, PF_BLUETOOTH, prio, &sco_proto, kern);
if (!sk)
return NULL;
@@ -501,7 +501,7 @@ static int sco_sock_create(struct net *net, struct socket *sock, int protocol,
sock->ops = &sco_sock_ops;
- sk = sco_sock_alloc(net, sock, protocol, GFP_ATOMIC);
+ sk = sco_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern);
if (!sk)
return -ENOMEM;
@@ -1026,7 +1026,7 @@ static void sco_conn_ready(struct sco_conn *conn)
bh_lock_sock(parent);
sk = sco_sock_alloc(sock_net(parent), NULL,
- BTPROTO_SCO, GFP_ATOMIC);
+ BTPROTO_SCO, GFP_ATOMIC, 0);
if (!sk) {
bh_unlock_sock(parent);
sco_conn_unlock(conn);
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 1ab3dc9c8f99..659371af39e4 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -371,6 +371,8 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
uint8_t tmp[16], data[16];
int err;
+ SMP_DBG("k %16phN r %16phN", k, r);
+
if (!tfm) {
BT_ERR("tfm %p", tfm);
return -EINVAL;
@@ -400,6 +402,8 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
/* Most significant octet of encryptedData corresponds to data[0] */
swap_buf(data, r, 16);
+ SMP_DBG("r %16phN", r);
+
return err;
}
@@ -410,6 +414,10 @@ static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16],
u8 p1[16], p2[16];
int err;
+ SMP_DBG("k %16phN r %16phN", k, r);
+ SMP_DBG("iat %u ia %6phN rat %u ra %6phN", _iat, ia, _rat, ra);
+ SMP_DBG("preq %7phN pres %7phN", preq, pres);
+
memset(p1, 0, 16);
/* p1 = pres || preq || _rat || _iat */
@@ -418,10 +426,7 @@ static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16],
memcpy(p1 + 2, preq, 7);
memcpy(p1 + 9, pres, 7);
- /* p2 = padding || ia || ra */
- memcpy(p2, ra, 6);
- memcpy(p2 + 6, ia, 6);
- memset(p2 + 12, 0, 4);
+ SMP_DBG("p1 %16phN", p1);
/* res = r XOR p1 */
u128_xor((u128 *) res, (u128 *) r, (u128 *) p1);
@@ -433,6 +438,13 @@ static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16],
return err;
}
+ /* p2 = padding || ia || ra */
+ memcpy(p2, ra, 6);
+ memcpy(p2 + 6, ia, 6);
+ memset(p2 + 12, 0, 4);
+
+ SMP_DBG("p2 %16phN", p2);
+
/* res = res XOR p2 */
u128_xor((u128 *) res, (u128 *) res, (u128 *) p2);
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 02c24cf63c34..a1abe4936fe1 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -121,13 +121,13 @@ static struct notifier_block br_device_notifier = {
.notifier_call = br_device_event
};
-static int br_netdev_switch_event(struct notifier_block *unused,
- unsigned long event, void *ptr)
+static int br_switchdev_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
{
- struct net_device *dev = netdev_switch_notifier_info_to_dev(ptr);
+ struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
struct net_bridge_port *p;
struct net_bridge *br;
- struct netdev_switch_notifier_fdb_info *fdb_info;
+ struct switchdev_notifier_fdb_info *fdb_info;
int err = NOTIFY_DONE;
rtnl_lock();
@@ -138,14 +138,14 @@ static int br_netdev_switch_event(struct notifier_block *unused,
br = p->br;
switch (event) {
- case NETDEV_SWITCH_FDB_ADD:
+ case SWITCHDEV_FDB_ADD:
fdb_info = ptr;
err = br_fdb_external_learn_add(br, p, fdb_info->addr,
fdb_info->vid);
if (err)
err = notifier_from_errno(err);
break;
- case NETDEV_SWITCH_FDB_DEL:
+ case SWITCHDEV_FDB_DEL:
fdb_info = ptr;
err = br_fdb_external_learn_del(br, p, fdb_info->addr,
fdb_info->vid);
@@ -159,8 +159,8 @@ out:
return err;
}
-static struct notifier_block br_netdev_switch_notifier = {
- .notifier_call = br_netdev_switch_event,
+static struct notifier_block br_switchdev_notifier = {
+ .notifier_call = br_switchdev_event,
};
static void __net_exit br_net_exit(struct net *net)
@@ -214,7 +214,7 @@ static int __init br_init(void)
if (err)
goto err_out3;
- err = register_netdev_switch_notifier(&br_netdev_switch_notifier);
+ err = register_switchdev_notifier(&br_switchdev_notifier);
if (err)
goto err_out4;
@@ -235,7 +235,7 @@ static int __init br_init(void)
return 0;
err_out5:
- unregister_netdev_switch_notifier(&br_netdev_switch_notifier);
+ unregister_switchdev_notifier(&br_switchdev_notifier);
err_out4:
unregister_netdevice_notifier(&br_device_notifier);
err_out3:
@@ -253,7 +253,7 @@ static void __exit br_deinit(void)
{
stp_proto_unregister(&br_stp_proto);
br_netlink_fini();
- unregister_netdev_switch_notifier(&br_netdev_switch_notifier);
+ unregister_switchdev_notifier(&br_switchdev_notifier);
unregister_netdevice_notifier(&br_device_notifier);
brioctl_set(NULL);
unregister_pernet_subsys(&br_net_ops);
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 659fb96672e4..13949a71591d 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -736,6 +736,12 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
struct net_bridge_fdb_entry *fdb;
bool modified = false;
+ /* If the port cannot learn allow only local and static entries */
+ if (!(state & NUD_PERMANENT) && !(state & NUD_NOARP) &&
+ !(source->state == BR_STATE_LEARNING ||
+ source->state == BR_STATE_FORWARDING))
+ return -EPERM;
+
fdb = fdb_find(head, addr, vid);
if (fdb == NULL) {
if (!(flags & NLM_F_CREATE))
@@ -867,13 +873,15 @@ out:
return err;
}
-static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vlan)
+static int fdb_delete_by_addr_and_port(struct net_bridge_port *p,
+ const u8 *addr, u16 vlan)
{
+ struct net_bridge *br = p->br;
struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)];
struct net_bridge_fdb_entry *fdb;
fdb = fdb_find(head, addr, vlan);
- if (!fdb)
+ if (!fdb || fdb->dst != p)
return -ENOENT;
fdb_delete(br, fdb);
@@ -886,7 +894,7 @@ static int __br_fdb_delete(struct net_bridge_port *p,
int err;
spin_lock_bh(&p->br->hash_lock);
- err = fdb_delete_by_addr(p->br, addr, vid);
+ err = fdb_delete_by_addr_and_port(p, addr, vid);
spin_unlock_bh(&p->br->hash_lock);
return err;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index ff667e18b2d6..2e246a1a9b43 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -975,9 +975,6 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
int err = 0;
__be32 group;
- if (!pskb_may_pull(skb, sizeof(*ih)))
- return -EINVAL;
-
ih = igmpv3_report_hdr(skb);
num = ntohs(ih->ngrec);
len = sizeof(*ih);
@@ -1247,25 +1244,14 @@ static int br_ip4_multicast_query(struct net_bridge *br,
max_delay = 10 * HZ;
group = 0;
}
- } else {
- if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) {
- err = -EINVAL;
- goto out;
- }
-
+ } else if (skb->len >= sizeof(*ih3)) {
ih3 = igmpv3_query_hdr(skb);
if (ih3->nsrcs)
goto out;
max_delay = ih3->code ?
IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1;
- }
-
- /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer
- * all-systems destination addresses (224.0.0.1) for general queries
- */
- if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) {
- err = -EINVAL;
+ } else {
goto out;
}
@@ -1328,12 +1314,6 @@ static int br_ip6_multicast_query(struct net_bridge *br,
(port && port->state == BR_STATE_DISABLED))
goto out;
- /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
- if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) {
- err = -EINVAL;
- goto out;
- }
-
if (skb->len == sizeof(*mld)) {
if (!pskb_may_pull(skb, sizeof(*mld))) {
err = -EINVAL;
@@ -1357,14 +1337,6 @@ static int br_ip6_multicast_query(struct net_bridge *br,
is_general_query = group && ipv6_addr_any(group);
- /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer
- * all-nodes destination address (ff02::1) for general queries
- */
- if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) {
- err = -EINVAL;
- goto out;
- }
-
if (is_general_query) {
saddr.proto = htons(ETH_P_IPV6);
saddr.u.ip6 = ip6h->saddr;
@@ -1556,74 +1528,22 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
struct sk_buff *skb,
u16 vid)
{
- struct sk_buff *skb2 = skb;
- const struct iphdr *iph;
+ struct sk_buff *skb_trimmed = NULL;
struct igmphdr *ih;
- unsigned int len;
- unsigned int offset;
int err;
- /* We treat OOM as packet loss for now. */
- if (!pskb_may_pull(skb, sizeof(*iph)))
- return -EINVAL;
-
- iph = ip_hdr(skb);
-
- if (iph->ihl < 5 || iph->version != 4)
- return -EINVAL;
-
- if (!pskb_may_pull(skb, ip_hdrlen(skb)))
- return -EINVAL;
-
- iph = ip_hdr(skb);
+ err = ip_mc_check_igmp(skb, &skb_trimmed);
- if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
- return -EINVAL;
-
- if (iph->protocol != IPPROTO_IGMP) {
- if (!ipv4_is_local_multicast(iph->daddr))
+ if (err == -ENOMSG) {
+ if (!ipv4_is_local_multicast(ip_hdr(skb)->daddr))
BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
return 0;
+ } else if (err < 0) {
+ return err;
}
- len = ntohs(iph->tot_len);
- if (skb->len < len || len < ip_hdrlen(skb))
- return -EINVAL;
-
- if (skb->len > len) {
- skb2 = skb_clone(skb, GFP_ATOMIC);
- if (!skb2)
- return -ENOMEM;
-
- err = pskb_trim_rcsum(skb2, len);
- if (err)
- goto err_out;
- }
-
- len -= ip_hdrlen(skb2);
- offset = skb_network_offset(skb2) + ip_hdrlen(skb2);
- __skb_pull(skb2, offset);
- skb_reset_transport_header(skb2);
-
- err = -EINVAL;
- if (!pskb_may_pull(skb2, sizeof(*ih)))
- goto out;
-
- switch (skb2->ip_summed) {
- case CHECKSUM_COMPLETE:
- if (!csum_fold(skb2->csum))
- break;
- /* fall through */
- case CHECKSUM_NONE:
- skb2->csum = 0;
- if (skb_checksum_complete(skb2))
- goto out;
- }
-
- err = 0;
-
BR_INPUT_SKB_CB(skb)->igmp = 1;
- ih = igmp_hdr(skb2);
+ ih = igmp_hdr(skb);
switch (ih->type) {
case IGMP_HOST_MEMBERSHIP_REPORT:
@@ -1632,21 +1552,19 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
err = br_ip4_multicast_add_group(br, port, ih->group, vid);
break;
case IGMPV3_HOST_MEMBERSHIP_REPORT:
- err = br_ip4_multicast_igmp3_report(br, port, skb2, vid);
+ err = br_ip4_multicast_igmp3_report(br, port, skb_trimmed, vid);
break;
case IGMP_HOST_MEMBERSHIP_QUERY:
- err = br_ip4_multicast_query(br, port, skb2, vid);
+ err = br_ip4_multicast_query(br, port, skb_trimmed, vid);
break;
case IGMP_HOST_LEAVE_MESSAGE:
br_ip4_multicast_leave_group(br, port, ih->group, vid);
break;
}
-out:
- __skb_push(skb2, offset);
-err_out:
- if (skb2 != skb)
- kfree_skb(skb2);
+ if (skb_trimmed)
+ kfree_skb(skb_trimmed);
+
return err;
}
@@ -1656,138 +1574,42 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
struct sk_buff *skb,
u16 vid)
{
- struct sk_buff *skb2;
- const struct ipv6hdr *ip6h;
- u8 icmp6_type;
- u8 nexthdr;
- __be16 frag_off;
- unsigned int len;
- int offset;
+ struct sk_buff *skb_trimmed = NULL;
+ struct mld_msg *mld;
int err;
- if (!pskb_may_pull(skb, sizeof(*ip6h)))
- return -EINVAL;
-
- ip6h = ipv6_hdr(skb);
-
- /*
- * We're interested in MLD messages only.
- * - Version is 6
- * - MLD has always Router Alert hop-by-hop option
- * - But we do not support jumbrograms.
- */
- if (ip6h->version != 6)
- return 0;
-
- /* Prevent flooding this packet if there is no listener present */
- if (!ipv6_addr_is_ll_all_nodes(&ip6h->daddr))
- BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
-
- if (ip6h->nexthdr != IPPROTO_HOPOPTS ||
- ip6h->payload_len == 0)
- return 0;
-
- len = ntohs(ip6h->payload_len) + sizeof(*ip6h);
- if (skb->len < len)
- return -EINVAL;
-
- nexthdr = ip6h->nexthdr;
- offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr, &frag_off);
+ err = ipv6_mc_check_mld(skb, &skb_trimmed);
- if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
+ if (err == -ENOMSG) {
+ if (!ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr))
+ BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
return 0;
-
- /* Okay, we found ICMPv6 header */
- skb2 = skb_clone(skb, GFP_ATOMIC);
- if (!skb2)
- return -ENOMEM;
-
- err = -EINVAL;
- if (!pskb_may_pull(skb2, offset + sizeof(struct icmp6hdr)))
- goto out;
-
- len -= offset - skb_network_offset(skb2);
-
- __skb_pull(skb2, offset);
- skb_reset_transport_header(skb2);
- skb_postpull_rcsum(skb2, skb_network_header(skb2),
- skb_network_header_len(skb2));
-
- icmp6_type = icmp6_hdr(skb2)->icmp6_type;
-
- switch (icmp6_type) {
- case ICMPV6_MGM_QUERY:
- case ICMPV6_MGM_REPORT:
- case ICMPV6_MGM_REDUCTION:
- case ICMPV6_MLD2_REPORT:
- break;
- default:
- err = 0;
- goto out;
- }
-
- /* Okay, we found MLD message. Check further. */
- if (skb2->len > len) {
- err = pskb_trim_rcsum(skb2, len);
- if (err)
- goto out;
- err = -EINVAL;
- }
-
- ip6h = ipv6_hdr(skb2);
-
- switch (skb2->ip_summed) {
- case CHECKSUM_COMPLETE:
- if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb2->len,
- IPPROTO_ICMPV6, skb2->csum))
- break;
- /*FALLTHROUGH*/
- case CHECKSUM_NONE:
- skb2->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr,
- &ip6h->daddr,
- skb2->len,
- IPPROTO_ICMPV6, 0));
- if (__skb_checksum_complete(skb2))
- goto out;
+ } else if (err < 0) {
+ return err;
}
- err = 0;
-
BR_INPUT_SKB_CB(skb)->igmp = 1;
+ mld = (struct mld_msg *)skb_transport_header(skb);
- switch (icmp6_type) {
+ switch (mld->mld_type) {
case ICMPV6_MGM_REPORT:
- {
- struct mld_msg *mld;
- if (!pskb_may_pull(skb2, sizeof(*mld))) {
- err = -EINVAL;
- goto out;
- }
- mld = (struct mld_msg *)skb_transport_header(skb2);
BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid);
break;
- }
case ICMPV6_MLD2_REPORT:
- err = br_ip6_multicast_mld2_report(br, port, skb2, vid);
+ err = br_ip6_multicast_mld2_report(br, port, skb_trimmed, vid);
break;
case ICMPV6_MGM_QUERY:
- err = br_ip6_multicast_query(br, port, skb2, vid);
+ err = br_ip6_multicast_query(br, port, skb_trimmed, vid);
break;
case ICMPV6_MGM_REDUCTION:
- {
- struct mld_msg *mld;
- if (!pskb_may_pull(skb2, sizeof(*mld))) {
- err = -EINVAL;
- goto out;
- }
- mld = (struct mld_msg *)skb_transport_header(skb2);
br_ip6_multicast_leave_group(br, port, &mld->mld_mca, vid);
- }
+ break;
}
-out:
- kfree_skb(skb2);
+ if (skb_trimmed)
+ kfree_skb(skb_trimmed);
+
return err;
}
#endif
@@ -1949,11 +1771,9 @@ out:
int br_multicast_set_router(struct net_bridge *br, unsigned long val)
{
- int err = -ENOENT;
+ int err = -EINVAL;
spin_lock_bh(&br->multicast_lock);
- if (!netif_running(br->dev))
- goto unlock;
switch (val) {
case 0:
@@ -1964,13 +1784,8 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val)
br->multicast_router = val;
err = 0;
break;
-
- default:
- err = -EINVAL;
- break;
}
-unlock:
spin_unlock_bh(&br->multicast_lock);
return err;
@@ -1979,11 +1794,9 @@ unlock:
int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val)
{
struct net_bridge *br = p->br;
- int err = -ENOENT;
+ int err = -EINVAL;
spin_lock(&br->multicast_lock);
- if (!netif_running(br->dev) || p->state == BR_STATE_DISABLED)
- goto unlock;
switch (val) {
case 0:
@@ -2005,13 +1818,8 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val)
br_multicast_add_router(br, p);
break;
-
- default:
- err = -EINVAL;
- break;
}
-unlock:
spin_unlock(&br->multicast_lock);
return err;
@@ -2116,15 +1924,11 @@ unlock:
int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val)
{
- int err = -ENOENT;
+ int err = -EINVAL;
u32 old;
struct net_bridge_mdb_htable *mdb;
spin_lock_bh(&br->multicast_lock);
- if (!netif_running(br->dev))
- goto unlock;
-
- err = -EINVAL;
if (!is_power_of_2(val))
goto unlock;
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 60ddfbeb47f5..46660a28feef 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -125,6 +125,14 @@ static struct nf_bridge_info *nf_bridge_info_get(const struct sk_buff *skb)
return skb->nf_bridge;
}
+static void nf_bridge_info_free(struct sk_buff *skb)
+{
+ if (skb->nf_bridge) {
+ nf_bridge_put(skb->nf_bridge);
+ skb->nf_bridge = NULL;
+ }
+}
+
static inline struct rtable *bridge_parent_rtable(const struct net_device *dev)
{
struct net_bridge_port *port;
@@ -832,17 +840,39 @@ static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb)
skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size);
__skb_push(skb, data->encap_size);
+ nf_bridge_info_free(skb);
return br_dev_queue_push_xmit(sk, skb);
}
+static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb,
+ int (*output)(struct sock *, struct sk_buff *))
+{
+ unsigned int mtu = ip_skb_dst_mtu(skb);
+ struct iphdr *iph = ip_hdr(skb);
+ struct rtable *rt = skb_rtable(skb);
+ struct net_device *dev = rt->dst.dev;
+
+ if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
+ (IPCB(skb)->frag_max_size &&
+ IPCB(skb)->frag_max_size > mtu))) {
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ kfree_skb(skb);
+ return -EMSGSIZE;
+ }
+
+ return ip_do_fragment(sk, skb, output);
+}
+
static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
{
int ret;
int frag_max_size;
unsigned int mtu_reserved;
- if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP))
+ if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP)) {
+ nf_bridge_info_free(skb);
return br_dev_queue_push_xmit(sk, skb);
+ }
mtu_reserved = nf_bridge_mtu_reduction(skb);
/* This is wrong! We should preserve the original fragment
@@ -866,8 +896,9 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
data->size);
- ret = ip_fragment(sk, skb, br_nf_push_frag_xmit);
+ ret = br_nf_ip_fragment(sk, skb, br_nf_push_frag_xmit);
} else {
+ nf_bridge_info_free(skb);
ret = br_dev_queue_push_xmit(sk, skb);
}
@@ -876,7 +907,8 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
#else
static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
{
- return br_dev_queue_push_xmit(sk, skb);
+ nf_bridge_info_free(skb);
+ return br_dev_queue_push_xmit(sk, skb);
}
#endif
@@ -964,6 +996,8 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
nf_bridge->neigh_header,
ETH_HLEN - ETH_ALEN);
skb->dev = nf_bridge->physindev;
+
+ nf_bridge->physoutdev = NULL;
br_handle_frame_finish(NULL, skb);
}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 4b5c236998ff..6b67ed3831de 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -586,7 +586,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
struct nlattr *afspec;
struct net_bridge_port *p;
struct nlattr *tb[IFLA_BRPORT_MAX + 1];
- int err = 0, ret_offload = 0;
+ int err = 0;
protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO);
afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
@@ -628,16 +628,6 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
afspec, RTM_SETLINK);
}
- if (p && !(flags & BRIDGE_FLAGS_SELF)) {
- /* set bridge attributes in hardware if supported
- */
- ret_offload = netdev_switch_port_bridge_setlink(dev, nlh,
- flags);
- if (ret_offload && ret_offload != -EOPNOTSUPP)
- br_warn(p->br, "error setting attrs on port %u(%s)\n",
- (unsigned int)p->port_no, p->dev->name);
- }
-
if (err == 0)
br_ifinfo_notify(RTM_NEWLINK, p);
out:
@@ -649,7 +639,7 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
{
struct nlattr *afspec;
struct net_bridge_port *p;
- int err = 0, ret_offload = 0;
+ int err = 0;
afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
if (!afspec)
@@ -668,16 +658,6 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
*/
br_ifinfo_notify(RTM_NEWLINK, p);
- if (p && !(flags & BRIDGE_FLAGS_SELF)) {
- /* del bridge attributes in hardware
- */
- ret_offload = netdev_switch_port_bridge_dellink(dev, nlh,
- flags);
- if (ret_offload && ret_offload != -EOPNOTSUPP)
- br_warn(p->br, "error deleting attrs on port %u (%s)\n",
- (unsigned int)p->port_no, p->dev->name);
- }
-
return err;
}
static int br_validate(struct nlattr *tb[], struct nlattr *data[])
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 3362c29400f1..1f36fa70639b 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -33,8 +33,8 @@
/* Control of forwarding link local multicast */
#define BR_GROUPFWD_DEFAULT 0
-/* Don't allow forwarding control protocols like STP and LLDP */
-#define BR_GROUPFWD_RESTRICTED 0x4007u
+/* Don't allow forwarding of control protocols like STP, MAC PAUSE and LACP */
+#define BR_GROUPFWD_RESTRICTED 0x0007u
/* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */
#define BR_GROUPFWD_8021AD 0xB801u
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index fb3ebe615513..45f1ff113af9 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -39,10 +39,14 @@ void br_log_state(const struct net_bridge_port *p)
void br_set_state(struct net_bridge_port *p, unsigned int state)
{
+ struct switchdev_attr attr = {
+ .id = SWITCHDEV_ATTR_PORT_STP_STATE,
+ .u.stp_state = state,
+ };
int err;
p->state = state;
- err = netdev_switch_port_stp_update(p->dev, state);
+ err = switchdev_port_attr_set(p->dev, &attr);
if (err && err != -EOPNOTSUPP)
br_warn(p->br, "error setting offload STP state on port %u(%s)\n",
(unsigned int) p->port_no, p->dev->name);
diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c
index 071d87214dde..0c40570069ba 100644
--- a/net/bridge/netfilter/ebt_stp.c
+++ b/net/bridge/netfilter/ebt_stp.c
@@ -164,8 +164,10 @@ static int ebt_stp_mt_check(const struct xt_mtchk_param *par)
!(info->bitmask & EBT_STP_MASK))
return -EINVAL;
/* Make sure the match only receives stp frames */
- if (!ether_addr_equal(e->destmac, bridge_ula) ||
- !ether_addr_equal(e->destmsk, msk) || !(e->bitmask & EBT_DESTMAC))
+ if (!par->nft_compat &&
+ (!ether_addr_equal(e->destmac, bridge_ula) ||
+ !ether_addr_equal(e->destmsk, msk) ||
+ !(e->bitmask & EBT_DESTMAC)))
return -EINVAL;
return 0;
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 91180a7fc943..5149d9e71114 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -139,7 +139,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb,
ethproto = h->h_proto;
if (e->bitmask & EBT_802_3) {
- if (FWINV2(ntohs(ethproto) >= ETH_P_802_3_MIN, EBT_IPROTO))
+ if (FWINV2(eth_proto_is_802_3(ethproto), EBT_IPROTO))
return 1;
} else if (!(e->bitmask & EBT_NOPROTO) &&
FWINV2(e->ethproto != ethproto, EBT_IPROTO))
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 112ad784838a..3cc71b9f5517 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -1055,7 +1055,7 @@ static int caif_create(struct net *net, struct socket *sock, int protocol,
* is really not used at all in the net/core or socket.c but the
* initialization makes sure that sock->state is not uninitialized.
*/
- sk = sk_alloc(net, PF_CAIF, GFP_KERNEL, &prot);
+ sk = sk_alloc(net, PF_CAIF, GFP_KERNEL, &prot, kern);
if (!sk)
return -ENOMEM;
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 32d710eaf1fc..d4d404bdfc9a 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -179,7 +179,7 @@ static int can_create(struct net *net, struct socket *sock, int protocol,
sock->ops = cp->ops;
- sk = sk_alloc(net, PF_CAN, GFP_KERNEL, cp->prot);
+ sk = sk_alloc(net, PF_CAN, GFP_KERNEL, cp->prot, kern);
if (!sk) {
err = -ENOMEM;
goto errout;
diff --git a/net/can/gw.c b/net/can/gw.c
index a6f448e18ea8..455168718c2e 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -110,6 +110,7 @@ struct cf_mod {
void (*xor)(struct can_frame *cf, struct cgw_csum_xor *xor);
void (*crc8)(struct can_frame *cf, struct cgw_csum_crc8 *crc8);
} csumfunc;
+ u32 uid;
};
@@ -548,6 +549,11 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type,
goto cancel;
}
+ if (gwj->mod.uid) {
+ if (nla_put_u32(skb, CGW_MOD_UID, gwj->mod.uid) < 0)
+ goto cancel;
+ }
+
if (gwj->mod.csumfunc.crc8) {
if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN,
&gwj->mod.csum.crc8) < 0)
@@ -619,6 +625,7 @@ static const struct nla_policy cgw_policy[CGW_MAX+1] = {
[CGW_DST_IF] = { .type = NLA_U32 },
[CGW_FILTER] = { .len = sizeof(struct can_filter) },
[CGW_LIM_HOPS] = { .type = NLA_U8 },
+ [CGW_MOD_UID] = { .type = NLA_U32 },
};
/* check for common and gwtype specific attributes */
@@ -761,6 +768,10 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod,
else
mod->csumfunc.xor = cgw_csum_xor_neg;
}
+
+ if (tb[CGW_MOD_UID]) {
+ nla_memcpy(&mod->uid, tb[CGW_MOD_UID], sizeof(u32));
+ }
}
if (gwtype == CGW_TYPE_CAN_CAN) {
@@ -802,6 +813,8 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct rtcanmsg *r;
struct cgw_job *gwj;
+ struct cf_mod mod;
+ struct can_can_gw ccgw;
u8 limhops = 0;
int err = 0;
@@ -819,6 +832,36 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh)
if (r->gwtype != CGW_TYPE_CAN_CAN)
return -EINVAL;
+ err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops);
+ if (err < 0)
+ return err;
+
+ if (mod.uid) {
+
+ ASSERT_RTNL();
+
+ /* check for updating an existing job with identical uid */
+ hlist_for_each_entry(gwj, &cgw_list, list) {
+
+ if (gwj->mod.uid != mod.uid)
+ continue;
+
+ /* interfaces & filters must be identical */
+ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw)))
+ return -EINVAL;
+
+ /* update modifications with disabled softirq & quit */
+ local_bh_disable();
+ memcpy(&gwj->mod, &mod, sizeof(mod));
+ local_bh_enable();
+ return 0;
+ }
+ }
+
+ /* ifindex == 0 is not allowed for job creation */
+ if (!ccgw.src_idx || !ccgw.dst_idx)
+ return -ENODEV;
+
gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL);
if (!gwj)
return -ENOMEM;
@@ -828,18 +871,14 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh)
gwj->deleted_frames = 0;
gwj->flags = r->flags;
gwj->gwtype = r->gwtype;
+ gwj->limit_hops = limhops;
- err = cgw_parse_attr(nlh, &gwj->mod, CGW_TYPE_CAN_CAN, &gwj->ccgw,
- &limhops);
- if (err < 0)
- goto out;
+ /* insert already parsed information */
+ memcpy(&gwj->mod, &mod, sizeof(mod));
+ memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw));
err = -ENODEV;
- /* ifindex == 0 is not allowed for job creation */
- if (!gwj->ccgw.src_idx || !gwj->ccgw.dst_idx)
- goto out;
-
gwj->src.dev = __dev_get_by_index(&init_net, gwj->ccgw.src_idx);
if (!gwj->src.dev)
@@ -856,8 +895,6 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh)
if (gwj->dst.dev->type != ARPHRD_CAN)
goto out;
- gwj->limit_hops = limhops;
-
ASSERT_RTNL();
err = cgw_register_filter(gwj);
@@ -931,8 +968,15 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh)
if (gwj->limit_hops != limhops)
continue;
- if (memcmp(&gwj->mod, &mod, sizeof(mod)))
- continue;
+ /* we have a match when uid is enabled and identical */
+ if (gwj->mod.uid || mod.uid) {
+ if (gwj->mod.uid != mod.uid)
+ continue;
+ } else {
+ /* no uid => check for identical modifications */
+ if (memcmp(&gwj->mod, &mod, sizeof(mod)))
+ continue;
+ }
/* if (r->gwtype == CGW_TYPE_CAN_CAN) - is made sure here */
if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw)))
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 967080a9f043..073262fea6dd 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -480,8 +480,8 @@ static int ceph_tcp_connect(struct ceph_connection *con)
int ret;
BUG_ON(con->sock);
- ret = sock_create_kern(con->peer_addr.in_addr.ss_family, SOCK_STREAM,
- IPPROTO_TCP, &sock);
+ ret = sock_create_kern(&init_net, con->peer_addr.in_addr.ss_family,
+ SOCK_STREAM, IPPROTO_TCP, &sock);
if (ret)
return ret;
sock->sk->sk_allocation = GFP_NOFS;
diff --git a/net/core/dev.c b/net/core/dev.c
index aa82f9ab6a36..6778a9999d52 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -135,6 +135,7 @@
#include <linux/if_macvlan.h>
#include <linux/errqueue.h>
#include <linux/hrtimer.h>
+#include <linux/netfilter_ingress.h>
#include "net-sysfs.h"
@@ -468,10 +469,14 @@ EXPORT_SYMBOL(dev_remove_pack);
*/
void dev_add_offload(struct packet_offload *po)
{
- struct list_head *head = &offload_base;
+ struct packet_offload *elem;
spin_lock(&offload_lock);
- list_add_rcu(&po->list, head);
+ list_for_each_entry(elem, &offload_base, list) {
+ if (po->priority < elem->priority)
+ break;
+ }
+ list_add_rcu(&po->list, elem->list.prev);
spin_unlock(&offload_lock);
}
EXPORT_SYMBOL(dev_add_offload);
@@ -1630,7 +1635,7 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
}
EXPORT_SYMBOL(call_netdevice_notifiers);
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_INGRESS
static struct static_key ingress_needed __read_mostly;
void net_inc_ingress_queue(void)
@@ -2343,6 +2348,34 @@ void netif_device_attach(struct net_device *dev)
}
EXPORT_SYMBOL(netif_device_attach);
+/*
+ * Returns a Tx hash based on the given packet descriptor a Tx queues' number
+ * to be used as a distribution range.
+ */
+u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
+ unsigned int num_tx_queues)
+{
+ u32 hash;
+ u16 qoffset = 0;
+ u16 qcount = num_tx_queues;
+
+ if (skb_rx_queue_recorded(skb)) {
+ hash = skb_get_rx_queue(skb);
+ while (unlikely(hash >= num_tx_queues))
+ hash -= num_tx_queues;
+ return hash;
+ }
+
+ if (dev->num_tc) {
+ u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+ qoffset = dev->tc_to_txq[tc].offset;
+ qcount = dev->tc_to_txq[tc].count;
+ }
+
+ return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
+}
+EXPORT_SYMBOL(__skb_tx_hash);
+
static void skb_warn_bad_offload(const struct sk_buff *skb)
{
static const netdev_features_t null_features = 0;
@@ -2901,6 +2934,84 @@ int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(dev_loopback_xmit);
+static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+{
+#ifdef CONFIG_XPS
+ struct xps_dev_maps *dev_maps;
+ struct xps_map *map;
+ int queue_index = -1;
+
+ rcu_read_lock();
+ dev_maps = rcu_dereference(dev->xps_maps);
+ if (dev_maps) {
+ map = rcu_dereference(
+ dev_maps->cpu_map[skb->sender_cpu - 1]);
+ if (map) {
+ if (map->len == 1)
+ queue_index = map->queues[0];
+ else
+ queue_index = map->queues[reciprocal_scale(skb_get_hash(skb),
+ map->len)];
+ if (unlikely(queue_index >= dev->real_num_tx_queues))
+ queue_index = -1;
+ }
+ }
+ rcu_read_unlock();
+
+ return queue_index;
+#else
+ return -1;
+#endif
+}
+
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+{
+ struct sock *sk = skb->sk;
+ int queue_index = sk_tx_queue_get(sk);
+
+ if (queue_index < 0 || skb->ooo_okay ||
+ queue_index >= dev->real_num_tx_queues) {
+ int new_index = get_xps_queue(dev, skb);
+ if (new_index < 0)
+ new_index = skb_tx_hash(dev, skb);
+
+ if (queue_index != new_index && sk &&
+ rcu_access_pointer(sk->sk_dst_cache))
+ sk_tx_queue_set(sk, new_index);
+
+ queue_index = new_index;
+ }
+
+ return queue_index;
+}
+
+struct netdev_queue *netdev_pick_tx(struct net_device *dev,
+ struct sk_buff *skb,
+ void *accel_priv)
+{
+ int queue_index = 0;
+
+#ifdef CONFIG_XPS
+ if (skb->sender_cpu == 0)
+ skb->sender_cpu = raw_smp_processor_id() + 1;
+#endif
+
+ if (dev->real_num_tx_queues != 1) {
+ const struct net_device_ops *ops = dev->netdev_ops;
+ if (ops->ndo_select_queue)
+ queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+ __netdev_pick_tx);
+ else
+ queue_index = __netdev_pick_tx(dev, skb);
+
+ if (!accel_priv)
+ queue_index = netdev_cap_txqueue(dev, queue_index);
+ }
+
+ skb_set_queue_mapping(skb, queue_index);
+ return netdev_get_tx_queue(dev, queue_index);
+}
+
/**
* __dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
@@ -3513,66 +3624,47 @@ int (*br_fdb_test_addr_hook)(struct net_device *dev,
EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
#endif
-#ifdef CONFIG_NET_CLS_ACT
-/* TODO: Maybe we should just force sch_ingress to be compiled in
- * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
- * a compare and 2 stores extra right now if we dont have it on
- * but have CONFIG_NET_CLS_ACT
- * NOTE: This doesn't stop any functionality; if you dont have
- * the ingress scheduler, you just can't add policies on ingress.
- *
- */
-static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
-{
- struct net_device *dev = skb->dev;
- u32 ttl = G_TC_RTTL(skb->tc_verd);
- int result = TC_ACT_OK;
- struct Qdisc *q;
-
- if (unlikely(MAX_RED_LOOP < ttl++)) {
- net_warn_ratelimited("Redir loop detected Dropping packet (%d->%d)\n",
- skb->skb_iif, dev->ifindex);
- return TC_ACT_SHOT;
- }
-
- skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
- skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
-
- q = rcu_dereference(rxq->qdisc);
- if (q != &noop_qdisc) {
- spin_lock(qdisc_lock(q));
- if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
- result = qdisc_enqueue_root(skb, q);
- spin_unlock(qdisc_lock(q));
- }
-
- return result;
-}
-
static inline struct sk_buff *handle_ing(struct sk_buff *skb,
struct packet_type **pt_prev,
int *ret, struct net_device *orig_dev)
{
- struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);
+#ifdef CONFIG_NET_CLS_ACT
+ struct tcf_proto *cl = rcu_dereference_bh(skb->dev->ingress_cl_list);
+ struct tcf_result cl_res;
- if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc)
+ /* If there's at least one ingress present somewhere (so
+ * we get here via enabled static key), remaining devices
+ * that are not configured with an ingress qdisc will bail
+ * out here.
+ */
+ if (!cl)
return skb;
-
if (*pt_prev) {
*ret = deliver_skb(skb, *pt_prev, orig_dev);
*pt_prev = NULL;
}
- switch (ing_filter(skb, rxq)) {
+ qdisc_skb_cb(skb)->pkt_len = skb->len;
+ skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
+ qdisc_bstats_update_cpu(cl->q, skb);
+
+ switch (tc_classify(skb, cl, &cl_res)) {
+ case TC_ACT_OK:
+ case TC_ACT_RECLASSIFY:
+ skb->tc_index = TC_H_MIN(cl_res.classid);
+ break;
case TC_ACT_SHOT:
+ qdisc_qstats_drop_cpu(cl->q);
case TC_ACT_STOLEN:
+ case TC_ACT_QUEUED:
kfree_skb(skb);
return NULL;
+ default:
+ break;
}
-
+#endif /* CONFIG_NET_CLS_ACT */
return skb;
}
-#endif
/**
* netdev_rx_handler_register - register receive handler
@@ -3645,6 +3737,22 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
}
}
+static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
+ int *ret, struct net_device *orig_dev)
+{
+#ifdef CONFIG_NETFILTER_INGRESS
+ if (nf_hook_ingress_active(skb)) {
+ if (*pt_prev) {
+ *ret = deliver_skb(skb, *pt_prev, orig_dev);
+ *pt_prev = NULL;
+ }
+
+ return nf_hook_ingress(skb);
+ }
+#endif /* CONFIG_NETFILTER_INGRESS */
+ return 0;
+}
+
static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
{
struct packet_type *ptype, *pt_prev;
@@ -3704,13 +3812,17 @@ another_round:
}
skip_taps:
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_INGRESS
if (static_key_false(&ingress_needed)) {
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
goto unlock;
- }
+ if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0)
+ goto unlock;
+ }
+#endif
+#ifdef CONFIG_NET_CLS_ACT
skb->tc_verd = 0;
ncls:
#endif
@@ -6313,6 +6425,17 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
return 0;
}
+void netif_tx_stop_all_queues(struct net_device *dev)
+{
+ unsigned int i;
+
+ for (i = 0; i < dev->num_tx_queues; i++) {
+ struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
+ netif_tx_stop_queue(txq);
+ }
+}
+EXPORT_SYMBOL(netif_tx_stop_all_queues);
+
/**
* register_netdevice - register a network device
* @dev: device to register
@@ -6862,6 +6985,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev->group = INIT_NETDEV_GROUP;
if (!dev->ethtool_ops)
dev->ethtool_ops = &default_ethtool_ops;
+
+ nf_hook_ingress_init(dev);
+
return dev;
free_all:
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 1d00b8922902..b495ab1797fa 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -98,7 +98,6 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_RXALL_BIT] = "rx-all",
[NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload",
[NETIF_F_BUSY_POLL_BIT] = "busy-poll",
- [NETIF_F_HW_SWITCH_OFFLOAD_BIT] = "hw-switch-offload",
};
static const char
@@ -107,6 +106,13 @@ rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = {
[ETH_RSS_HASH_XOR_BIT] = "xor",
};
+static const char
+tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN] = {
+ [ETHTOOL_ID_UNSPEC] = "Unspec",
+ [ETHTOOL_RX_COPYBREAK] = "rx-copybreak",
+ [ETHTOOL_TX_COPYBREAK] = "tx-copybreak",
+};
+
static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
{
struct ethtool_gfeatures cmd = {
@@ -195,6 +201,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset)
if (sset == ETH_SS_RSS_HASH_FUNCS)
return ARRAY_SIZE(rss_hash_func_strings);
+ if (sset == ETH_SS_TUNABLES)
+ return ARRAY_SIZE(tunable_strings);
+
if (ops->get_sset_count && ops->get_strings)
return ops->get_sset_count(dev, sset);
else
@@ -212,6 +221,8 @@ static void __ethtool_get_strings(struct net_device *dev,
else if (stringset == ETH_SS_RSS_HASH_FUNCS)
memcpy(data, rss_hash_func_strings,
sizeof(rss_hash_func_strings));
+ else if (stringset == ETH_SS_TUNABLES)
+ memcpy(data, tunable_strings, sizeof(tunable_strings));
else
/* ops->get_strings is valid because checked earlier */
ops->get_strings(dev, stringset, data);
diff --git a/net/core/filter.c b/net/core/filter.c
index bf831a85c315..d271c06bf01f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -36,6 +36,7 @@
#include <net/netlink.h>
#include <linux/skbuff.h>
#include <net/sock.h>
+#include <net/flow_dissector.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <asm/uaccess.h>
@@ -45,6 +46,7 @@
#include <linux/seccomp.h>
#include <linux/if_vlan.h>
#include <linux/bpf.h>
+#include <net/sch_generic.h>
/**
* sk_filter - run a packet through a socket filter
@@ -355,8 +357,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
* for socket filters: ctx == 'struct sk_buff *', for seccomp:
* ctx == 'struct seccomp_data *'.
*/
-int bpf_convert_filter(struct sock_filter *prog, int len,
- struct bpf_insn *new_prog, int *new_len)
+static int bpf_convert_filter(struct sock_filter *prog, int len,
+ struct bpf_insn *new_prog, int *new_len)
{
int new_flen = 0, pass = 0, target, i;
struct bpf_insn *new_insn;
@@ -371,7 +373,8 @@ int bpf_convert_filter(struct sock_filter *prog, int len,
return -EINVAL;
if (new_prog) {
- addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL);
+ addrs = kcalloc(len, sizeof(*addrs),
+ GFP_KERNEL | __GFP_NOWARN);
if (!addrs)
return -ENOMEM;
}
@@ -751,7 +754,8 @@ static bool chk_code_allowed(u16 code_to_probe)
*
* Returns 0 if the rule set is legal or -EINVAL if not.
*/
-int bpf_check_classic(const struct sock_filter *filter, unsigned int flen)
+static int bpf_check_classic(const struct sock_filter *filter,
+ unsigned int flen)
{
bool anc_found;
int pc;
@@ -825,7 +829,6 @@ int bpf_check_classic(const struct sock_filter *filter, unsigned int flen)
return -EINVAL;
}
-EXPORT_SYMBOL(bpf_check_classic);
static int bpf_prog_store_orig_filter(struct bpf_prog *fp,
const struct sock_fprog *fprog)
@@ -839,7 +842,9 @@ static int bpf_prog_store_orig_filter(struct bpf_prog *fp,
fkprog = fp->orig_prog;
fkprog->len = fprog->len;
- fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL);
+
+ fkprog->filter = kmemdup(fp->insns, fsize,
+ GFP_KERNEL | __GFP_NOWARN);
if (!fkprog->filter) {
kfree(fp->orig_prog);
return -ENOMEM;
@@ -941,7 +946,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
* pass. At this time, the user BPF is stored in fp->insns.
*/
old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter),
- GFP_KERNEL);
+ GFP_KERNEL | __GFP_NOWARN);
if (!old_prog) {
err = -ENOMEM;
goto out_err;
@@ -988,7 +993,8 @@ out_err:
return ERR_PTR(err);
}
-static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp)
+static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp,
+ bpf_aux_classic_check_t trans)
{
int err;
@@ -1001,6 +1007,17 @@ static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp)
return ERR_PTR(err);
}
+ /* There might be additional checks and transformations
+ * needed on classic filters, f.e. in case of seccomp.
+ */
+ if (trans) {
+ err = trans(fp->insns, fp->len);
+ if (err) {
+ __bpf_prog_release(fp);
+ return ERR_PTR(err);
+ }
+ }
+
/* Probe if we can JIT compile the filter and if so, do
* the compilation of the filter.
*/
@@ -1050,7 +1067,7 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
- fp = bpf_prepare_filter(fp);
+ fp = bpf_prepare_filter(fp, NULL);
if (IS_ERR(fp))
return PTR_ERR(fp);
@@ -1059,6 +1076,53 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
}
EXPORT_SYMBOL_GPL(bpf_prog_create);
+/**
+ * bpf_prog_create_from_user - create an unattached filter from user buffer
+ * @pfp: the unattached filter that is created
+ * @fprog: the filter program
+ * @trans: post-classic verifier transformation handler
+ *
+ * This function effectively does the same as bpf_prog_create(), only
+ * that it builds up its insns buffer from user space provided buffer.
+ * It also allows for passing a bpf_aux_classic_check_t handler.
+ */
+int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
+ bpf_aux_classic_check_t trans)
+{
+ unsigned int fsize = bpf_classic_proglen(fprog);
+ struct bpf_prog *fp;
+
+ /* Make sure new filter is there and in the right amounts. */
+ if (fprog->filter == NULL)
+ return -EINVAL;
+
+ fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
+ if (!fp)
+ return -ENOMEM;
+
+ if (copy_from_user(fp->insns, fprog->filter, fsize)) {
+ __bpf_prog_free(fp);
+ return -EFAULT;
+ }
+
+ fp->len = fprog->len;
+ /* Since unattached filters are not copied back to user
+ * space through sk_get_filter(), we do not need to hold
+ * a copy here, and can spare us the work.
+ */
+ fp->orig_prog = NULL;
+
+ /* bpf_prepare_filter() already takes care of freeing
+ * memory in case something goes wrong.
+ */
+ fp = bpf_prepare_filter(fp, trans);
+ if (IS_ERR(fp))
+ return PTR_ERR(fp);
+
+ *pfp = fp;
+ return 0;
+}
+
void bpf_prog_destroy(struct bpf_prog *fp)
{
__bpf_prog_release(fp);
@@ -1135,7 +1199,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
- prog = bpf_prepare_filter(prog);
+ prog = bpf_prepare_filter(prog, NULL);
if (IS_ERR(prog))
return PTR_ERR(prog);
@@ -1175,21 +1239,6 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
return 0;
}
-/**
- * bpf_skb_clone_not_writable - is the header of a clone not writable
- * @skb: buffer to check
- * @len: length up to which to write, can be negative
- *
- * Returns true if modifying the header part of the cloned buffer
- * does require the data to be copied. I.e. this version works with
- * negative lengths needed for eBPF case!
- */
-static bool bpf_skb_clone_unwritable(const struct sk_buff *skb, int len)
-{
- return skb_header_cloned(skb) ||
- (int) skb_headroom(skb) + len > skb->hdr_len;
-}
-
#define BPF_RECOMPUTE_CSUM(flags) ((flags) & 1)
static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
@@ -1212,9 +1261,8 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
if (unlikely((u32) offset > 0xffff || len > sizeof(buf)))
return -EFAULT;
- offset -= skb->data - skb_mac_header(skb);
if (unlikely(skb_cloned(skb) &&
- bpf_skb_clone_unwritable(skb, offset + len)))
+ !skb_clone_writable(skb, offset + len)))
return -EFAULT;
ptr = skb_header_pointer(skb, offset, len, buf);
@@ -1258,9 +1306,8 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
if (unlikely((u32) offset > 0xffff))
return -EFAULT;
- offset -= skb->data - skb_mac_header(skb);
if (unlikely(skb_cloned(skb) &&
- bpf_skb_clone_unwritable(skb, offset + sizeof(sum))))
+ !skb_clone_writable(skb, offset + sizeof(sum))))
return -EFAULT;
ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
@@ -1306,9 +1353,8 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
if (unlikely((u32) offset > 0xffff))
return -EFAULT;
- offset -= skb->data - skb_mac_header(skb);
if (unlikely(skb_cloned(skb) &&
- bpf_skb_clone_unwritable(skb, offset + sizeof(sum))))
+ !skb_clone_writable(skb, offset + sizeof(sum))))
return -EFAULT;
ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
@@ -1344,6 +1390,40 @@ const struct bpf_func_proto bpf_l4_csum_replace_proto = {
.arg5_type = ARG_ANYTHING,
};
+#define BPF_IS_REDIRECT_INGRESS(flags) ((flags) & 1)
+
+static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2;
+ struct net_device *dev;
+
+ dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex);
+ if (unlikely(!dev))
+ return -EINVAL;
+
+ if (unlikely(!(dev->flags & IFF_UP)))
+ return -EINVAL;
+
+ skb2 = skb_clone(skb, GFP_ATOMIC);
+ if (unlikely(!skb2))
+ return -ENOMEM;
+
+ if (BPF_IS_REDIRECT_INGRESS(flags))
+ return dev_forward_skb(dev, skb2);
+
+ skb2->dev = dev;
+ return dev_queue_xmit(skb2);
+}
+
+const struct bpf_func_proto bpf_clone_redirect_proto = {
+ .func = bpf_clone_redirect,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
+
static const struct bpf_func_proto *
sk_filter_func_proto(enum bpf_func_id func_id)
{
@@ -1358,6 +1438,10 @@ sk_filter_func_proto(enum bpf_func_id func_id)
return &bpf_get_prandom_u32_proto;
case BPF_FUNC_get_smp_processor_id:
return &bpf_get_smp_processor_id_proto;
+ case BPF_FUNC_tail_call:
+ return &bpf_tail_call_proto;
+ case BPF_FUNC_ktime_get_ns:
+ return &bpf_ktime_get_ns_proto;
default:
return NULL;
}
@@ -1373,18 +1457,15 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
return &bpf_l3_csum_replace_proto;
case BPF_FUNC_l4_csum_replace:
return &bpf_l4_csum_replace_proto;
+ case BPF_FUNC_clone_redirect:
+ return &bpf_clone_redirect_proto;
default:
return sk_filter_func_proto(func_id);
}
}
-static bool sk_filter_is_valid_access(int off, int size,
- enum bpf_access_type type)
+static bool __is_valid_access(int off, int size, enum bpf_access_type type)
{
- /* only read is allowed */
- if (type != BPF_READ)
- return false;
-
/* check bounds */
if (off < 0 || off >= sizeof(struct __sk_buff))
return false;
@@ -1400,8 +1481,42 @@ static bool sk_filter_is_valid_access(int off, int size,
return true;
}
-static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off,
- struct bpf_insn *insn_buf)
+static bool sk_filter_is_valid_access(int off, int size,
+ enum bpf_access_type type)
+{
+ if (type == BPF_WRITE) {
+ switch (off) {
+ case offsetof(struct __sk_buff, cb[0]) ...
+ offsetof(struct __sk_buff, cb[4]):
+ break;
+ default:
+ return false;
+ }
+ }
+
+ return __is_valid_access(off, size, type);
+}
+
+static bool tc_cls_act_is_valid_access(int off, int size,
+ enum bpf_access_type type)
+{
+ if (type == BPF_WRITE) {
+ switch (off) {
+ case offsetof(struct __sk_buff, mark):
+ case offsetof(struct __sk_buff, tc_index):
+ case offsetof(struct __sk_buff, cb[0]) ...
+ offsetof(struct __sk_buff, cb[4]):
+ break;
+ default:
+ return false;
+ }
+ }
+ return __is_valid_access(off, size, type);
+}
+
+static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
+ int src_reg, int ctx_off,
+ struct bpf_insn *insn_buf)
{
struct bpf_insn *insn = insn_buf;
@@ -1434,8 +1549,34 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off,
offsetof(struct sk_buff, priority));
break;
+ case offsetof(struct __sk_buff, ingress_ifindex):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, skb_iif) != 4);
+
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, skb_iif));
+ break;
+
+ case offsetof(struct __sk_buff, ifindex):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
+
+ *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)),
+ dst_reg, src_reg,
+ offsetof(struct sk_buff, dev));
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1);
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, dst_reg,
+ offsetof(struct net_device, ifindex));
+ break;
+
case offsetof(struct __sk_buff, mark):
- return convert_skb_access(SKF_AD_MARK, dst_reg, src_reg, insn);
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+
+ if (type == BPF_WRITE)
+ *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, mark));
+ else
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, mark));
+ break;
case offsetof(struct __sk_buff, pkt_type):
return convert_skb_access(SKF_AD_PKTTYPE, dst_reg, src_reg, insn);
@@ -1450,6 +1591,38 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off,
case offsetof(struct __sk_buff, vlan_tci):
return convert_skb_access(SKF_AD_VLAN_TAG,
dst_reg, src_reg, insn);
+
+ case offsetof(struct __sk_buff, cb[0]) ...
+ offsetof(struct __sk_buff, cb[4]):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20);
+
+ ctx_off -= offsetof(struct __sk_buff, cb[0]);
+ ctx_off += offsetof(struct sk_buff, cb);
+ ctx_off += offsetof(struct qdisc_skb_cb, data);
+ if (type == BPF_WRITE)
+ *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, ctx_off);
+ else
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, ctx_off);
+ break;
+
+ case offsetof(struct __sk_buff, tc_index):
+#ifdef CONFIG_NET_SCHED
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2);
+
+ if (type == BPF_WRITE)
+ *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg,
+ offsetof(struct sk_buff, tc_index));
+ else
+ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+ offsetof(struct sk_buff, tc_index));
+ break;
+#else
+ if (type == BPF_WRITE)
+ *insn++ = BPF_MOV64_REG(dst_reg, dst_reg);
+ else
+ *insn++ = BPF_MOV64_IMM(dst_reg, 0);
+ break;
+#endif
}
return insn - insn_buf;
@@ -1458,13 +1631,13 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off,
static const struct bpf_verifier_ops sk_filter_ops = {
.get_func_proto = sk_filter_func_proto,
.is_valid_access = sk_filter_is_valid_access,
- .convert_ctx_access = sk_filter_convert_ctx_access,
+ .convert_ctx_access = bpf_net_convert_ctx_access,
};
static const struct bpf_verifier_ops tc_cls_act_ops = {
.get_func_proto = tc_cls_act_func_proto,
- .is_valid_access = sk_filter_is_valid_access,
- .convert_ctx_access = sk_filter_convert_ctx_access,
+ .is_valid_access = tc_cls_act_is_valid_access,
+ .convert_ctx_access = bpf_net_convert_ctx_access,
};
static struct bpf_prog_type_list sk_filter_type __read_mostly = {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2c35c02a931e..476e5dda59e1 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1,3 +1,4 @@
+#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/export.h>
#include <linux/ip.h>
@@ -12,19 +13,60 @@
#include <linux/if_tunnel.h>
#include <linux/if_pppox.h>
#include <linux/ppp_defs.h>
-#include <net/flow_keys.h>
+#include <linux/stddef.h>
+#include <linux/if_ether.h>
+#include <linux/mpls.h>
+#include <net/flow_dissector.h>
#include <scsi/fc/fc_fcoe.h>
-/* copy saddr & daddr, possibly using 64bit load/store
- * Equivalent to : flow->src = iph->saddr;
- * flow->dst = iph->daddr;
- */
-static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph)
+static bool skb_flow_dissector_uses_key(struct flow_dissector *flow_dissector,
+ enum flow_dissector_key_id key_id)
+{
+ return flow_dissector->used_keys & (1 << key_id);
+}
+
+static void skb_flow_dissector_set_key(struct flow_dissector *flow_dissector,
+ enum flow_dissector_key_id key_id)
+{
+ flow_dissector->used_keys |= (1 << key_id);
+}
+
+static void *skb_flow_dissector_target(struct flow_dissector *flow_dissector,
+ enum flow_dissector_key_id key_id,
+ void *target_container)
+{
+ return ((char *) target_container) + flow_dissector->offset[key_id];
+}
+
+void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
+ const struct flow_dissector_key *key,
+ unsigned int key_count)
{
- BUILD_BUG_ON(offsetof(typeof(*flow), dst) !=
- offsetof(typeof(*flow), src) + sizeof(flow->src));
- memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
+ unsigned int i;
+
+ memset(flow_dissector, 0, sizeof(*flow_dissector));
+
+ for (i = 0; i < key_count; i++, key++) {
+ /* User should make sure that every key target offset is withing
+ * boundaries of unsigned short.
+ */
+ BUG_ON(key->offset > USHRT_MAX);
+ BUG_ON(skb_flow_dissector_uses_key(flow_dissector,
+ key->key_id));
+
+ skb_flow_dissector_set_key(flow_dissector, key->key_id);
+ flow_dissector->offset[key->key_id] = key->offset;
+ }
+
+ /* Ensure that the dissector always includes control and basic key.
+ * That way we are able to avoid handling lack of these in fast path.
+ */
+ BUG_ON(!skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_CONTROL));
+ BUG_ON(!skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_BASIC));
}
+EXPORT_SYMBOL(skb_flow_dissector_init);
/**
* __skb_flow_get_ports - extract the upper layer ports and return them
@@ -63,17 +105,30 @@ EXPORT_SYMBOL(__skb_flow_get_ports);
/**
* __skb_flow_dissect - extract the flow_keys struct and return it
* @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
+ * @flow_dissector: list of keys to dissect
+ * @target_container: target structure to put dissected values into
* @data: raw buffer pointer to the packet, if NULL use skb->data
* @proto: protocol for which to get the flow, if @data is NULL use skb->protocol
* @nhoff: network header offset, if @data is NULL use skb_network_offset(skb)
* @hlen: packet header length, if @data is NULL use skb_headlen(skb)
*
- * The function will try to retrieve the struct flow_keys from either the skbuff
- * or a raw buffer specified by the rest parameters
+ * The function will try to retrieve individual keys into target specified
+ * by flow_dissector from either the skbuff or a raw buffer specified by the
+ * rest parameters.
+ *
+ * Caller must take care of zeroing target container memory.
*/
-bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
+bool __skb_flow_dissect(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container,
void *data, __be16 proto, int nhoff, int hlen)
{
+ struct flow_dissector_key_control *key_control;
+ struct flow_dissector_key_basic *key_basic;
+ struct flow_dissector_key_addrs *key_addrs;
+ struct flow_dissector_key_ports *key_ports;
+ struct flow_dissector_key_tags *key_tags;
+ struct flow_dissector_key_keyid *key_keyid;
u8 ip_proto;
if (!data) {
@@ -83,7 +138,30 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
hlen = skb_headlen(skb);
}
- memset(flow, 0, sizeof(*flow));
+ /* It is ensured by skb_flow_dissector_init() that control key will
+ * be always present.
+ */
+ key_control = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_CONTROL,
+ target_container);
+
+ /* It is ensured by skb_flow_dissector_init() that basic key will
+ * be always present.
+ */
+ key_basic = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ target_container);
+
+ if (skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+ struct ethhdr *eth = eth_hdr(skb);
+ struct flow_dissector_key_eth_addrs *key_eth_addrs;
+
+ key_eth_addrs = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ETH_ADDRS,
+ target_container);
+ memcpy(key_eth_addrs, &eth->h_dest, sizeof(*key_eth_addrs));
+ }
again:
switch (proto) {
@@ -100,14 +178,15 @@ ip:
if (ip_is_fragment(iph))
ip_proto = 0;
- /* skip the address processing if skb is NULL. The assumption
- * here is that if there is no skb we are not looking for flow
- * info but lengths and protocols.
- */
- if (!skb)
+ if (!skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_IPV4_ADDRS))
break;
- iph_to_flow_copy_addrs(flow, iph);
+ key_addrs = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container);
+ memcpy(&key_addrs->v4addrs, &iph->saddr,
+ sizeof(key_addrs->v4addrs));
+ key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
break;
}
case htons(ETH_P_IPV6): {
@@ -123,25 +202,27 @@ ipv6:
ip_proto = iph->nexthdr;
nhoff += sizeof(struct ipv6hdr);
- /* see comment above in IPv4 section */
- if (!skb)
- break;
+ if (skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+ struct flow_dissector_key_ipv6_addrs *key_ipv6_addrs;
+
+ key_ipv6_addrs = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+ target_container);
- flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr);
- flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
+ memcpy(key_ipv6_addrs, &iph->saddr, sizeof(*key_ipv6_addrs));
+ key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+ }
flow_label = ip6_flowlabel(iph);
if (flow_label) {
- /* Awesome, IPv6 packet has a flow label so we can
- * use that to represent the ports without any
- * further dissection.
- */
- flow->n_proto = proto;
- flow->ip_proto = ip_proto;
- flow->ports = flow_label;
- flow->thoff = (u16)nhoff;
-
- return true;
+ if (skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
+ key_tags = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_FLOW_LABEL,
+ target_container);
+ key_tags->flow_label = ntohl(flow_label);
+ }
}
break;
@@ -155,6 +236,15 @@ ipv6:
if (!vlan)
return false;
+ if (skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_VLANID)) {
+ key_tags = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_VLANID,
+ target_container);
+
+ key_tags->vlan_id = skb_vlan_tag_get_id(skb);
+ }
+
proto = vlan->h_vlan_encapsulated_proto;
nhoff += sizeof(*vlan);
goto again;
@@ -186,19 +276,58 @@ ipv6:
hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
if (!hdr)
return false;
- flow->src = hdr->srcnode;
- flow->dst = 0;
- flow->n_proto = proto;
- flow->thoff = (u16)nhoff;
+ key_basic->n_proto = proto;
+ key_control->thoff = (u16)nhoff;
+
+ if (skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_TIPC_ADDRS)) {
+ key_addrs = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_TIPC_ADDRS,
+ target_container);
+ key_addrs->tipcaddrs.srcnode = hdr->srcnode;
+ key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC_ADDRS;
+ }
+ return true;
+ }
+
+ case htons(ETH_P_MPLS_UC):
+ case htons(ETH_P_MPLS_MC): {
+ struct mpls_label *hdr, _hdr[2];
+mpls:
+ hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
+ hlen, &_hdr);
+ if (!hdr)
+ return false;
+
+ if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >>
+ MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) {
+ if (skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
+ key_keyid = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
+ target_container);
+ key_keyid->keyid = hdr[1].entry &
+ htonl(MPLS_LS_LABEL_MASK);
+ }
+
+ key_basic->n_proto = proto;
+ key_basic->ip_proto = ip_proto;
+ key_control->thoff = (u16)nhoff;
+
+ return true;
+ }
+
return true;
}
+
case htons(ETH_P_FCOE):
- flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
+ key_control->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
/* fall through */
default:
return false;
}
+ip_proto_again:
switch (ip_proto) {
case IPPROTO_GRE: {
struct gre_hdr {
@@ -213,30 +342,65 @@ ipv6:
* Only look inside GRE if version zero and no
* routing
*/
- if (!(hdr->flags & (GRE_VERSION|GRE_ROUTING))) {
- proto = hdr->proto;
+ if (hdr->flags & (GRE_VERSION | GRE_ROUTING))
+ break;
+
+ proto = hdr->proto;
+ nhoff += 4;
+ if (hdr->flags & GRE_CSUM)
nhoff += 4;
- if (hdr->flags & GRE_CSUM)
- nhoff += 4;
- if (hdr->flags & GRE_KEY)
- nhoff += 4;
- if (hdr->flags & GRE_SEQ)
- nhoff += 4;
- if (proto == htons(ETH_P_TEB)) {
- const struct ethhdr *eth;
- struct ethhdr _eth;
-
- eth = __skb_header_pointer(skb, nhoff,
- sizeof(_eth),
- data, hlen, &_eth);
- if (!eth)
- return false;
- proto = eth->h_proto;
- nhoff += sizeof(*eth);
+ if (hdr->flags & GRE_KEY) {
+ const __be32 *keyid;
+ __be32 _keyid;
+
+ keyid = __skb_header_pointer(skb, nhoff, sizeof(_keyid),
+ data, hlen, &_keyid);
+
+ if (!keyid)
+ return false;
+
+ if (skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_GRE_KEYID)) {
+ key_keyid = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_GRE_KEYID,
+ target_container);
+ key_keyid->keyid = *keyid;
}
- goto again;
+ nhoff += 4;
}
- break;
+ if (hdr->flags & GRE_SEQ)
+ nhoff += 4;
+ if (proto == htons(ETH_P_TEB)) {
+ const struct ethhdr *eth;
+ struct ethhdr _eth;
+
+ eth = __skb_header_pointer(skb, nhoff,
+ sizeof(_eth),
+ data, hlen, &_eth);
+ if (!eth)
+ return false;
+ proto = eth->h_proto;
+ nhoff += sizeof(*eth);
+ }
+ goto again;
+ }
+ case NEXTHDR_HOP:
+ case NEXTHDR_ROUTING:
+ case NEXTHDR_DEST: {
+ u8 _opthdr[2], *opthdr;
+
+ if (proto != htons(ETH_P_IPV6))
+ break;
+
+ opthdr = __skb_header_pointer(skb, nhoff, sizeof(_opthdr),
+ data, hlen, &_opthdr);
+ if (!opthdr)
+ return false;
+
+ ip_proto = opthdr[0];
+ nhoff += (opthdr[1] + 1) << 3;
+
+ goto ip_proto_again;
}
case IPPROTO_IPIP:
proto = htons(ETH_P_IP);
@@ -244,18 +408,25 @@ ipv6:
case IPPROTO_IPV6:
proto = htons(ETH_P_IPV6);
goto ipv6;
+ case IPPROTO_MPLS:
+ proto = htons(ETH_P_MPLS_UC);
+ goto mpls;
default:
break;
}
- flow->n_proto = proto;
- flow->ip_proto = ip_proto;
- flow->thoff = (u16) nhoff;
-
- /* unless skb is set we don't need to record port info */
- if (skb)
- flow->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
- data, hlen);
+ key_basic->n_proto = proto;
+ key_basic->ip_proto = ip_proto;
+ key_control->thoff = (u16)nhoff;
+
+ if (skb_flow_dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_PORTS)) {
+ key_ports = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_PORTS,
+ target_container);
+ key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
+ data, hlen);
+ }
return true;
}
@@ -267,27 +438,109 @@ static __always_inline void __flow_hash_secret_init(void)
net_get_random_once(&hashrnd, sizeof(hashrnd));
}
-static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c)
+static __always_inline u32 __flow_hash_words(u32 *words, u32 length, u32 keyval)
{
- __flow_hash_secret_init();
- return jhash_3words(a, b, c, hashrnd);
+ return jhash2(words, length, keyval);
}
-static inline u32 __flow_hash_from_keys(struct flow_keys *keys)
+static inline void *flow_keys_hash_start(struct flow_keys *flow)
{
- u32 hash;
+ BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32));
+ return (void *)flow + FLOW_KEYS_HASH_OFFSET;
+}
+
+static inline size_t flow_keys_hash_length(struct flow_keys *flow)
+{
+ size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs);
+ BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32));
+ BUILD_BUG_ON(offsetof(typeof(*flow), addrs) !=
+ sizeof(*flow) - sizeof(flow->addrs));
+
+ switch (flow->control.addr_type) {
+ case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+ diff -= sizeof(flow->addrs.v4addrs);
+ break;
+ case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+ diff -= sizeof(flow->addrs.v6addrs);
+ break;
+ case FLOW_DISSECTOR_KEY_TIPC_ADDRS:
+ diff -= sizeof(flow->addrs.tipcaddrs);
+ break;
+ }
+ return (sizeof(*flow) - diff) / sizeof(u32);
+}
+
+__be32 flow_get_u32_src(const struct flow_keys *flow)
+{
+ switch (flow->control.addr_type) {
+ case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+ return flow->addrs.v4addrs.src;
+ case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+ return (__force __be32)ipv6_addr_hash(
+ &flow->addrs.v6addrs.src);
+ case FLOW_DISSECTOR_KEY_TIPC_ADDRS:
+ return flow->addrs.tipcaddrs.srcnode;
+ default:
+ return 0;
+ }
+}
+EXPORT_SYMBOL(flow_get_u32_src);
- /* get a consistent hash (same value on both flow directions) */
- if (((__force u32)keys->dst < (__force u32)keys->src) ||
- (((__force u32)keys->dst == (__force u32)keys->src) &&
- ((__force u16)keys->port16[1] < (__force u16)keys->port16[0]))) {
- swap(keys->dst, keys->src);
- swap(keys->port16[0], keys->port16[1]);
+__be32 flow_get_u32_dst(const struct flow_keys *flow)
+{
+ switch (flow->control.addr_type) {
+ case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+ return flow->addrs.v4addrs.dst;
+ case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+ return (__force __be32)ipv6_addr_hash(
+ &flow->addrs.v6addrs.dst);
+ default:
+ return 0;
}
+}
+EXPORT_SYMBOL(flow_get_u32_dst);
- hash = __flow_hash_3words((__force u32)keys->dst,
- (__force u32)keys->src,
- (__force u32)keys->ports);
+static inline void __flow_hash_consistentify(struct flow_keys *keys)
+{
+ int addr_diff, i;
+
+ switch (keys->control.addr_type) {
+ case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+ addr_diff = (__force u32)keys->addrs.v4addrs.dst -
+ (__force u32)keys->addrs.v4addrs.src;
+ if ((addr_diff < 0) ||
+ (addr_diff == 0 &&
+ ((__force u16)keys->ports.dst <
+ (__force u16)keys->ports.src))) {
+ swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst);
+ swap(keys->ports.src, keys->ports.dst);
+ }
+ break;
+ case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+ addr_diff = memcmp(&keys->addrs.v6addrs.dst,
+ &keys->addrs.v6addrs.src,
+ sizeof(keys->addrs.v6addrs.dst));
+ if ((addr_diff < 0) ||
+ (addr_diff == 0 &&
+ ((__force u16)keys->ports.dst <
+ (__force u16)keys->ports.src))) {
+ for (i = 0; i < 4; i++)
+ swap(keys->addrs.v6addrs.src.s6_addr32[i],
+ keys->addrs.v6addrs.dst.s6_addr32[i]);
+ swap(keys->ports.src, keys->ports.dst);
+ }
+ break;
+ }
+}
+
+static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
+{
+ u32 hash;
+
+ __flow_hash_consistentify(keys);
+
+ hash = __flow_hash_words((u32 *)flow_keys_hash_start(keys),
+ flow_keys_hash_length(keys), keyval);
if (!hash)
hash = 1;
@@ -296,12 +549,52 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys)
u32 flow_hash_from_keys(struct flow_keys *keys)
{
- return __flow_hash_from_keys(keys);
+ __flow_hash_secret_init();
+ return __flow_hash_from_keys(keys, hashrnd);
}
EXPORT_SYMBOL(flow_hash_from_keys);
-/*
- * __skb_get_hash: calculate a flow hash based on src/dst addresses
+static inline u32 ___skb_get_hash(const struct sk_buff *skb,
+ struct flow_keys *keys, u32 keyval)
+{
+ if (!skb_flow_dissect_flow_keys(skb, keys))
+ return 0;
+
+ return __flow_hash_from_keys(keys, keyval);
+}
+
+struct _flow_keys_digest_data {
+ __be16 n_proto;
+ u8 ip_proto;
+ u8 padding;
+ __be32 ports;
+ __be32 src;
+ __be32 dst;
+};
+
+void make_flow_keys_digest(struct flow_keys_digest *digest,
+ const struct flow_keys *flow)
+{
+ struct _flow_keys_digest_data *data =
+ (struct _flow_keys_digest_data *)digest;
+
+ BUILD_BUG_ON(sizeof(*data) > sizeof(*digest));
+
+ memset(digest, 0, sizeof(*digest));
+
+ data->n_proto = flow->basic.n_proto;
+ data->ip_proto = flow->basic.ip_proto;
+ data->ports = flow->ports.ports;
+ data->src = flow->addrs.v4addrs.src;
+ data->dst = flow->addrs.v4addrs.dst;
+}
+EXPORT_SYMBOL(make_flow_keys_digest);
+
+/**
+ * __skb_get_hash: calculate a flow hash
+ * @skb: sk_buff to calculate flow hash from
+ *
+ * This function calculates a flow hash based on src/dst addresses
* and src/dst port numbers. Sets hash in skb to non-zero hash value
* on success, zero indicates no valid hash. Also, sets l4_hash in skb
* if hash is a canonical 4-tuple hash over transport ports.
@@ -309,53 +602,34 @@ EXPORT_SYMBOL(flow_hash_from_keys);
void __skb_get_hash(struct sk_buff *skb)
{
struct flow_keys keys;
+ u32 hash;
- if (!skb_flow_dissect(skb, &keys))
- return;
+ __flow_hash_secret_init();
- if (keys.ports)
+ hash = ___skb_get_hash(skb, &keys, hashrnd);
+ if (!hash)
+ return;
+ if (keys.ports.ports)
skb->l4_hash = 1;
-
skb->sw_hash = 1;
-
- skb->hash = __flow_hash_from_keys(&keys);
+ skb->hash = hash;
}
EXPORT_SYMBOL(__skb_get_hash);
-/*
- * Returns a Tx hash based on the given packet descriptor a Tx queues' number
- * to be used as a distribution range.
- */
-u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
- unsigned int num_tx_queues)
+__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
{
- u32 hash;
- u16 qoffset = 0;
- u16 qcount = num_tx_queues;
-
- if (skb_rx_queue_recorded(skb)) {
- hash = skb_get_rx_queue(skb);
- while (unlikely(hash >= num_tx_queues))
- hash -= num_tx_queues;
- return hash;
- }
-
- if (dev->num_tc) {
- u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
- qoffset = dev->tc_to_txq[tc].offset;
- qcount = dev->tc_to_txq[tc].count;
- }
+ struct flow_keys keys;
- return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
+ return ___skb_get_hash(skb, &keys, perturb);
}
-EXPORT_SYMBOL(__skb_tx_hash);
+EXPORT_SYMBOL(skb_get_hash_perturb);
u32 __skb_get_poff(const struct sk_buff *skb, void *data,
const struct flow_keys *keys, int hlen)
{
- u32 poff = keys->thoff;
+ u32 poff = keys->control.thoff;
- switch (keys->ip_proto) {
+ switch (keys->basic.ip_proto) {
case IPPROTO_TCP: {
/* access doff as u8 to avoid unaligned access */
const u8 *doff;
@@ -396,8 +670,12 @@ u32 __skb_get_poff(const struct sk_buff *skb, void *data,
return poff;
}
-/* skb_get_poff() returns the offset to the payload as far as it could
- * be dissected. The main user is currently BPF, so that we can dynamically
+/**
+ * skb_get_poff - get the offset to the payload
+ * @skb: sk_buff to get the payload offset from
+ *
+ * The function will get the offset to the payload as far as it could
+ * be dissected. The main user is currently BPF, so that we can dynamically
* truncate packets without needing to push actual payload to the user
* space and can analyze headers only, instead.
*/
@@ -405,86 +683,76 @@ u32 skb_get_poff(const struct sk_buff *skb)
{
struct flow_keys keys;
- if (!skb_flow_dissect(skb, &keys))
+ if (!skb_flow_dissect_flow_keys(skb, &keys))
return 0;
return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
}
-static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+static const struct flow_dissector_key flow_keys_dissector_keys[] = {
+ {
+ .key_id = FLOW_DISSECTOR_KEY_CONTROL,
+ .offset = offsetof(struct flow_keys, control),
+ },
+ {
+ .key_id = FLOW_DISSECTOR_KEY_BASIC,
+ .offset = offsetof(struct flow_keys, basic),
+ },
+ {
+ .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+ .offset = offsetof(struct flow_keys, addrs.v4addrs),
+ },
+ {
+ .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+ .offset = offsetof(struct flow_keys, addrs.v6addrs),
+ },
+ {
+ .key_id = FLOW_DISSECTOR_KEY_TIPC_ADDRS,
+ .offset = offsetof(struct flow_keys, addrs.tipcaddrs),
+ },
+ {
+ .key_id = FLOW_DISSECTOR_KEY_PORTS,
+ .offset = offsetof(struct flow_keys, ports),
+ },
+ {
+ .key_id = FLOW_DISSECTOR_KEY_VLANID,
+ .offset = offsetof(struct flow_keys, tags),
+ },
+ {
+ .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL,
+ .offset = offsetof(struct flow_keys, tags),
+ },
+ {
+ .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID,
+ .offset = offsetof(struct flow_keys, keyid),
+ },
+};
+
+static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = {
+ {
+ .key_id = FLOW_DISSECTOR_KEY_CONTROL,
+ .offset = offsetof(struct flow_keys, control),
+ },
+ {
+ .key_id = FLOW_DISSECTOR_KEY_BASIC,
+ .offset = offsetof(struct flow_keys, basic),
+ },
+};
+
+struct flow_dissector flow_keys_dissector __read_mostly;
+EXPORT_SYMBOL(flow_keys_dissector);
+
+struct flow_dissector flow_keys_buf_dissector __read_mostly;
+
+static int __init init_default_flow_dissectors(void)
{
-#ifdef CONFIG_XPS
- struct xps_dev_maps *dev_maps;
- struct xps_map *map;
- int queue_index = -1;
-
- rcu_read_lock();
- dev_maps = rcu_dereference(dev->xps_maps);
- if (dev_maps) {
- map = rcu_dereference(
- dev_maps->cpu_map[skb->sender_cpu - 1]);
- if (map) {
- if (map->len == 1)
- queue_index = map->queues[0];
- else
- queue_index = map->queues[reciprocal_scale(skb_get_hash(skb),
- map->len)];
- if (unlikely(queue_index >= dev->real_num_tx_queues))
- queue_index = -1;
- }
- }
- rcu_read_unlock();
-
- return queue_index;
-#else
- return -1;
-#endif
-}
-
-static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
-{
- struct sock *sk = skb->sk;
- int queue_index = sk_tx_queue_get(sk);
-
- if (queue_index < 0 || skb->ooo_okay ||
- queue_index >= dev->real_num_tx_queues) {
- int new_index = get_xps_queue(dev, skb);
- if (new_index < 0)
- new_index = skb_tx_hash(dev, skb);
-
- if (queue_index != new_index && sk &&
- rcu_access_pointer(sk->sk_dst_cache))
- sk_tx_queue_set(sk, new_index);
-
- queue_index = new_index;
- }
-
- return queue_index;
+ skb_flow_dissector_init(&flow_keys_dissector,
+ flow_keys_dissector_keys,
+ ARRAY_SIZE(flow_keys_dissector_keys));
+ skb_flow_dissector_init(&flow_keys_buf_dissector,
+ flow_keys_buf_dissector_keys,
+ ARRAY_SIZE(flow_keys_buf_dissector_keys));
+ return 0;
}
-struct netdev_queue *netdev_pick_tx(struct net_device *dev,
- struct sk_buff *skb,
- void *accel_priv)
-{
- int queue_index = 0;
-
-#ifdef CONFIG_XPS
- if (skb->sender_cpu == 0)
- skb->sender_cpu = raw_smp_processor_id() + 1;
-#endif
-
- if (dev->real_num_tx_queues != 1) {
- const struct net_device_ops *ops = dev->netdev_ops;
- if (ops->ndo_select_queue)
- queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
- __netdev_pick_tx);
- else
- queue_index = __netdev_pick_tx(dev, skb);
-
- if (!accel_priv)
- queue_index = netdev_cap_txqueue(dev, queue_index);
- }
-
- skb_set_queue_mapping(skb, queue_index);
- return netdev_get_tx_queue(dev, queue_index);
-}
+late_initcall_sync(init_default_flow_dissectors);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 3de654256028..3a74df750af4 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -913,6 +913,7 @@ static void neigh_timer_handler(unsigned long arg)
neigh->nud_state = NUD_PROBE;
neigh->updated = jiffies;
atomic_set(&neigh->probes, 0);
+ notify = 1;
next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME);
}
} else {
@@ -1144,6 +1145,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
if (new != old) {
neigh_del_timer(neigh);
+ if (new & NUD_PROBE)
+ atomic_set(&neigh->probes, 0);
if (new & NUD_IN_TIMER)
neigh_add_timer(neigh, (jiffies +
((new & NUD_REACHABLE) ?
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 4238d6da5c60..18b34d771ed4 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -458,11 +458,15 @@ static ssize_t phys_switch_id_show(struct device *dev,
return restart_syscall();
if (dev_isalive(netdev)) {
- struct netdev_phys_item_id ppid;
+ struct switchdev_attr attr = {
+ .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+ .flags = SWITCHDEV_F_NO_RECURSE,
+ };
- ret = netdev_switch_parent_id_get(netdev, &ppid);
+ ret = switchdev_port_attr_get(netdev, &attr);
if (!ret)
- ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id);
+ ret = sprintf(buf, "%*phN\n", attr.u.ppid.id_len,
+ attr.u.ppid.id);
}
rtnl_unlock();
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 572af0011997..2c2eb1b629b1 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -147,24 +147,17 @@ static void ops_free_list(const struct pernet_operations *ops,
}
}
-static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd,
- int id);
+/* should be called with nsid_lock held */
static int alloc_netid(struct net *net, struct net *peer, int reqid)
{
- int min = 0, max = 0, id;
-
- ASSERT_RTNL();
+ int min = 0, max = 0;
if (reqid >= 0) {
min = reqid;
max = reqid + 1;
}
- id = idr_alloc(&net->netns_ids, peer, min, max, GFP_KERNEL);
- if (id >= 0)
- rtnl_net_notifyid(net, peer, RTM_NEWNSID, id);
-
- return id;
+ return idr_alloc(&net->netns_ids, peer, min, max, GFP_ATOMIC);
}
/* This function is used by idr_for_each(). If net is equal to peer, the
@@ -180,11 +173,16 @@ static int net_eq_idr(int id, void *net, void *peer)
return 0;
}
-static int __peernet2id(struct net *net, struct net *peer, bool alloc)
+/* Should be called with nsid_lock held. If a new id is assigned, the bool alloc
+ * is set to true, thus the caller knows that the new id must be notified via
+ * rtnl.
+ */
+static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc)
{
int id = idr_for_each(&net->netns_ids, net_eq_idr, peer);
+ bool alloc_it = *alloc;
- ASSERT_RTNL();
+ *alloc = false;
/* Magic value for id 0. */
if (id == NET_ID_ZERO)
@@ -192,36 +190,77 @@ static int __peernet2id(struct net *net, struct net *peer, bool alloc)
if (id > 0)
return id;
- if (alloc)
- return alloc_netid(net, peer, -1);
+ if (alloc_it) {
+ id = alloc_netid(net, peer, -1);
+ *alloc = true;
+ return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
+ }
+
+ return NETNSA_NSID_NOT_ASSIGNED;
+}
+
+/* should be called with nsid_lock held */
+static int __peernet2id(struct net *net, struct net *peer)
+{
+ bool no = false;
- return -ENOENT;
+ return __peernet2id_alloc(net, peer, &no);
}
+static void rtnl_net_notifyid(struct net *net, int cmd, int id);
/* This function returns the id of a peer netns. If no id is assigned, one will
* be allocated and returned.
*/
+int peernet2id_alloc(struct net *net, struct net *peer)
+{
+ unsigned long flags;
+ bool alloc;
+ int id;
+
+ spin_lock_irqsave(&net->nsid_lock, flags);
+ alloc = atomic_read(&peer->count) == 0 ? false : true;
+ id = __peernet2id_alloc(net, peer, &alloc);
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
+ if (alloc && id >= 0)
+ rtnl_net_notifyid(net, RTM_NEWNSID, id);
+ return id;
+}
+EXPORT_SYMBOL(peernet2id_alloc);
+
+/* This function returns, if assigned, the id of a peer netns. */
int peernet2id(struct net *net, struct net *peer)
{
- bool alloc = atomic_read(&peer->count) == 0 ? false : true;
+ unsigned long flags;
int id;
- id = __peernet2id(net, peer, alloc);
- return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
+ spin_lock_irqsave(&net->nsid_lock, flags);
+ id = __peernet2id(net, peer);
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
+ return id;
+}
+
+/* This function returns true is the peer netns has an id assigned into the
+ * current netns.
+ */
+bool peernet_has_id(struct net *net, struct net *peer)
+{
+ return peernet2id(net, peer) >= 0;
}
-EXPORT_SYMBOL(peernet2id);
struct net *get_net_ns_by_id(struct net *net, int id)
{
+ unsigned long flags;
struct net *peer;
if (id < 0)
return NULL;
rcu_read_lock();
+ spin_lock_irqsave(&net->nsid_lock, flags);
peer = idr_find(&net->netns_ids, id);
if (peer)
get_net(peer);
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
rcu_read_unlock();
return peer;
@@ -242,6 +281,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
net->dev_base_seq = 1;
net->user_ns = user_ns;
idr_init(&net->netns_ids);
+ spin_lock_init(&net->nsid_lock);
list_for_each_entry(ops, &pernet_list, list) {
error = ops_init(ops, net);
@@ -362,14 +402,19 @@ static void cleanup_net(struct work_struct *work)
list_del_rcu(&net->list);
list_add_tail(&net->exit_list, &net_exit_list);
for_each_net(tmp) {
- int id = __peernet2id(tmp, net, false);
+ int id;
- if (id >= 0) {
- rtnl_net_notifyid(tmp, net, RTM_DELNSID, id);
+ spin_lock_irq(&tmp->nsid_lock);
+ id = __peernet2id(tmp, net);
+ if (id >= 0)
idr_remove(&tmp->netns_ids, id);
- }
+ spin_unlock_irq(&tmp->nsid_lock);
+ if (id >= 0)
+ rtnl_net_notifyid(tmp, RTM_DELNSID, id);
}
+ spin_lock_irq(&net->nsid_lock);
idr_destroy(&net->netns_ids);
+ spin_unlock_irq(&net->nsid_lock);
}
rtnl_unlock();
@@ -497,6 +542,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tb[NETNSA_MAX + 1];
+ unsigned long flags;
struct net *peer;
int nsid, err;
@@ -517,14 +563,19 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
if (IS_ERR(peer))
return PTR_ERR(peer);
- if (__peernet2id(net, peer, false) >= 0) {
+ spin_lock_irqsave(&net->nsid_lock, flags);
+ if (__peernet2id(net, peer) >= 0) {
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
err = -EEXIST;
goto out;
}
err = alloc_netid(net, peer, nsid);
- if (err > 0)
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
+ if (err >= 0) {
+ rtnl_net_notifyid(net, RTM_NEWNSID, err);
err = 0;
+ }
out:
put_net(peer);
return err;
@@ -538,14 +589,10 @@ static int rtnl_net_get_size(void)
}
static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags,
- int cmd, struct net *net, struct net *peer,
- int nsid)
+ int cmd, struct net *net, int nsid)
{
struct nlmsghdr *nlh;
struct rtgenmsg *rth;
- int id;
-
- ASSERT_RTNL();
nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rth), flags);
if (!nlh)
@@ -554,14 +601,7 @@ static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags,
rth = nlmsg_data(nlh);
rth->rtgen_family = AF_UNSPEC;
- if (nsid >= 0) {
- id = nsid;
- } else {
- id = __peernet2id(net, peer, false);
- if (id < 0)
- id = NETNSA_NSID_NOT_ASSIGNED;
- }
- if (nla_put_s32(skb, NETNSA_NSID, id))
+ if (nla_put_s32(skb, NETNSA_NSID, nsid))
goto nla_put_failure;
nlmsg_end(skb, nlh);
@@ -578,7 +618,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh)
struct nlattr *tb[NETNSA_MAX + 1];
struct sk_buff *msg;
struct net *peer;
- int err;
+ int err, id;
err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
rtnl_net_policy);
@@ -600,8 +640,9 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh)
goto out;
}
+ id = peernet2id(net, peer);
err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
- RTM_NEWNSID, net, peer, -1);
+ RTM_NEWNSID, net, id);
if (err < 0)
goto err_out;
@@ -633,7 +674,7 @@ static int rtnl_net_dumpid_one(int id, void *peer, void *data)
ret = rtnl_net_fill(net_cb->skb, NETLINK_CB(net_cb->cb->skb).portid,
net_cb->cb->nlh->nlmsg_seq, NLM_F_MULTI,
- RTM_NEWNSID, net_cb->net, peer, id);
+ RTM_NEWNSID, net_cb->net, id);
if (ret < 0)
return ret;
@@ -652,17 +693,17 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
.idx = 0,
.s_idx = cb->args[0],
};
+ unsigned long flags;
- ASSERT_RTNL();
-
+ spin_lock_irqsave(&net->nsid_lock, flags);
idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb);
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
cb->args[0] = net_cb.idx;
return skb->len;
}
-static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd,
- int id)
+static void rtnl_net_notifyid(struct net *net, int cmd, int id)
{
struct sk_buff *msg;
int err = -ENOMEM;
@@ -671,7 +712,7 @@ static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd,
if (!msg)
goto out;
- err = rtnl_net_fill(msg, 0, 0, 0, cmd, net, peer, id);
+ err = rtnl_net_fill(msg, 0, 0, 0, cmd, net, id);
if (err < 0)
goto err_out;
diff --git a/net/core/netevent.c b/net/core/netevent.c
index f17ccd291d39..8b3bc4fac613 100644
--- a/net/core/netevent.c
+++ b/net/core/netevent.c
@@ -31,10 +31,7 @@ static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain);
*/
int register_netevent_notifier(struct notifier_block *nb)
{
- int err;
-
- err = atomic_notifier_chain_register(&netevent_notif_chain, nb);
- return err;
+ return atomic_notifier_chain_register(&netevent_notif_chain, nb);
}
EXPORT_SYMBOL_GPL(register_netevent_notifier);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 508155b283dd..d93cbc5715f4 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -177,7 +177,7 @@
#include <asm/dma.h>
#include <asm/div64.h> /* do_div */
-#define VERSION "2.74"
+#define VERSION "2.75"
#define IP_NAME_SZ 32
#define MAX_MPLS_LABELS 16 /* This is the max label stack depth */
#define MPLS_STACK_BOTTOM htonl(0x00000100)
@@ -210,6 +210,10 @@
#define T_REMDEVALL (1<<2) /* Remove all devs */
#define T_REMDEV (1<<3) /* Remove one dev */
+/* Xmit modes */
+#define M_START_XMIT 0 /* Default normal TX */
+#define M_NETIF_RECEIVE 1 /* Inject packets into stack */
+
/* If lock -- protects updating of if_list */
#define if_lock(t) spin_lock(&(t->if_lock));
#define if_unlock(t) spin_unlock(&(t->if_lock));
@@ -251,13 +255,14 @@ struct pktgen_dev {
* we will do a random selection from within the range.
*/
__u32 flags;
- int removal_mark; /* non-zero => the device is marked for
- * removal by worker thread */
-
+ int xmit_mode;
int min_pkt_size;
int max_pkt_size;
int pkt_overhead; /* overhead for MPLS, VLANs, IPSEC etc */
int nfrags;
+ int removal_mark; /* non-zero => the device is marked for
+ * removal by worker thread */
+
struct page *page;
u64 delay; /* nano-seconds */
@@ -507,7 +512,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf,
pktgen_reset_all_threads(pn);
else
- pr_warn("Unknown command: %s\n", data);
+ return -EINVAL;
return count;
}
@@ -567,7 +572,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
" dst_min: %s dst_max: %s\n",
pkt_dev->dst_min, pkt_dev->dst_max);
seq_printf(seq,
- " src_min: %s src_max: %s\n",
+ " src_min: %s src_max: %s\n",
pkt_dev->src_min, pkt_dev->src_max);
}
@@ -620,6 +625,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
if (pkt_dev->node >= 0)
seq_printf(seq, " node: %d\n", pkt_dev->node);
+ if (pkt_dev->xmit_mode == M_NETIF_RECEIVE)
+ seq_puts(seq, " xmit_mode: netif_receive\n");
+
seq_puts(seq, " Flags: ");
if (pkt_dev->flags & F_IPV6)
@@ -1081,7 +1089,8 @@ static ssize_t pktgen_if_write(struct file *file,
if (len < 0)
return len;
if ((value > 0) &&
- (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))
+ ((pkt_dev->xmit_mode == M_NETIF_RECEIVE) ||
+ !(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))
return -ENOTSUPP;
i += len;
pkt_dev->clone_skb = value;
@@ -1134,7 +1143,7 @@ static ssize_t pktgen_if_write(struct file *file,
return len;
i += len;
- if ((value > 1) &&
+ if ((value > 1) && (pkt_dev->xmit_mode == M_START_XMIT) &&
(!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))
return -ENOTSUPP;
pkt_dev->burst = value < 1 ? 1 : value;
@@ -1160,6 +1169,45 @@ static ssize_t pktgen_if_write(struct file *file,
sprintf(pg_result, "ERROR: node not possible");
return count;
}
+ if (!strcmp(name, "xmit_mode")) {
+ char f[32];
+
+ memset(f, 0, 32);
+ len = strn_len(&user_buffer[i], sizeof(f) - 1);
+ if (len < 0)
+ return len;
+
+ if (copy_from_user(f, &user_buffer[i], len))
+ return -EFAULT;
+ i += len;
+
+ if (strcmp(f, "start_xmit") == 0) {
+ pkt_dev->xmit_mode = M_START_XMIT;
+ } else if (strcmp(f, "netif_receive") == 0) {
+ /* clone_skb set earlier, not supported in this mode */
+ if (pkt_dev->clone_skb > 0)
+ return -ENOTSUPP;
+
+ pkt_dev->xmit_mode = M_NETIF_RECEIVE;
+
+ /* make sure new packet is allocated every time
+ * pktgen_xmit() is called
+ */
+ pkt_dev->last_ok = 1;
+
+ /* override clone_skb if user passed default value
+ * at module loading time
+ */
+ pkt_dev->clone_skb = 0;
+ } else {
+ sprintf(pg_result,
+ "xmit_mode -:%s:- unknown\nAvailable modes: %s",
+ f, "start_xmit, netif_receive\n");
+ return count;
+ }
+ sprintf(pg_result, "OK: xmit_mode=%s", f);
+ return count;
+ }
if (!strcmp(name, "flag")) {
char f[32];
memset(f, 0, 32);
@@ -1267,6 +1315,9 @@ static ssize_t pktgen_if_write(struct file *file,
else if (strcmp(f, "NO_TIMESTAMP") == 0)
pkt_dev->flags |= F_NO_TIMESTAMP;
+ else if (strcmp(f, "!NO_TIMESTAMP") == 0)
+ pkt_dev->flags &= ~F_NO_TIMESTAMP;
+
else {
sprintf(pg_result,
"Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s",
@@ -2594,9 +2645,9 @@ static int process_ipsec(struct pktgen_dev *pkt_dev,
struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x;
int nhead = 0;
if (x) {
- int ret;
- __u8 *eth;
+ struct ethhdr *eth;
struct iphdr *iph;
+ int ret;
nhead = x->props.header_len - skb_headroom(skb);
if (nhead > 0) {
@@ -2616,9 +2667,9 @@ static int process_ipsec(struct pktgen_dev *pkt_dev,
goto err;
}
/* restore ll */
- eth = (__u8 *) skb_push(skb, ETH_HLEN);
- memcpy(eth, pkt_dev->hh, 12);
- *(u16 *) &eth[12] = protocol;
+ eth = (struct ethhdr *)skb_push(skb, ETH_HLEN);
+ memcpy(eth, pkt_dev->hh, 2 * ETH_ALEN);
+ eth->h_proto = protocol;
/* Update IPv4 header len as well as checksum value */
iph = ip_hdr(skb);
@@ -3317,6 +3368,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
unsigned int burst = ACCESS_ONCE(pkt_dev->burst);
struct net_device *odev = pkt_dev->odev;
struct netdev_queue *txq;
+ struct sk_buff *skb;
int ret;
/* If device is offline, then don't send */
@@ -3354,6 +3406,37 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
if (pkt_dev->delay && pkt_dev->last_ok)
spin(pkt_dev, pkt_dev->next_tx);
+ if (pkt_dev->xmit_mode == M_NETIF_RECEIVE) {
+ skb = pkt_dev->skb;
+ skb->protocol = eth_type_trans(skb, skb->dev);
+ atomic_add(burst, &skb->users);
+ local_bh_disable();
+ do {
+ ret = netif_receive_skb(skb);
+ if (ret == NET_RX_DROP)
+ pkt_dev->errors++;
+ pkt_dev->sofar++;
+ pkt_dev->seq_num++;
+ if (atomic_read(&skb->users) != burst) {
+ /* skb was queued by rps/rfs or taps,
+ * so cannot reuse this skb
+ */
+ atomic_sub(burst - 1, &skb->users);
+ /* get out of the loop and wait
+ * until skb is consumed
+ */
+ break;
+ }
+ /* skb was 'freed' by stack, so clean few
+ * bits and reuse it
+ */
+#ifdef CONFIG_NET_CLS_ACT
+ skb->tc_verd = 0; /* reset reclass/redir ttl */
+#endif
+ } while (--burst > 0);
+ goto out; /* Skips xmit_mode M_START_XMIT */
+ }
+
txq = skb_get_tx_queue(odev, pkt_dev->skb);
local_bh_disable();
@@ -3401,6 +3484,7 @@ xmit_more:
unlock:
HARD_TX_UNLOCK(odev, txq);
+out:
local_bh_enable();
/* If pkt_dev->count is zero, then run forever */
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 8de36824018d..077b6d280371 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1004,16 +1004,20 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev)
static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
{
int err;
- struct netdev_phys_item_id psid;
+ struct switchdev_attr attr = {
+ .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+ .flags = SWITCHDEV_F_NO_RECURSE,
+ };
- err = netdev_switch_parent_id_get(dev, &psid);
+ err = switchdev_port_attr_get(dev, &attr);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
return err;
}
- if (nla_put(skb, IFLA_PHYS_SWITCH_ID, psid.id_len, psid.id))
+ if (nla_put(skb, IFLA_PHYS_SWITCH_ID, attr.u.ppid.id_len,
+ attr.u.ppid.id))
return -EMSGSIZE;
return 0;
@@ -1204,7 +1208,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
if (!net_eq(dev_net(dev), link_net)) {
- int id = peernet2id(dev_net(dev), link_net);
+ int id = peernet2id_alloc(dev_net(dev), link_net);
if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
goto nla_put_failure;
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 51dd3193a33e..fd3ce461fbe6 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -154,7 +154,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
net_secret_init();
memcpy(hash, saddr, 16);
for (i = 0; i < 4; i++)
- secret[i] = net_secret[i] + daddr[i];
+ secret[i] = net_secret[i] + (__force u32)daddr[i];
secret[4] = net_secret[4] +
(((__force u16)sport << 16) + (__force u16)dport);
for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 41ec02242ea7..b6a19ca0f99e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -347,94 +347,18 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
}
EXPORT_SYMBOL(build_skb);
-struct netdev_alloc_cache {
- struct page_frag frag;
- /* we maintain a pagecount bias, so that we dont dirty cache line
- * containing page->_count every time we allocate a fragment.
- */
- unsigned int pagecnt_bias;
-};
-static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
-static DEFINE_PER_CPU(struct netdev_alloc_cache, napi_alloc_cache);
-
-static struct page *__page_frag_refill(struct netdev_alloc_cache *nc,
- gfp_t gfp_mask)
-{
- const unsigned int order = NETDEV_FRAG_PAGE_MAX_ORDER;
- struct page *page = NULL;
- gfp_t gfp = gfp_mask;
-
- if (order) {
- gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
- __GFP_NOMEMALLOC;
- page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
- nc->frag.size = PAGE_SIZE << (page ? order : 0);
- }
-
- if (unlikely(!page))
- page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
-
- nc->frag.page = page;
-
- return page;
-}
-
-static void *__alloc_page_frag(struct netdev_alloc_cache __percpu *cache,
- unsigned int fragsz, gfp_t gfp_mask)
-{
- struct netdev_alloc_cache *nc = this_cpu_ptr(cache);
- struct page *page = nc->frag.page;
- unsigned int size;
- int offset;
-
- if (unlikely(!page)) {
-refill:
- page = __page_frag_refill(nc, gfp_mask);
- if (!page)
- return NULL;
-
- /* if size can vary use frag.size else just use PAGE_SIZE */
- size = NETDEV_FRAG_PAGE_MAX_ORDER ? nc->frag.size : PAGE_SIZE;
-
- /* Even if we own the page, we do not use atomic_set().
- * This would break get_page_unless_zero() users.
- */
- atomic_add(size - 1, &page->_count);
-
- /* reset page count bias and offset to start of new frag */
- nc->pagecnt_bias = size;
- nc->frag.offset = size;
- }
-
- offset = nc->frag.offset - fragsz;
- if (unlikely(offset < 0)) {
- if (!atomic_sub_and_test(nc->pagecnt_bias, &page->_count))
- goto refill;
-
- /* if size can vary use frag.size else just use PAGE_SIZE */
- size = NETDEV_FRAG_PAGE_MAX_ORDER ? nc->frag.size : PAGE_SIZE;
-
- /* OK, page count is 0, we can safely set it */
- atomic_set(&page->_count, size);
-
- /* reset page count bias and offset to start of new frag */
- nc->pagecnt_bias = size;
- offset = size - fragsz;
- }
-
- nc->pagecnt_bias--;
- nc->frag.offset = offset;
-
- return page_address(page) + offset;
-}
+static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
+static DEFINE_PER_CPU(struct page_frag_cache, napi_alloc_cache);
static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
{
+ struct page_frag_cache *nc;
unsigned long flags;
void *data;
local_irq_save(flags);
- data = __alloc_page_frag(&netdev_alloc_cache, fragsz, gfp_mask);
+ nc = this_cpu_ptr(&netdev_alloc_cache);
+ data = __alloc_page_frag(nc, fragsz, gfp_mask);
local_irq_restore(flags);
return data;
}
@@ -454,7 +378,9 @@ EXPORT_SYMBOL(netdev_alloc_frag);
static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
{
- return __alloc_page_frag(&napi_alloc_cache, fragsz, gfp_mask);
+ struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+
+ return __alloc_page_frag(nc, fragsz, gfp_mask);
}
void *napi_alloc_frag(unsigned int fragsz)
@@ -464,76 +390,70 @@ void *napi_alloc_frag(unsigned int fragsz)
EXPORT_SYMBOL(napi_alloc_frag);
/**
- * __alloc_rx_skb - allocate an skbuff for rx
+ * __netdev_alloc_skb - allocate an skbuff for rx on a specific device
+ * @dev: network device to receive on
* @length: length to allocate
* @gfp_mask: get_free_pages mask, passed to alloc_skb
- * @flags: If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
- * allocations in case we have to fallback to __alloc_skb()
- * If SKB_ALLOC_NAPI is set, page fragment will be allocated
- * from napi_cache instead of netdev_cache.
*
* Allocate a new &sk_buff and assign it a usage count of one. The
- * buffer has unspecified headroom built in. Users should allocate
+ * buffer has NET_SKB_PAD headroom built in. Users should allocate
* the headroom they think they need without accounting for the
* built in space. The built in space is used for optimisations.
*
* %NULL is returned if there is no free memory.
*/
-static struct sk_buff *__alloc_rx_skb(unsigned int length, gfp_t gfp_mask,
- int flags)
+struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
+ gfp_t gfp_mask)
{
- struct sk_buff *skb = NULL;
- unsigned int fragsz = SKB_DATA_ALIGN(length) +
- SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ struct page_frag_cache *nc;
+ unsigned long flags;
+ struct sk_buff *skb;
+ bool pfmemalloc;
+ void *data;
- if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
- void *data;
+ len += NET_SKB_PAD;
- if (sk_memalloc_socks())
- gfp_mask |= __GFP_MEMALLOC;
+ if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
+ (gfp_mask & (__GFP_WAIT | GFP_DMA))) {
+ skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
+ if (!skb)
+ goto skb_fail;
+ goto skb_success;
+ }
- data = (flags & SKB_ALLOC_NAPI) ?
- __napi_alloc_frag(fragsz, gfp_mask) :
- __netdev_alloc_frag(fragsz, gfp_mask);
+ len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ len = SKB_DATA_ALIGN(len);
- if (likely(data)) {
- skb = build_skb(data, fragsz);
- if (unlikely(!skb))
- put_page(virt_to_head_page(data));
- }
- } else {
- skb = __alloc_skb(length, gfp_mask,
- SKB_ALLOC_RX, NUMA_NO_NODE);
- }
- return skb;
-}
+ if (sk_memalloc_socks())
+ gfp_mask |= __GFP_MEMALLOC;
-/**
- * __netdev_alloc_skb - allocate an skbuff for rx on a specific device
- * @dev: network device to receive on
- * @length: length to allocate
- * @gfp_mask: get_free_pages mask, passed to alloc_skb
- *
- * Allocate a new &sk_buff and assign it a usage count of one. The
- * buffer has NET_SKB_PAD headroom built in. Users should allocate
- * the headroom they think they need without accounting for the
- * built in space. The built in space is used for optimisations.
- *
- * %NULL is returned if there is no free memory.
- */
-struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
- unsigned int length, gfp_t gfp_mask)
-{
- struct sk_buff *skb;
+ local_irq_save(flags);
+
+ nc = this_cpu_ptr(&netdev_alloc_cache);
+ data = __alloc_page_frag(nc, len, gfp_mask);
+ pfmemalloc = nc->pfmemalloc;
- length += NET_SKB_PAD;
- skb = __alloc_rx_skb(length, gfp_mask, 0);
+ local_irq_restore(flags);
- if (likely(skb)) {
- skb_reserve(skb, NET_SKB_PAD);
- skb->dev = dev;
+ if (unlikely(!data))
+ return NULL;
+
+ skb = __build_skb(data, len);
+ if (unlikely(!skb)) {
+ skb_free_frag(data);
+ return NULL;
}
+ /* use OR instead of assignment to avoid clearing of bits in mask */
+ if (pfmemalloc)
+ skb->pfmemalloc = 1;
+ skb->head_frag = 1;
+
+skb_success:
+ skb_reserve(skb, NET_SKB_PAD);
+ skb->dev = dev;
+
+skb_fail:
return skb;
}
EXPORT_SYMBOL(__netdev_alloc_skb);
@@ -551,19 +471,49 @@ EXPORT_SYMBOL(__netdev_alloc_skb);
*
* %NULL is returned if there is no free memory.
*/
-struct sk_buff *__napi_alloc_skb(struct napi_struct *napi,
- unsigned int length, gfp_t gfp_mask)
+struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
+ gfp_t gfp_mask)
{
+ struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache);
struct sk_buff *skb;
+ void *data;
- length += NET_SKB_PAD + NET_IP_ALIGN;
- skb = __alloc_rx_skb(length, gfp_mask, SKB_ALLOC_NAPI);
+ len += NET_SKB_PAD + NET_IP_ALIGN;
- if (likely(skb)) {
- skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
- skb->dev = napi->dev;
+ if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
+ (gfp_mask & (__GFP_WAIT | GFP_DMA))) {
+ skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
+ if (!skb)
+ goto skb_fail;
+ goto skb_success;
}
+ len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ len = SKB_DATA_ALIGN(len);
+
+ if (sk_memalloc_socks())
+ gfp_mask |= __GFP_MEMALLOC;
+
+ data = __alloc_page_frag(nc, len, gfp_mask);
+ if (unlikely(!data))
+ return NULL;
+
+ skb = __build_skb(data, len);
+ if (unlikely(!skb)) {
+ skb_free_frag(data);
+ return NULL;
+ }
+
+ /* use OR instead of assignment to avoid clearing of bits in mask */
+ if (nc->pfmemalloc)
+ skb->pfmemalloc = 1;
+ skb->head_frag = 1;
+
+skb_success:
+ skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+ skb->dev = napi->dev;
+
+skb_fail:
return skb;
}
EXPORT_SYMBOL(__napi_alloc_skb);
@@ -611,10 +561,12 @@ static void skb_clone_fraglist(struct sk_buff *skb)
static void skb_free_head(struct sk_buff *skb)
{
+ unsigned char *head = skb->head;
+
if (skb->head_frag)
- put_page(virt_to_head_page(skb->head));
+ skb_free_frag(head);
else
- kfree(skb->head);
+ kfree(head);
}
static void skb_release_data(struct sk_buff *skb)
@@ -1918,15 +1870,39 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
return false;
}
+ssize_t skb_socket_splice(struct sock *sk,
+ struct pipe_inode_info *pipe,
+ struct splice_pipe_desc *spd)
+{
+ int ret;
+
+ /* Drop the socket lock, otherwise we have reverse
+ * locking dependencies between sk_lock and i_mutex
+ * here as compared to sendfile(). We enter here
+ * with the socket lock held, and splice_to_pipe() will
+ * grab the pipe inode lock. For sendfile() emulation,
+ * we call into ->sendpage() with the i_mutex lock held
+ * and networking will grab the socket lock.
+ */
+ release_sock(sk);
+ ret = splice_to_pipe(pipe, spd);
+ lock_sock(sk);
+
+ return ret;
+}
+
/*
* Map data from the skb to a pipe. Should handle both the linear part,
* the fragments, and the frag list. It does NOT handle frag lists within
* the frag list, if such a thing exists. We'd probably need to recurse to
* handle that cleanly.
*/
-int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
+int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
struct pipe_inode_info *pipe, unsigned int tlen,
- unsigned int flags)
+ unsigned int flags,
+ ssize_t (*splice_cb)(struct sock *,
+ struct pipe_inode_info *,
+ struct splice_pipe_desc *))
{
struct partial_page partial[MAX_SKB_FRAGS];
struct page *pages[MAX_SKB_FRAGS];
@@ -1939,7 +1915,6 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
.spd_release = sock_spd_release,
};
struct sk_buff *frag_iter;
- struct sock *sk = skb->sk;
int ret = 0;
/*
@@ -1962,23 +1937,12 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
}
done:
- if (spd.nr_pages) {
- /*
- * Drop the socket lock, otherwise we have reverse
- * locking dependencies between sk_lock and i_mutex
- * here as compared to sendfile(). We enter here
- * with the socket lock held, and splice_to_pipe() will
- * grab the pipe inode lock. For sendfile() emulation,
- * we call into ->sendpage() with the i_mutex lock held
- * and networking will grab the socket lock.
- */
- release_sock(sk);
- ret = splice_to_pipe(pipe, &spd);
- lock_sock(sk);
- }
+ if (spd.nr_pages)
+ ret = splice_cb(sk, pipe, &spd);
return ret;
}
+EXPORT_SYMBOL_GPL(skb_splice_bits);
/**
* skb_store_bits - store bits from kernel buffer to skb
@@ -2963,6 +2927,24 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
}
EXPORT_SYMBOL(skb_append_datato_frags);
+int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
+ int offset, size_t size)
+{
+ int i = skb_shinfo(skb)->nr_frags;
+
+ if (skb_can_coalesce(skb, i, page, offset)) {
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size);
+ } else if (i < MAX_SKB_FRAGS) {
+ get_page(page);
+ skb_fill_page_desc(skb, i, page, offset, size);
+ } else {
+ return -EMSGSIZE;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(skb_append_pagefrags);
+
/**
* skb_pull_rcsum - pull skb and update receive checksum
* @skb: buffer to update
@@ -4030,6 +4012,93 @@ int skb_checksum_setup(struct sk_buff *skb, bool recalculate)
}
EXPORT_SYMBOL(skb_checksum_setup);
+/**
+ * skb_checksum_maybe_trim - maybe trims the given skb
+ * @skb: the skb to check
+ * @transport_len: the data length beyond the network header
+ *
+ * Checks whether the given skb has data beyond the given transport length.
+ * If so, returns a cloned skb trimmed to this transport length.
+ * Otherwise returns the provided skb. Returns NULL in error cases
+ * (e.g. transport_len exceeds skb length or out-of-memory).
+ *
+ * Caller needs to set the skb transport header and release the returned skb.
+ * Provided skb is consumed.
+ */
+static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb,
+ unsigned int transport_len)
+{
+ struct sk_buff *skb_chk;
+ unsigned int len = skb_transport_offset(skb) + transport_len;
+ int ret;
+
+ if (skb->len < len) {
+ kfree_skb(skb);
+ return NULL;
+ } else if (skb->len == len) {
+ return skb;
+ }
+
+ skb_chk = skb_clone(skb, GFP_ATOMIC);
+ kfree_skb(skb);
+
+ if (!skb_chk)
+ return NULL;
+
+ ret = pskb_trim_rcsum(skb_chk, len);
+ if (ret) {
+ kfree_skb(skb_chk);
+ return NULL;
+ }
+
+ return skb_chk;
+}
+
+/**
+ * skb_checksum_trimmed - validate checksum of an skb
+ * @skb: the skb to check
+ * @transport_len: the data length beyond the network header
+ * @skb_chkf: checksum function to use
+ *
+ * Applies the given checksum function skb_chkf to the provided skb.
+ * Returns a checked and maybe trimmed skb. Returns NULL on error.
+ *
+ * If the skb has data beyond the given transport length, then a
+ * trimmed & cloned skb is checked and returned.
+ *
+ * Caller needs to set the skb transport header and release the returned skb.
+ * Provided skb is consumed.
+ */
+struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb,
+ unsigned int transport_len,
+ __sum16(*skb_chkf)(struct sk_buff *skb))
+{
+ struct sk_buff *skb_chk;
+ unsigned int offset = skb_transport_offset(skb);
+ __sum16 ret;
+
+ skb_chk = skb_checksum_maybe_trim(skb, transport_len);
+ if (!skb_chk)
+ return NULL;
+
+ if (!pskb_may_pull(skb_chk, offset)) {
+ kfree_skb(skb_chk);
+ return NULL;
+ }
+
+ __skb_pull(skb_chk, offset);
+ ret = skb_chkf(skb_chk);
+ __skb_push(skb_chk, offset);
+
+ if (ret) {
+ kfree_skb(skb_chk);
+ return NULL;
+ }
+
+ return skb_chk;
+}
+EXPORT_SYMBOL(skb_checksum_trimmed);
+
void __skb_warn_lro_forwarding(const struct sk_buff *skb)
{
net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n",
diff --git a/net/core/sock.c b/net/core/sock.c
index dc30dc5bb1b8..7063c329c1b6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1393,9 +1393,10 @@ EXPORT_SYMBOL_GPL(sock_update_netprioidx);
* @family: protocol family
* @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
* @prot: struct proto associated with this new sock instance
+ * @kern: is this to be a kernel socket?
*/
struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
- struct proto *prot)
+ struct proto *prot, int kern)
{
struct sock *sk;
@@ -1408,7 +1409,10 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
*/
sk->sk_prot = sk->sk_prot_creator = prot;
sock_lock_init(sk);
- sock_net_set(sk, get_net(net));
+ sk->sk_net_refcnt = kern ? 0 : 1;
+ if (likely(sk->sk_net_refcnt))
+ get_net(net);
+ sock_net_set(sk, net);
atomic_set(&sk->sk_wmem_alloc, 1);
sock_update_classid(sk);
@@ -1442,7 +1446,8 @@ static void __sk_free(struct sock *sk)
if (sk->sk_peer_cred)
put_cred(sk->sk_peer_cred);
put_pid(sk->sk_peer_pid);
- put_net(sock_net(sk));
+ if (likely(sk->sk_net_refcnt))
+ put_net(sock_net(sk));
sk_prot_free(sk->sk_prot_creator, sk);
}
@@ -1458,25 +1463,6 @@ void sk_free(struct sock *sk)
}
EXPORT_SYMBOL(sk_free);
-/*
- * Last sock_put should drop reference to sk->sk_net. It has already
- * been dropped in sk_change_net. Taking reference to stopping namespace
- * is not an option.
- * Take reference to a socket to remove it from hash _alive_ and after that
- * destroy it in the context of init_net.
- */
-void sk_release_kernel(struct sock *sk)
-{
- if (sk == NULL || sk->sk_socket == NULL)
- return;
-
- sock_hold(sk);
- sock_release(sk->sk_socket);
- sock_net_set(sk, get_net(&init_net));
- sock_put(sk);
-}
-EXPORT_SYMBOL(sk_release_kernel);
-
static void sk_update_clone(const struct sock *sk, struct sock *newsk)
{
if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
@@ -1592,6 +1578,8 @@ EXPORT_SYMBOL_GPL(sk_clone_lock);
void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
+ u32 max_segs = 1;
+
__sk_dst_set(sk, dst);
sk->sk_route_caps = dst->dev->features;
if (sk->sk_route_caps & NETIF_F_GSO)
@@ -1603,9 +1591,10 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
} else {
sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
sk->sk_gso_max_size = dst->dev->gso_max_size;
- sk->sk_gso_max_segs = dst->dev->gso_max_segs;
+ max_segs = max_t(u32, dst->dev->gso_max_segs, 1);
}
}
+ sk->sk_gso_max_segs = max_segs;
}
EXPORT_SYMBOL_GPL(sk_setup_caps);
@@ -2080,12 +2069,13 @@ EXPORT_SYMBOL(__sk_mem_schedule);
/**
* __sk_reclaim - reclaim memory_allocated
* @sk: socket
+ * @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
*/
-void __sk_mem_reclaim(struct sock *sk)
+void __sk_mem_reclaim(struct sock *sk, int amount)
{
- sk_memory_allocated_sub(sk,
- sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT);
- sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1;
+ amount >>= SK_MEM_QUANTUM_SHIFT;
+ sk_memory_allocated_sub(sk, amount);
+ sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
if (sk_under_memory_pressure(sk) &&
(sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
diff --git a/net/core/stream.c b/net/core/stream.c
index 301c05f26060..d70f77a0c889 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -119,6 +119,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
int err = 0;
long vm_wait = 0;
long current_timeo = *timeo_p;
+ bool noblock = (*timeo_p ? false : true);
DEFINE_WAIT(wait);
if (sk_stream_memory_free(sk))
@@ -131,8 +132,11 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
- if (!*timeo_p)
+ if (!*timeo_p) {
+ if (noblock)
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
goto do_nonblock;
+ }
if (signal_pending(current))
goto do_interrupted;
clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
diff --git a/net/core/utils.c b/net/core/utils.c
index 7b803884c162..a7732a068043 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -304,13 +304,15 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
__be32 from, __be32 to, int pseudohdr)
{
if (skb->ip_summed != CHECKSUM_PARTIAL) {
- *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), from),
- to));
+ csum_replace4(sum, from, to);
if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr)
- skb->csum = ~csum_add(csum_sub(~(skb->csum), from), to);
+ skb->csum = ~csum_add(csum_sub(~(skb->csum),
+ (__force __wsum)from),
+ (__force __wsum)to);
} else if (pseudohdr)
- *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), from),
- to));
+ *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum),
+ (__force __wsum)from),
+ (__force __wsum)to));
}
EXPORT_SYMBOL(inet_proto_csum_replace4);
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 754484b3cd0e..675cf94e04f8 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -468,10 +468,10 @@ static struct proto dn_proto = {
.obj_size = sizeof(struct dn_sock),
};
-static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gfp)
+static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gfp, int kern)
{
struct dn_scp *scp;
- struct sock *sk = sk_alloc(net, PF_DECnet, gfp, &dn_proto);
+ struct sock *sk = sk_alloc(net, PF_DECnet, gfp, &dn_proto, kern);
if (!sk)
goto out;
@@ -693,7 +693,7 @@ static int dn_create(struct net *net, struct socket *sock, int protocol,
}
- if ((sk = dn_alloc_sock(net, sock, GFP_KERNEL)) == NULL)
+ if ((sk = dn_alloc_sock(net, sock, GFP_KERNEL, kern)) == NULL)
return -ENOBUFS;
sk->sk_protocol = protocol;
@@ -1096,7 +1096,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags)
cb = DN_SKB_CB(skb);
sk->sk_ack_backlog--;
- newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation);
+ newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0);
if (newsk == NULL) {
release_sock(sk);
kfree_skb(skb);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 827cda560a55..04ffad311704 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -345,6 +345,24 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state)
return ret;
}
+static int dsa_slave_port_attr_set(struct net_device *dev,
+ struct switchdev_attr *attr)
+{
+ int ret = 0;
+
+ switch (attr->id) {
+ case SWITCHDEV_ATTR_PORT_STP_STATE:
+ if (attr->trans == SWITCHDEV_TRANS_COMMIT)
+ ret = dsa_slave_stp_update(dev, attr->u.stp_state);
+ break;
+ default:
+ ret = -EOPNOTSUPP;
+ break;
+ }
+
+ return ret;
+}
+
static int dsa_slave_bridge_port_join(struct net_device *dev,
struct net_device *br)
{
@@ -382,14 +400,20 @@ static int dsa_slave_bridge_port_leave(struct net_device *dev)
return ret;
}
-static int dsa_slave_parent_id_get(struct net_device *dev,
- struct netdev_phys_item_id *psid)
+static int dsa_slave_port_attr_get(struct net_device *dev,
+ struct switchdev_attr *attr)
{
struct dsa_slave_priv *p = netdev_priv(dev);
struct dsa_switch *ds = p->parent;
- psid->id_len = sizeof(ds->index);
- memcpy(&psid->id, &ds->index, psid->id_len);
+ switch (attr->id) {
+ case SWITCHDEV_ATTR_PORT_PARENT_ID:
+ attr->u.ppid.id_len = sizeof(ds->index);
+ memcpy(&attr->u.ppid.id, &ds->index, attr->u.ppid.id_len);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
return 0;
}
@@ -675,9 +699,9 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
.ndo_get_iflink = dsa_slave_get_iflink,
};
-static const struct swdev_ops dsa_slave_swdev_ops = {
- .swdev_parent_id_get = dsa_slave_parent_id_get,
- .swdev_port_stp_update = dsa_slave_stp_update,
+static const struct switchdev_ops dsa_slave_switchdev_ops = {
+ .switchdev_port_attr_get = dsa_slave_port_attr_get,
+ .switchdev_port_attr_set = dsa_slave_port_attr_set,
};
static void dsa_slave_adjust_link(struct net_device *dev)
@@ -810,12 +834,19 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
return 0;
}
+static struct lock_class_key dsa_slave_netdev_xmit_lock_key;
+static void dsa_slave_set_lockdep_class_one(struct net_device *dev,
+ struct netdev_queue *txq,
+ void *_unused)
+{
+ lockdep_set_class(&txq->_xmit_lock,
+ &dsa_slave_netdev_xmit_lock_key);
+}
+
int dsa_slave_suspend(struct net_device *slave_dev)
{
struct dsa_slave_priv *p = netdev_priv(slave_dev);
- netif_device_detach(slave_dev);
-
if (p->phy) {
phy_stop(p->phy);
p->old_pause = -1;
@@ -859,7 +890,10 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
eth_hw_addr_inherit(slave_dev, master);
slave_dev->tx_queue_len = 0;
slave_dev->netdev_ops = &dsa_slave_netdev_ops;
- slave_dev->swdev_ops = &dsa_slave_swdev_ops;
+ slave_dev->switchdev_ops = &dsa_slave_switchdev_ops;
+
+ netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one,
+ NULL);
SET_NETDEV_DEV(slave_dev, parent);
slave_dev->dev.of_node = ds->pd->port_dn[port];
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index f3bad41d725f..77e0f0e7a88e 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -58,6 +58,7 @@
#include <net/ipv6.h>
#include <net/ip.h>
#include <net/dsa.h>
+#include <net/flow_dissector.h>
#include <linux/uaccess.h>
__setup("ether=", netdev_boot_setup);
@@ -130,9 +131,9 @@ u32 eth_get_headlen(void *data, unsigned int len)
return len;
/* parse any remaining L2/L3 headers, check for L4 */
- if (!__skb_flow_dissect(NULL, &keys, data,
- eth->h_proto, sizeof(*eth), len))
- return max_t(u32, keys.thoff, sizeof(*eth));
+ if (!skb_flow_dissect_flow_keys_buf(&keys, data, eth->h_proto,
+ sizeof(*eth), len))
+ return max_t(u32, keys.control.thoff, sizeof(*eth));
/* parse for any L4 headers */
return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len);
@@ -156,10 +157,11 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
skb->dev = dev;
skb_reset_mac_header(skb);
+
+ eth = (struct ethhdr *)skb->data;
skb_pull_inline(skb, ETH_HLEN);
- eth = eth_hdr(skb);
- if (unlikely(is_multicast_ether_addr(eth->h_dest))) {
+ if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) {
if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
skb->pkt_type = PACKET_BROADCAST;
else
@@ -178,7 +180,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
if (unlikely(netdev_uses_dsa(dev)))
return htons(ETH_P_XDSA);
- if (likely(ntohs(eth->h_proto) >= ETH_P_802_3_MIN))
+ if (likely(eth_proto_is_802_3(eth->h_proto)))
return eth->h_proto;
/*
@@ -468,6 +470,7 @@ EXPORT_SYMBOL(eth_gro_complete);
static struct packet_offload eth_packet_offload __read_mostly = {
.type = cpu_to_be16(ETH_P_TEB),
+ .priority = 10,
.callbacks = {
.gro_receive = eth_gro_receive,
.gro_complete = eth_gro_complete,
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 0ae5822ef944..f20a387a1011 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -55,27 +55,6 @@
LIST_HEAD(lowpan_devices);
static int lowpan_open_count;
-static __le16 lowpan_get_pan_id(const struct net_device *dev)
-{
- struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
-
- return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev);
-}
-
-static __le16 lowpan_get_short_addr(const struct net_device *dev)
-{
- struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
-
- return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev);
-}
-
-static u8 lowpan_get_dsn(const struct net_device *dev)
-{
- struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
-
- return ieee802154_mlme_ops(real_dev)->get_dsn(real_dev);
-}
-
static struct header_ops lowpan_header_ops = {
.create = lowpan_header_create,
};
@@ -103,12 +82,6 @@ static const struct net_device_ops lowpan_netdev_ops = {
.ndo_start_xmit = lowpan_xmit,
};
-static struct ieee802154_mlme_ops lowpan_mlme = {
- .get_pan_id = lowpan_get_pan_id,
- .get_short_addr = lowpan_get_short_addr,
- .get_dsn = lowpan_get_dsn,
-};
-
static void lowpan_setup(struct net_device *dev)
{
dev->addr_len = IEEE802154_ADDR_LEN;
@@ -124,7 +97,6 @@ static void lowpan_setup(struct net_device *dev)
dev->netdev_ops = &lowpan_netdev_ops;
dev->header_ops = &lowpan_header_ops;
- dev->ml_priv = &lowpan_mlme;
dev->destructor = free_netdev;
dev->features |= NETIF_F_NETNS_LOCAL;
}
diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c
index 2349070bd534..98acf7319754 100644
--- a/net/ieee802154/6lowpan/tx.c
+++ b/net/ieee802154/6lowpan/tx.c
@@ -207,7 +207,7 @@ static int lowpan_header(struct sk_buff *skb, struct net_device *dev)
/* prepare wpan address data */
sa.mode = IEEE802154_ADDR_LONG;
- sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
+ sa.pan_id = lowpan_dev_info(dev)->real_dev->ieee802154_ptr->pan_id;
sa.extended_addr = ieee802154_devaddr_from_raw(saddr);
/* intra-PAN communications */
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index 2ee00e8a0308..b0248e934230 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -121,8 +121,6 @@ wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size)
/* atomic_inc_return makes it start at 1, make it start at 0 */
rdev->wpan_phy_idx--;
- mutex_init(&rdev->wpan_phy.pib_lock);
-
INIT_LIST_HEAD(&rdev->wpan_dev_list);
device_initialize(&rdev->wpan_phy.dev);
dev_set_name(&rdev->wpan_phy.dev, PHY_NAME "%d", rdev->wpan_phy_idx);
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 2b4955d7aae5..3503c38954f9 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -97,8 +97,10 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
BUG_ON(!phy);
get_device(&phy->dev);
- short_addr = ops->get_short_addr(dev);
- pan_id = ops->get_pan_id(dev);
+ rtnl_lock();
+ short_addr = dev->ieee802154_ptr->short_addr;
+ pan_id = dev->ieee802154_ptr->pan_id;
+ rtnl_unlock();
if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) ||
@@ -117,12 +119,12 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
rtnl_unlock();
if (nla_put_s8(msg, IEEE802154_ATTR_TXPOWER,
- params.transmit_power) ||
+ params.transmit_power / 100) ||
nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, params.lbt) ||
nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE,
params.cca.mode) ||
nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL,
- params.cca_ed_level) ||
+ params.cca_ed_level / 100) ||
nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES,
params.csma_retries) ||
nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE,
@@ -166,10 +168,7 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info)
if (!dev)
return NULL;
- /* Check on mtu is currently a hacked solution because lowpan
- * and wpan have the same ARPHRD type.
- */
- if (dev->type != ARPHRD_IEEE802154 || dev->mtu != IEEE802154_MTU) {
+ if (dev->type != ARPHRD_IEEE802154) {
dev_put(dev);
return NULL;
}
@@ -244,7 +243,9 @@ int ieee802154_associate_resp(struct sk_buff *skb, struct genl_info *info)
addr.mode = IEEE802154_ADDR_LONG;
addr.extended_addr = nla_get_hwaddr(
info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]);
- addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
+ rtnl_lock();
+ addr.pan_id = dev->ieee802154_ptr->pan_id;
+ rtnl_unlock();
ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr,
nla_get_shortaddr(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]),
@@ -281,7 +282,9 @@ int ieee802154_disassociate_req(struct sk_buff *skb, struct genl_info *info)
addr.short_addr = nla_get_shortaddr(
info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]);
}
- addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
+ rtnl_lock();
+ addr.pan_id = dev->ieee802154_ptr->pan_id;
+ rtnl_unlock();
ret = ieee802154_mlme_ops(dev)->disassoc_req(dev, &addr,
nla_get_u8(info->attrs[IEEE802154_ATTR_REASON]));
@@ -449,11 +452,7 @@ int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb)
idx = 0;
for_each_netdev(net, dev) {
- /* Check on mtu is currently a hacked solution because lowpan
- * and wpan have the same ARPHRD type.
- */
- if (idx < s_idx || dev->type != ARPHRD_IEEE802154 ||
- dev->mtu != IEEE802154_MTU)
+ if (idx < s_idx || dev->type != ARPHRD_IEEE802154)
goto cont;
if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).portid,
@@ -510,7 +509,7 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
ops->get_mac_params(dev, &params);
if (info->attrs[IEEE802154_ATTR_TXPOWER])
- params.transmit_power = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]);
+ params.transmit_power = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]) * 100;
if (info->attrs[IEEE802154_ATTR_LBT_ENABLED])
params.lbt = nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]);
@@ -519,7 +518,7 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
params.cca.mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]);
if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL])
- params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]);
+ params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) * 100;
if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES])
params.csma_retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]);
@@ -783,11 +782,7 @@ ieee802154_llsec_dump_table(struct sk_buff *skb, struct netlink_callback *cb,
int rc;
for_each_netdev(net, dev) {
- /* Check on mtu is currently a hacked solution because lowpan
- * and wpan have the same ARPHRD type.
- */
- if (idx < first_dev || dev->type != ARPHRD_IEEE802154 ||
- dev->mtu != IEEE802154_MTU)
+ if (idx < first_dev || dev->type != ARPHRD_IEEE802154)
goto skip;
data.ops = ieee802154_mlme_ops(dev);
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 346c6665d25e..77d73014bde3 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -50,26 +50,26 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
if (!hdr)
goto out;
- mutex_lock(&phy->pib_lock);
+ rtnl_lock();
if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) ||
nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) ||
nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel))
goto nla_put_failure;
for (i = 0; i < 32; i++) {
- if (phy->channels_supported[i])
- buf[pages++] = phy->channels_supported[i] | (i << 27);
+ if (phy->supported.channels[i])
+ buf[pages++] = phy->supported.channels[i] | (i << 27);
}
if (pages &&
nla_put(msg, IEEE802154_ATTR_CHANNEL_PAGE_LIST,
pages * sizeof(uint32_t), buf))
goto nla_put_failure;
- mutex_unlock(&phy->pib_lock);
+ rtnl_unlock();
kfree(buf);
genlmsg_end(msg, hdr);
return 0;
nla_put_failure:
- mutex_unlock(&phy->pib_lock);
+ rtnl_unlock();
genlmsg_cancel(msg, hdr);
out:
kfree(buf);
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index f3c12f6a4a39..7dbb1f4ce7df 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -207,10 +207,11 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
[NL802154_ATTR_PAGE] = { .type = NLA_U8, },
[NL802154_ATTR_CHANNEL] = { .type = NLA_U8, },
- [NL802154_ATTR_TX_POWER] = { .type = NLA_S8, },
+ [NL802154_ATTR_TX_POWER] = { .type = NLA_S32, },
[NL802154_ATTR_CCA_MODE] = { .type = NLA_U32, },
[NL802154_ATTR_CCA_OPT] = { .type = NLA_U32, },
+ [NL802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, },
[NL802154_ATTR_SUPPORTED_CHANNEL] = { .type = NLA_U32, },
@@ -225,6 +226,8 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
[NL802154_ATTR_MAX_FRAME_RETRIES] = { .type = NLA_S8, },
[NL802154_ATTR_LBT_MODE] = { .type = NLA_U8, },
+
+ [NL802154_ATTR_WPAN_PHY_CAPS] = { .type = NLA_NESTED },
};
/* message building helper */
@@ -236,6 +239,28 @@ static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq,
}
static int
+nl802154_put_flags(struct sk_buff *msg, int attr, u32 mask)
+{
+ struct nlattr *nl_flags = nla_nest_start(msg, attr);
+ int i;
+
+ if (!nl_flags)
+ return -ENOBUFS;
+
+ i = 0;
+ while (mask) {
+ if ((mask & 1) && nla_put_flag(msg, i))
+ return -ENOBUFS;
+
+ mask >>= 1;
+ i++;
+ }
+
+ nla_nest_end(msg, nl_flags);
+ return 0;
+}
+
+static int
nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev,
struct sk_buff *msg)
{
@@ -248,7 +273,7 @@ nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev,
for (page = 0; page <= IEEE802154_MAX_PAGE; page++) {
if (nla_put_u32(msg, NL802154_ATTR_SUPPORTED_CHANNEL,
- rdev->wpan_phy.channels_supported[page]))
+ rdev->wpan_phy.supported.channels[page]))
return -ENOBUFS;
}
nla_nest_end(msg, nl_page);
@@ -256,6 +281,92 @@ nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev,
return 0;
}
+static int
+nl802154_put_capabilities(struct sk_buff *msg,
+ struct cfg802154_registered_device *rdev)
+{
+ const struct wpan_phy_supported *caps = &rdev->wpan_phy.supported;
+ struct nlattr *nl_caps, *nl_channels;
+ int i;
+
+ nl_caps = nla_nest_start(msg, NL802154_ATTR_WPAN_PHY_CAPS);
+ if (!nl_caps)
+ return -ENOBUFS;
+
+ nl_channels = nla_nest_start(msg, NL802154_CAP_ATTR_CHANNELS);
+ if (!nl_channels)
+ return -ENOBUFS;
+
+ for (i = 0; i <= IEEE802154_MAX_PAGE; i++) {
+ if (caps->channels[i]) {
+ if (nl802154_put_flags(msg, i, caps->channels[i]))
+ return -ENOBUFS;
+ }
+ }
+
+ nla_nest_end(msg, nl_channels);
+
+ if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) {
+ struct nlattr *nl_ed_lvls;
+
+ nl_ed_lvls = nla_nest_start(msg,
+ NL802154_CAP_ATTR_CCA_ED_LEVELS);
+ if (!nl_ed_lvls)
+ return -ENOBUFS;
+
+ for (i = 0; i < caps->cca_ed_levels_size; i++) {
+ if (nla_put_s32(msg, i, caps->cca_ed_levels[i]))
+ return -ENOBUFS;
+ }
+
+ nla_nest_end(msg, nl_ed_lvls);
+ }
+
+ if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) {
+ struct nlattr *nl_tx_pwrs;
+
+ nl_tx_pwrs = nla_nest_start(msg, NL802154_CAP_ATTR_TX_POWERS);
+ if (!nl_tx_pwrs)
+ return -ENOBUFS;
+
+ for (i = 0; i < caps->tx_powers_size; i++) {
+ if (nla_put_s32(msg, i, caps->tx_powers[i]))
+ return -ENOBUFS;
+ }
+
+ nla_nest_end(msg, nl_tx_pwrs);
+ }
+
+ if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) {
+ if (nl802154_put_flags(msg, NL802154_CAP_ATTR_CCA_MODES,
+ caps->cca_modes) ||
+ nl802154_put_flags(msg, NL802154_CAP_ATTR_CCA_OPTS,
+ caps->cca_opts))
+ return -ENOBUFS;
+ }
+
+ if (nla_put_u8(msg, NL802154_CAP_ATTR_MIN_MINBE, caps->min_minbe) ||
+ nla_put_u8(msg, NL802154_CAP_ATTR_MAX_MINBE, caps->max_minbe) ||
+ nla_put_u8(msg, NL802154_CAP_ATTR_MIN_MAXBE, caps->min_maxbe) ||
+ nla_put_u8(msg, NL802154_CAP_ATTR_MAX_MAXBE, caps->max_maxbe) ||
+ nla_put_u8(msg, NL802154_CAP_ATTR_MIN_CSMA_BACKOFFS,
+ caps->min_csma_backoffs) ||
+ nla_put_u8(msg, NL802154_CAP_ATTR_MAX_CSMA_BACKOFFS,
+ caps->max_csma_backoffs) ||
+ nla_put_s8(msg, NL802154_CAP_ATTR_MIN_FRAME_RETRIES,
+ caps->min_frame_retries) ||
+ nla_put_s8(msg, NL802154_CAP_ATTR_MAX_FRAME_RETRIES,
+ caps->max_frame_retries) ||
+ nl802154_put_flags(msg, NL802154_CAP_ATTR_IFTYPES,
+ caps->iftypes) ||
+ nla_put_u32(msg, NL802154_CAP_ATTR_LBT, caps->lbt))
+ return -ENOBUFS;
+
+ nla_nest_end(msg, nl_caps);
+
+ return 0;
+}
+
static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev,
enum nl802154_commands cmd,
struct sk_buff *msg, u32 portid, u32 seq,
@@ -286,23 +397,38 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev,
rdev->wpan_phy.current_channel))
goto nla_put_failure;
- /* supported channels array */
+ /* TODO remove this behaviour, we still keep support it for a while
+ * so users can change the behaviour to the new one.
+ */
if (nl802154_send_wpan_phy_channels(rdev, msg))
goto nla_put_failure;
/* cca mode */
- if (nla_put_u32(msg, NL802154_ATTR_CCA_MODE,
- rdev->wpan_phy.cca.mode))
- goto nla_put_failure;
+ if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) {
+ if (nla_put_u32(msg, NL802154_ATTR_CCA_MODE,
+ rdev->wpan_phy.cca.mode))
+ goto nla_put_failure;
+
+ if (rdev->wpan_phy.cca.mode == NL802154_CCA_ENERGY_CARRIER) {
+ if (nla_put_u32(msg, NL802154_ATTR_CCA_OPT,
+ rdev->wpan_phy.cca.opt))
+ goto nla_put_failure;
+ }
+ }
- if (rdev->wpan_phy.cca.mode == NL802154_CCA_ENERGY_CARRIER) {
- if (nla_put_u32(msg, NL802154_ATTR_CCA_OPT,
- rdev->wpan_phy.cca.opt))
+ if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) {
+ if (nla_put_s32(msg, NL802154_ATTR_TX_POWER,
+ rdev->wpan_phy.transmit_power))
goto nla_put_failure;
}
- if (nla_put_s8(msg, NL802154_ATTR_TX_POWER,
- rdev->wpan_phy.transmit_power))
+ if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) {
+ if (nla_put_s32(msg, NL802154_ATTR_CCA_ED_LEVEL,
+ rdev->wpan_phy.cca_ed_level))
+ goto nla_put_failure;
+ }
+
+ if (nl802154_put_capabilities(msg, rdev))
goto nla_put_failure;
finish:
@@ -575,7 +701,8 @@ static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info)
if (info->attrs[NL802154_ATTR_IFTYPE]) {
type = nla_get_u32(info->attrs[NL802154_ATTR_IFTYPE]);
- if (type > NL802154_IFTYPE_MAX)
+ if (type > NL802154_IFTYPE_MAX ||
+ !(rdev->wpan_phy.supported.iftypes & BIT(type)))
return -EINVAL;
}
@@ -625,7 +752,8 @@ static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info)
channel = nla_get_u8(info->attrs[NL802154_ATTR_CHANNEL]);
/* check 802.15.4 constraints */
- if (page > IEEE802154_MAX_PAGE || channel > IEEE802154_MAX_CHANNEL)
+ if (page > IEEE802154_MAX_PAGE || channel > IEEE802154_MAX_CHANNEL ||
+ !(rdev->wpan_phy.supported.channels[page] & BIT(channel)))
return -EINVAL;
return rdev_set_channel(rdev, page, channel);
@@ -636,12 +764,17 @@ static int nl802154_set_cca_mode(struct sk_buff *skb, struct genl_info *info)
struct cfg802154_registered_device *rdev = info->user_ptr[0];
struct wpan_phy_cca cca;
+ if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE))
+ return -EOPNOTSUPP;
+
if (!info->attrs[NL802154_ATTR_CCA_MODE])
return -EINVAL;
cca.mode = nla_get_u32(info->attrs[NL802154_ATTR_CCA_MODE]);
/* checking 802.15.4 constraints */
- if (cca.mode < NL802154_CCA_ENERGY || cca.mode > NL802154_CCA_ATTR_MAX)
+ if (cca.mode < NL802154_CCA_ENERGY ||
+ cca.mode > NL802154_CCA_ATTR_MAX ||
+ !(rdev->wpan_phy.supported.cca_modes & BIT(cca.mode)))
return -EINVAL;
if (cca.mode == NL802154_CCA_ENERGY_CARRIER) {
@@ -649,13 +782,58 @@ static int nl802154_set_cca_mode(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
cca.opt = nla_get_u32(info->attrs[NL802154_ATTR_CCA_OPT]);
- if (cca.opt > NL802154_CCA_OPT_ATTR_MAX)
+ if (cca.opt > NL802154_CCA_OPT_ATTR_MAX ||
+ !(rdev->wpan_phy.supported.cca_opts & BIT(cca.opt)))
return -EINVAL;
}
return rdev_set_cca_mode(rdev, &cca);
}
+static int nl802154_set_cca_ed_level(struct sk_buff *skb, struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ s32 ed_level;
+ int i;
+
+ if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL))
+ return -EOPNOTSUPP;
+
+ if (!info->attrs[NL802154_ATTR_CCA_ED_LEVEL])
+ return -EINVAL;
+
+ ed_level = nla_get_s32(info->attrs[NL802154_ATTR_CCA_ED_LEVEL]);
+
+ for (i = 0; i < rdev->wpan_phy.supported.cca_ed_levels_size; i++) {
+ if (ed_level == rdev->wpan_phy.supported.cca_ed_levels[i])
+ return rdev_set_cca_ed_level(rdev, ed_level);
+ }
+
+ return -EINVAL;
+}
+
+static int nl802154_set_tx_power(struct sk_buff *skb, struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ s32 power;
+ int i;
+
+ if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER))
+ return -EOPNOTSUPP;
+
+ if (!info->attrs[NL802154_ATTR_TX_POWER])
+ return -EINVAL;
+
+ power = nla_get_s32(info->attrs[NL802154_ATTR_TX_POWER]);
+
+ for (i = 0; i < rdev->wpan_phy.supported.tx_powers_size; i++) {
+ if (power == rdev->wpan_phy.supported.tx_powers[i])
+ return rdev_set_tx_power(rdev, power);
+ }
+
+ return -EINVAL;
+}
+
static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info)
{
struct cfg802154_registered_device *rdev = info->user_ptr[0];
@@ -668,14 +846,22 @@ static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info)
return -EBUSY;
/* don't change address fields on monitor */
- if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
- return -EINVAL;
-
- if (!info->attrs[NL802154_ATTR_PAN_ID])
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR ||
+ !info->attrs[NL802154_ATTR_PAN_ID])
return -EINVAL;
pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]);
+ /* TODO
+ * I am not sure about to check here on broadcast pan_id.
+ * Broadcast is a valid setting, comment from 802.15.4:
+ * If this value is 0xffff, the device is not associated.
+ *
+ * This could useful to simple deassociate an device.
+ */
+ if (pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST))
+ return -EINVAL;
+
return rdev_set_pan_id(rdev, wpan_dev, pan_id);
}
@@ -691,14 +877,27 @@ static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info)
return -EBUSY;
/* don't change address fields on monitor */
- if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
- return -EINVAL;
-
- if (!info->attrs[NL802154_ATTR_SHORT_ADDR])
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR ||
+ !info->attrs[NL802154_ATTR_SHORT_ADDR])
return -EINVAL;
short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]);
+ /* TODO
+ * I am not sure about to check here on broadcast short_addr.
+ * Broadcast is a valid setting, comment from 802.15.4:
+ * A value of 0xfffe indicates that the device has
+ * associated but has not been allocated an address. A
+ * value of 0xffff indicates that the device does not
+ * have a short address.
+ *
+ * I think we should allow to set these settings but
+ * don't allow to allow socket communication with it.
+ */
+ if (short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC) ||
+ short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST))
+ return -EINVAL;
+
return rdev_set_short_addr(rdev, wpan_dev, short_addr);
}
@@ -722,7 +921,11 @@ nl802154_set_backoff_exponent(struct sk_buff *skb, struct genl_info *info)
max_be = nla_get_u8(info->attrs[NL802154_ATTR_MAX_BE]);
/* check 802.15.4 constraints */
- if (max_be < 3 || max_be > 8 || min_be > max_be)
+ if (min_be < rdev->wpan_phy.supported.min_minbe ||
+ min_be > rdev->wpan_phy.supported.max_minbe ||
+ max_be < rdev->wpan_phy.supported.min_maxbe ||
+ max_be > rdev->wpan_phy.supported.max_maxbe ||
+ min_be > max_be)
return -EINVAL;
return rdev_set_backoff_exponent(rdev, wpan_dev, min_be, max_be);
@@ -747,7 +950,8 @@ nl802154_set_max_csma_backoffs(struct sk_buff *skb, struct genl_info *info)
info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS]);
/* check 802.15.4 constraints */
- if (max_csma_backoffs > 5)
+ if (max_csma_backoffs < rdev->wpan_phy.supported.min_csma_backoffs ||
+ max_csma_backoffs > rdev->wpan_phy.supported.max_csma_backoffs)
return -EINVAL;
return rdev_set_max_csma_backoffs(rdev, wpan_dev, max_csma_backoffs);
@@ -771,7 +975,8 @@ nl802154_set_max_frame_retries(struct sk_buff *skb, struct genl_info *info)
info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES]);
/* check 802.15.4 constraints */
- if (max_frame_retries < -1 || max_frame_retries > 7)
+ if (max_frame_retries < rdev->wpan_phy.supported.min_frame_retries ||
+ max_frame_retries > rdev->wpan_phy.supported.max_frame_retries)
return -EINVAL;
return rdev_set_max_frame_retries(rdev, wpan_dev, max_frame_retries);
@@ -791,6 +996,9 @@ static int nl802154_set_lbt_mode(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
mode = !!nla_get_u8(info->attrs[NL802154_ATTR_LBT_MODE]);
+ if (!wpan_phy_supported_bool(mode, rdev->wpan_phy.supported.lbt))
+ return -EINVAL;
+
return rdev_set_lbt_mode(rdev, wpan_dev, mode);
}
@@ -937,6 +1145,22 @@ static const struct genl_ops nl802154_ops[] = {
NL802154_FLAG_NEED_RTNL,
},
{
+ .cmd = NL802154_CMD_SET_CCA_ED_LEVEL,
+ .doit = nl802154_set_cca_ed_level,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_SET_TX_POWER,
+ .doit = nl802154_set_tx_power,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
.cmd = NL802154_CMD_SET_PAN_ID,
.doit = nl802154_set_pan_id,
.policy = nl802154_policy,
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 7b5a9dd94fe5..b2155a123f6c 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -75,6 +75,29 @@ rdev_set_cca_mode(struct cfg802154_registered_device *rdev,
}
static inline int
+rdev_set_cca_ed_level(struct cfg802154_registered_device *rdev, s32 ed_level)
+{
+ int ret;
+
+ trace_802154_rdev_set_cca_ed_level(&rdev->wpan_phy, ed_level);
+ ret = rdev->ops->set_cca_ed_level(&rdev->wpan_phy, ed_level);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
+}
+
+static inline int
+rdev_set_tx_power(struct cfg802154_registered_device *rdev,
+ s32 power)
+{
+ int ret;
+
+ trace_802154_rdev_set_tx_power(&rdev->wpan_phy, power);
+ ret = rdev->ops->set_tx_power(&rdev->wpan_phy, power);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
+}
+
+static inline int
rdev_set_pan_id(struct cfg802154_registered_device *rdev,
struct wpan_dev *wpan_dev, __le16 pan_id)
{
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index b60c65f70346..02abef2c1621 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -64,10 +64,8 @@ ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr)
if (tmp->type != ARPHRD_IEEE802154)
continue;
- pan_id = ieee802154_mlme_ops(tmp)->get_pan_id(tmp);
- short_addr =
- ieee802154_mlme_ops(tmp)->get_short_addr(tmp);
-
+ pan_id = tmp->ieee802154_ptr->pan_id;
+ short_addr = tmp->ieee802154_ptr->short_addr;
if (pan_id == addr->pan_id &&
short_addr == addr->short_addr) {
dev = tmp;
@@ -228,15 +226,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len)
goto out;
}
- if (dev->type != ARPHRD_IEEE802154) {
- err = -ENODEV;
- goto out_put;
- }
-
sk->sk_bound_dev_if = dev->ifindex;
sk_dst_reset(sk);
-out_put:
dev_put(dev);
out:
release_sock(sk);
@@ -286,7 +278,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
if (size > mtu) {
pr_debug("size = %Zu, mtu = %u\n", size, mtu);
- err = -EINVAL;
+ err = -EMSGSIZE;
goto out_dev;
}
@@ -797,9 +789,9 @@ static int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb)
/* Data frame processing */
BUG_ON(dev->type != ARPHRD_IEEE802154);
- pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
- short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev);
- hw_addr = ieee802154_devaddr_from_raw(dev->dev_addr);
+ pan_id = dev->ieee802154_ptr->pan_id;
+ short_addr = dev->ieee802154_ptr->short_addr;
+ hw_addr = dev->ieee802154_ptr->extended_addr;
read_lock(&dgram_lock);
sk_for_each(sk, &dgram_head) {
@@ -1014,7 +1006,7 @@ static int ieee802154_create(struct net *net, struct socket *sock,
}
rc = -ENOMEM;
- sk = sk_alloc(net, PF_IEEE802154, GFP_KERNEL, proto);
+ sk = sk_alloc(net, PF_IEEE802154, GFP_KERNEL, proto, kern);
if (!sk)
goto out;
rc = 0;
diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h
index 5ac25eb6ed17..73eb7605c1eb 100644
--- a/net/ieee802154/trace.h
+++ b/net/ieee802154/trace.h
@@ -1,4 +1,4 @@
-/* Based on net/wireless/tracing.h */
+/* Based on net/wireless/trace.h */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM cfg802154
@@ -93,6 +93,21 @@ TRACE_EVENT(802154_rdev_set_channel,
__entry->page, __entry->channel)
);
+TRACE_EVENT(802154_rdev_set_tx_power,
+ TP_PROTO(struct wpan_phy *wpan_phy, s32 power),
+ TP_ARGS(wpan_phy, power),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ __field(s32, power)
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ __entry->power = power;
+ ),
+ TP_printk(WPAN_PHY_PR_FMT ", power: %d", WPAN_PHY_PR_ARG,
+ __entry->power)
+);
+
TRACE_EVENT(802154_rdev_set_cca_mode,
TP_PROTO(struct wpan_phy *wpan_phy, const struct wpan_phy_cca *cca),
TP_ARGS(wpan_phy, cca),
@@ -108,6 +123,21 @@ TRACE_EVENT(802154_rdev_set_cca_mode,
WPAN_CCA_PR_ARG)
);
+TRACE_EVENT(802154_rdev_set_cca_ed_level,
+ TP_PROTO(struct wpan_phy *wpan_phy, s32 ed_level),
+ TP_ARGS(wpan_phy, ed_level),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ __field(s32, ed_level)
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ __entry->ed_level = ed_level;
+ ),
+ TP_printk(WPAN_PHY_PR_FMT ", ed_level: %d", WPAN_PHY_PR_ARG,
+ __entry->ed_level)
+);
+
DECLARE_EVENT_CLASS(802154_le16_template,
TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
__le16 le16arg),
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index bd2901604842..6fb3c90ad726 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -331,8 +331,8 @@ config NET_FOU_IP_TUNNELS
When this option is enabled IP tunnels can be configured to use
FOU or GUE encapsulation.
-config GENEVE
- tristate "Generic Network Virtualization Encapsulation (Geneve)"
+config GENEVE_CORE
+ tristate "Generic Network Virtualization Encapsulation library"
depends on INET
select NET_UDP_TUNNEL
---help---
@@ -615,6 +615,22 @@ config TCP_CONG_DCTCP
For further details see:
http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+config TCP_CONG_CDG
+ tristate "CAIA Delay-Gradient (CDG)"
+ default n
+ ---help---
+ CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies
+ the TCP sender in order to:
+
+ o Use the delay gradient as a congestion signal.
+ o Back off with an average probability that is independent of the RTT.
+ o Coexist with flows that use loss-based congestion control.
+ o Tolerate packet loss unrelated to congestion.
+
+ For further details see:
+ D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
+ delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg
+
choice
prompt "Default TCP congestion control"
default DEFAULT_CUBIC
@@ -646,6 +662,9 @@ choice
config DEFAULT_DCTCP
bool "DCTCP" if TCP_CONG_DCTCP=y
+ config DEFAULT_CDG
+ bool "CDG" if TCP_CONG_CDG=y
+
config DEFAULT_RENO
bool "Reno"
endchoice
@@ -668,6 +687,7 @@ config DEFAULT_TCP_CONG
default "veno" if DEFAULT_VENO
default "reno" if DEFAULT_RENO
default "dctcp" if DEFAULT_DCTCP
+ default "cdg" if DEFAULT_CDG
default "cubic"
config TCP_MD5SIG
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 518c04ed666e..efc43f300b8c 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -42,6 +42,7 @@ obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
+obj-$(CONFIG_TCP_CONG_CDG) += tcp_cdg.o
obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
obj-$(CONFIG_TCP_CONG_DCTCP) += tcp_dctcp.o
obj-$(CONFIG_TCP_CONG_WESTWOOD) += tcp_westwood.o
@@ -56,7 +57,7 @@ obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
-obj-$(CONFIG_GENEVE) += geneve.o
+obj-$(CONFIG_GENEVE_CORE) += geneve_core.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
xfrm4_output.o xfrm4_protocol.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8b47a4d79d04..cc858ef44451 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -317,7 +317,7 @@ lookup_protocol:
WARN_ON(!answer_prot->slab);
err = -ENOBUFS;
- sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
+ sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern);
if (!sk)
goto out;
@@ -488,7 +488,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
inet->inet_saddr = 0; /* Use device */
/* Make sure we are allowed to bind here. */
- if (sk->sk_prot->get_port(sk, snum)) {
+ if ((snum || !inet->bind_address_no_port) &&
+ sk->sk_prot->get_port(sk, snum)) {
inet->inet_saddr = inet->inet_rcv_saddr = 0;
err = -EADDRINUSE;
goto out_release_sock;
@@ -1430,7 +1431,7 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family,
struct net *net)
{
struct socket *sock;
- int rc = sock_create_kern(family, type, protocol, &sock);
+ int rc = sock_create_kern(net, family, type, protocol, &sock);
if (rc == 0) {
*sk = sock->sk;
@@ -1440,8 +1441,6 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family,
* we do not wish this socket to see incoming packets.
*/
(*sk)->sk_prot->unhash(*sk);
-
- sk_change_net(*sk, net);
}
return rc;
}
@@ -1597,7 +1596,7 @@ static __net_init int inet_init_net(struct net *net)
*/
seqlock_init(&net->ipv4.ip_local_ports.lock);
net->ipv4.ip_local_ports.range[0] = 32768;
- net->ipv4.ip_local_ports.range[1] = 61000;
+ net->ipv4.ip_local_ports.range[1] = 60999;
seqlock_init(&net->ipv4.ping_group_range.lock);
/*
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 8d695b6659c7..28ec3c1823bf 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -713,8 +713,6 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
struct hlist_head *dest;
unsigned int new_hash;
- hlist_del(&fi->fib_hash);
-
new_hash = fib_info_hashfn(fi);
dest = &new_info_hash[new_hash];
hlist_add_head(&fi->fib_hash, dest);
@@ -731,8 +729,6 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
struct hlist_head *ldest;
unsigned int new_hash;
- hlist_del(&fi->fib_lhash);
-
new_hash = fib_laddr_hashfn(fi->fib_prefsrc);
ldest = &new_laddrhash[new_hash];
hlist_add_head(&fi->fib_lhash, ldest);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 09b62e17dd8c..3c699c4e90a4 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -72,6 +72,7 @@
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/vmalloc.h>
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/protocol.h>
@@ -324,13 +325,15 @@ static inline void empty_child_dec(struct key_vector *n)
static struct key_vector *leaf_new(t_key key, struct fib_alias *fa)
{
- struct tnode *kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL);
- struct key_vector *l = kv->kv;
+ struct key_vector *l;
+ struct tnode *kv;
+ kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL);
if (!kv)
return NULL;
/* initialize key vector */
+ l = kv->kv;
l->key = key;
l->pos = 0;
l->bits = 0;
@@ -345,24 +348,26 @@ static struct key_vector *leaf_new(t_key key, struct fib_alias *fa)
static struct key_vector *tnode_new(t_key key, int pos, int bits)
{
- struct tnode *tnode = tnode_alloc(bits);
unsigned int shift = pos + bits;
- struct key_vector *tn = tnode->kv;
+ struct key_vector *tn;
+ struct tnode *tnode;
/* verify bits and pos their msb bits clear and values are valid */
BUG_ON(!bits || (shift > KEYLENGTH));
- pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0),
- sizeof(struct key_vector *) << bits);
-
+ tnode = tnode_alloc(bits);
if (!tnode)
return NULL;
+ pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0),
+ sizeof(struct key_vector *) << bits);
+
if (bits == KEYLENGTH)
tnode->full_children = 1;
else
tnode->empty_children = 1ul << bits;
+ tn = tnode->kv;
tn->key = (shift < KEYLENGTH) ? (key >> shift) << shift : 0;
tn->pos = pos;
tn->bits = bits;
@@ -1166,13 +1171,13 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
new_fa->fa_slen = fa->fa_slen;
new_fa->tb_id = tb->tb_id;
- err = netdev_switch_fib_ipv4_add(key, plen, fi,
- new_fa->fa_tos,
- cfg->fc_type,
- cfg->fc_nlflags,
- tb->tb_id);
+ err = switchdev_fib_ipv4_add(key, plen, fi,
+ new_fa->fa_tos,
+ cfg->fc_type,
+ cfg->fc_nlflags,
+ tb->tb_id);
if (err) {
- netdev_switch_fib_ipv4_abort(fi);
+ switchdev_fib_ipv4_abort(fi);
kmem_cache_free(fn_alias_kmem, new_fa);
goto out;
}
@@ -1216,12 +1221,10 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
new_fa->tb_id = tb->tb_id;
/* (Optionally) offload fib entry to switch hardware. */
- err = netdev_switch_fib_ipv4_add(key, plen, fi, tos,
- cfg->fc_type,
- cfg->fc_nlflags,
- tb->tb_id);
+ err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type,
+ cfg->fc_nlflags, tb->tb_id);
if (err) {
- netdev_switch_fib_ipv4_abort(fi);
+ switchdev_fib_ipv4_abort(fi);
goto out_free_new_fa;
}
@@ -1240,7 +1243,7 @@ succeeded:
return 0;
out_sw_fib_del:
- netdev_switch_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id);
+ switchdev_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id);
out_free_new_fa:
kmem_cache_free(fn_alias_kmem, new_fa);
out:
@@ -1518,8 +1521,8 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
if (!fa_to_delete)
return -ESRCH;
- netdev_switch_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos,
- cfg->fc_type, tb->tb_id);
+ switchdev_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos,
+ cfg->fc_type, tb->tb_id);
rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
&cfg->fc_nlinfo, 0);
@@ -1768,10 +1771,9 @@ void fib_table_flush_external(struct fib_table *tb)
if (!fi || !(fi->fib_flags & RTNH_F_OFFLOAD))
continue;
- netdev_switch_fib_ipv4_del(n->key,
- KEYLENGTH - fa->fa_slen,
- fi, fa->fa_tos,
- fa->fa_type, tb->tb_id);
+ switchdev_fib_ipv4_del(n->key, KEYLENGTH - fa->fa_slen,
+ fi, fa->fa_tos, fa->fa_type,
+ tb->tb_id);
}
/* update leaf slen */
@@ -1836,10 +1838,9 @@ int fib_table_flush(struct fib_table *tb)
continue;
}
- netdev_switch_fib_ipv4_del(n->key,
- KEYLENGTH - fa->fa_slen,
- fi, fa->fa_tos,
- fa->fa_type, tb->tb_id);
+ switchdev_fib_ipv4_del(n->key, KEYLENGTH - fa->fa_slen,
+ fi, fa->fa_tos, fa->fa_type,
+ tb->tb_id);
hlist_del_rcu(&fa->fa_list);
fib_release_info(fa->fa_info);
alias_free_mem_rcu(fa);
@@ -2057,11 +2058,12 @@ static struct key_vector *fib_trie_get_next(struct fib_trie_iter *iter)
static struct key_vector *fib_trie_get_first(struct fib_trie_iter *iter,
struct trie *t)
{
- struct key_vector *n, *pn = t->kv;
+ struct key_vector *n, *pn;
if (!t)
return NULL;
+ pn = t->kv;
n = rcu_dereference(pn->tnode[0]);
if (!n)
return NULL;
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve_core.c
index 8986e63f3bda..311a4ba6950a 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve_core.c
@@ -60,11 +60,6 @@ struct geneve_net {
static int geneve_net_id;
-static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
-{
- return (struct genevehdr *)(udp_hdr(skb) + 1);
-}
-
static struct geneve_sock *geneve_find_sock(struct net *net,
sa_family_t family, __be16 port)
{
@@ -435,7 +430,7 @@ static int __init geneve_init_module(void)
if (rc)
return rc;
- pr_info("Geneve driver\n");
+ pr_info("Geneve core logic\n");
return 0;
}
@@ -449,5 +444,4 @@ module_exit(geneve_cleanup_module);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jesse Gross <jesse@nicira.com>");
-MODULE_DESCRIPTION("Driver for GENEVE encapsulated traffic");
-MODULE_ALIAS_RTNL_LINK("geneve");
+MODULE_DESCRIPTION("Driver library for GENEVE encapsulated traffic");
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index a3a697f5ffba..651cdf648ec4 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1339,6 +1339,168 @@ out:
}
EXPORT_SYMBOL(ip_mc_inc_group);
+static int ip_mc_check_iphdr(struct sk_buff *skb)
+{
+ const struct iphdr *iph;
+ unsigned int len;
+ unsigned int offset = skb_network_offset(skb) + sizeof(*iph);
+
+ if (!pskb_may_pull(skb, offset))
+ return -EINVAL;
+
+ iph = ip_hdr(skb);
+
+ if (iph->version != 4 || ip_hdrlen(skb) < sizeof(*iph))
+ return -EINVAL;
+
+ offset += ip_hdrlen(skb) - sizeof(*iph);
+
+ if (!pskb_may_pull(skb, offset))
+ return -EINVAL;
+
+ iph = ip_hdr(skb);
+
+ if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
+ return -EINVAL;
+
+ len = skb_network_offset(skb) + ntohs(iph->tot_len);
+ if (skb->len < len || len < offset)
+ return -EINVAL;
+
+ skb_set_transport_header(skb, offset);
+
+ return 0;
+}
+
+static int ip_mc_check_igmp_reportv3(struct sk_buff *skb)
+{
+ unsigned int len = skb_transport_offset(skb);
+
+ len += sizeof(struct igmpv3_report);
+
+ return pskb_may_pull(skb, len) ? 0 : -EINVAL;
+}
+
+static int ip_mc_check_igmp_query(struct sk_buff *skb)
+{
+ unsigned int len = skb_transport_offset(skb);
+
+ len += sizeof(struct igmphdr);
+ if (skb->len < len)
+ return -EINVAL;
+
+ /* IGMPv{1,2}? */
+ if (skb->len != len) {
+ /* or IGMPv3? */
+ len += sizeof(struct igmpv3_query) - sizeof(struct igmphdr);
+ if (skb->len < len || !pskb_may_pull(skb, len))
+ return -EINVAL;
+ }
+
+ /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer
+ * all-systems destination addresses (224.0.0.1) for general queries
+ */
+ if (!igmp_hdr(skb)->group &&
+ ip_hdr(skb)->daddr != htonl(INADDR_ALLHOSTS_GROUP))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int ip_mc_check_igmp_msg(struct sk_buff *skb)
+{
+ switch (igmp_hdr(skb)->type) {
+ case IGMP_HOST_LEAVE_MESSAGE:
+ case IGMP_HOST_MEMBERSHIP_REPORT:
+ case IGMPV2_HOST_MEMBERSHIP_REPORT:
+ /* fall through */
+ return 0;
+ case IGMPV3_HOST_MEMBERSHIP_REPORT:
+ return ip_mc_check_igmp_reportv3(skb);
+ case IGMP_HOST_MEMBERSHIP_QUERY:
+ return ip_mc_check_igmp_query(skb);
+ default:
+ return -ENOMSG;
+ }
+}
+
+static inline __sum16 ip_mc_validate_checksum(struct sk_buff *skb)
+{
+ return skb_checksum_simple_validate(skb);
+}
+
+static int __ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed)
+
+{
+ struct sk_buff *skb_chk;
+ unsigned int transport_len;
+ unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr);
+ int ret;
+
+ transport_len = ntohs(ip_hdr(skb)->tot_len) - ip_hdrlen(skb);
+
+ skb_get(skb);
+ skb_chk = skb_checksum_trimmed(skb, transport_len,
+ ip_mc_validate_checksum);
+ if (!skb_chk)
+ return -EINVAL;
+
+ if (!pskb_may_pull(skb_chk, len)) {
+ kfree_skb(skb_chk);
+ return -EINVAL;
+ }
+
+ ret = ip_mc_check_igmp_msg(skb_chk);
+ if (ret) {
+ kfree_skb(skb_chk);
+ return ret;
+ }
+
+ if (skb_trimmed)
+ *skb_trimmed = skb_chk;
+ else
+ kfree_skb(skb_chk);
+
+ return 0;
+}
+
+/**
+ * ip_mc_check_igmp - checks whether this is a sane IGMP packet
+ * @skb: the skb to validate
+ * @skb_trimmed: to store an skb pointer trimmed to IPv4 packet tail (optional)
+ *
+ * Checks whether an IPv4 packet is a valid IGMP packet. If so sets
+ * skb network and transport headers accordingly and returns zero.
+ *
+ * -EINVAL: A broken packet was detected, i.e. it violates some internet
+ * standard
+ * -ENOMSG: IP header validation succeeded but it is not an IGMP packet.
+ * -ENOMEM: A memory allocation failure happened.
+ *
+ * Optionally, an skb pointer might be provided via skb_trimmed (or set it
+ * to NULL): After parsing an IGMP packet successfully it will point to
+ * an skb which has its tail aligned to the IP packet end. This might
+ * either be the originally provided skb or a trimmed, cloned version if
+ * the skb frame had data beyond the IP packet. A cloned skb allows us
+ * to leave the original skb and its full frame unchanged (which might be
+ * desirable for layer 2 frame jugglers).
+ *
+ * The caller needs to release a reference count from any returned skb_trimmed.
+ */
+int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed)
+{
+ int ret = ip_mc_check_iphdr(skb);
+
+ if (ret < 0)
+ return ret;
+
+ if (ip_hdr(skb)->protocol != IPPROTO_IGMP)
+ return -ENOMSG;
+
+ return __ip_mc_check_igmp(skb, skb_trimmed);
+}
+EXPORT_SYMBOL(ip_mc_check_igmp);
+
/*
* Resend IGMP JOIN report; used by netdev notifier.
*/
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8976ca423a07..60021d0d9326 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -99,6 +99,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
struct net *net = sock_net(sk);
int smallest_size = -1, smallest_rover;
kuid_t uid = sock_i_uid(sk);
+ int attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
local_bh_disable();
if (!snum) {
@@ -106,6 +107,14 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
again:
inet_get_local_port_range(net, &low, &high);
+ if (attempt_half) {
+ int half = low + ((high - low) >> 1);
+
+ if (attempt_half == 1)
+ high = half;
+ else
+ low = half;
+ }
remaining = (high - low) + 1;
smallest_rover = rover = prandom_u32() % remaining + low;
@@ -127,11 +136,6 @@ again:
(tb->num_owners < smallest_size || smallest_size == -1)) {
smallest_size = tb->num_owners;
smallest_rover = rover;
- if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 &&
- !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) {
- snum = smallest_rover;
- goto tb_found;
- }
}
if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) {
snum = rover;
@@ -159,6 +163,11 @@ again:
snum = smallest_rover;
goto have_snum;
}
+ if (attempt_half == 1) {
+ /* OK we now try the upper half of the range */
+ attempt_half = 2;
+ goto again;
+ }
goto fail;
}
/* OK, here is the one we will use. HEAD is
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index c6fb80bd5826..5f9b063bbe8a 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -18,6 +18,7 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/wait.h>
+#include <linux/vmalloc.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
@@ -90,10 +91,6 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket
void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
const unsigned short snum)
{
- struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
-
- atomic_inc(&hashinfo->bsockets);
-
inet_sk(sk)->inet_num = snum;
sk_add_bind_node(sk, &tb->owners);
tb->num_owners++;
@@ -111,8 +108,6 @@ static void __inet_put_port(struct sock *sk)
struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash];
struct inet_bind_bucket *tb;
- atomic_dec(&hashinfo->bsockets);
-
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
__sk_del_bind_node(sk);
@@ -399,9 +394,10 @@ not_unique:
return -EADDRNOTAVAIL;
}
-static inline u32 inet_sk_port_offset(const struct sock *sk)
+static u32 inet_sk_port_offset(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
+
return secure_ipv4_port_ephemeral(inet->inet_rcv_saddr,
inet->inet_daddr,
inet->inet_dport);
@@ -507,8 +503,14 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
+ /* By starting with offset being an even number,
+ * we tend to leave about 50% of ports for other uses,
+ * like bind(0).
+ */
+ offset &= ~1;
+
local_bh_disable();
- for (i = 1; i <= remaining; i++) {
+ for (i = 0; i < remaining; i++) {
port = low + (i + offset) % remaining;
if (inet_is_local_reserved_port(net, port))
continue;
@@ -552,7 +554,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
return -EADDRNOTAVAIL;
ok:
- hint += i;
+ hint += (i + 2) & ~1;
/* Head lock still held and bh's disabled */
inet_bind_hash(sk, tb, port);
@@ -599,7 +601,11 @@ out:
int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
- return __inet_hash_connect(death_row, sk, inet_sk_port_offset(sk),
+ u32 port_offset = 0;
+
+ if (!inet_sk(sk)->inet_num)
+ port_offset = inet_sk_port_offset(sk);
+ return __inet_hash_connect(death_row, sk, port_offset,
__inet_check_established);
}
EXPORT_SYMBOL_GPL(inet_hash_connect);
@@ -608,7 +614,6 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
{
int i;
- atomic_set(&h->bsockets, 0);
for (i = 0; i < INET_LHTABLE_SIZE; i++) {
spin_lock_init(&h->listening_hash[i].lock);
INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].head,
@@ -616,3 +621,33 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
}
}
EXPORT_SYMBOL_GPL(inet_hashinfo_init);
+
+int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
+{
+ unsigned int i, nblocks = 1;
+
+ if (sizeof(spinlock_t) != 0) {
+ /* allocate 2 cache lines or at least one spinlock per cpu */
+ nblocks = max_t(unsigned int,
+ 2 * L1_CACHE_BYTES / sizeof(spinlock_t),
+ 1);
+ nblocks = roundup_pow_of_two(nblocks * num_possible_cpus());
+
+ /* no more locks than number of hash buckets */
+ nblocks = min(nblocks, hashinfo->ehash_mask + 1);
+
+ hashinfo->ehash_locks = kmalloc_array(nblocks, sizeof(spinlock_t),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!hashinfo->ehash_locks)
+ hashinfo->ehash_locks = vmalloc(nblocks * sizeof(spinlock_t));
+
+ if (!hashinfo->ehash_locks)
+ return -ENOMEM;
+
+ for (i = 0; i < nblocks; i++)
+ spin_lock_init(&hashinfo->ehash_locks[i]);
+ }
+ hashinfo->ehash_locks_mask = nblocks - 1;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(inet_ehash_locks_alloc);
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 00ec8d5d7e7e..2ffbd16b79e0 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -170,7 +170,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
}
EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
-void tw_timer_handler(unsigned long data)
+static void tw_timer_handler(unsigned long data)
{
struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 3674484946a5..2d3aa408fbdc 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,17 +39,21 @@
#include <net/route.h>
#include <net/xfrm.h>
-static bool ip_may_fragment(const struct sk_buff *skb)
-{
- return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
- skb->ignore_df;
-}
-
static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
{
if (skb->len <= mtu)
return false;
+ if (unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0))
+ return false;
+
+ /* original fragment exceeds mtu and DF is set */
+ if (unlikely(IPCB(skb)->frag_max_size > mtu))
+ return true;
+
+ if (skb->ignore_df)
+ return false;
+
if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
return false;
@@ -114,7 +118,7 @@ int ip_forward(struct sk_buff *skb)
IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
- if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) {
+ if (ip_exceeds_mtu(skb, mtu)) {
IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index cc1da6d9cb35..a50dc6d408d1 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -75,6 +75,7 @@ struct ipq {
__be16 id;
u8 protocol;
u8 ecn; /* RFC3168 support */
+ u16 max_df_size; /* largest frag with DF set seen */
int iif;
unsigned int rid;
struct inet_peer *peer;
@@ -173,6 +174,15 @@ static void ipq_kill(struct ipq *ipq)
inet_frag_kill(&ipq->q, &ip4_frags);
}
+static bool frag_expire_skip_icmp(u32 user)
+{
+ return user == IP_DEFRAG_AF_PACKET ||
+ ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_IN,
+ __IP_DEFRAG_CONNTRACK_IN_END) ||
+ ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_BRIDGE_IN,
+ __IP_DEFRAG_CONNTRACK_BRIDGE_IN);
+}
+
/*
* Oops, a fragment queue timed out. Kill it and send an ICMP reply.
*/
@@ -217,10 +227,8 @@ static void ip_expire(unsigned long arg)
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
- if (qp->user == IP_DEFRAG_AF_PACKET ||
- ((qp->user >= IP_DEFRAG_CONNTRACK_IN) &&
- (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) &&
- (skb_rtable(head)->rt_type != RTN_LOCAL)))
+ if (frag_expire_skip_icmp(qp->user) &&
+ (skb_rtable(head)->rt_type != RTN_LOCAL))
goto out_rcu_unlock;
/* Send an ICMP "Fragment Reassembly Timeout" message. */
@@ -319,6 +327,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
struct sk_buff *prev, *next;
struct net_device *dev;
+ unsigned int fragsize;
int flags, offset;
int ihl, end;
int err = -ENOENT;
@@ -474,9 +483,14 @@ found:
if (offset == 0)
qp->q.flags |= INET_FRAG_FIRST_IN;
+ fragsize = skb->len + ihl;
+
+ if (fragsize > qp->q.max_size)
+ qp->q.max_size = fragsize;
+
if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
- skb->len + ihl > qp->q.max_size)
- qp->q.max_size = skb->len + ihl;
+ fragsize > qp->max_df_size)
+ qp->max_df_size = fragsize;
if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
qp->q.meat == qp->q.len) {
@@ -606,13 +620,27 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
head->next = NULL;
head->dev = dev;
head->tstamp = qp->q.stamp;
- IPCB(head)->frag_max_size = qp->q.max_size;
+ IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
iph = ip_hdr(head);
- /* max_size != 0 implies at least one fragment had IP_DF set */
- iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
iph->tot_len = htons(len);
iph->tos |= ecn;
+
+ /* When we set IP_DF on a refragmented skb we must also force a
+ * call to ip_fragment to avoid forwarding a DF-skb of size s while
+ * original sender only sent fragments of size f (where f < s).
+ *
+ * We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest
+ * frag seen to avoid sending tiny DF-fragments in case skb was built
+ * from one very small df-fragment and one large non-df frag.
+ */
+ if (qp->max_df_size == qp->q.max_size) {
+ IPCB(head)->flags |= IPSKB_FRAG_PMTU;
+ iph->frag_off = htons(IP_DF);
+ } else {
+ iph->frag_off = 0;
+ }
+
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c65b93a7b711..55f3c2e94357 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -83,6 +83,10 @@
int sysctl_ip_default_ttl __read_mostly = IPDEFTTL;
EXPORT_SYMBOL(sysctl_ip_default_ttl);
+static int ip_fragment(struct sock *sk, struct sk_buff *skb,
+ unsigned int mtu,
+ int (*output)(struct sock *, struct sk_buff *));
+
/* Generate a checksum for an outgoing IP datagram. */
void ip_send_check(struct iphdr *iph)
{
@@ -91,7 +95,7 @@ void ip_send_check(struct iphdr *iph)
}
EXPORT_SYMBOL(ip_send_check);
-int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
+static int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
{
struct iphdr *iph = ip_hdr(skb);
@@ -168,7 +172,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
}
EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
-static inline int ip_finish_output2(struct sock *sk, struct sk_buff *skb)
+static int ip_finish_output2(struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = (struct rtable *)dst;
@@ -216,7 +220,8 @@ static inline int ip_finish_output2(struct sock *sk, struct sk_buff *skb)
return -EINVAL;
}
-static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb)
+static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb,
+ unsigned int mtu)
{
netdev_features_t features;
struct sk_buff *segs;
@@ -224,7 +229,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb)
/* 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))
+ skb_gso_network_seglen(skb) <= mtu)
return ip_finish_output2(sk, skb);
/* Slowpath - GSO segment length is exceeding the dst MTU.
@@ -248,7 +253,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb)
int err;
segs->next = NULL;
- err = ip_fragment(sk, segs, ip_finish_output2);
+ err = ip_fragment(sk, segs, mtu, ip_finish_output2);
if (err && ret == 0)
ret = err;
@@ -260,6 +265,8 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb)
static int ip_finish_output(struct sock *sk, struct sk_buff *skb)
{
+ unsigned int mtu;
+
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
/* Policy lookup after SNAT yielded a new policy */
if (skb_dst(skb)->xfrm) {
@@ -267,11 +274,12 @@ static int ip_finish_output(struct sock *sk, struct sk_buff *skb)
return dst_output_sk(sk, skb);
}
#endif
+ mtu = ip_skb_dst_mtu(skb);
if (skb_is_gso(skb))
- return ip_finish_output_gso(sk, skb);
+ return ip_finish_output_gso(sk, skb, mtu);
- if (skb->len > ip_skb_dst_mtu(skb))
- return ip_fragment(sk, skb, ip_finish_output2);
+ if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU))
+ return ip_fragment(sk, skb, mtu, ip_finish_output2);
return ip_finish_output2(sk, skb);
}
@@ -478,6 +486,31 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
skb_copy_secmark(to, from);
}
+static int ip_fragment(struct sock *sk, struct sk_buff *skb,
+ unsigned int mtu,
+ int (*output)(struct sock *, struct sk_buff *))
+{
+ struct iphdr *iph = ip_hdr(skb);
+
+ if ((iph->frag_off & htons(IP_DF)) == 0)
+ return ip_do_fragment(sk, skb, output);
+
+ if (unlikely(!skb->ignore_df ||
+ (IPCB(skb)->frag_max_size &&
+ IPCB(skb)->frag_max_size > mtu))) {
+ struct rtable *rt = skb_rtable(skb);
+ struct net_device *dev = rt->dst.dev;
+
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
+ kfree_skb(skb);
+ return -EMSGSIZE;
+ }
+
+ return ip_do_fragment(sk, skb, output);
+}
+
/*
* This IP datagram is too large to be sent in one piece. Break it up into
* smaller pieces (each of size equal to IP header plus
@@ -485,8 +518,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
* single device frame, and queue such a frame for sending.
*/
-int ip_fragment(struct sock *sk, struct sk_buff *skb,
- int (*output)(struct sock *, struct sk_buff *))
+int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
+ int (*output)(struct sock *, struct sk_buff *))
{
struct iphdr *iph;
int ptr;
@@ -507,15 +540,8 @@ int ip_fragment(struct sock *sk, struct sk_buff *skb,
iph = ip_hdr(skb);
mtu = ip_skb_dst_mtu(skb);
- if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
- (IPCB(skb)->frag_max_size &&
- IPCB(skb)->frag_max_size > mtu))) {
- IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
- htonl(mtu));
- kfree_skb(skb);
- return -EMSGSIZE;
- }
+ if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu)
+ mtu = IPCB(skb)->frag_max_size;
/*
* Setup starting values.
@@ -711,6 +737,9 @@ slow_path:
iph = ip_hdr(skb2);
iph->frag_off = htons((offset >> 3));
+ if (IPCB(skb)->flags & IPSKB_FRAG_PMTU)
+ iph->frag_off |= htons(IP_DF);
+
/* ANK: dirty, but effective trick. Upgrade options only if
* the segment to be fragmented was THE FIRST (otherwise,
* options are already fixed) and make it ONCE
@@ -751,7 +780,7 @@ fail:
IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
return err;
}
-EXPORT_SYMBOL(ip_fragment);
+EXPORT_SYMBOL(ip_do_fragment);
int
ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
@@ -1217,11 +1246,9 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
}
while (size > 0) {
- int i;
-
- if (skb_is_gso(skb))
+ if (skb_is_gso(skb)) {
len = size;
- else {
+ } else {
/* Check if the remaining data fits into current packet. */
len = mtu - skb->len;
@@ -1273,15 +1300,10 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
continue;
}
- i = skb_shinfo(skb)->nr_frags;
if (len > size)
len = size;
- if (skb_can_coalesce(skb, i, page, offset)) {
- skb_frag_size_add(&skb_shinfo(skb)->frags[i-1], len);
- } else if (i < MAX_SKB_FRAGS) {
- get_page(page);
- skb_fill_page_desc(skb, i, page, offset, len);
- } else {
+
+ if (skb_append_pagefrags(skb, page, offset, len)) {
err = -EMSGSIZE;
goto error;
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 7cfb0893f263..04ae2992a5cd 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -582,6 +582,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
case IP_TRANSPARENT:
case IP_MINTTL:
case IP_NODEFRAG:
+ case IP_BIND_ADDRESS_NO_PORT:
case IP_UNICAST_IF:
case IP_MULTICAST_TTL:
case IP_MULTICAST_ALL:
@@ -732,6 +733,9 @@ static int do_ip_setsockopt(struct sock *sk, int level,
}
inet->nodefrag = val ? 1 : 0;
break;
+ case IP_BIND_ADDRESS_NO_PORT:
+ inet->bind_address_no_port = val ? 1 : 0;
+ break;
case IP_MTU_DISCOVER:
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
goto e_inval;
@@ -1324,6 +1328,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_NODEFRAG:
val = inet->nodefrag;
break;
+ case IP_BIND_ADDRESS_NO_PORT:
+ val = inet->bind_address_no_port;
+ break;
case IP_MTU_DISCOVER:
val = inet->pmtudisc;
break;
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index ce63ab21b6cd..6a51a71a6c67 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -98,7 +98,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
return -ENOMEM;
eh = (struct ethhdr *)skb->data;
- if (likely(ntohs(eh->h_proto) >= ETH_P_802_3_MIN))
+ if (likely(eth_proto_is_802_3(eh->h_proto)))
skb->protocol = eh->h_proto;
else
skb->protocol = htons(ETH_P_802_2);
@@ -165,6 +165,8 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
{
int i;
+ netdev_stats_to_stats64(tot, &dev->stats);
+
for_each_possible_cpu(i) {
const struct pcpu_sw_netstats *tstats =
per_cpu_ptr(dev->tstats, i);
@@ -185,22 +187,6 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
tot->tx_bytes += tx_bytes;
}
- tot->multicast = dev->stats.multicast;
-
- tot->rx_crc_errors = dev->stats.rx_crc_errors;
- tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
- tot->rx_length_errors = dev->stats.rx_length_errors;
- tot->rx_frame_errors = dev->stats.rx_frame_errors;
- tot->rx_errors = dev->stats.rx_errors;
-
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- tot->collisions = dev->stats.collisions;
-
return tot;
}
EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index ff96396ebec5..254238daf58b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -251,7 +251,8 @@ ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
return -EINVAL;
}
- p.i_key = p.o_key = p.i_flags = p.o_flags = 0;
+ p.i_key = p.o_key = 0;
+ p.i_flags = p.o_flags = 0;
if (p.iph.ttl)
p.iph.frag_off |= htons(IP_DF);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 2d0e265fef6e..e7abf5145edc 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1444,7 +1444,6 @@ static int
compat_find_calc_match(struct xt_entry_match *m,
const char *name,
const struct ipt_ip *ip,
- unsigned int hookmask,
int *size)
{
struct xt_match *match;
@@ -1513,8 +1512,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
entry_offset = (void *)e - (void *)base;
j = 0;
xt_ematch_foreach(ematch, e) {
- ret = compat_find_calc_match(ematch, name,
- &e->ip, e->comefrom, &off);
+ ret = compat_find_calc_match(ematch, name, &e->ip, &off);
if (ret != 0)
goto release_matches;
++j;
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 771ab3d01ad3..45cb16a6a4a3 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -367,6 +367,11 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
struct clusterip_config *config;
int ret;
+ if (par->nft_compat) {
+ pr_err("cannot use CLUSTERIP target from nftables compat\n");
+ return -EOPNOTSUPP;
+ }
+
if (cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP &&
cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT &&
cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT_DPT) {
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index e9e67793055f..fe8cc183411e 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -18,7 +18,7 @@
#include <net/netfilter/nf_conntrack_synproxy.h>
static struct iphdr *
-synproxy_build_ip(struct sk_buff *skb, u32 saddr, u32 daddr)
+synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr)
{
struct iphdr *iph;
@@ -220,7 +220,7 @@ synproxy_send_client_ack(const struct synproxy_net *snet,
nth->ack_seq = th->ack_seq;
tcp_flag_word(nth) = TCP_FLAG_ACK;
nth->doff = tcp_hdr_size / 4;
- nth->window = ntohs(htons(th->window) >> opts->wscale);
+ nth->window = htons(ntohs(th->window) >> opts->wscale);
nth->check = 0;
nth->urg_ptr = 0;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index e1f3b911dd1e..da5d483e236a 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -298,6 +298,8 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPACKSkippedFinWait2", LINUX_MIB_TCPACKSKIPPEDFINWAIT2),
SNMP_MIB_ITEM("TCPACKSkippedTimeWait", LINUX_MIB_TCPACKSKIPPEDTIMEWAIT),
SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE),
+ SNMP_MIB_ITEM("TCPWinProbe", LINUX_MIB_TCPWINPROBE),
+ SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f45f2a12f37b..f6055984c307 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -457,12 +457,9 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
}
#define IP_IDENTS_SZ 2048u
-struct ip_ident_bucket {
- atomic_t id;
- u32 stamp32;
-};
-static struct ip_ident_bucket *ip_idents __read_mostly;
+static atomic_t *ip_idents __read_mostly;
+static u32 *ip_tstamps __read_mostly;
/* In order to protect privacy, we add a perturbation to identifiers
* if one generator is seldom used. This makes hard for an attacker
@@ -470,15 +467,16 @@ static struct ip_ident_bucket *ip_idents __read_mostly;
*/
u32 ip_idents_reserve(u32 hash, int segs)
{
- struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ;
- u32 old = ACCESS_ONCE(bucket->stamp32);
+ u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ;
+ atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
+ u32 old = ACCESS_ONCE(*p_tstamp);
u32 now = (u32)jiffies;
u32 delta = 0;
- if (old != now && cmpxchg(&bucket->stamp32, old, now) == old)
+ if (old != now && cmpxchg(p_tstamp, old, now) == old)
delta = prandom_u32_max(now - old);
- return atomic_add_return(segs + delta, &bucket->id) - segs;
+ return atomic_add_return(segs + delta, p_id) - segs;
}
EXPORT_SYMBOL(ip_idents_reserve);
@@ -2097,7 +2095,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
goto out;
}
if (ipv4_is_local_multicast(fl4->daddr) ||
- ipv4_is_lbcast(fl4->daddr)) {
+ ipv4_is_lbcast(fl4->daddr) ||
+ fl4->flowi4_proto == IPPROTO_IGMP) {
if (!fl4->saddr)
fl4->saddr = inet_select_addr(dev_out, 0,
RT_SCOPE_LINK);
@@ -2742,6 +2741,10 @@ int __init ip_rt_init(void)
prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
+ ip_tstamps = kcalloc(IP_IDENTS_SZ, sizeof(*ip_tstamps), GFP_KERNEL);
+ if (!ip_tstamps)
+ panic("IP: failed to allocate ip_tstamps\n");
+
for_each_possible_cpu(cpu) {
struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index df849e5a10f1..d70b1f603692 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -219,9 +219,9 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
}
EXPORT_SYMBOL_GPL(__cookie_v4_check);
-static struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
- struct request_sock *req,
- struct dst_entry *dst)
+struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
+ struct request_sock *req,
+ struct dst_entry *dst)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct sock *child;
@@ -235,7 +235,7 @@ static struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
}
return child;
}
-
+EXPORT_SYMBOL(tcp_get_cookie_sock);
/*
* when syncookies are in effect and tcp timestamps are enabled we stored
@@ -391,7 +391,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
ireq->rcv_wscale = rcv_wscale;
ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst);
- ret = get_cookie_sock(sk, skb, req, &rt->dst);
+ ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst);
/* ip_queue_xmit() depends on our flow being setup
* Normal sockets get it right from inet_csk_route_child_sock()
*/
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index c3852a7ff3c7..433231ccfb17 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -41,11 +41,19 @@ static int tcp_syn_retries_min = 1;
static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
+static int min_sndbuf = SOCK_MIN_SNDBUF;
+static int min_rcvbuf = SOCK_MIN_RCVBUF;
/* Update system visible IP port range */
static void set_local_port_range(struct net *net, int range[2])
{
+ bool same_parity = !((range[0] ^ range[1]) & 1);
+
write_seqlock(&net->ipv4.ip_local_ports.lock);
+ if (same_parity && !net->ipv4.ip_local_ports.warned) {
+ net->ipv4.ip_local_ports.warned = true;
+ pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n");
+ }
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);
@@ -522,7 +530,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(sysctl_tcp_wmem),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
+ .extra1 = &min_sndbuf,
},
{
.procname = "tcp_notsent_lowat",
@@ -537,7 +545,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(sysctl_tcp_rmem),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
+ .extra1 = &min_rcvbuf,
},
{
.procname = "tcp_app_win",
@@ -702,7 +710,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
+ .extra1 = &one,
.extra2 = &gso_max_segs,
},
{
@@ -750,7 +758,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(sysctl_udp_rmem_min),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one
+ .extra1 = &min_rcvbuf,
},
{
.procname = "udp_wmem_min",
@@ -758,7 +766,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(sysctl_udp_wmem_min),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one
+ .extra1 = &min_sndbuf,
},
{ }
};
@@ -821,6 +829,13 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec
},
{
+ .procname = "tcp_ecn_fallback",
+ .data = &init_net.ipv4.sysctl_tcp_ecn_fallback,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
.procname = "ip_local_port_range",
.maxlen = sizeof(init_net.ipv4.ip_local_ports.range),
.data = &init_net.ipv4.ip_local_ports.range,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f1377f2a0472..65f791f74845 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -695,8 +695,9 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
struct tcp_splice_state *tss = rd_desc->arg.data;
int ret;
- ret = skb_splice_bits(skb, offset, tss->pipe, min(rd_desc->count, len),
- tss->flags);
+ ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe,
+ min(rd_desc->count, len), tss->flags,
+ skb_socket_splice);
if (ret > 0)
rd_desc->count -= ret;
return ret;
@@ -809,16 +810,28 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
}
EXPORT_SYMBOL(tcp_splice_read);
-struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
+struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
+ bool force_schedule)
{
struct sk_buff *skb;
/* The TCP header must be at least 32-bit aligned. */
size = ALIGN(size, 4);
+ if (unlikely(tcp_under_memory_pressure(sk)))
+ sk_mem_reclaim_partial(sk);
+
skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
- if (skb) {
- if (sk_wmem_schedule(sk, skb->truesize)) {
+ if (likely(skb)) {
+ bool mem_scheduled;
+
+ if (force_schedule) {
+ mem_scheduled = true;
+ sk_forced_mem_schedule(sk, skb->truesize);
+ } else {
+ mem_scheduled = sk_wmem_schedule(sk, skb->truesize);
+ }
+ if (likely(mem_scheduled)) {
skb_reserve(skb, sk->sk_prot->max_header);
/*
* Make sure that we have exactly size bytes
@@ -908,7 +921,8 @@ new_segment:
if (!sk_stream_memory_free(sk))
goto wait_for_sndbuf;
- skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+ skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
+ skb_queue_empty(&sk->sk_write_queue));
if (!skb)
goto wait_for_memory;
@@ -987,6 +1001,9 @@ do_error:
if (copied)
goto out;
out_err:
+ /* make sure we wake any epoll edge trigger waiter */
+ if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN))
+ sk->sk_write_space(sk);
return sk_stream_error(sk, flags, err);
}
@@ -1144,7 +1161,8 @@ new_segment:
skb = sk_stream_alloc_skb(sk,
select_size(sk, sg),
- sk->sk_allocation);
+ sk->sk_allocation,
+ skb_queue_empty(&sk->sk_write_queue));
if (!skb)
goto wait_for_memory;
@@ -1275,6 +1293,9 @@ do_error:
goto out;
out_err:
err = sk_stream_error(sk, flags, err);
+ /* make sure we wake any epoll edge trigger waiter */
+ if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN))
+ sk->sk_write_space(sk);
release_sock(sk);
return err;
}
@@ -2483,6 +2504,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
icsk->icsk_syn_retries = val;
break;
+ case TCP_SAVE_SYN:
+ if (val < 0 || val > 1)
+ err = -EINVAL;
+ else
+ tp->save_syn = val;
+ break;
+
case TCP_LINGER2:
if (val < 0)
tp->linger2 = -1;
@@ -2672,6 +2700,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_bytes_acked = tp->bytes_acked;
info->tcpi_bytes_received = tp->bytes_received;
} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
+ info->tcpi_segs_out = tp->segs_out;
+ info->tcpi_segs_in = tp->segs_in;
}
EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -2821,6 +2851,42 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
case TCP_NOTSENT_LOWAT:
val = tp->notsent_lowat;
break;
+ case TCP_SAVE_SYN:
+ val = tp->save_syn;
+ break;
+ case TCP_SAVED_SYN: {
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ lock_sock(sk);
+ if (tp->saved_syn) {
+ if (len < tp->saved_syn[0]) {
+ if (put_user(tp->saved_syn[0], optlen)) {
+ release_sock(sk);
+ return -EFAULT;
+ }
+ release_sock(sk);
+ return -EINVAL;
+ }
+ len = tp->saved_syn[0];
+ if (put_user(len, optlen)) {
+ release_sock(sk);
+ return -EFAULT;
+ }
+ if (copy_to_user(optval, tp->saved_syn + 1, len)) {
+ release_sock(sk);
+ return -EFAULT;
+ }
+ tcp_saved_syn_free(tp);
+ release_sock(sk);
+ } else {
+ release_sock(sk);
+ len = 0;
+ if (put_user(len, optlen))
+ return -EFAULT;
+ }
+ return 0;
+ }
default:
return -ENOPROTOOPT;
}
@@ -3025,11 +3091,12 @@ __setup("thash_entries=", set_thash_entries);
static void __init tcp_init_mem(void)
{
- unsigned long limit = nr_free_buffer_pages() / 8;
+ unsigned long limit = nr_free_buffer_pages() / 16;
+
limit = max(limit, 128UL);
- sysctl_tcp_mem[0] = limit / 4 * 3;
- sysctl_tcp_mem[1] = limit;
- sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
+ sysctl_tcp_mem[0] = limit / 4 * 3; /* 4.68 % */
+ sysctl_tcp_mem[1] = limit; /* 6.25 % */
+ sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; /* 9.37 % */
}
void __init tcp_init(void)
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
new file mode 100644
index 000000000000..a52ce2db53f2
--- /dev/null
+++ b/net/ipv4/tcp_cdg.c
@@ -0,0 +1,433 @@
+/*
+ * CAIA Delay-Gradient (CDG) congestion control
+ *
+ * This implementation is based on the paper:
+ * D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
+ * delay gradients." In IFIP Networking, pages 328-341. Springer, 2011.
+ *
+ * Scavenger traffic (Less-than-Best-Effort) should disable coexistence
+ * heuristics using parameters use_shadow=0 and use_ineff=0.
+ *
+ * Parameters window, backoff_beta, and backoff_factor are crucial for
+ * throughput and delay. Future work is needed to determine better defaults,
+ * and to provide guidelines for use in different environments/contexts.
+ *
+ * Except for window, knobs are configured via /sys/module/tcp_cdg/parameters/.
+ * Parameter window is only configurable when loading tcp_cdg as a module.
+ *
+ * Notable differences from paper/FreeBSD:
+ * o Using Hybrid Slow start and Proportional Rate Reduction.
+ * o Add toggle for shadow window mechanism. Suggested by David Hayes.
+ * o Add toggle for non-congestion loss tolerance.
+ * o Scaling parameter G is changed to a backoff factor;
+ * conversion is given by: backoff_factor = 1000/(G * window).
+ * o Limit shadow window to 2 * cwnd, or to cwnd when application limited.
+ * o More accurate e^-x.
+ */
+#include <linux/kernel.h>
+#include <linux/random.h>
+#include <linux/module.h>
+#include <net/tcp.h>
+
+#define HYSTART_ACK_TRAIN 1
+#define HYSTART_DELAY 2
+
+static int window __read_mostly = 8;
+static unsigned int backoff_beta __read_mostly = 0.7071 * 1024; /* sqrt 0.5 */
+static unsigned int backoff_factor __read_mostly = 42;
+static unsigned int hystart_detect __read_mostly = 3;
+static unsigned int use_ineff __read_mostly = 5;
+static bool use_shadow __read_mostly = true;
+static bool use_tolerance __read_mostly;
+
+module_param(window, int, 0444);
+MODULE_PARM_DESC(window, "gradient window size (power of two <= 256)");
+module_param(backoff_beta, uint, 0644);
+MODULE_PARM_DESC(backoff_beta, "backoff beta (0-1024)");
+module_param(backoff_factor, uint, 0644);
+MODULE_PARM_DESC(backoff_factor, "backoff probability scale factor");
+module_param(hystart_detect, uint, 0644);
+MODULE_PARM_DESC(hystart_detect, "use Hybrid Slow start "
+ "(0: disabled, 1: ACK train, 2: delay threshold, 3: both)");
+module_param(use_ineff, uint, 0644);
+MODULE_PARM_DESC(use_ineff, "use ineffectual backoff detection (threshold)");
+module_param(use_shadow, bool, 0644);
+MODULE_PARM_DESC(use_shadow, "use shadow window heuristic");
+module_param(use_tolerance, bool, 0644);
+MODULE_PARM_DESC(use_tolerance, "use loss tolerance heuristic");
+
+struct minmax {
+ union {
+ struct {
+ s32 min;
+ s32 max;
+ };
+ u64 v64;
+ };
+};
+
+enum cdg_state {
+ CDG_UNKNOWN = 0,
+ CDG_NONFULL = 1,
+ CDG_FULL = 2,
+ CDG_BACKOFF = 3,
+};
+
+struct cdg {
+ struct minmax rtt;
+ struct minmax rtt_prev;
+ struct minmax *gradients;
+ struct minmax gsum;
+ bool gfilled;
+ u8 tail;
+ u8 state;
+ u8 delack;
+ u32 rtt_seq;
+ u32 undo_cwnd;
+ u32 shadow_wnd;
+ u16 backoff_cnt;
+ u16 sample_cnt;
+ s32 delay_min;
+ u32 last_ack;
+ u32 round_start;
+};
+
+/**
+ * nexp_u32 - negative base-e exponential
+ * @ux: x in units of micro
+ *
+ * Returns exp(ux * -1e-6) * U32_MAX.
+ */
+static u32 __pure nexp_u32(u32 ux)
+{
+ static const u16 v[] = {
+ /* exp(-x)*65536-1 for x = 0, 0.000256, 0.000512, ... */
+ 65535,
+ 65518, 65501, 65468, 65401, 65267, 65001, 64470, 63422,
+ 61378, 57484, 50423, 38795, 22965, 8047, 987, 14,
+ };
+ u32 msb = ux >> 8;
+ u32 res;
+ int i;
+
+ /* Cut off when ux >= 2^24 (actual result is <= 222/U32_MAX). */
+ if (msb > U16_MAX)
+ return 0;
+
+ /* Scale first eight bits linearly: */
+ res = U32_MAX - (ux & 0xff) * (U32_MAX / 1000000);
+
+ /* Obtain e^(x + y + ...) by computing e^x * e^y * ...: */
+ for (i = 1; msb; i++, msb >>= 1) {
+ u32 y = v[i & -(msb & 1)] + U32_C(1);
+
+ res = ((u64)res * y) >> 16;
+ }
+
+ return res;
+}
+
+/* Based on the HyStart algorithm (by Ha et al.) that is implemented in
+ * tcp_cubic. Differences/experimental changes:
+ * o Using Hayes' delayed ACK filter.
+ * o Using a usec clock for the ACK train.
+ * o Reset ACK train when application limited.
+ * o Invoked at any cwnd (i.e. also when cwnd < 16).
+ * o Invoked only when cwnd < ssthresh (i.e. not when cwnd == ssthresh).
+ */
+static void tcp_cdg_hystart_update(struct sock *sk)
+{
+ struct cdg *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ ca->delay_min = min_not_zero(ca->delay_min, ca->rtt.min);
+ if (ca->delay_min == 0)
+ return;
+
+ if (hystart_detect & HYSTART_ACK_TRAIN) {
+ u32 now_us = local_clock() / NSEC_PER_USEC;
+
+ if (ca->last_ack == 0 || !tcp_is_cwnd_limited(sk)) {
+ ca->last_ack = now_us;
+ ca->round_start = now_us;
+ } else if (before(now_us, ca->last_ack + 3000)) {
+ u32 base_owd = max(ca->delay_min / 2U, 125U);
+
+ ca->last_ack = now_us;
+ if (after(now_us, ca->round_start + base_owd)) {
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPHYSTARTTRAINDETECT);
+ NET_ADD_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPHYSTARTTRAINCWND,
+ tp->snd_cwnd);
+ tp->snd_ssthresh = tp->snd_cwnd;
+ return;
+ }
+ }
+ }
+
+ if (hystart_detect & HYSTART_DELAY) {
+ if (ca->sample_cnt < 8) {
+ ca->sample_cnt++;
+ } else {
+ s32 thresh = max(ca->delay_min + ca->delay_min / 8U,
+ 125U);
+
+ if (ca->rtt.min > thresh) {
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPHYSTARTDELAYDETECT);
+ NET_ADD_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPHYSTARTDELAYCWND,
+ tp->snd_cwnd);
+ tp->snd_ssthresh = tp->snd_cwnd;
+ }
+ }
+ }
+}
+
+static s32 tcp_cdg_grad(struct cdg *ca)
+{
+ s32 gmin = ca->rtt.min - ca->rtt_prev.min;
+ s32 gmax = ca->rtt.max - ca->rtt_prev.max;
+ s32 grad;
+
+ if (ca->gradients) {
+ ca->gsum.min += gmin - ca->gradients[ca->tail].min;
+ ca->gsum.max += gmax - ca->gradients[ca->tail].max;
+ ca->gradients[ca->tail].min = gmin;
+ ca->gradients[ca->tail].max = gmax;
+ ca->tail = (ca->tail + 1) & (window - 1);
+ gmin = ca->gsum.min;
+ gmax = ca->gsum.max;
+ }
+
+ /* We keep sums to ignore gradients during cwnd reductions;
+ * the paper's smoothed gradients otherwise simplify to:
+ * (rtt_latest - rtt_oldest) / window.
+ *
+ * We also drop division by window here.
+ */
+ grad = gmin > 0 ? gmin : gmax;
+
+ /* Extrapolate missing values in gradient window: */
+ if (!ca->gfilled) {
+ if (!ca->gradients && window > 1)
+ grad *= window; /* Memory allocation failed. */
+ else if (ca->tail == 0)
+ ca->gfilled = true;
+ else
+ grad = (grad * window) / (int)ca->tail;
+ }
+
+ /* Backoff was effectual: */
+ if (gmin <= -32 || gmax <= -32)
+ ca->backoff_cnt = 0;
+
+ if (use_tolerance) {
+ /* Reduce small variations to zero: */
+ gmin = DIV_ROUND_CLOSEST(gmin, 64);
+ gmax = DIV_ROUND_CLOSEST(gmax, 64);
+
+ if (gmin > 0 && gmax <= 0)
+ ca->state = CDG_FULL;
+ else if ((gmin > 0 && gmax > 0) || gmax < 0)
+ ca->state = CDG_NONFULL;
+ }
+ return grad;
+}
+
+static bool tcp_cdg_backoff(struct sock *sk, u32 grad)
+{
+ struct cdg *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (prandom_u32() <= nexp_u32(grad * backoff_factor))
+ return false;
+
+ if (use_ineff) {
+ ca->backoff_cnt++;
+ if (ca->backoff_cnt > use_ineff)
+ return false;
+ }
+
+ ca->shadow_wnd = max(ca->shadow_wnd, tp->snd_cwnd);
+ ca->state = CDG_BACKOFF;
+ tcp_enter_cwr(sk);
+ return true;
+}
+
+/* Not called in CWR or Recovery state. */
+static void tcp_cdg_cong_avoid(struct sock *sk, u32 ack, u32 acked)
+{
+ struct cdg *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 prior_snd_cwnd;
+ u32 incr;
+
+ if (tp->snd_cwnd < tp->snd_ssthresh && hystart_detect)
+ tcp_cdg_hystart_update(sk);
+
+ if (after(ack, ca->rtt_seq) && ca->rtt.v64) {
+ s32 grad = 0;
+
+ if (ca->rtt_prev.v64)
+ grad = tcp_cdg_grad(ca);
+ ca->rtt_seq = tp->snd_nxt;
+ ca->rtt_prev = ca->rtt;
+ ca->rtt.v64 = 0;
+ ca->last_ack = 0;
+ ca->sample_cnt = 0;
+
+ if (grad > 0 && tcp_cdg_backoff(sk, grad))
+ return;
+ }
+
+ if (!tcp_is_cwnd_limited(sk)) {
+ ca->shadow_wnd = min(ca->shadow_wnd, tp->snd_cwnd);
+ return;
+ }
+
+ prior_snd_cwnd = tp->snd_cwnd;
+ tcp_reno_cong_avoid(sk, ack, acked);
+
+ incr = tp->snd_cwnd - prior_snd_cwnd;
+ ca->shadow_wnd = max(ca->shadow_wnd, ca->shadow_wnd + incr);
+}
+
+static void tcp_cdg_acked(struct sock *sk, u32 num_acked, s32 rtt_us)
+{
+ struct cdg *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (rtt_us <= 0)
+ return;
+
+ /* A heuristic for filtering delayed ACKs, adapted from:
+ * D.A. Hayes. "Timing enhancements to the FreeBSD kernel to support
+ * delay and rate based TCP mechanisms." TR 100219A. CAIA, 2010.
+ */
+ if (tp->sacked_out == 0) {
+ if (num_acked == 1 && ca->delack) {
+ /* A delayed ACK is only used for the minimum if it is
+ * provenly lower than an existing non-zero minimum.
+ */
+ ca->rtt.min = min(ca->rtt.min, rtt_us);
+ ca->delack--;
+ return;
+ } else if (num_acked > 1 && ca->delack < 5) {
+ ca->delack++;
+ }
+ }
+
+ ca->rtt.min = min_not_zero(ca->rtt.min, rtt_us);
+ ca->rtt.max = max(ca->rtt.max, rtt_us);
+}
+
+static u32 tcp_cdg_ssthresh(struct sock *sk)
+{
+ struct cdg *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ ca->undo_cwnd = tp->snd_cwnd;
+
+ if (ca->state == CDG_BACKOFF)
+ return max(2U, (tp->snd_cwnd * min(1024U, backoff_beta)) >> 10);
+
+ if (ca->state == CDG_NONFULL && use_tolerance)
+ return tp->snd_cwnd;
+
+ ca->shadow_wnd = min(ca->shadow_wnd >> 1, tp->snd_cwnd);
+ if (use_shadow)
+ return max3(2U, ca->shadow_wnd, tp->snd_cwnd >> 1);
+ return max(2U, tp->snd_cwnd >> 1);
+}
+
+static u32 tcp_cdg_undo_cwnd(struct sock *sk)
+{
+ struct cdg *ca = inet_csk_ca(sk);
+
+ return max(tcp_sk(sk)->snd_cwnd, ca->undo_cwnd);
+}
+
+static void tcp_cdg_cwnd_event(struct sock *sk, const enum tcp_ca_event ev)
+{
+ struct cdg *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct minmax *gradients;
+
+ switch (ev) {
+ case CA_EVENT_CWND_RESTART:
+ gradients = ca->gradients;
+ if (gradients)
+ memset(gradients, 0, window * sizeof(gradients[0]));
+ memset(ca, 0, sizeof(*ca));
+
+ ca->gradients = gradients;
+ ca->rtt_seq = tp->snd_nxt;
+ ca->shadow_wnd = tp->snd_cwnd;
+ break;
+ case CA_EVENT_COMPLETE_CWR:
+ ca->state = CDG_UNKNOWN;
+ ca->rtt_seq = tp->snd_nxt;
+ ca->rtt_prev = ca->rtt;
+ ca->rtt.v64 = 0;
+ break;
+ default:
+ break;
+ }
+}
+
+static void tcp_cdg_init(struct sock *sk)
+{
+ struct cdg *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ /* We silently fall back to window = 1 if allocation fails. */
+ if (window > 1)
+ ca->gradients = kcalloc(window, sizeof(ca->gradients[0]),
+ GFP_NOWAIT | __GFP_NOWARN);
+ ca->rtt_seq = tp->snd_nxt;
+ ca->shadow_wnd = tp->snd_cwnd;
+}
+
+static void tcp_cdg_release(struct sock *sk)
+{
+ struct cdg *ca = inet_csk_ca(sk);
+
+ kfree(ca->gradients);
+}
+
+struct tcp_congestion_ops tcp_cdg __read_mostly = {
+ .cong_avoid = tcp_cdg_cong_avoid,
+ .cwnd_event = tcp_cdg_cwnd_event,
+ .pkts_acked = tcp_cdg_acked,
+ .undo_cwnd = tcp_cdg_undo_cwnd,
+ .ssthresh = tcp_cdg_ssthresh,
+ .release = tcp_cdg_release,
+ .init = tcp_cdg_init,
+ .owner = THIS_MODULE,
+ .name = "cdg",
+};
+
+static int __init tcp_cdg_register(void)
+{
+ if (backoff_beta > 1024 || window < 1 || window > 256)
+ return -ERANGE;
+ if (!is_power_of_2(window))
+ return -EINVAL;
+
+ BUILD_BUG_ON(sizeof(struct cdg) > ICSK_CA_PRIV_SIZE);
+ tcp_register_congestion_control(&tcp_cdg);
+ return 0;
+}
+
+static void __exit tcp_cdg_unregister(void)
+{
+ tcp_unregister_congestion_control(&tcp_cdg);
+}
+
+module_init(tcp_cdg_register);
+module_exit(tcp_cdg_unregister);
+MODULE_AUTHOR("Kenneth Klette Jonassen");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("TCP CDG");
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 4c41c1287197..7092a61c4dc8 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -204,20 +204,26 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
/* Expired RTT */
if (!before(tp->snd_una, ca->next_seq)) {
- /* For avoiding denominator == 1. */
- if (ca->acked_bytes_total == 0)
- ca->acked_bytes_total = 1;
+ u64 bytes_ecn = ca->acked_bytes_ecn;
+ u32 alpha = ca->dctcp_alpha;
/* alpha = (1 - g) * alpha + g * F */
- ca->dctcp_alpha = ca->dctcp_alpha -
- (ca->dctcp_alpha >> dctcp_shift_g) +
- (ca->acked_bytes_ecn << (10U - dctcp_shift_g)) /
- ca->acked_bytes_total;
- if (ca->dctcp_alpha > DCTCP_MAX_ALPHA)
- /* Clamp dctcp_alpha to max. */
- ca->dctcp_alpha = DCTCP_MAX_ALPHA;
+ alpha -= alpha >> dctcp_shift_g;
+ if (bytes_ecn) {
+ /* If dctcp_shift_g == 1, a 32bit value would overflow
+ * after 8 Mbytes.
+ */
+ bytes_ecn <<= (10 - dctcp_shift_g);
+ do_div(bytes_ecn, max(1U, ca->acked_bytes_total));
+ alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA);
+ }
+ /* dctcp_alpha can be read from dctcp_get_info() without
+ * synchro, so we ask compiler to not use dctcp_alpha
+ * as a temporary variable in prior operations.
+ */
+ WRITE_ONCE(ca->dctcp_alpha, alpha);
dctcp_reset(tp, ca);
}
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c9ab964189a0..684f095d196e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -359,7 +359,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
/* Check #1 */
if (tp->rcv_ssthresh < tp->window_clamp &&
(int)tp->rcv_ssthresh < tcp_space(sk) &&
- !sk_under_memory_pressure(sk)) {
+ !tcp_under_memory_pressure(sk)) {
int incr;
/* Check #2. Increase window, if skb with such overhead
@@ -446,7 +446,7 @@ static void tcp_clamp_window(struct sock *sk)
if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
- !sk_under_memory_pressure(sk) &&
+ !tcp_under_memory_pressure(sk) &&
sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
sysctl_tcp_rmem[2]);
@@ -1130,7 +1130,12 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
struct tcp_sacktag_state {
int reord;
int fack_count;
- long rtt_us; /* RTT measured by SACKing never-retransmitted data */
+ /* Timestamps for earliest and latest never-retransmitted segment
+ * that was SACKed. RTO needs the earliest RTT to stay conservative,
+ * but congestion control should still get an accurate delay signal.
+ */
+ struct skb_mstamp first_sackt;
+ struct skb_mstamp last_sackt;
int flag;
};
@@ -1233,14 +1238,9 @@ static u8 tcp_sacktag_one(struct sock *sk,
state->reord);
if (!after(end_seq, tp->high_seq))
state->flag |= FLAG_ORIG_SACK_ACKED;
- /* Pick the earliest sequence sacked for RTT */
- if (state->rtt_us < 0) {
- struct skb_mstamp now;
-
- skb_mstamp_get(&now);
- state->rtt_us = skb_mstamp_us_delta(&now,
- xmit_time);
- }
+ if (state->first_sackt.v64 == 0)
+ state->first_sackt = *xmit_time;
+ state->last_sackt = *xmit_time;
}
if (sacked & TCPCB_LOST) {
@@ -1316,16 +1316,12 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
* code can come after this skb later on it's better to keep
* setting gso_size to something.
*/
- if (!skb_shinfo(prev)->gso_size) {
- skb_shinfo(prev)->gso_size = mss;
- skb_shinfo(prev)->gso_type = sk->sk_gso_type;
- }
+ if (!TCP_SKB_CB(prev)->tcp_gso_size)
+ TCP_SKB_CB(prev)->tcp_gso_size = mss;
/* CHECKME: To clear or not to clear? Mimics normal skb currently */
- if (tcp_skb_pcount(skb) <= 1) {
- skb_shinfo(skb)->gso_size = 0;
- skb_shinfo(skb)->gso_type = 0;
- }
+ if (tcp_skb_pcount(skb) <= 1)
+ TCP_SKB_CB(skb)->tcp_gso_size = 0;
/* Difference in this won't matter, both ACKed by the same cumul. ACK */
TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);
@@ -1634,7 +1630,7 @@ static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_bl
static int
tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
- u32 prior_snd_una, long *sack_rtt_us)
+ u32 prior_snd_una, struct tcp_sacktag_state *state)
{
struct tcp_sock *tp = tcp_sk(sk);
const unsigned char *ptr = (skb_transport_header(ack_skb) +
@@ -1642,7 +1638,6 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
struct tcp_sack_block_wire *sp_wire = (struct tcp_sack_block_wire *)(ptr+2);
struct tcp_sack_block sp[TCP_NUM_SACKS];
struct tcp_sack_block *cache;
- struct tcp_sacktag_state state;
struct sk_buff *skb;
int num_sacks = min(TCP_NUM_SACKS, (ptr[1] - TCPOLEN_SACK_BASE) >> 3);
int used_sacks;
@@ -1650,9 +1645,8 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
int i, j;
int first_sack_index;
- state.flag = 0;
- state.reord = tp->packets_out;
- state.rtt_us = -1L;
+ state->flag = 0;
+ state->reord = tp->packets_out;
if (!tp->sacked_out) {
if (WARN_ON(tp->fackets_out))
@@ -1663,7 +1657,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire,
num_sacks, prior_snd_una);
if (found_dup_sack)
- state.flag |= FLAG_DSACKING_ACK;
+ state->flag |= FLAG_DSACKING_ACK;
/* Eliminate too old ACKs, but take into
* account more or less fresh ones, they can
@@ -1728,7 +1722,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
}
skb = tcp_write_queue_head(sk);
- state.fack_count = 0;
+ state->fack_count = 0;
i = 0;
if (!tp->sacked_out) {
@@ -1762,10 +1756,10 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
/* Head todo? */
if (before(start_seq, cache->start_seq)) {
- skb = tcp_sacktag_skip(skb, sk, &state,
+ skb = tcp_sacktag_skip(skb, sk, state,
start_seq);
skb = tcp_sacktag_walk(skb, sk, next_dup,
- &state,
+ state,
start_seq,
cache->start_seq,
dup_sack);
@@ -1776,7 +1770,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
goto advance_sp;
skb = tcp_maybe_skipping_dsack(skb, sk, next_dup,
- &state,
+ state,
cache->end_seq);
/* ...tail remains todo... */
@@ -1785,12 +1779,12 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
skb = tcp_highest_sack(sk);
if (!skb)
break;
- state.fack_count = tp->fackets_out;
+ state->fack_count = tp->fackets_out;
cache++;
goto walk;
}
- skb = tcp_sacktag_skip(skb, sk, &state, cache->end_seq);
+ skb = tcp_sacktag_skip(skb, sk, state, cache->end_seq);
/* Check overlap against next cached too (past this one already) */
cache++;
continue;
@@ -1800,12 +1794,12 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
skb = tcp_highest_sack(sk);
if (!skb)
break;
- state.fack_count = tp->fackets_out;
+ state->fack_count = tp->fackets_out;
}
- skb = tcp_sacktag_skip(skb, sk, &state, start_seq);
+ skb = tcp_sacktag_skip(skb, sk, state, start_seq);
walk:
- skb = tcp_sacktag_walk(skb, sk, next_dup, &state,
+ skb = tcp_sacktag_walk(skb, sk, next_dup, state,
start_seq, end_seq, dup_sack);
advance_sp:
@@ -1820,9 +1814,9 @@ advance_sp:
for (j = 0; j < used_sacks; j++)
tp->recv_sack_cache[i++] = sp[j];
- if ((state.reord < tp->fackets_out) &&
+ if ((state->reord < tp->fackets_out) &&
((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker))
- tcp_update_reordering(sk, tp->fackets_out - state.reord, 0);
+ tcp_update_reordering(sk, tp->fackets_out - state->reord, 0);
tcp_mark_lost_retrans(sk);
tcp_verify_left_out(tp);
@@ -1834,8 +1828,7 @@ out:
WARN_ON((int)tp->retrans_out < 0);
WARN_ON((int)tcp_packets_in_flight(tp) < 0);
#endif
- *sack_rtt_us = state.rtt_us;
- return state.flag;
+ return state->flag;
}
/* Limits sacked_out so that sum with lost_out isn't ever larger than
@@ -2255,7 +2248,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
(oldcnt >= packets))
break;
- mss = skb_shinfo(skb)->gso_size;
+ mss = tcp_skb_mss(skb);
err = tcp_fragment(sk, skb, (packets - oldcnt) * mss,
mss, GFP_ATOMIC);
if (err < 0)
@@ -2555,6 +2548,7 @@ void tcp_enter_cwr(struct sock *sk)
tcp_set_ca_state(sk, TCP_CA_CWR);
}
}
+EXPORT_SYMBOL(tcp_enter_cwr);
static void tcp_try_keep_open(struct sock *sk)
{
@@ -3055,7 +3049,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
* arrived at the other end.
*/
static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
- u32 prior_snd_una, long sack_rtt_us)
+ u32 prior_snd_una,
+ struct tcp_sacktag_state *sack)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct skb_mstamp first_ackt, last_ackt, now;
@@ -3063,8 +3058,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
u32 prior_sacked = tp->sacked_out;
u32 reord = tp->packets_out;
bool fully_acked = true;
- long ca_seq_rtt_us = -1L;
+ long sack_rtt_us = -1L;
long seq_rtt_us = -1L;
+ long ca_rtt_us = -1L;
struct sk_buff *skb;
u32 pkts_acked = 0;
bool rtt_update;
@@ -3153,15 +3149,16 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
skb_mstamp_get(&now);
if (likely(first_ackt.v64)) {
seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt);
- ca_seq_rtt_us = skb_mstamp_us_delta(&now, &last_ackt);
+ ca_rtt_us = skb_mstamp_us_delta(&now, &last_ackt);
+ }
+ if (sack->first_sackt.v64) {
+ sack_rtt_us = skb_mstamp_us_delta(&now, &sack->first_sackt);
+ ca_rtt_us = skb_mstamp_us_delta(&now, &sack->last_sackt);
}
rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us);
if (flag & FLAG_ACKED) {
- const struct tcp_congestion_ops *ca_ops
- = inet_csk(sk)->icsk_ca_ops;
-
tcp_rearm_rto(sk);
if (unlikely(icsk->icsk_mtup.probe_size &&
!after(tp->mtu_probe.probe_seq_end, tp->snd_una))) {
@@ -3184,11 +3181,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
tp->fackets_out -= min(pkts_acked, tp->fackets_out);
- if (ca_ops->pkts_acked) {
- long rtt_us = min_t(ulong, ca_seq_rtt_us, sack_rtt_us);
- ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
- }
-
} else if (skb && rtt_update && sack_rtt_us >= 0 &&
sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) {
/* Do not re-arm RTO if the sack RTT is measured from data sent
@@ -3198,6 +3190,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
tcp_rearm_rto(sk);
}
+ if (icsk->icsk_ca_ops->pkts_acked)
+ icsk->icsk_ca_ops->pkts_acked(sk, pkts_acked, ca_rtt_us);
+
#if FASTRETRANS_DEBUG > 0
WARN_ON((int)tp->sacked_out < 0);
WARN_ON((int)tp->lost_out < 0);
@@ -3238,7 +3233,7 @@ static void tcp_ack_probe(struct sock *sk)
* This function is not for random using!
*/
} else {
- unsigned long when = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
+ unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
when, TCP_RTO_MAX);
@@ -3466,6 +3461,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_sacktag_state sack_state;
u32 prior_snd_una = tp->snd_una;
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
@@ -3474,7 +3470,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
int prior_packets = tp->packets_out;
const int prior_unsacked = tp->packets_out - tp->sacked_out;
int acked = 0; /* Number of packets newly acked */
- long sack_rtt_us = -1L;
+
+ sack_state.first_sackt.v64 = 0;
/* We very likely will need to access write queue head. */
prefetchw(sk->sk_write_queue.next);
@@ -3538,7 +3535,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (TCP_SKB_CB(skb)->sacked)
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
- &sack_rtt_us);
+ &sack_state);
if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) {
flag |= FLAG_ECE;
@@ -3563,7 +3560,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
/* See if we can take anything off of the retransmit queue. */
acked = tp->packets_out;
flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una,
- sack_rtt_us);
+ &sack_state);
acked -= tp->packets_out;
/* Advance cwnd if state allows */
@@ -3615,7 +3612,7 @@ old_ack:
*/
if (TCP_SKB_CB(skb)->sacked) {
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
- &sack_rtt_us);
+ &sack_state);
tcp_fastretrans_alert(sk, acked, prior_unsacked,
is_dupack, flag);
}
@@ -4514,10 +4511,12 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
if (eaten <= 0) {
queue_and_out:
- if (eaten < 0 &&
- tcp_try_rmem_schedule(sk, skb, skb->truesize))
- goto drop;
-
+ if (eaten < 0) {
+ if (skb_queue_len(&sk->sk_receive_queue) == 0)
+ sk_forced_mem_schedule(sk, skb->truesize);
+ else if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
+ goto drop;
+ }
eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
}
tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
@@ -4788,7 +4787,7 @@ static int tcp_prune_queue(struct sock *sk)
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
tcp_clamp_window(sk);
- else if (sk_under_memory_pressure(sk))
+ else if (tcp_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
tcp_collapse_ofo_queue(sk);
@@ -4832,7 +4831,7 @@ static bool tcp_should_expand_sndbuf(const struct sock *sk)
return false;
/* If we are under global TCP memory pressure, do not expand. */
- if (sk_under_memory_pressure(sk))
+ if (tcp_under_memory_pressure(sk))
return false;
/* If we are under soft global TCP memory pressure, do not expand. */
@@ -6067,6 +6066,23 @@ static bool tcp_syn_flood_action(struct sock *sk,
return want_cookie;
}
+static void tcp_reqsk_record_syn(const struct sock *sk,
+ struct request_sock *req,
+ const struct sk_buff *skb)
+{
+ if (tcp_sk(sk)->save_syn) {
+ u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb);
+ u32 *copy;
+
+ copy = kmalloc(len + sizeof(u32), GFP_ATOMIC);
+ if (copy) {
+ copy[0] = len;
+ memcpy(&copy[1], skb_network_header(skb), len);
+ req->saved_syn = copy;
+ }
+ }
+}
+
int tcp_conn_request(struct request_sock_ops *rsk_ops,
const struct tcp_request_sock_ops *af_ops,
struct sock *sk, struct sk_buff *skb)
@@ -6199,6 +6215,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
tcp_rsk(req)->tfo_listener = false;
af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
}
+ tcp_reqsk_record_syn(sk, req, skb);
return 0;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fc1c658ec6c1..d7d4c2b79cf2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1400,7 +1400,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
return 0;
}
- if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb))
+ if (tcp_checksum_complete(skb))
goto csum_err;
if (sk->sk_state == TCP_LISTEN) {
@@ -1626,6 +1626,7 @@ process:
skb->dev = NULL;
bh_lock_sock_nested(sk);
+ tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
ret = 0;
if (!sock_owned_by_user(sk)) {
if (!tcp_prequeue(sk, skb))
@@ -1646,7 +1647,7 @@ no_tcp_socket:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard_it;
- if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
+ if (tcp_checksum_complete(skb)) {
csum_error:
TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
bad_packet:
@@ -1670,10 +1671,6 @@ do_time_wait:
goto discard_it;
}
- if (skb->len < (th->doff << 2)) {
- inet_twsk_put(inet_twsk(sk));
- goto bad_packet;
- }
if (tcp_checksum_complete(skb)) {
inet_twsk_put(inet_twsk(sk));
goto csum_error;
@@ -1802,6 +1799,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
/* If socket is aborted during connect operation */
tcp_free_fastopen_req(tp);
+ tcp_saved_syn_free(tp);
sk_sockets_allocated_dec(sk);
sock_release_memcg(sk);
@@ -2410,12 +2408,15 @@ static int __net_init tcp_sk_init(struct net *net)
goto fail;
*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
}
+
net->ipv4.sysctl_tcp_ecn = 2;
+ net->ipv4.sysctl_tcp_ecn_fallback = 1;
+
net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
- return 0;
+ return 0;
fail:
tcp_sk_exit(net);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 17e7339ee5ca..4bc00cb79e60 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -451,6 +451,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->rcv_wup = newtp->copied_seq =
newtp->rcv_nxt = treq->rcv_isn + 1;
+ newtp->segs_in = 0;
newtp->snd_sml = newtp->snd_una =
newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
@@ -539,6 +540,9 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->fastopen_rsk = NULL;
newtp->syn_data_acked = 0;
+ newtp->saved_syn = req->saved_syn;
+ req->saved_syn = NULL;
+
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS);
}
return newsk;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 3f7c2fca5431..9864a2dbadce 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -77,7 +77,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
oldlen = (u16)~skb->len;
__skb_pull(skb, thlen);
- mss = tcp_skb_mss(skb);
+ mss = skb_shinfo(skb)->gso_size;
if (unlikely(skb->len <= mss))
goto out;
@@ -242,7 +242,7 @@ found:
flush |= *(u32 *)((u8 *)th + i) ^
*(u32 *)((u8 *)th2 + i);
- mss = tcp_skb_mss(p);
+ mss = skb_shinfo(p)->gso_size;
flush |= (len - 1) >= mss;
flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a369e8a70b2c..b1c218df2c85 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -50,8 +50,8 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1;
*/
int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
-/* Default TSQ limit of two TSO segments */
-int sysctl_tcp_limit_output_bytes __read_mostly = 131072;
+/* Default TSQ limit of four TSO segments */
+int sysctl_tcp_limit_output_bytes __read_mostly = 262144;
/* This limits the percentage of the congestion window which we
* will allow a single TSO frame to consume. Building TSO frames
@@ -350,6 +350,15 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
}
}
+static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
+{
+ if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)
+ /* tp->ecn_flags are cleared at a later point in time when
+ * SYN ACK is ultimatively being received.
+ */
+ TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR);
+}
+
static void
tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th,
struct sock *sk)
@@ -393,8 +402,6 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
*/
static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
{
- struct skb_shared_info *shinfo = skb_shinfo(skb);
-
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
@@ -402,8 +409,6 @@ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
TCP_SKB_CB(skb)->sacked = 0;
tcp_skb_pcount_set(skb, 1);
- shinfo->gso_size = 0;
- shinfo->gso_type = 0;
TCP_SKB_CB(skb)->seq = seq;
if (flags & (TCPHDR_SYN | TCPHDR_FIN))
@@ -994,6 +999,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
}
tcp_options_write((__be32 *)(th + 1), tp, &opts);
+ skb_shinfo(skb)->gso_type = sk->sk_gso_type;
if (likely((tcb->tcp_flags & TCPHDR_SYN) == 0))
tcp_ecn_send(sk, skb, tcp_header_size);
@@ -1018,8 +1024,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
tcp_skb_pcount(skb));
- /* OK, its time to fill skb_shinfo(skb)->gso_segs */
+ tp->segs_out += tcp_skb_pcount(skb);
+ /* OK, its time to fill skb_shinfo(skb)->gso_{segs|size} */
skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb);
+ skb_shinfo(skb)->gso_size = tcp_skb_mss(skb);
/* Our usage of tstamp should remain private */
skb->tstamp.tv64 = 0;
@@ -1056,25 +1064,17 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
}
/* Initialize TSO segments for a packet. */
-static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
- unsigned int mss_now)
+static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now)
{
- struct skb_shared_info *shinfo = skb_shinfo(skb);
-
- /* Make sure we own this skb before messing gso_size/gso_segs */
- WARN_ON_ONCE(skb_cloned(skb));
-
if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) {
/* Avoid the costly divide in the normal
* non-TSO case.
*/
tcp_skb_pcount_set(skb, 1);
- shinfo->gso_size = 0;
- shinfo->gso_type = 0;
+ TCP_SKB_CB(skb)->tcp_gso_size = 0;
} else {
tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now));
- shinfo->gso_size = mss_now;
- shinfo->gso_type = sk->sk_gso_type;
+ TCP_SKB_CB(skb)->tcp_gso_size = mss_now;
}
}
@@ -1163,7 +1163,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
return -ENOMEM;
/* Get a new skb... force flag on. */
- buff = sk_stream_alloc_skb(sk, nsize, gfp);
+ buff = sk_stream_alloc_skb(sk, nsize, gfp, true);
if (!buff)
return -ENOMEM; /* We'll just try again later. */
@@ -1206,8 +1206,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
old_factor = tcp_skb_pcount(skb);
/* Fix up tso_factor for both original and new SKB. */
- tcp_set_skb_tso_segs(sk, skb, mss_now);
- tcp_set_skb_tso_segs(sk, buff, mss_now);
+ tcp_set_skb_tso_segs(skb, mss_now);
+ tcp_set_skb_tso_segs(buff, mss_now);
/* If this packet has been sent out already, we must
* adjust the various packet counters.
@@ -1287,7 +1287,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
/* Any change of skb->len requires recalculation of tso factor. */
if (tcp_skb_pcount(skb) > 1)
- tcp_set_skb_tso_segs(sk, skb, tcp_skb_mss(skb));
+ tcp_set_skb_tso_segs(skb, tcp_skb_mss(skb));
return 0;
}
@@ -1619,13 +1619,12 @@ static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp,
* This must be invoked the first time we consider transmitting
* SKB onto the wire.
*/
-static int tcp_init_tso_segs(const struct sock *sk, struct sk_buff *skb,
- unsigned int mss_now)
+static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now)
{
int tso_segs = tcp_skb_pcount(skb);
if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) {
- tcp_set_skb_tso_segs(sk, skb, mss_now);
+ tcp_set_skb_tso_segs(skb, mss_now);
tso_segs = tcp_skb_pcount(skb);
}
return tso_segs;
@@ -1680,7 +1679,7 @@ static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb,
const struct tcp_sock *tp = tcp_sk(sk);
unsigned int cwnd_quota;
- tcp_init_tso_segs(sk, skb, cur_mss);
+ tcp_init_tso_segs(skb, cur_mss);
if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
return 0;
@@ -1722,7 +1721,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
if (skb->len != skb->data_len)
return tcp_fragment(sk, skb, len, mss_now, gfp);
- buff = sk_stream_alloc_skb(sk, 0, gfp);
+ buff = sk_stream_alloc_skb(sk, 0, gfp, true);
if (unlikely(!buff))
return -ENOMEM;
@@ -1749,8 +1748,8 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
tcp_fragment_tstamp(skb, buff);
/* Fix up tso_factor for both original and new SKB. */
- tcp_set_skb_tso_segs(sk, skb, mss_now);
- tcp_set_skb_tso_segs(sk, buff, mss_now);
+ tcp_set_skb_tso_segs(skb, mss_now);
+ tcp_set_skb_tso_segs(buff, mss_now);
/* Link BUFF into the send queue. */
__skb_header_release(buff);
@@ -1941,7 +1940,7 @@ static int tcp_mtu_probe(struct sock *sk)
}
/* We're allowed to probe. Build it now. */
- nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC);
+ nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
if (!nskb)
return -1;
sk->sk_wmem_queued += nskb->truesize;
@@ -1984,7 +1983,7 @@ static int tcp_mtu_probe(struct sock *sk)
skb->len, 0);
} else {
__pskb_trim_head(skb, copy);
- tcp_set_skb_tso_segs(sk, skb, mss_now);
+ tcp_set_skb_tso_segs(skb, mss_now);
}
TCP_SKB_CB(skb)->seq += copy;
}
@@ -1994,7 +1993,7 @@ static int tcp_mtu_probe(struct sock *sk)
if (len >= probe_size)
break;
}
- tcp_init_tso_segs(sk, nskb, nskb->len);
+ tcp_init_tso_segs(nskb, nskb->len);
/* We're ready to send. If this fails, the probe will
* be resegmented into mss-sized pieces by tcp_write_xmit().
@@ -2056,7 +2055,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
while ((skb = tcp_send_head(sk))) {
unsigned int limit;
- tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
+ tso_segs = tcp_init_tso_segs(skb, mss_now);
BUG_ON(!tso_segs);
if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
@@ -2078,7 +2077,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
break;
- if (tso_segs == 1 || !max_segs) {
+ if (tso_segs == 1) {
if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
(tcp_skb_is_last(sk, skb) ?
nonagle : TCP_NAGLE_PUSH))))
@@ -2091,7 +2090,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
}
limit = mss_now;
- if (tso_segs > 1 && max_segs && !tcp_urg_mode(tp))
+ if (tso_segs > 1 && !tcp_urg_mode(tp))
limit = tcp_mss_split_point(sk, skb, mss_now,
min_t(unsigned int,
cwnd_quota,
@@ -2392,7 +2391,7 @@ u32 __tcp_select_window(struct sock *sk)
if (free_space < (full_space >> 1)) {
icsk->icsk_ack.quick = 0;
- if (sk_under_memory_pressure(sk))
+ if (tcp_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh,
4U * tp->advmss);
@@ -2610,11 +2609,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
if (unlikely(oldpcount > 1)) {
if (skb_unclone(skb, GFP_ATOMIC))
return -ENOMEM;
- tcp_init_tso_segs(sk, skb, cur_mss);
+ tcp_init_tso_segs(skb, cur_mss);
tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
}
}
+ /* RFC3168, section 6.1.1.1. ECN fallback */
+ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN)
+ tcp_ecn_clear_syn(sk, skb);
+
tcp_retrans_try_collapse(sk, skb, cur_mss);
/* Make a copy, if the first transmission SKB clone we made
@@ -2816,8 +2819,10 @@ begin_fwd:
* connection tear down and (memory) recovery.
* Otherwise tcp_send_fin() could be tempted to either delay FIN
* or even be forced to close flow without any FIN.
+ * In general, we want to allow one skb per socket to avoid hangs
+ * with edge trigger epoll()
*/
-static void sk_forced_wmem_schedule(struct sock *sk, int size)
+void sk_forced_mem_schedule(struct sock *sk, int size)
{
int amt, status;
@@ -2841,7 +2846,7 @@ void tcp_send_fin(struct sock *sk)
* Note: in the latter case, FIN packet will be sent after a timeout,
* as TCP stack thinks it has already been transmitted.
*/
- if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+ if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) {
coalesce:
TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
TCP_SKB_CB(tskb)->end_seq++;
@@ -2864,7 +2869,7 @@ coalesce:
return;
}
skb_reserve(skb, MAX_TCP_HEADER);
- sk_forced_wmem_schedule(sk, skb->truesize);
+ sk_forced_mem_schedule(sk, skb->truesize);
/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
tcp_init_nondata_skb(skb, tp->write_seq,
TCPHDR_ACK | TCPHDR_FIN);
@@ -3175,7 +3180,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
/* limit to order-0 allocations */
space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
- syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation);
+ syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation, false);
if (!syn_data)
goto fallback;
syn_data->ip_summed = CHECKSUM_PARTIAL;
@@ -3241,7 +3246,7 @@ int tcp_connect(struct sock *sk)
return 0;
}
- buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+ buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, true);
if (unlikely(!buff))
return -ENOBUFS;
@@ -3382,7 +3387,7 @@ EXPORT_SYMBOL_GPL(tcp_send_ack);
* one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is
* out-of-date with SND.UNA-1 to probe window.
*/
-static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
+static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
@@ -3400,6 +3405,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
*/
tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
skb_mstamp_get(&skb->skb_mstamp);
+ NET_INC_STATS_BH(sock_net(sk), mib);
return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
}
@@ -3407,12 +3413,12 @@ void tcp_send_window_probe(struct sock *sk)
{
if (sk->sk_state == TCP_ESTABLISHED) {
tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
- tcp_xmit_probe_skb(sk, 0);
+ tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE);
}
}
/* Initiate keepalive or window probe from timer. */
-int tcp_write_wakeup(struct sock *sk)
+int tcp_write_wakeup(struct sock *sk, int mib)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
@@ -3440,7 +3446,7 @@ int tcp_write_wakeup(struct sock *sk)
if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC))
return -1;
} else if (!tcp_skb_pcount(skb))
- tcp_set_skb_tso_segs(sk, skb, mss);
+ tcp_set_skb_tso_segs(skb, mss);
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
@@ -3449,8 +3455,8 @@ int tcp_write_wakeup(struct sock *sk)
return err;
} else {
if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF))
- tcp_xmit_probe_skb(sk, 1);
- return tcp_xmit_probe_skb(sk, 0);
+ tcp_xmit_probe_skb(sk, 1, mib);
+ return tcp_xmit_probe_skb(sk, 0, mib);
}
}
@@ -3464,7 +3470,7 @@ void tcp_send_probe0(struct sock *sk)
unsigned long probe_max;
int err;
- err = tcp_write_wakeup(sk);
+ err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE);
if (tp->packets_out || !tcp_send_head(sk)) {
/* Cancel probe timer, if it is not required. */
@@ -3490,7 +3496,7 @@ void tcp_send_probe0(struct sock *sk)
probe_max = TCP_RESOURCE_PROBE_INTERVAL;
}
inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
- inet_csk_rto_backoff(icsk, probe_max),
+ tcp_probe0_when(sk, probe_max),
TCP_RTO_MAX);
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 8c65dc147d8b..5b752f58a900 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -247,7 +247,7 @@ void tcp_delack_timer_handler(struct sock *sk)
}
out:
- if (sk_under_memory_pressure(sk))
+ if (tcp_under_memory_pressure(sk))
sk_mem_reclaim(sk);
}
@@ -616,7 +616,7 @@ static void tcp_keepalive_timer (unsigned long data)
tcp_write_err(sk);
goto out;
}
- if (tcp_write_wakeup(sk) <= 0) {
+ if (tcp_write_wakeup(sk, LINUX_MIB_TCPKEEPALIVE) <= 0) {
icsk->icsk_probes_out++;
elapsed = keepalive_intvl_when(tp);
} else {
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 6bb98cc193c9..933ea903f7b8 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -15,12 +15,10 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
struct socket *sock = NULL;
struct sockaddr_in udp_addr;
- err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock);
+ err = sock_create_kern(net, AF_INET, SOCK_DGRAM, 0, &sock);
if (err < 0)
goto error;
- sk_change_net(sock->sk, net);
-
udp_addr.sin_family = AF_INET;
udp_addr.sin_addr = cfg->local_ip;
udp_addr.sin_port = cfg->local_udp_port;
@@ -47,7 +45,7 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
error:
if (sock) {
kernel_sock_shutdown(sock, SHUT_RDWR);
- sk_release_kernel(sock->sk);
+ sock_release(sock);
}
*sockp = NULL;
return err;
@@ -101,7 +99,7 @@ void udp_tunnel_sock_release(struct socket *sock)
{
rcu_assign_sk_user_data(sock->sk, NULL);
kernel_sock_shutdown(sock, SHUT_RDWR);
- sk_release_kernel(sock->sk);
+ sock_release(sock);
}
EXPORT_SYMBOL_GPL(udp_tunnel_sock_release);
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 2e8c06108ab9..0f3f1999719a 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -48,4 +48,5 @@ obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o
ifneq ($(CONFIG_IPV6),)
obj-$(CONFIG_NET_UDP_TUNNEL) += ip6_udp_tunnel.o
+obj-y += mcast_snoop.o
endif
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 37b70e82bff8..21c2c818df3b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2121,6 +2121,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0);
if (!fn)
goto out;
+
+ noflags |= RTF_CACHE;
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
if (rt->dst.dev->ifindex != dev->ifindex)
continue;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index eef63b394c5a..7de52b65173f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -167,7 +167,7 @@ lookup_protocol:
WARN_ON(!answer_prot->slab);
err = -ENOBUFS;
- sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot);
+ sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot, kern);
if (!sk)
goto out;
@@ -362,7 +362,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
np->saddr = addr->sin6_addr;
/* Make sure we are allowed to bind here. */
- if (sk->sk_prot->get_port(sk, snum)) {
+ if ((snum || !inet->bind_address_no_port) &&
+ sk->sk_prot->get_port(sk, snum)) {
inet_reset_saddr(sk);
err = -EADDRINUSE;
goto out;
@@ -768,6 +769,7 @@ static int __net_init inet6_net_init(struct net *net)
net->ipv6.sysctl.auto_flowlabels = 0;
net->ipv6.sysctl.idgen_retries = 3;
net->ipv6.sysctl.idgen_delay = 1 * HZ;
+ net->ipv6.sysctl.flowlabel_state_ranges = 1;
atomic_set(&net->ipv6.fib6_sernum, 1);
err = ipv6_init_mibs(net);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 2c2b5d51f15c..713d7434c911 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -207,7 +207,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
struct inet_peer *peer;
peer = inet_getpeer_v6(net->ipv6.peers,
- &rt->rt6i_dst.addr, 1);
+ &fl6->daddr, 1);
res = inet_peer_xrlim_allow(peer, tmo);
if (peer)
inet_putpeer(peer);
@@ -337,7 +337,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net,
* We won't send icmp if the destination is known
* anycast.
*/
- if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
+ if (ipv6_anycast_destination(dst, &fl6->daddr)) {
net_dbg_ratelimited("icmp6_send: acast source\n");
dst_release(dst);
return ERR_PTR(-EINVAL);
@@ -564,7 +564,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
if (!ipv6_unicast_destination(skb) &&
!(net->ipv6.sysctl.anycast_src_echo_reply &&
- ipv6_anycast_destination(skb)))
+ ipv6_anycast_destination(skb_dst(skb), saddr)))
saddr = NULL;
memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 871641bc1ed4..b4fd96de97e6 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -257,7 +257,7 @@ not_unique:
return -EADDRNOTAVAIL;
}
-static inline u32 inet6_sk_port_offset(const struct sock *sk)
+static u32 inet6_sk_port_offset(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
@@ -269,7 +269,11 @@ static inline u32 inet6_sk_port_offset(const struct sock *sk)
int inet6_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
- return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk),
+ u32 port_offset = 0;
+
+ if (!inet_sk(sk)->inet_num)
+ port_offset = inet6_sk_port_offset(sk);
+ return __inet_hash_connect(death_row, sk, port_offset,
__inet6_check_established);
}
EXPORT_SYMBOL_GPL(inet6_hash_connect);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index bde57b113009..55d19861ab20 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -154,10 +154,32 @@ static void node_free(struct fib6_node *fn)
kmem_cache_free(fib6_node_kmem, fn);
}
+static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
+{
+ int cpu;
+
+ if (!non_pcpu_rt->rt6i_pcpu)
+ return;
+
+ for_each_possible_cpu(cpu) {
+ struct rt6_info **ppcpu_rt;
+ struct rt6_info *pcpu_rt;
+
+ ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu);
+ pcpu_rt = *ppcpu_rt;
+ if (pcpu_rt) {
+ dst_free(&pcpu_rt->dst);
+ *ppcpu_rt = NULL;
+ }
+ }
+}
+
static void rt6_release(struct rt6_info *rt)
{
- if (atomic_dec_and_test(&rt->rt6i_ref))
+ if (atomic_dec_and_test(&rt->rt6i_ref)) {
+ rt6_free_pcpu(rt);
dst_free(&rt->dst);
+ }
}
static void fib6_link_table(struct net *net, struct fib6_table *tb)
@@ -738,6 +760,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
rt6_clean_expires(iter);
else
rt6_set_expires(iter, rt->dst.expires);
+ iter->rt6i_pmtu = rt->rt6i_pmtu;
return -EEXIST;
}
/* If we have the same destination and the same metric,
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index d491125011c4..1f9ebe3cbb4a 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -595,6 +595,10 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
return -EINVAL;
+ if (net->ipv6.sysctl.flowlabel_state_ranges &&
+ (freq.flr_label & IPV6_FLOWLABEL_STATELESS_FLAG))
+ return -ERANGE;
+
fl = fl_create(net, sk, &freq, optval, optlen, &err);
if (!fl)
return err;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index bc09cb97b840..d5f7716662db 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -105,7 +105,7 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
}
rcu_read_lock_bh();
- nexthop = rt6_nexthop((struct rt6_info *)dst);
+ nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
@@ -459,7 +459,7 @@ int ip6_forward(struct sk_buff *skb)
else
target = &hdr->daddr;
- peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
+ peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
@@ -551,7 +551,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
struct frag_hdr *fh;
unsigned int mtu, hlen, left, len;
int hroom, troom;
- __be32 frag_id = 0;
+ __be32 frag_id;
int ptr, offset = 0, err = 0;
u8 *prevhdr, nexthdr = 0;
struct net *net = dev_net(skb_dst(skb)->dev);
@@ -564,18 +564,17 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
/* We must not fragment if the socket is set to force MTU discovery
* or if the skb it not generated by a local socket.
*/
- if (unlikely(!skb->ignore_df && skb->len > mtu) ||
- (IP6CB(skb)->frag_max_size &&
- IP6CB(skb)->frag_max_size > mtu)) {
- if (skb->sk && dst_allfrag(skb_dst(skb)))
- sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+ if (unlikely(!skb->ignore_df && skb->len > mtu))
+ goto fail_toobig;
- skb->dev = skb_dst(skb)->dev;
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
- IPSTATS_MIB_FRAGFAILS);
- kfree_skb(skb);
- return -EMSGSIZE;
+ if (IP6CB(skb)->frag_max_size) {
+ if (IP6CB(skb)->frag_max_size > mtu)
+ goto fail_toobig;
+
+ /* don't send fragments larger than what we received */
+ mtu = IP6CB(skb)->frag_max_size;
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
}
if (np && np->frag_size < mtu) {
@@ -584,6 +583,9 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
}
mtu -= hlen + sizeof(struct frag_hdr);
+ frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
+ &ipv6_hdr(skb)->saddr);
+
if (skb_has_frag_list(skb)) {
int first_len = skb_pagelen(skb);
struct sk_buff *frag2;
@@ -632,11 +634,10 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
skb_reset_network_header(skb);
memcpy(skb_network_header(skb), tmp_hdr, hlen);
- ipv6_select_ident(net, fh, rt);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(IP6_MF);
- frag_id = fh->identification;
+ fh->identification = frag_id;
first_len = skb_pagelen(skb);
skb->data_len = first_len - skb_headlen(skb);
@@ -778,11 +779,7 @@ slow_path:
*/
fh->nexthdr = nexthdr;
fh->reserved = 0;
- if (!frag_id) {
- ipv6_select_ident(net, fh, rt);
- frag_id = fh->identification;
- } else
- fh->identification = frag_id;
+ fh->identification = frag_id;
/*
* Copy a block of the IP datagram.
@@ -815,6 +812,14 @@ slow_path:
consume_skb(skb);
return err;
+fail_toobig:
+ if (skb->sk && dst_allfrag(skb_dst(skb)))
+ sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+
+ skb->dev = skb_dst(skb)->dev;
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ err = -EMSGSIZE;
+
fail:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
@@ -936,7 +941,8 @@ static int ip6_dst_lookup_tail(struct sock *sk,
*/
rt = (struct rt6_info *) *dst;
rcu_read_lock_bh();
- n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt));
+ n = __ipv6_neigh_lookup_noref(rt->dst.dev,
+ rt6_nexthop(rt, &fl6->daddr));
err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
rcu_read_unlock_bh();
@@ -1060,11 +1066,10 @@ static inline int ip6_ufo_append_data(struct sock *sk,
int odd, struct sk_buff *skb),
void *from, int length, int hh_len, int fragheaderlen,
int transhdrlen, int mtu, unsigned int flags,
- struct rt6_info *rt)
+ const struct flowi6 *fl6)
{
struct sk_buff *skb;
- struct frag_hdr fhdr;
int err;
/* There is support for UDP large send offload by network
@@ -1106,8 +1111,9 @@ static inline int ip6_ufo_append_data(struct sock *sk,
skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
sizeof(struct frag_hdr)) & ~7;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
- ipv6_select_ident(sock_net(sk), &fhdr, rt);
- skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
+ skb_shinfo(skb)->ip6_frag_id = ipv6_select_ident(sock_net(sk),
+ &fl6->daddr,
+ &fl6->saddr);
append:
return skb_append_datato_frags(sk, skb, getfrag, from,
@@ -1332,7 +1338,7 @@ emsgsize:
(sk->sk_type == SOCK_DGRAM)) {
err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen,
- transhdrlen, mtu, flags, rt);
+ transhdrlen, mtu, flags, fl6);
if (err)
goto error;
return 0;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 5cafd92c2312..2e67b660118b 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -151,7 +151,7 @@ EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset);
void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *) dst;
- t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+ t->dst_cookie = rt6_get_cookie(rt);
dst_release(t->dst_cache);
t->dst_cache = dst;
}
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index bba8903e871f..e1a1136bda7c 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -19,12 +19,10 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
int err;
struct socket *sock = NULL;
- err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock);
+ err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, 0, &sock);
if (err < 0)
goto error;
- sk_change_net(sock->sk, net);
-
udp6_addr.sin6_family = AF_INET6;
memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6,
sizeof(udp6_addr.sin6_addr));
@@ -55,7 +53,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
error:
if (sock) {
kernel_sock_shutdown(sock, SHUT_RDWR);
- sk_release_kernel(sock->sk);
+ sock_release(sock);
}
*sockp = NULL;
return err;
diff --git a/net/ipv6/mcast_snoop.c b/net/ipv6/mcast_snoop.c
new file mode 100644
index 000000000000..df8afe5ab31e
--- /dev/null
+++ b/net/ipv6/mcast_snoop.c
@@ -0,0 +1,213 @@
+/* Copyright (C) 2010: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ * Copyright (C) 2015: Linus Lüssing <linus.luessing@c0d3.blue>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ *
+ * Based on the MLD support added to br_multicast.c by YOSHIFUJI Hideaki.
+ */
+
+#include <linux/skbuff.h>
+#include <net/ipv6.h>
+#include <net/mld.h>
+#include <net/addrconf.h>
+#include <net/ip6_checksum.h>
+
+static int ipv6_mc_check_ip6hdr(struct sk_buff *skb)
+{
+ const struct ipv6hdr *ip6h;
+ unsigned int len;
+ unsigned int offset = skb_network_offset(skb) + sizeof(*ip6h);
+
+ if (!pskb_may_pull(skb, offset))
+ return -EINVAL;
+
+ ip6h = ipv6_hdr(skb);
+
+ if (ip6h->version != 6)
+ return -EINVAL;
+
+ len = offset + ntohs(ip6h->payload_len);
+ if (skb->len < len || len <= offset)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int ipv6_mc_check_exthdrs(struct sk_buff *skb)
+{
+ const struct ipv6hdr *ip6h;
+ int offset;
+ u8 nexthdr;
+ __be16 frag_off;
+
+ ip6h = ipv6_hdr(skb);
+
+ if (ip6h->nexthdr != IPPROTO_HOPOPTS)
+ return -ENOMSG;
+
+ nexthdr = ip6h->nexthdr;
+ offset = skb_network_offset(skb) + sizeof(*ip6h);
+ offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
+
+ if (offset < 0)
+ return -EINVAL;
+
+ if (nexthdr != IPPROTO_ICMPV6)
+ return -ENOMSG;
+
+ skb_set_transport_header(skb, offset);
+
+ return 0;
+}
+
+static int ipv6_mc_check_mld_reportv2(struct sk_buff *skb)
+{
+ unsigned int len = skb_transport_offset(skb);
+
+ len += sizeof(struct mld2_report);
+
+ return pskb_may_pull(skb, len) ? 0 : -EINVAL;
+}
+
+static int ipv6_mc_check_mld_query(struct sk_buff *skb)
+{
+ struct mld_msg *mld;
+ unsigned int len = skb_transport_offset(skb);
+
+ /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+ if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL))
+ return -EINVAL;
+
+ len += sizeof(struct mld_msg);
+ if (skb->len < len)
+ return -EINVAL;
+
+ /* MLDv1? */
+ if (skb->len != len) {
+ /* or MLDv2? */
+ len += sizeof(struct mld2_query) - sizeof(struct mld_msg);
+ if (skb->len < len || !pskb_may_pull(skb, len))
+ return -EINVAL;
+ }
+
+ mld = (struct mld_msg *)skb_transport_header(skb);
+
+ /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer
+ * all-nodes destination address (ff02::1) for general queries
+ */
+ if (ipv6_addr_any(&mld->mld_mca) &&
+ !ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int ipv6_mc_check_mld_msg(struct sk_buff *skb)
+{
+ struct mld_msg *mld = (struct mld_msg *)skb_transport_header(skb);
+
+ switch (mld->mld_type) {
+ case ICMPV6_MGM_REDUCTION:
+ case ICMPV6_MGM_REPORT:
+ /* fall through */
+ return 0;
+ case ICMPV6_MLD2_REPORT:
+ return ipv6_mc_check_mld_reportv2(skb);
+ case ICMPV6_MGM_QUERY:
+ return ipv6_mc_check_mld_query(skb);
+ default:
+ return -ENOMSG;
+ }
+}
+
+static inline __sum16 ipv6_mc_validate_checksum(struct sk_buff *skb)
+{
+ return skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo);
+}
+
+static int __ipv6_mc_check_mld(struct sk_buff *skb,
+ struct sk_buff **skb_trimmed)
+
+{
+ struct sk_buff *skb_chk = NULL;
+ unsigned int transport_len;
+ unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg);
+ int ret;
+
+ transport_len = ntohs(ipv6_hdr(skb)->payload_len);
+ transport_len -= skb_transport_offset(skb) - sizeof(struct ipv6hdr);
+
+ skb_get(skb);
+ skb_chk = skb_checksum_trimmed(skb, transport_len,
+ ipv6_mc_validate_checksum);
+ if (!skb_chk)
+ return -EINVAL;
+
+ if (!pskb_may_pull(skb_chk, len)) {
+ kfree_skb(skb_chk);
+ return -EINVAL;
+ }
+
+ ret = ipv6_mc_check_mld_msg(skb_chk);
+ if (ret) {
+ kfree_skb(skb_chk);
+ return ret;
+ }
+
+ if (skb_trimmed)
+ *skb_trimmed = skb_chk;
+ else
+ kfree_skb(skb_chk);
+
+ return 0;
+}
+
+/**
+ * ipv6_mc_check_mld - checks whether this is a sane MLD packet
+ * @skb: the skb to validate
+ * @skb_trimmed: to store an skb pointer trimmed to IPv6 packet tail (optional)
+ *
+ * Checks whether an IPv6 packet is a valid MLD packet. If so sets
+ * skb network and transport headers accordingly and returns zero.
+ *
+ * -EINVAL: A broken packet was detected, i.e. it violates some internet
+ * standard
+ * -ENOMSG: IP header validation succeeded but it is not an MLD packet.
+ * -ENOMEM: A memory allocation failure happened.
+ *
+ * Optionally, an skb pointer might be provided via skb_trimmed (or set it
+ * to NULL): After parsing an MLD packet successfully it will point to
+ * an skb which has its tail aligned to the IP packet end. This might
+ * either be the originally provided skb or a trimmed, cloned version if
+ * the skb frame had data beyond the IP packet. A cloned skb allows us
+ * to leave the original skb and its full frame unchanged (which might be
+ * desirable for layer 2 frame jugglers).
+ *
+ * The caller needs to release a reference count from any returned skb_trimmed.
+ */
+int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed)
+{
+ int ret;
+
+ ret = ipv6_mc_check_ip6hdr(skb);
+ if (ret < 0)
+ return ret;
+
+ ret = ipv6_mc_check_exthdrs(skb);
+ if (ret < 0)
+ return ret;
+
+ return __ipv6_mc_check_mld(skb, skb_trimmed);
+}
+EXPORT_SYMBOL(ipv6_mc_check_mld);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 96f153c0846b..0a05b35a90fc 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1506,7 +1506,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
"Redirect: destination is not a neighbour\n");
goto release;
}
- peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
+ peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1);
ret = inet_peer_xrlim_allow(peer, 1*HZ);
if (peer)
inet_putpeer(peer);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 62f5b0d0bc9b..cdd085f8b770 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1459,7 +1459,6 @@ static int
compat_find_calc_match(struct xt_entry_match *m,
const char *name,
const struct ip6t_ip6 *ipv6,
- unsigned int hookmask,
int *size)
{
struct xt_match *match;
@@ -1528,8 +1527,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
entry_offset = (void *)e - (void *)base;
j = 0;
xt_ematch_foreach(ematch, e) {
- ret = compat_find_calc_match(ematch, name,
- &e->ipv6, e->comefrom, &off);
+ ret = compat_find_calc_match(ematch, name, &e->ipv6, &off);
if (ret != 0)
goto release_matches;
++j;
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 85892af57364..21678acd4521 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -10,7 +10,8 @@
#include <net/secure_seq.h>
static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
- struct in6_addr *dst, struct in6_addr *src)
+ const struct in6_addr *dst,
+ const struct in6_addr *src)
{
u32 hash, id;
@@ -60,17 +61,17 @@ void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
-void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr,
- struct rt6_info *rt)
+__be32 ipv6_select_ident(struct net *net,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
static u32 ip6_idents_hashrnd __read_mostly;
u32 id;
net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
- id = __ipv6_select_ident(net, ip6_idents_hashrnd, &rt->rt6i_dst.addr,
- &rt->rt6i_src.addr);
- fhdr->identification = htonl(id);
+ id = __ipv6_select_ident(net, ip6_idents_hashrnd, daddr, saddr);
+ return htonl(id);
}
EXPORT_SYMBOL(ipv6_select_ident);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 8072bd4139b7..ca4700cb26c4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -865,6 +865,9 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_oif = np->ucast_oif;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+ if (inet->hdrincl)
+ fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
+
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
@@ -1324,13 +1327,7 @@ static struct inet_protosw rawv6_protosw = {
int __init rawv6_init(void)
{
- int ret;
-
- ret = inet6_register_protosw(&rawv6_protosw);
- if (ret)
- goto out;
-out:
- return ret;
+ return inet6_register_protosw(&rawv6_protosw);
}
void rawv6_exit(void)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c73ae5039e46..1a1122a6bbf5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -72,8 +72,7 @@ enum rt6_nud_state {
RT6_NUD_SUCCEED = 1
};
-static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
- const struct in6_addr *dest);
+static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort);
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ip6_default_advmss(const struct dst_entry *dst);
static unsigned int ip6_mtu(const struct dst_entry *dst);
@@ -92,6 +91,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
+static void rt6_dst_from_metrics_check(struct rt6_info *rt);
static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
#ifdef CONFIG_IPV6_ROUTE_INFO
@@ -104,65 +104,82 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *gwaddr, int ifindex);
#endif
-static void rt6_bind_peer(struct rt6_info *rt, int create)
+struct uncached_list {
+ spinlock_t lock;
+ struct list_head head;
+};
+
+static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
+
+static void rt6_uncached_list_add(struct rt6_info *rt)
{
- struct inet_peer_base *base;
- struct inet_peer *peer;
+ struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list);
- base = inetpeer_base_ptr(rt->_rt6i_peer);
- if (!base)
- return;
+ rt->dst.flags |= DST_NOCACHE;
+ rt->rt6i_uncached_list = ul;
+
+ spin_lock_bh(&ul->lock);
+ list_add_tail(&rt->rt6i_uncached, &ul->head);
+ spin_unlock_bh(&ul->lock);
+}
- peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
- if (peer) {
- if (!rt6_set_peer(rt, peer))
- inet_putpeer(peer);
+static void rt6_uncached_list_del(struct rt6_info *rt)
+{
+ if (!list_empty(&rt->rt6i_uncached)) {
+ struct uncached_list *ul = rt->rt6i_uncached_list;
+
+ spin_lock_bh(&ul->lock);
+ list_del(&rt->rt6i_uncached);
+ spin_unlock_bh(&ul->lock);
}
}
-static struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create)
+static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
{
- if (rt6_has_peer(rt))
- return rt6_peer_ptr(rt);
+ struct net_device *loopback_dev = net->loopback_dev;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
+ struct rt6_info *rt;
+
+ spin_lock_bh(&ul->lock);
+ list_for_each_entry(rt, &ul->head, rt6i_uncached) {
+ struct inet6_dev *rt_idev = rt->rt6i_idev;
+ struct net_device *rt_dev = rt->dst.dev;
+
+ if (rt_idev && (rt_idev->dev == dev || !dev) &&
+ rt_idev->dev != loopback_dev) {
+ rt->rt6i_idev = in6_dev_get(loopback_dev);
+ in6_dev_put(rt_idev);
+ }
- rt6_bind_peer(rt, create);
- return (rt6_has_peer(rt) ? rt6_peer_ptr(rt) : NULL);
+ if (rt_dev && (rt_dev == dev || !dev) &&
+ rt_dev != loopback_dev) {
+ rt->dst.dev = loopback_dev;
+ dev_hold(rt->dst.dev);
+ dev_put(rt_dev);
+ }
+ }
+ spin_unlock_bh(&ul->lock);
+ }
}
-static struct inet_peer *rt6_get_peer_create(struct rt6_info *rt)
+static u32 *rt6_pcpu_cow_metrics(struct rt6_info *rt)
{
- return __rt6_get_peer(rt, 1);
+ return dst_metrics_write_ptr(rt->dst.from);
}
static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
{
- struct rt6_info *rt = (struct rt6_info *) dst;
- struct inet_peer *peer;
- u32 *p = NULL;
+ struct rt6_info *rt = (struct rt6_info *)dst;
- if (!(rt->dst.flags & DST_HOST))
+ if (rt->rt6i_flags & RTF_PCPU)
+ return rt6_pcpu_cow_metrics(rt);
+ else if (rt->rt6i_flags & RTF_CACHE)
+ return NULL;
+ else
return dst_cow_metrics_generic(dst, old);
-
- peer = rt6_get_peer_create(rt);
- if (peer) {
- u32 *old_p = __DST_METRICS_PTR(old);
- unsigned long prev, new;
-
- p = peer->metrics;
- if (inet_metrics_new(peer) ||
- (old & DST_METRICS_FORCE_OVERWRITE))
- memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
-
- new = (unsigned long) p;
- prev = cmpxchg(&dst->_metrics, old, new);
-
- if (prev != old) {
- p = __DST_METRICS_PTR(prev);
- if (prev & DST_METRICS_READ_ONLY)
- p = NULL;
- }
- }
- return p;
}
static inline const void *choose_neigh_daddr(struct rt6_info *rt,
@@ -299,10 +316,10 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
#endif
/* allocate dst with ip6_dst_ops */
-static inline struct rt6_info *ip6_dst_alloc(struct net *net,
- struct net_device *dev,
- int flags,
- struct fib6_table *table)
+static struct rt6_info *__ip6_dst_alloc(struct net *net,
+ struct net_device *dev,
+ int flags,
+ struct fib6_table *table)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
0, DST_OBSOLETE_FORCE_CHK, flags);
@@ -311,21 +328,54 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
struct dst_entry *dst = &rt->dst;
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
- rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
INIT_LIST_HEAD(&rt->rt6i_siblings);
+ INIT_LIST_HEAD(&rt->rt6i_uncached);
+ }
+ return rt;
+}
+
+static struct rt6_info *ip6_dst_alloc(struct net *net,
+ struct net_device *dev,
+ int flags,
+ struct fib6_table *table)
+{
+ struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags, table);
+
+ if (rt) {
+ rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC);
+ if (rt->rt6i_pcpu) {
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct rt6_info **p;
+
+ p = per_cpu_ptr(rt->rt6i_pcpu, cpu);
+ /* no one shares rt */
+ *p = NULL;
+ }
+ } else {
+ dst_destroy((struct dst_entry *)rt);
+ return NULL;
+ }
}
+
return rt;
}
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
- struct inet6_dev *idev = rt->rt6i_idev;
struct dst_entry *from = dst->from;
+ struct inet6_dev *idev;
+
+ dst_destroy_metrics_generic(dst);
- if (!(rt->dst.flags & DST_HOST))
- dst_destroy_metrics_generic(dst);
+ if (rt->rt6i_pcpu)
+ free_percpu(rt->rt6i_pcpu);
+ rt6_uncached_list_del(rt);
+
+ idev = rt->rt6i_idev;
if (idev) {
rt->rt6i_idev = NULL;
in6_dev_put(idev);
@@ -333,11 +383,6 @@ static void ip6_dst_destroy(struct dst_entry *dst)
dst->from = NULL;
dst_release(from);
-
- if (rt6_has_peer(rt)) {
- struct inet_peer *peer = rt6_peer_ptr(rt);
- inet_putpeer(peer);
- }
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -652,15 +697,33 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
u32 metric, int oif, int strict,
bool *do_rr)
{
- struct rt6_info *rt, *match;
+ struct rt6_info *rt, *match, *cont;
int mpri = -1;
match = NULL;
- for (rt = rr_head; rt && rt->rt6i_metric == metric;
- rt = rt->dst.rt6_next)
+ cont = NULL;
+ for (rt = rr_head; rt; rt = rt->dst.rt6_next) {
+ if (rt->rt6i_metric != metric) {
+ cont = rt;
+ break;
+ }
+
match = find_match(rt, oif, strict, &mpri, match, do_rr);
- for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
- rt = rt->dst.rt6_next)
+ }
+
+ for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) {
+ if (rt->rt6i_metric != metric) {
+ cont = rt;
+ break;
+ }
+
+ match = find_match(rt, oif, strict, &mpri, match, do_rr);
+ }
+
+ if (match || !cont)
+ return match;
+
+ for (rt = cont; rt; rt = rt->dst.rt6_next)
match = find_match(rt, oif, strict, &mpri, match, do_rr);
return match;
@@ -694,6 +757,11 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
return match ? match : net->ipv6.ip6_null_entry;
}
+static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt)
+{
+ return (rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY));
+}
+
#ifdef CONFIG_IPV6_ROUTE_INFO
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr)
@@ -872,9 +940,9 @@ int ip6_ins_rt(struct rt6_info *rt)
return __ip6_ins_rt(rt, &info, &mxc);
}
-static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
- const struct in6_addr *daddr,
- const struct in6_addr *saddr)
+static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
struct rt6_info *rt;
@@ -882,15 +950,26 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
* Clone the route.
*/
- rt = ip6_rt_copy(ort, daddr);
+ if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
+ ort = (struct rt6_info *)ort->dst.from;
- if (rt) {
+ rt = __ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev,
+ 0, ort->rt6i_table);
+
+ if (!rt)
+ return NULL;
+
+ ip6_rt_copy_init(rt, ort);
+ rt->rt6i_flags |= RTF_CACHE;
+ rt->rt6i_metric = 0;
+ rt->dst.flags |= DST_HOST;
+ rt->rt6i_dst.addr = *daddr;
+ rt->rt6i_dst.plen = 128;
+
+ if (!rt6_is_gw_or_nonexthop(ort)) {
if (ort->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
-
- rt->rt6i_flags |= RTF_CACHE;
-
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen && saddr) {
rt->rt6i_src.addr = *saddr;
@@ -902,30 +981,65 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
return rt;
}
-static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
- const struct in6_addr *daddr)
+static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
{
- struct rt6_info *rt = ip6_rt_copy(ort, daddr);
+ struct rt6_info *pcpu_rt;
- if (rt)
- rt->rt6i_flags |= RTF_CACHE;
- return rt;
+ pcpu_rt = __ip6_dst_alloc(dev_net(rt->dst.dev),
+ rt->dst.dev, rt->dst.flags,
+ rt->rt6i_table);
+
+ if (!pcpu_rt)
+ return NULL;
+ ip6_rt_copy_init(pcpu_rt, rt);
+ pcpu_rt->rt6i_protocol = rt->rt6i_protocol;
+ pcpu_rt->rt6i_flags |= RTF_PCPU;
+ return pcpu_rt;
+}
+
+/* It should be called with read_lock_bh(&tb6_lock) acquired */
+static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
+{
+ struct rt6_info *pcpu_rt, *prev, **p;
+
+ p = this_cpu_ptr(rt->rt6i_pcpu);
+ pcpu_rt = *p;
+
+ if (pcpu_rt)
+ goto done;
+
+ pcpu_rt = ip6_rt_pcpu_alloc(rt);
+ if (!pcpu_rt) {
+ struct net *net = dev_net(rt->dst.dev);
+
+ pcpu_rt = net->ipv6.ip6_null_entry;
+ goto done;
+ }
+
+ prev = cmpxchg(p, NULL, pcpu_rt);
+ if (prev) {
+ /* If someone did it before us, return prev instead */
+ dst_destroy(&pcpu_rt->dst);
+ pcpu_rt = prev;
+ }
+
+done:
+ dst_hold(&pcpu_rt->dst);
+ rt6_dst_from_metrics_check(pcpu_rt);
+ return pcpu_rt;
}
static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
struct flowi6 *fl6, int flags)
{
struct fib6_node *fn, *saved_fn;
- struct rt6_info *rt, *nrt;
+ struct rt6_info *rt;
int strict = 0;
- int attempts = 3;
- int err;
strict |= flags & RT6_LOOKUP_F_IFACE;
if (net->ipv6.devconf_all->forwarding == 0)
strict |= RT6_LOOKUP_F_REACHABLE;
-redo_fib6_lookup_lock:
read_lock_bh(&table->tb6_lock);
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
@@ -944,51 +1058,52 @@ redo_rt6_select:
strict &= ~RT6_LOOKUP_F_REACHABLE;
fn = saved_fn;
goto redo_rt6_select;
- } else {
- dst_hold(&rt->dst);
- read_unlock_bh(&table->tb6_lock);
- goto out2;
}
}
- dst_hold(&rt->dst);
- read_unlock_bh(&table->tb6_lock);
- if (rt->rt6i_flags & RTF_CACHE)
- goto out2;
+ if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) {
+ dst_use(&rt->dst, jiffies);
+ read_unlock_bh(&table->tb6_lock);
- if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)))
- nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
- else if (!(rt->dst.flags & DST_HOST))
- nrt = rt6_alloc_clone(rt, &fl6->daddr);
- else
- goto out2;
+ rt6_dst_from_metrics_check(rt);
+ return rt;
+ } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
+ !(rt->rt6i_flags & RTF_GATEWAY))) {
+ /* Create a RTF_CACHE clone which will not be
+ * owned by the fib6 tree. It is for the special case where
+ * the daddr in the skb during the neighbor look-up is different
+ * from the fl6->daddr used to look-up route here.
+ */
- ip6_rt_put(rt);
- rt = nrt ? : net->ipv6.ip6_null_entry;
+ struct rt6_info *uncached_rt;
- dst_hold(&rt->dst);
- if (nrt) {
- err = ip6_ins_rt(nrt);
- if (!err)
- goto out2;
- }
+ dst_use(&rt->dst, jiffies);
+ read_unlock_bh(&table->tb6_lock);
- if (--attempts <= 0)
- goto out2;
+ uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL);
+ dst_release(&rt->dst);
- /*
- * Race condition! In the gap, when table->tb6_lock was
- * released someone could insert this route. Relookup.
- */
- ip6_rt_put(rt);
- goto redo_fib6_lookup_lock;
+ if (uncached_rt)
+ rt6_uncached_list_add(uncached_rt);
+ else
+ uncached_rt = net->ipv6.ip6_null_entry;
-out2:
- rt->dst.lastuse = jiffies;
- rt->dst.__use++;
+ dst_hold(&uncached_rt->dst);
+ return uncached_rt;
- return rt;
+ } else {
+ /* Get a percpu copy */
+
+ struct rt6_info *pcpu_rt;
+
+ rt->dst.lastuse = jiffies;
+ rt->dst.__use++;
+ pcpu_rt = rt6_get_pcpu_route(rt);
+ read_unlock_bh(&table->tb6_lock);
+
+ return pcpu_rt;
+ }
}
static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
@@ -1059,7 +1174,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
new = &rt->dst;
memset(new + 1, 0, sizeof(*rt) - sizeof(*new));
- rt6_init_peer(rt, net->ipv6.peers);
new->__use = 1;
new->input = dst_discard;
@@ -1093,6 +1207,33 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
* Destination cache support functions
*/
+static void rt6_dst_from_metrics_check(struct rt6_info *rt)
+{
+ if (rt->dst.from &&
+ dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(rt->dst.from))
+ dst_init_metrics(&rt->dst, dst_metrics_ptr(rt->dst.from), true);
+}
+
+static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
+{
+ if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
+ return NULL;
+
+ if (rt6_check_expired(rt))
+ return NULL;
+
+ return &rt->dst;
+}
+
+static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
+{
+ if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
+ rt6_check((struct rt6_info *)(rt->dst.from), cookie))
+ return &rt->dst;
+ else
+ return NULL;
+}
+
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
{
struct rt6_info *rt;
@@ -1103,13 +1244,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
* into this function always.
*/
- if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
- return NULL;
- if (rt6_check_expired(rt))
- return NULL;
+ rt6_dst_from_metrics_check(rt);
- return dst;
+ if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE))
+ return rt6_dst_from_check(rt, cookie);
+ else
+ return rt6_check(rt, cookie);
}
static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
@@ -1148,24 +1289,63 @@ static void ip6_link_failure(struct sk_buff *skb)
}
}
-static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb, u32 mtu)
+static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
+{
+ struct net *net = dev_net(rt->dst.dev);
+
+ rt->rt6i_flags |= RTF_MODIFIED;
+ rt->rt6i_pmtu = mtu;
+ rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
+}
+
+static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
+ const struct ipv6hdr *iph, u32 mtu)
{
struct rt6_info *rt6 = (struct rt6_info *)dst;
- dst_confirm(dst);
- if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
- struct net *net = dev_net(dst->dev);
+ if (rt6->rt6i_flags & RTF_LOCAL)
+ return;
- rt6->rt6i_flags |= RTF_MODIFIED;
- if (mtu < IPV6_MIN_MTU)
- mtu = IPV6_MIN_MTU;
+ dst_confirm(dst);
+ mtu = max_t(u32, mtu, IPV6_MIN_MTU);
+ if (mtu >= dst_mtu(dst))
+ return;
- dst_metric_set(dst, RTAX_MTU, mtu);
- rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
+ if (rt6->rt6i_flags & RTF_CACHE) {
+ rt6_do_update_pmtu(rt6, mtu);
+ } else {
+ const struct in6_addr *daddr, *saddr;
+ struct rt6_info *nrt6;
+
+ if (iph) {
+ daddr = &iph->daddr;
+ saddr = &iph->saddr;
+ } else if (sk) {
+ daddr = &sk->sk_v6_daddr;
+ saddr = &inet6_sk(sk)->saddr;
+ } else {
+ return;
+ }
+ nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr);
+ if (nrt6) {
+ rt6_do_update_pmtu(nrt6, mtu);
+
+ /* ip6_ins_rt(nrt6) will bump the
+ * rt6->rt6i_node->fn_sernum
+ * which will fail the next rt6_check() and
+ * invalidate the sk->sk_dst_cache.
+ */
+ ip6_ins_rt(nrt6);
+ }
}
}
+static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb, u32 mtu)
+{
+ __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu);
+}
+
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
int oif, u32 mark)
{
@@ -1182,7 +1362,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
- ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu));
+ __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu));
dst_release(dst);
}
EXPORT_SYMBOL_GPL(ip6_update_pmtu);
@@ -1341,12 +1521,17 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)
static unsigned int ip6_mtu(const struct dst_entry *dst)
{
+ const struct rt6_info *rt = (const struct rt6_info *)dst;
+ unsigned int mtu = rt->rt6i_pmtu;
struct inet6_dev *idev;
- unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
if (mtu)
goto out;
+ mtu = dst_metric_raw(dst, RTAX_MTU);
+ if (mtu)
+ goto out;
+
mtu = IPV6_MIN_MTU;
rcu_read_lock();
@@ -1590,10 +1775,8 @@ int ip6_route_add(struct fib6_config *cfg)
ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
rt->rt6i_dst.plen = cfg->fc_dst_len;
- if (rt->rt6i_dst.plen == 128) {
+ if (rt->rt6i_dst.plen == 128)
rt->dst.flags |= DST_HOST;
- dst_metrics_set_force_overwrite(&rt->dst);
- }
#ifdef CONFIG_IPV6_SUBTREES
ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
@@ -1651,6 +1834,16 @@ int ip6_route_add(struct fib6_config *cfg)
int gwa_type;
gw_addr = &cfg->fc_gateway;
+
+ /* if gw_addr is local we will fail to detect this in case
+ * address is still TENTATIVE (DAD in progress). rt6_lookup()
+ * will return already-added prefix route via interface that
+ * prefix route was assigned to, which might be non-loopback.
+ */
+ err = -EINVAL;
+ if (ipv6_chk_addr_and_flags(net, gw_addr, NULL, 0, 0))
+ goto out;
+
rt->rt6i_gateway = *gw_addr;
gwa_type = ipv6_addr_type(gw_addr);
@@ -1664,7 +1857,6 @@ int ip6_route_add(struct fib6_config *cfg)
(SIT, PtP, NBMA NOARP links) it is handy to allow
some exceptions. --ANK
*/
- err = -EINVAL;
if (!(gwa_type & IPV6_ADDR_UNICAST))
goto out;
@@ -1785,6 +1977,9 @@ static int ip6_route_del(struct fib6_config *cfg)
if (fn) {
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+ if ((rt->rt6i_flags & RTF_CACHE) &&
+ !(cfg->fc_flags & RTF_CACHE))
+ continue;
if (cfg->fc_ifindex &&
(!rt->dst.dev ||
rt->dst.dev->ifindex != cfg->fc_ifindex))
@@ -1894,7 +2089,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
NEIGH_UPDATE_F_ISROUTER))
);
- nrt = ip6_rt_copy(rt, &msg->dest);
+ nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL);
if (!nrt)
goto out;
@@ -1926,42 +2121,35 @@ out:
* Misc support functions
*/
-static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
- const struct in6_addr *dest)
+static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
{
- struct net *net = dev_net(ort->dst.dev);
- struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0,
- ort->rt6i_table);
+ BUG_ON(from->dst.from);
- if (rt) {
- rt->dst.input = ort->dst.input;
- rt->dst.output = ort->dst.output;
- rt->dst.flags |= DST_HOST;
-
- rt->rt6i_dst.addr = *dest;
- rt->rt6i_dst.plen = 128;
- dst_copy_metrics(&rt->dst, &ort->dst);
- rt->dst.error = ort->dst.error;
- rt->rt6i_idev = ort->rt6i_idev;
- if (rt->rt6i_idev)
- in6_dev_hold(rt->rt6i_idev);
- rt->dst.lastuse = jiffies;
-
- if (ort->rt6i_flags & RTF_GATEWAY)
- rt->rt6i_gateway = ort->rt6i_gateway;
- else
- rt->rt6i_gateway = *dest;
- rt->rt6i_flags = ort->rt6i_flags;
- rt6_set_from(rt, ort);
- rt->rt6i_metric = 0;
+ rt->rt6i_flags &= ~RTF_EXPIRES;
+ dst_hold(&from->dst);
+ rt->dst.from = &from->dst;
+ dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true);
+}
+static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
+{
+ rt->dst.input = ort->dst.input;
+ rt->dst.output = ort->dst.output;
+ rt->rt6i_dst = ort->rt6i_dst;
+ rt->dst.error = ort->dst.error;
+ rt->rt6i_idev = ort->rt6i_idev;
+ if (rt->rt6i_idev)
+ in6_dev_hold(rt->rt6i_idev);
+ rt->dst.lastuse = jiffies;
+ rt->rt6i_gateway = ort->rt6i_gateway;
+ rt->rt6i_flags = ort->rt6i_flags;
+ rt6_set_from(rt, ort);
+ rt->rt6i_metric = ort->rt6i_metric;
#ifdef CONFIG_IPV6_SUBTREES
- memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
+ rt->rt6i_src = ort->rt6i_src;
#endif
- memcpy(&rt->rt6i_prefsrc, &ort->rt6i_prefsrc, sizeof(struct rt6key));
- rt->rt6i_table = ort->rt6i_table;
- }
- return rt;
+ rt->rt6i_prefsrc = ort->rt6i_prefsrc;
+ rt->rt6i_table = ort->rt6i_table;
}
#ifdef CONFIG_IPV6_ROUTE_INFO
@@ -2336,6 +2524,7 @@ void rt6_ifdown(struct net *net, struct net_device *dev)
fib6_clean_all(net, fib6_ifdown, &adn);
icmp6_clean_all(fib6_ifdown, &adn);
+ rt6_uncached_list_flush_dev(net, dev);
}
struct rt6_mtu_change_arg {
@@ -2373,11 +2562,20 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
PMTU discouvery.
*/
if (rt->dst.dev == arg->dev &&
- !dst_metric_locked(&rt->dst, RTAX_MTU) &&
- (dst_mtu(&rt->dst) >= arg->mtu ||
- (dst_mtu(&rt->dst) < arg->mtu &&
- dst_mtu(&rt->dst) == idev->cnf.mtu6))) {
- dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
+ !dst_metric_locked(&rt->dst, RTAX_MTU)) {
+ if (rt->rt6i_flags & RTF_CACHE) {
+ /* For RTF_CACHE with rt6i_pmtu == 0
+ * (i.e. a redirected route),
+ * the metrics of its rt->dst.from has already
+ * been updated.
+ */
+ if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu)
+ rt->rt6i_pmtu = arg->mtu;
+ } else if (dst_mtu(&rt->dst) >= arg->mtu ||
+ (dst_mtu(&rt->dst) < arg->mtu &&
+ dst_mtu(&rt->dst) == idev->cnf.mtu6)) {
+ dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
+ }
}
return 0;
}
@@ -2434,6 +2632,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
if (rtm->rtm_type == RTN_LOCAL)
cfg->fc_flags |= RTF_LOCAL;
+ if (rtm->rtm_flags & RTM_F_CLONED)
+ cfg->fc_flags |= RTF_CACHE;
+
cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
cfg->fc_nlinfo.nlh = nlh;
cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
@@ -2608,6 +2809,7 @@ static int rt6_fill_node(struct net *net,
int iif, int type, u32 portid, u32 seq,
int prefix, int nowait, unsigned int flags)
{
+ u32 metrics[RTAX_MAX];
struct rtmsg *rtm;
struct nlmsghdr *nlh;
long expires;
@@ -2721,7 +2923,10 @@ static int rt6_fill_node(struct net *net,
goto nla_put_failure;
}
- if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
+ memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
+ if (rt->rt6i_pmtu)
+ metrics[RTAX_MTU - 1] = rt->rt6i_pmtu;
+ if (rtnetlink_put_metrics(skb, metrics) < 0)
goto nla_put_failure;
if (rt->rt6i_flags & RTF_GATEWAY) {
@@ -3216,6 +3421,7 @@ static struct notifier_block ip6_route_dev_notifier = {
int __init ip6_route_init(void)
{
int ret;
+ int cpu;
ret = -ENOMEM;
ip6_dst_ops_template.kmem_cachep =
@@ -3275,6 +3481,13 @@ int __init ip6_route_init(void)
if (ret)
goto out_register_late_subsys;
+ for_each_possible_cpu(cpu) {
+ struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
+
+ INIT_LIST_HEAD(&ul->head);
+ spin_lock_init(&ul->lock);
+ }
+
out:
return ret;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 21bc2eb53c57..0909f4e0d53c 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -41,23 +41,6 @@ static __u16 const msstab[] = {
9000 - 60,
};
-static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
- struct request_sock *req,
- struct dst_entry *dst)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
- struct sock *child;
-
- child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst);
- if (child) {
- atomic_set(&req->rsk_refcnt, 1);
- inet_csk_reqsk_queue_add(sk, req, child);
- } else {
- reqsk_free(req);
- }
- return child;
-}
-
static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
ipv6_cookie_scratch);
@@ -264,7 +247,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
ireq->rcv_wscale = rcv_wscale;
ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst);
- ret = get_cookie_sock(sk, skb, req, dst);
+ ret = tcp_get_cookie_sock(sk, skb, req, dst);
out:
return ret;
out_free:
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index abcc79f649b3..4e705add4f18 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -68,6 +68,13 @@ static struct ctl_table ipv6_table_template[] = {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
+ {
+ .procname = "flowlabel_state_ranges",
+ .data = &init_net.ipv6.sysctl.flowlabel_state_ranges,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{ }
};
@@ -109,6 +116,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net)
ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect;
ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries;
ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay;
+ ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges;
ipv6_route_table = ipv6_route_sysctl_init(net);
if (!ipv6_route_table)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3adffb300238..6748c4277aff 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -99,8 +99,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
dst_hold(dst);
sk->sk_rx_dst = dst;
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
- if (rt->rt6i_node)
- inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+ inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
}
}
@@ -121,7 +120,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
- struct rt6_info *rt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
@@ -259,10 +257,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
sk->sk_gso_type = SKB_GSO_TCPV6;
__ip6_dst_store(sk, dst, NULL, NULL);
- rt = (struct rt6_info *) dst;
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp &&
- ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr))
+ ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr))
tcp_fetch_timewait_stamp(sk, dst);
icsk->icsk_ext_hdr_len = 0;
@@ -1251,7 +1248,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
return 0;
}
- if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb))
+ if (tcp_checksum_complete(skb))
goto csum_err;
if (sk->sk_state == TCP_LISTEN) {
@@ -1421,6 +1418,7 @@ process:
skb->dev = NULL;
bh_lock_sock_nested(sk);
+ tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
ret = 0;
if (!sock_owned_by_user(sk)) {
if (!tcp_prequeue(sk, skb))
@@ -1442,7 +1440,7 @@ no_tcp_socket:
tcp_v6_fill_cb(skb, hdr, th);
- if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
+ if (tcp_checksum_complete(skb)) {
csum_error:
TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
bad_packet:
@@ -1467,10 +1465,6 @@ do_time_wait:
tcp_v6_fill_cb(skb, hdr, th);
- if (skb->len < (th->doff<<2)) {
- inet_twsk_put(inet_twsk(sk));
- goto bad_packet;
- }
if (tcp_checksum_complete(skb)) {
inet_twsk_put(inet_twsk(sk));
goto csum_error;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index f337a908a76a..ed0583c1b9fc 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -71,20 +71,12 @@ static int xfrm6_get_tos(const struct flowi *fl)
return 0;
}
-static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst)
-{
- struct rt6_info *rt = (struct rt6_info *)xdst;
-
- rt6_init_peer(rt, net->ipv6.peers);
-}
-
static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
int nfheader_len)
{
if (dst->ops->family == AF_INET6) {
struct rt6_info *rt = (struct rt6_info *)dst;
- if (rt->rt6i_node)
- path->path_cookie = rt->rt6i_node->fn_sernum;
+ path->path_cookie = rt6_get_cookie(rt);
}
path->u.rt6.rt6i_nfheader_len = nfheader_len;
@@ -106,16 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
return -ENODEV;
}
- rt6_transfer_peer(&xdst->u.rt6, rt);
-
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST |
RTF_LOCAL);
xdst->u.rt6.rt6i_metric = rt->rt6i_metric;
xdst->u.rt6.rt6i_node = rt->rt6i_node;
- if (rt->rt6i_node)
- xdst->route_cookie = rt->rt6i_node->fn_sernum;
+ xdst->route_cookie = rt6_get_cookie(rt);
xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
xdst->u.rt6.rt6i_src = rt->rt6i_src;
@@ -255,10 +244,6 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
if (likely(xdst->u.rt6.rt6i_idev))
in6_dev_put(xdst->u.rt6.rt6i_idev);
dst_destroy_metrics_generic(dst);
- if (rt6_has_peer(&xdst->u.rt6)) {
- struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6);
- inet_putpeer(peer);
- }
xfrm_dst_destroy(xdst);
}
@@ -308,7 +293,6 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.get_saddr = xfrm6_get_saddr,
.decode_session = _decode_session6,
.get_tos = xfrm6_get_tos,
- .init_dst = xfrm6_init_dst,
.init_path = xfrm6_init_path,
.fill_dst = xfrm6_fill_dst,
.blackhole_route = ip6_blackhole_route,
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 4ea5d7497b5f..48d0dc89b58d 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1347,7 +1347,7 @@ static int ipx_create(struct net *net, struct socket *sock, int protocol,
goto out;
rc = -ENOMEM;
- sk = sk_alloc(net, PF_IPX, GFP_KERNEL, &ipx_proto);
+ sk = sk_alloc(net, PF_IPX, GFP_KERNEL, &ipx_proto, kern);
if (!sk)
goto out;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index ee0ea25c8e7a..fae6822cc367 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1100,7 +1100,7 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
}
/* Allocate networking socket */
- sk = sk_alloc(net, PF_IRDA, GFP_KERNEL, &irda_proto);
+ sk = sk_alloc(net, PF_IRDA, GFP_KERNEL, &irda_proto, kern);
if (sk == NULL)
return -ENOMEM;
diff --git a/net/irda/timer.c b/net/irda/timer.c
index 0c4c115a5cab..f2280f73b057 100644
--- a/net/irda/timer.c
+++ b/net/irda/timer.c
@@ -60,8 +60,8 @@ void irlap_start_query_timer(struct irlap_cb *self, int S, int s)
* to avoid messing with for incoming connections requests and
* to accommodate devices that perform discovery slower than us.
* Jean II */
- timeout = ((sysctl_slot_timeout * HZ / 1000) * (S - s)
- + XIDEXTRA_TIMEOUT + SMALLBUSY_TIMEOUT);
+ timeout = msecs_to_jiffies(sysctl_slot_timeout) * (S - s)
+ + XIDEXTRA_TIMEOUT + SMALLBUSY_TIMEOUT;
/* Set or re-set the timer. We reset the timer for each received
* discovery query, which allow us to automatically adjust to
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 6daa52a18d40..918151c11348 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -535,12 +535,12 @@ static void iucv_sock_init(struct sock *sk, struct sock *parent)
sk->sk_type = parent->sk_type;
}
-static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio)
+static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio, int kern)
{
struct sock *sk;
struct iucv_sock *iucv;
- sk = sk_alloc(&init_net, PF_IUCV, prio, &iucv_proto);
+ sk = sk_alloc(&init_net, PF_IUCV, prio, &iucv_proto, kern);
if (!sk)
return NULL;
iucv = iucv_sk(sk);
@@ -602,7 +602,7 @@ static int iucv_sock_create(struct net *net, struct socket *sock, int protocol,
return -ESOCKTNOSUPPORT;
}
- sk = iucv_sock_alloc(sock, protocol, GFP_KERNEL);
+ sk = iucv_sock_alloc(sock, protocol, GFP_KERNEL, kern);
if (!sk)
return -ENOMEM;
@@ -1723,7 +1723,7 @@ static int iucv_callback_connreq(struct iucv_path *path,
}
/* Create the new socket */
- nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC);
+ nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0);
if (!nsk) {
err = pr_iucv->path_sever(path, user_data);
iucv_path_free(path);
@@ -1933,7 +1933,7 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb)
goto out;
}
- nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC);
+ nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0);
bh_lock_sock(sk);
if ((sk->sk_state != IUCV_LISTEN) ||
sk_acceptq_is_full(sk) ||
diff --git a/net/key/af_key.c b/net/key/af_key.c
index f0d52d721b3a..9e834ec475a9 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -149,7 +149,7 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol,
return -EPROTONOSUPPORT;
err = -ENOMEM;
- sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto);
+ sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto, kern);
if (sk == NULL)
goto out;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index a29a504492af..f6b090df3930 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1334,9 +1334,10 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
if (sock)
inet_shutdown(sock, 2);
} else {
- if (sock)
+ if (sock) {
kernel_sock_shutdown(sock, SHUT_RDWR);
- sk_release_kernel(sk);
+ sock_release(sock);
+ }
}
l2tp_tunnel_sock_put(sk);
@@ -1399,13 +1400,11 @@ static int l2tp_tunnel_sock_create(struct net *net,
if (cfg->local_ip6 && cfg->peer_ip6) {
struct sockaddr_l2tpip6 ip6_addr = {0};
- err = sock_create_kern(AF_INET6, SOCK_DGRAM,
+ err = sock_create_kern(net, AF_INET6, SOCK_DGRAM,
IPPROTO_L2TP, &sock);
if (err < 0)
goto out;
- sk_change_net(sock->sk, net);
-
ip6_addr.l2tp_family = AF_INET6;
memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6,
sizeof(ip6_addr.l2tp_addr));
@@ -1429,13 +1428,11 @@ static int l2tp_tunnel_sock_create(struct net *net,
{
struct sockaddr_l2tpip ip_addr = {0};
- err = sock_create_kern(AF_INET, SOCK_DGRAM,
+ err = sock_create_kern(net, AF_INET, SOCK_DGRAM,
IPPROTO_L2TP, &sock);
if (err < 0)
goto out;
- sk_change_net(sock->sk, net);
-
ip_addr.l2tp_family = AF_INET;
ip_addr.l2tp_addr = cfg->local_ip;
ip_addr.l2tp_conn_id = tunnel_id;
@@ -1462,7 +1459,7 @@ out:
*sockp = sock;
if ((err < 0) && sock) {
kernel_sock_shutdown(sock, SHUT_RDWR);
- sk_release_kernel(sock->sk);
+ sock_release(sock);
*sockp = NULL;
}
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index e9b0dec56b8e..f56c9f69e9f2 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -542,12 +542,12 @@ static int pppol2tp_backlog_recv(struct sock *sk, struct sk_buff *skb)
/* socket() handler. Initialize a new struct sock.
*/
-static int pppol2tp_create(struct net *net, struct socket *sock)
+static int pppol2tp_create(struct net *net, struct socket *sock, int kern)
{
int error = -ENOMEM;
struct sock *sk;
- sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppol2tp_sk_proto);
+ sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppol2tp_sk_proto, kern);
if (!sk)
goto out;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 17a8dff06090..8fd9febaa5ba 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -168,7 +168,7 @@ static int llc_ui_create(struct net *net, struct socket *sock, int protocol,
if (likely(sock->type == SOCK_DGRAM || sock->type == SOCK_STREAM)) {
rc = -ENOMEM;
- sk = llc_sk_alloc(net, PF_LLC, GFP_KERNEL, &llc_proto);
+ sk = llc_sk_alloc(net, PF_LLC, GFP_KERNEL, &llc_proto, kern);
if (sk) {
rc = 0;
llc_ui_sk_init(sock, sk);
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 81a61fce3afb..3e821daf9dd4 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -768,7 +768,7 @@ static struct sock *llc_create_incoming_sock(struct sock *sk,
struct llc_addr *daddr)
{
struct sock *newsk = llc_sk_alloc(sock_net(sk), sk->sk_family, GFP_ATOMIC,
- sk->sk_prot);
+ sk->sk_prot, 0);
struct llc_sock *newllc, *llc = llc_sk(sk);
if (!newsk)
@@ -931,9 +931,9 @@ static void llc_sk_init(struct sock *sk)
* Allocates a LLC sock and initializes it. Returns the new LLC sock
* or %NULL if there's no memory available for one
*/
-struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot)
+struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern)
{
- struct sock *sk = sk_alloc(net, family, priority, prot);
+ struct sock *sk = sk_alloc(net, family, priority, prot, kern);
if (!sk)
goto out;
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index 64a012a0c6e5..086de496a4c1 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -302,6 +302,20 @@ config MAC80211_DEBUG_COUNTERS
---help---
Selecting this option causes mac80211 to keep additional
and very verbose statistics about TX and RX handler use
- and show them in debugfs.
+ as well as a few selected dot11 counters. These will be
+ exposed in debugfs.
+
+ Note that some of the counters are not concurrency safe
+ and may thus not always be accurate.
If unsure, say N.
+
+config MAC80211_STA_HASH_MAX_SIZE
+ int "Station hash table maximum size" if MAC80211_DEBUG_MENU
+ default 0
+ ---help---
+ Setting this option to a low value (e.g. 4) allows testing the
+ hash table with collisions relatively deterministically (just
+ connect more stations than the number selected here.)
+
+ If unsure, leave the default of 0.
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index cce9d425c718..c8ba2e77737c 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -564,8 +564,8 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid,
return -EINVAL;
if ((tid >= IEEE80211_NUM_TIDS) ||
- !(local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION) ||
- (local->hw.flags & IEEE80211_HW_TX_AMPDU_SETUP_IN_HW))
+ !ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION) ||
+ ieee80211_hw_check(&local->hw, TX_AMPDU_SETUP_IN_HW))
return -EINVAL;
ht_dbg(sdata, "Open BA session requested for %pM tid %u\n",
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index ff347a0eebd4..bf7023f6c327 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2,7 +2,7 @@
* mac80211 configuration hooks for cfg80211
*
* Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net>
- * Copyright 2013-2014 Intel Mobile Communications GmbH
+ * Copyright 2013-2015 Intel Mobile Communications GmbH
*
* This file is GPLv2 as found in COPYING.
*/
@@ -137,6 +137,9 @@ static int ieee80211_set_noack_map(struct wiphy *wiphy,
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
sdata->noack_map = noack_map;
+
+ ieee80211_check_fast_xmit_iface(sdata);
+
return 0;
}
@@ -309,6 +312,7 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
u32 iv32;
u16 iv16;
int err = -ENOENT;
+ struct ieee80211_key_seq kseq = {};
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
@@ -339,10 +343,12 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
iv32 = key->u.tkip.tx.iv32;
iv16 = key->u.tkip.tx.iv16;
- if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)
- drv_get_tkip_seq(sdata->local,
- key->conf.hw_key_idx,
- &iv32, &iv16);
+ if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE &&
+ !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) {
+ drv_get_key_seq(sdata->local, key, &kseq);
+ iv32 = kseq.tkip.iv32;
+ iv16 = kseq.tkip.iv16;
+ }
seq[0] = iv16 & 0xff;
seq[1] = (iv16 >> 8) & 0xff;
@@ -355,52 +361,44 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
break;
case WLAN_CIPHER_SUITE_CCMP:
case WLAN_CIPHER_SUITE_CCMP_256:
- pn64 = atomic64_read(&key->u.ccmp.tx_pn);
- seq[0] = pn64;
- seq[1] = pn64 >> 8;
- seq[2] = pn64 >> 16;
- seq[3] = pn64 >> 24;
- seq[4] = pn64 >> 32;
- seq[5] = pn64 >> 40;
- params.seq = seq;
- params.seq_len = 6;
- break;
case WLAN_CIPHER_SUITE_AES_CMAC:
case WLAN_CIPHER_SUITE_BIP_CMAC_256:
- pn64 = atomic64_read(&key->u.aes_cmac.tx_pn);
- seq[0] = pn64;
- seq[1] = pn64 >> 8;
- seq[2] = pn64 >> 16;
- seq[3] = pn64 >> 24;
- seq[4] = pn64 >> 32;
- seq[5] = pn64 >> 40;
- params.seq = seq;
- params.seq_len = 6;
- break;
+ BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) !=
+ offsetof(typeof(kseq), aes_cmac));
case WLAN_CIPHER_SUITE_BIP_GMAC_128:
case WLAN_CIPHER_SUITE_BIP_GMAC_256:
- pn64 = atomic64_read(&key->u.aes_gmac.tx_pn);
- seq[0] = pn64;
- seq[1] = pn64 >> 8;
- seq[2] = pn64 >> 16;
- seq[3] = pn64 >> 24;
- seq[4] = pn64 >> 32;
- seq[5] = pn64 >> 40;
- params.seq = seq;
- params.seq_len = 6;
- break;
+ BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) !=
+ offsetof(typeof(kseq), aes_gmac));
case WLAN_CIPHER_SUITE_GCMP:
case WLAN_CIPHER_SUITE_GCMP_256:
- pn64 = atomic64_read(&key->u.gcmp.tx_pn);
- seq[0] = pn64;
- seq[1] = pn64 >> 8;
- seq[2] = pn64 >> 16;
- seq[3] = pn64 >> 24;
- seq[4] = pn64 >> 32;
- seq[5] = pn64 >> 40;
+ BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) !=
+ offsetof(typeof(kseq), gcmp));
+
+ if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE &&
+ !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) {
+ drv_get_key_seq(sdata->local, key, &kseq);
+ memcpy(seq, kseq.ccmp.pn, 6);
+ } else {
+ pn64 = atomic64_read(&key->conf.tx_pn);
+ seq[0] = pn64;
+ seq[1] = pn64 >> 8;
+ seq[2] = pn64 >> 16;
+ seq[3] = pn64 >> 24;
+ seq[4] = pn64 >> 32;
+ seq[5] = pn64 >> 40;
+ }
params.seq = seq;
params.seq_len = 6;
break;
+ default:
+ if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE))
+ break;
+ if (WARN_ON(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV))
+ break;
+ drv_get_key_seq(sdata->local, key, &kseq);
+ params.seq = kseq.hw.seq;
+ params.seq_len = kseq.hw.seq_len;
+ break;
}
params.key = key->conf.key;
@@ -1372,6 +1370,7 @@ static int ieee80211_change_station(struct wiphy *wiphy,
}
sta->sdata = vlansdata;
+ ieee80211_check_fast_xmit(sta);
if (sta->sta_state == IEEE80211_STA_AUTHORIZED &&
prev_4addr != new_4addr) {
@@ -1764,7 +1763,7 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy,
/* our RSSI threshold implementation is supported only for
* devices that report signal in dBm.
*/
- if (!(sdata->local->hw.flags & IEEE80211_HW_SIGNAL_DBM))
+ if (!ieee80211_hw_check(&sdata->local->hw, SIGNAL_DBM))
return -ENOTSUPP;
conf->rssi_threshold = nconf->rssi_threshold;
}
@@ -2099,10 +2098,14 @@ static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed)
int err;
if (changed & WIPHY_PARAM_FRAG_THRESHOLD) {
+ ieee80211_check_fast_xmit_all(local);
+
err = drv_set_frag_threshold(local, wiphy->frag_threshold);
- if (err)
+ if (err) {
+ ieee80211_check_fast_xmit_all(local);
return err;
+ }
}
if ((changed & WIPHY_PARAM_COVERAGE_CLASS) ||
@@ -2404,7 +2407,7 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
if (sdata->vif.type != NL80211_IFTYPE_STATION)
return -EOPNOTSUPP;
- if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS))
+ if (!ieee80211_hw_check(&local->hw, SUPPORTS_PS))
return -EOPNOTSUPP;
if (enabled == sdata->u.mgd.powersave &&
@@ -2419,7 +2422,7 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
__ieee80211_request_smps_mgd(sdata, sdata->u.mgd.req_smps);
sdata_unlock(sdata);
- if (local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS)
+ if (ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS))
ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS);
ieee80211_recalc_ps(local, -1);
@@ -2463,7 +2466,7 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy,
if (!ieee80211_sdata_running(sdata))
return -ENETDOWN;
- if (local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL) {
+ if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) {
ret = drv_set_bitrate_mask(local, sdata, mask);
if (ret)
return ret;
@@ -2514,6 +2517,19 @@ static bool ieee80211_coalesce_started_roc(struct ieee80211_local *local,
return true;
}
+static u64 ieee80211_mgmt_tx_cookie(struct ieee80211_local *local)
+{
+ lockdep_assert_held(&local->mtx);
+
+ local->roc_cookie_counter++;
+
+ /* wow, you wrapped 64 bits ... more likely a bug */
+ if (WARN_ON(local->roc_cookie_counter == 0))
+ local->roc_cookie_counter++;
+
+ return local->roc_cookie_counter;
+}
+
static int ieee80211_start_roc_work(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
struct ieee80211_channel *channel,
@@ -2551,7 +2567,6 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
roc->req_duration = duration;
roc->frame = txskb;
roc->type = type;
- roc->mgmt_tx_cookie = (unsigned long)txskb;
roc->sdata = sdata;
INIT_DELAYED_WORK(&roc->work, ieee80211_sw_roc_work);
INIT_LIST_HEAD(&roc->dependents);
@@ -2561,17 +2576,10 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
* or the SKB (for mgmt TX)
*/
if (!txskb) {
- /* local->mtx protects this */
- local->roc_cookie_counter++;
- roc->cookie = local->roc_cookie_counter;
- /* wow, you wrapped 64 bits ... more likely a bug */
- if (WARN_ON(roc->cookie == 0)) {
- roc->cookie = 1;
- local->roc_cookie_counter++;
- }
+ roc->cookie = ieee80211_mgmt_tx_cookie(local);
*cookie = roc->cookie;
} else {
- *cookie = (unsigned long)txskb;
+ roc->mgmt_tx_cookie = *cookie;
}
/* if there's one pending or we're scanning, queue this one */
@@ -3244,13 +3252,43 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
return err;
}
+static struct sk_buff *ieee80211_make_ack_skb(struct ieee80211_local *local,
+ struct sk_buff *skb, u64 *cookie,
+ gfp_t gfp)
+{
+ unsigned long spin_flags;
+ struct sk_buff *ack_skb;
+ int id;
+
+ ack_skb = skb_copy(skb, gfp);
+ if (!ack_skb)
+ return ERR_PTR(-ENOMEM);
+
+ spin_lock_irqsave(&local->ack_status_lock, spin_flags);
+ id = idr_alloc(&local->ack_status_frames, ack_skb,
+ 1, 0x10000, GFP_ATOMIC);
+ spin_unlock_irqrestore(&local->ack_status_lock, spin_flags);
+
+ if (id < 0) {
+ kfree_skb(ack_skb);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ IEEE80211_SKB_CB(skb)->ack_frame_id = id;
+
+ *cookie = ieee80211_mgmt_tx_cookie(local);
+ IEEE80211_SKB_CB(ack_skb)->ack.cookie = *cookie;
+
+ return ack_skb;
+}
+
static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
struct cfg80211_mgmt_tx_params *params,
u64 *cookie)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
struct ieee80211_local *local = sdata->local;
- struct sk_buff *skb;
+ struct sk_buff *skb, *ack_skb;
struct sta_info *sta;
const struct ieee80211_mgmt *mgmt = (void *)params->buf;
bool need_offchan = false;
@@ -3299,8 +3337,14 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
break;
case NL80211_IFTYPE_STATION:
case NL80211_IFTYPE_P2P_CLIENT:
- if (!sdata->u.mgd.associated)
+ sdata_lock(sdata);
+ if (!sdata->u.mgd.associated ||
+ (params->offchan && params->wait &&
+ local->ops->remain_on_channel &&
+ memcmp(sdata->u.mgd.associated->bssid,
+ mgmt->bssid, ETH_ALEN)))
need_offchan = true;
+ sdata_unlock(sdata);
break;
case NL80211_IFTYPE_P2P_DEVICE:
need_offchan = true;
@@ -3356,6 +3400,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
/* Update CSA counters */
if (sdata->vif.csa_active &&
(sdata->vif.type == NL80211_IFTYPE_AP ||
+ sdata->vif.type == NL80211_IFTYPE_MESH_POINT ||
sdata->vif.type == NL80211_IFTYPE_ADHOC) &&
params->n_csa_offsets) {
int i;
@@ -3382,8 +3427,23 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
skb->dev = sdata->dev;
+ if (!params->dont_wait_for_ack) {
+ /* make a copy to preserve the frame contents
+ * in case of encryption.
+ */
+ ack_skb = ieee80211_make_ack_skb(local, skb, cookie,
+ GFP_KERNEL);
+ if (IS_ERR(ack_skb)) {
+ ret = PTR_ERR(ack_skb);
+ kfree_skb(skb);
+ goto out_unlock;
+ }
+ } else {
+ /* for cookie below */
+ ack_skb = skb;
+ }
+
if (!need_offchan) {
- *cookie = (unsigned long) skb;
ieee80211_tx_skb(sdata, skb);
ret = 0;
goto out_unlock;
@@ -3391,7 +3451,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_TX_OFFCHAN |
IEEE80211_TX_INTFL_OFFCHAN_TX_OK;
- if (local->hw.flags & IEEE80211_HW_QUEUE_CONTROL)
+ if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL))
IEEE80211_SKB_CB(skb)->hw_queue =
local->hw.offchannel_tx_hw_queue;
@@ -3476,7 +3536,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct ieee80211_local *local = sdata->local;
struct ieee80211_qos_hdr *nullfunc;
- struct sk_buff *skb;
+ struct sk_buff *skb, *ack_skb;
int size = sizeof(*nullfunc);
__le16 fc;
bool qos;
@@ -3484,20 +3544,24 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
struct sta_info *sta;
struct ieee80211_chanctx_conf *chanctx_conf;
enum ieee80211_band band;
+ int ret;
+
+ /* the lock is needed to assign the cookie later */
+ mutex_lock(&local->mtx);
rcu_read_lock();
chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
if (WARN_ON(!chanctx_conf)) {
- rcu_read_unlock();
- return -EINVAL;
+ ret = -EINVAL;
+ goto unlock;
}
band = chanctx_conf->def.chan->band;
sta = sta_info_get_bss(sdata, peer);
if (sta) {
qos = sta->sta.wme;
} else {
- rcu_read_unlock();
- return -ENOLINK;
+ ret = -ENOLINK;
+ goto unlock;
}
if (qos) {
@@ -3513,8 +3577,8 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
skb = dev_alloc_skb(local->hw.extra_tx_headroom + size);
if (!skb) {
- rcu_read_unlock();
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto unlock;
}
skb->dev = dev;
@@ -3540,13 +3604,23 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
if (qos)
nullfunc->qos_ctrl = cpu_to_le16(7);
+ ack_skb = ieee80211_make_ack_skb(local, skb, cookie, GFP_ATOMIC);
+ if (IS_ERR(ack_skb)) {
+ kfree_skb(skb);
+ ret = PTR_ERR(ack_skb);
+ goto unlock;
+ }
+
local_bh_disable();
ieee80211_xmit(sdata, sta, skb);
local_bh_enable();
+
+ ret = 0;
+unlock:
rcu_read_unlock();
+ mutex_unlock(&local->mtx);
- *cookie = (unsigned long) skb;
- return 0;
+ return ret;
}
static int ieee80211_cfg_get_channel(struct wiphy *wiphy,
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 5bcd4e5589d3..f01c18a3160e 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -664,6 +664,8 @@ out:
ieee80211_bss_info_change_notify(sdata,
BSS_CHANGED_IDLE);
+ ieee80211_check_fast_xmit_iface(sdata);
+
return ret;
}
@@ -1008,6 +1010,8 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata)
if (WARN_ON(!chandef))
return -EINVAL;
+ ieee80211_change_chanctx(local, new_ctx, chandef);
+
vif_chsw[0].vif = &sdata->vif;
vif_chsw[0].old_ctx = &old_ctx->conf;
vif_chsw[0].new_ctx = &new_ctx->conf;
@@ -1030,6 +1034,8 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata)
if (sdata->vif.type == NL80211_IFTYPE_AP)
__ieee80211_vif_copy_chanctx_to_vlans(sdata, false);
+ ieee80211_check_fast_xmit_iface(sdata);
+
if (ieee80211_chanctx_refcount(local, old_ctx) == 0)
ieee80211_free_chanctx(local, old_ctx);
@@ -1079,6 +1085,8 @@ ieee80211_vif_use_reserved_assign(struct ieee80211_sub_if_data *sdata)
if (WARN_ON(!chandef))
return -EINVAL;
+ ieee80211_change_chanctx(local, new_ctx, chandef);
+
list_del(&sdata->reserved_chanctx_list);
sdata->reserved_chanctx = NULL;
@@ -1376,6 +1384,8 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local)
__ieee80211_vif_copy_chanctx_to_vlans(sdata,
false);
+ ieee80211_check_fast_xmit_iface(sdata);
+
sdata->radar_required = sdata->reserved_radar_required;
if (sdata->vif.bss_conf.chandef.width !=
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 23813ebb349c..3ea8b7de9633 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -1,4 +1,3 @@
-
/*
* mac80211 debugfs for wireless PHYs
*
@@ -92,62 +91,66 @@ static const struct file_operations reset_ops = {
};
#endif
+static const char *hw_flag_names[NUM_IEEE80211_HW_FLAGS + 1] = {
+#define FLAG(F) [IEEE80211_HW_##F] = #F
+ FLAG(HAS_RATE_CONTROL),
+ FLAG(RX_INCLUDES_FCS),
+ FLAG(HOST_BROADCAST_PS_BUFFERING),
+ FLAG(SIGNAL_UNSPEC),
+ FLAG(SIGNAL_DBM),
+ FLAG(NEED_DTIM_BEFORE_ASSOC),
+ FLAG(SPECTRUM_MGMT),
+ FLAG(AMPDU_AGGREGATION),
+ FLAG(SUPPORTS_PS),
+ FLAG(PS_NULLFUNC_STACK),
+ FLAG(SUPPORTS_DYNAMIC_PS),
+ FLAG(MFP_CAPABLE),
+ FLAG(WANT_MONITOR_VIF),
+ FLAG(NO_AUTO_VIF),
+ FLAG(SW_CRYPTO_CONTROL),
+ FLAG(SUPPORT_FAST_XMIT),
+ FLAG(REPORTS_TX_ACK_STATUS),
+ FLAG(CONNECTION_MONITOR),
+ FLAG(QUEUE_CONTROL),
+ FLAG(SUPPORTS_PER_STA_GTK),
+ FLAG(AP_LINK_PS),
+ FLAG(TX_AMPDU_SETUP_IN_HW),
+ FLAG(SUPPORTS_RC_TABLE),
+ FLAG(P2P_DEV_ADDR_FOR_INTF),
+ FLAG(TIMING_BEACON_ONLY),
+ FLAG(SUPPORTS_HT_CCK_RATES),
+ FLAG(CHANCTX_STA_CSA),
+ FLAG(SUPPORTS_CLONED_SKBS),
+ FLAG(SINGLE_SCAN_ON_ALL_BANDS),
+
+ /* keep last for the build bug below */
+ (void *)0x1
+#undef FLAG
+};
+
static ssize_t hwflags_read(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos)
{
struct ieee80211_local *local = file->private_data;
- int mxln = 500;
+ size_t bufsz = 30 * NUM_IEEE80211_HW_FLAGS;
+ char *buf = kzalloc(bufsz, GFP_KERNEL);
+ char *pos = buf, *end = buf + bufsz - 1;
ssize_t rv;
- char *buf = kzalloc(mxln, GFP_KERNEL);
- int sf = 0; /* how many written so far */
+ int i;
if (!buf)
- return 0;
-
- sf += scnprintf(buf, mxln - sf, "0x%x\n", local->hw.flags);
- if (local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL)
- sf += scnprintf(buf + sf, mxln - sf, "HAS_RATE_CONTROL\n");
- if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS)
- sf += scnprintf(buf + sf, mxln - sf, "RX_INCLUDES_FCS\n");
- if (local->hw.flags & IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING)
- sf += scnprintf(buf + sf, mxln - sf,
- "HOST_BCAST_PS_BUFFERING\n");
- if (local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE)
- sf += scnprintf(buf + sf, mxln - sf,
- "2GHZ_SHORT_SLOT_INCAPABLE\n");
- if (local->hw.flags & IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE)
- sf += scnprintf(buf + sf, mxln - sf,
- "2GHZ_SHORT_PREAMBLE_INCAPABLE\n");
- if (local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)
- sf += scnprintf(buf + sf, mxln - sf, "SIGNAL_UNSPEC\n");
- if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM)
- sf += scnprintf(buf + sf, mxln - sf, "SIGNAL_DBM\n");
- if (local->hw.flags & IEEE80211_HW_NEED_DTIM_BEFORE_ASSOC)
- sf += scnprintf(buf + sf, mxln - sf,
- "NEED_DTIM_BEFORE_ASSOC\n");
- if (local->hw.flags & IEEE80211_HW_SPECTRUM_MGMT)
- sf += scnprintf(buf + sf, mxln - sf, "SPECTRUM_MGMT\n");
- if (local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION)
- sf += scnprintf(buf + sf, mxln - sf, "AMPDU_AGGREGATION\n");
- if (local->hw.flags & IEEE80211_HW_SUPPORTS_PS)
- sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_PS\n");
- if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK)
- sf += scnprintf(buf + sf, mxln - sf, "PS_NULLFUNC_STACK\n");
- if (local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS)
- sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_DYNAMIC_PS\n");
- if (local->hw.flags & IEEE80211_HW_MFP_CAPABLE)
- sf += scnprintf(buf + sf, mxln - sf, "MFP_CAPABLE\n");
- if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
- sf += scnprintf(buf + sf, mxln - sf,
- "REPORTS_TX_ACK_STATUS\n");
- if (local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR)
- sf += scnprintf(buf + sf, mxln - sf, "CONNECTION_MONITOR\n");
- if (local->hw.flags & IEEE80211_HW_SUPPORTS_PER_STA_GTK)
- sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_PER_STA_GTK\n");
- if (local->hw.flags & IEEE80211_HW_AP_LINK_PS)
- sf += scnprintf(buf + sf, mxln - sf, "AP_LINK_PS\n");
- if (local->hw.flags & IEEE80211_HW_TX_AMPDU_SETUP_IN_HW)
- sf += scnprintf(buf + sf, mxln - sf, "TX_AMPDU_SETUP_IN_HW\n");
+ return -ENOMEM;
+
+ /* fail compilation if somebody adds or removes
+ * a flag without updating the name array above
+ */
+ BUILD_BUG_ON(hw_flag_names[NUM_IEEE80211_HW_FLAGS] != (void *)0x1);
+
+ for (i = 0; i < NUM_IEEE80211_HW_FLAGS; i++) {
+ if (test_bit(i, local->hw.flags))
+ pos += scnprintf(pos, end - pos, "%s",
+ hw_flag_names[i]);
+ }
rv = simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf));
kfree(buf);
@@ -219,8 +222,8 @@ static const struct file_operations stats_ ##name## _ops = { \
.llseek = generic_file_llseek, \
};
-#define DEBUGFS_STATS_ADD(name, field) \
- debugfs_create_u32(#name, 0400, statsd, (u32 *) &field);
+#define DEBUGFS_STATS_ADD(name) \
+ debugfs_create_u32(#name, 0400, statsd, &local->name);
#define DEBUGFS_DEVSTATS_ADD(name) \
debugfs_create_file(#name, 0400, statsd, local, &stats_ ##name## _ops);
@@ -255,53 +258,31 @@ void debugfs_hw_add(struct ieee80211_local *local)
if (!statsd)
return;
- DEBUGFS_STATS_ADD(transmitted_fragment_count,
- local->dot11TransmittedFragmentCount);
- DEBUGFS_STATS_ADD(multicast_transmitted_frame_count,
- local->dot11MulticastTransmittedFrameCount);
- DEBUGFS_STATS_ADD(failed_count, local->dot11FailedCount);
- DEBUGFS_STATS_ADD(retry_count, local->dot11RetryCount);
- DEBUGFS_STATS_ADD(multiple_retry_count,
- local->dot11MultipleRetryCount);
- DEBUGFS_STATS_ADD(frame_duplicate_count,
- local->dot11FrameDuplicateCount);
- DEBUGFS_STATS_ADD(received_fragment_count,
- local->dot11ReceivedFragmentCount);
- DEBUGFS_STATS_ADD(multicast_received_frame_count,
- local->dot11MulticastReceivedFrameCount);
- DEBUGFS_STATS_ADD(transmitted_frame_count,
- local->dot11TransmittedFrameCount);
#ifdef CONFIG_MAC80211_DEBUG_COUNTERS
- DEBUGFS_STATS_ADD(tx_handlers_drop, local->tx_handlers_drop);
- DEBUGFS_STATS_ADD(tx_handlers_queued, local->tx_handlers_queued);
- DEBUGFS_STATS_ADD(tx_handlers_drop_fragment,
- local->tx_handlers_drop_fragment);
- DEBUGFS_STATS_ADD(tx_handlers_drop_wep,
- local->tx_handlers_drop_wep);
- DEBUGFS_STATS_ADD(tx_handlers_drop_not_assoc,
- local->tx_handlers_drop_not_assoc);
- DEBUGFS_STATS_ADD(tx_handlers_drop_unauth_port,
- local->tx_handlers_drop_unauth_port);
- DEBUGFS_STATS_ADD(rx_handlers_drop, local->rx_handlers_drop);
- DEBUGFS_STATS_ADD(rx_handlers_queued, local->rx_handlers_queued);
- DEBUGFS_STATS_ADD(rx_handlers_drop_nullfunc,
- local->rx_handlers_drop_nullfunc);
- DEBUGFS_STATS_ADD(rx_handlers_drop_defrag,
- local->rx_handlers_drop_defrag);
- DEBUGFS_STATS_ADD(rx_handlers_drop_short,
- local->rx_handlers_drop_short);
- DEBUGFS_STATS_ADD(tx_expand_skb_head,
- local->tx_expand_skb_head);
- DEBUGFS_STATS_ADD(tx_expand_skb_head_cloned,
- local->tx_expand_skb_head_cloned);
- DEBUGFS_STATS_ADD(rx_expand_skb_head,
- local->rx_expand_skb_head);
- DEBUGFS_STATS_ADD(rx_expand_skb_head2,
- local->rx_expand_skb_head2);
- DEBUGFS_STATS_ADD(rx_handlers_fragments,
- local->rx_handlers_fragments);
- DEBUGFS_STATS_ADD(tx_status_drop,
- local->tx_status_drop);
+ DEBUGFS_STATS_ADD(dot11TransmittedFragmentCount);
+ DEBUGFS_STATS_ADD(dot11MulticastTransmittedFrameCount);
+ DEBUGFS_STATS_ADD(dot11FailedCount);
+ DEBUGFS_STATS_ADD(dot11RetryCount);
+ DEBUGFS_STATS_ADD(dot11MultipleRetryCount);
+ DEBUGFS_STATS_ADD(dot11FrameDuplicateCount);
+ DEBUGFS_STATS_ADD(dot11ReceivedFragmentCount);
+ DEBUGFS_STATS_ADD(dot11MulticastReceivedFrameCount);
+ DEBUGFS_STATS_ADD(dot11TransmittedFrameCount);
+ DEBUGFS_STATS_ADD(tx_handlers_drop);
+ DEBUGFS_STATS_ADD(tx_handlers_queued);
+ DEBUGFS_STATS_ADD(tx_handlers_drop_wep);
+ DEBUGFS_STATS_ADD(tx_handlers_drop_not_assoc);
+ DEBUGFS_STATS_ADD(tx_handlers_drop_unauth_port);
+ DEBUGFS_STATS_ADD(rx_handlers_drop);
+ DEBUGFS_STATS_ADD(rx_handlers_queued);
+ DEBUGFS_STATS_ADD(rx_handlers_drop_nullfunc);
+ DEBUGFS_STATS_ADD(rx_handlers_drop_defrag);
+ DEBUGFS_STATS_ADD(rx_handlers_drop_short);
+ DEBUGFS_STATS_ADD(tx_expand_skb_head);
+ DEBUGFS_STATS_ADD(tx_expand_skb_head_cloned);
+ DEBUGFS_STATS_ADD(rx_expand_skb_head_defrag);
+ DEBUGFS_STATS_ADD(rx_handlers_fragments);
+ DEBUGFS_STATS_ADD(tx_status_drop);
#endif
DEBUGFS_DEVSTATS_ADD(dot11ACKFailureCount);
DEBUGFS_DEVSTATS_ADD(dot11RTSFailureCount);
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index 71ac1b5f4da5..e82bf1e9d7a8 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -95,28 +95,13 @@ static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf,
break;
case WLAN_CIPHER_SUITE_CCMP:
case WLAN_CIPHER_SUITE_CCMP_256:
- pn = atomic64_read(&key->u.ccmp.tx_pn);
- len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
- (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
- (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
- break;
case WLAN_CIPHER_SUITE_AES_CMAC:
case WLAN_CIPHER_SUITE_BIP_CMAC_256:
- pn = atomic64_read(&key->u.aes_cmac.tx_pn);
- len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
- (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
- (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
- break;
case WLAN_CIPHER_SUITE_BIP_GMAC_128:
case WLAN_CIPHER_SUITE_BIP_GMAC_256:
- pn = atomic64_read(&key->u.aes_gmac.tx_pn);
- len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
- (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
- (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
- break;
case WLAN_CIPHER_SUITE_GCMP:
case WLAN_CIPHER_SUITE_GCMP_256:
- pn = atomic64_read(&key->u.gcmp.tx_pn);
+ pn = atomic64_read(&key->conf.tx_pn);
len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
(u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
(u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 252859e90e8a..06d52935036d 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -29,8 +29,6 @@ static ssize_t sta_ ##name## _read(struct file *file, \
format_string, sta->field); \
}
#define STA_READ_D(name, field) STA_READ(name, field, "%d\n")
-#define STA_READ_U(name, field) STA_READ(name, field, "%u\n")
-#define STA_READ_S(name, field) STA_READ(name, field, "%s\n")
#define STA_OPS(name) \
static const struct file_operations sta_ ##name## _ops = { \
@@ -52,10 +50,7 @@ static const struct file_operations sta_ ##name## _ops = { \
STA_OPS(name)
STA_FILE(aid, sta.aid, D);
-STA_FILE(dev, sdata->name, S);
-STA_FILE(last_signal, last_signal, D);
STA_FILE(last_ack_signal, last_ack_signal, D);
-STA_FILE(beacon_loss_count, beacon_loss_count, D);
static ssize_t sta_flags_read(struct file *file, char __user *userbuf,
size_t count, loff_t *ppos)
@@ -101,40 +96,6 @@ static ssize_t sta_num_ps_buf_frames_read(struct file *file,
}
STA_OPS(num_ps_buf_frames);
-static ssize_t sta_inactive_ms_read(struct file *file, char __user *userbuf,
- size_t count, loff_t *ppos)
-{
- struct sta_info *sta = file->private_data;
- return mac80211_format_buffer(userbuf, count, ppos, "%d\n",
- jiffies_to_msecs(jiffies - sta->last_rx));
-}
-STA_OPS(inactive_ms);
-
-
-static ssize_t sta_connected_time_read(struct file *file, char __user *userbuf,
- size_t count, loff_t *ppos)
-{
- struct sta_info *sta = file->private_data;
- struct timespec uptime;
- struct tm result;
- long connected_time_secs;
- char buf[100];
- int res;
- ktime_get_ts(&uptime);
- connected_time_secs = uptime.tv_sec - sta->last_connected;
- time_to_tm(connected_time_secs, 0, &result);
- result.tm_year -= 70;
- result.tm_mday -= 1;
- res = scnprintf(buf, sizeof(buf),
- "years - %ld\nmonths - %d\ndays - %d\nclock - %d:%d:%d\n\n",
- result.tm_year, result.tm_mon, result.tm_mday,
- result.tm_hour, result.tm_min, result.tm_sec);
- return simple_read_from_buffer(userbuf, count, ppos, buf, res);
-}
-STA_OPS(connected_time);
-
-
-
static ssize_t sta_last_seq_ctrl_read(struct file *file, char __user *userbuf,
size_t count, loff_t *ppos)
{
@@ -359,37 +320,6 @@ static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf,
}
STA_OPS(vht_capa);
-static ssize_t sta_current_tx_rate_read(struct file *file, char __user *userbuf,
- size_t count, loff_t *ppos)
-{
- struct sta_info *sta = file->private_data;
- struct rate_info rinfo;
- u16 rate;
- sta_set_rate_info_tx(sta, &sta->last_tx_rate, &rinfo);
- rate = cfg80211_calculate_bitrate(&rinfo);
-
- return mac80211_format_buffer(userbuf, count, ppos,
- "%d.%d MBit/s\n",
- rate/10, rate%10);
-}
-STA_OPS(current_tx_rate);
-
-static ssize_t sta_last_rx_rate_read(struct file *file, char __user *userbuf,
- size_t count, loff_t *ppos)
-{
- struct sta_info *sta = file->private_data;
- struct rate_info rinfo;
- u16 rate;
-
- sta_set_rate_info_rx(sta, &rinfo);
-
- rate = cfg80211_calculate_bitrate(&rinfo);
-
- return mac80211_format_buffer(userbuf, count, ppos,
- "%d.%d MBit/s\n",
- rate/10, rate%10);
-}
-STA_OPS(last_rx_rate);
#define DEBUGFS_ADD(name) \
debugfs_create_file(#name, 0400, \
@@ -432,30 +362,15 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta)
DEBUGFS_ADD(flags);
DEBUGFS_ADD(num_ps_buf_frames);
- DEBUGFS_ADD(inactive_ms);
- DEBUGFS_ADD(connected_time);
DEBUGFS_ADD(last_seq_ctrl);
DEBUGFS_ADD(agg_status);
- DEBUGFS_ADD(dev);
- DEBUGFS_ADD(last_signal);
- DEBUGFS_ADD(beacon_loss_count);
DEBUGFS_ADD(ht_capa);
DEBUGFS_ADD(vht_capa);
DEBUGFS_ADD(last_ack_signal);
- DEBUGFS_ADD(current_tx_rate);
- DEBUGFS_ADD(last_rx_rate);
- DEBUGFS_ADD_COUNTER(rx_packets, rx_packets);
- DEBUGFS_ADD_COUNTER(tx_packets, tx_packets);
- DEBUGFS_ADD_COUNTER(rx_bytes, rx_bytes);
- DEBUGFS_ADD_COUNTER(tx_bytes, tx_bytes);
DEBUGFS_ADD_COUNTER(rx_duplicates, num_duplicates);
DEBUGFS_ADD_COUNTER(rx_fragments, rx_fragments);
- DEBUGFS_ADD_COUNTER(rx_dropped, rx_dropped);
- DEBUGFS_ADD_COUNTER(tx_fragments, tx_fragments);
DEBUGFS_ADD_COUNTER(tx_filtered, tx_filtered_count);
- DEBUGFS_ADD_COUNTER(tx_retry_failed, tx_retry_failed);
- DEBUGFS_ADD_COUNTER(tx_retry_count, tx_retry_count);
if (sizeof(sta->driver_buffered_tids) == sizeof(u32))
debugfs_create_x32("driver_buffered_tids", 0400,
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 26e1ca8a474a..32a2e707e222 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -146,7 +146,7 @@ static inline int drv_add_interface(struct ieee80211_local *local,
if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
(sdata->vif.type == NL80211_IFTYPE_MONITOR &&
- !(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF) &&
+ !ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) &&
!(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE))))
return -EINVAL;
@@ -417,12 +417,13 @@ static inline int drv_get_stats(struct ieee80211_local *local,
return ret;
}
-static inline void drv_get_tkip_seq(struct ieee80211_local *local,
- u8 hw_key_idx, u32 *iv32, u16 *iv16)
+static inline void drv_get_key_seq(struct ieee80211_local *local,
+ struct ieee80211_key *key,
+ struct ieee80211_key_seq *seq)
{
- if (local->ops->get_tkip_seq)
- local->ops->get_tkip_seq(&local->hw, hw_key_idx, iv32, iv16);
- trace_drv_get_tkip_seq(local, hw_key_idx, iv32, iv16);
+ if (local->ops->get_key_seq)
+ local->ops->get_key_seq(&local->hw, &key->conf, seq);
+ trace_drv_get_key_seq(local, &key->conf);
}
static inline int drv_set_frag_threshold(struct ieee80211_local *local,
diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c
index 52bcea6ad9e8..188faab11c24 100644
--- a/net/mac80211/ethtool.c
+++ b/net/mac80211/ethtool.c
@@ -38,7 +38,7 @@ static void ieee80211_get_ringparam(struct net_device *dev,
static const char ieee80211_gstrings_sta_stats[][ETH_GSTRING_LEN] = {
"rx_packets", "rx_bytes",
"rx_duplicates", "rx_fragments", "rx_dropped",
- "tx_packets", "tx_bytes", "tx_fragments",
+ "tx_packets", "tx_bytes",
"tx_filtered", "tx_retry_failed", "tx_retries",
"beacon_loss", "sta_state", "txrate", "rxrate", "signal",
"channel", "noise", "ch_time", "ch_time_busy",
@@ -87,7 +87,6 @@ static void ieee80211_get_stats(struct net_device *dev,
\
data[i++] += sinfo.tx_packets; \
data[i++] += sinfo.tx_bytes; \
- data[i++] += sta->tx_fragments; \
data[i++] += sta->tx_filtered_count; \
data[i++] += sta->tx_retry_failed; \
data[i++] += sta->tx_retry_count; \
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index bfef1b215050..7f72bc9bae2e 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -146,6 +146,7 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata,
csa_settings->chandef.chan->center_freq);
presp->csa_counter_offsets[0] = (pos - presp->head);
*pos++ = csa_settings->count;
+ presp->csa_current_counter = csa_settings->count;
}
/* put the remaining rates in WLAN_EID_EXT_SUPP_RATES */
@@ -1031,8 +1032,11 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata,
}
}
- if (sta && elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS)
+ if (sta && !sta->sta.wme &&
+ elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS) {
sta->sta.wme = true;
+ ieee80211_check_fast_xmit(sta);
+ }
if (sta && elems->ht_operation && elems->ht_cap_elem &&
sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT &&
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index c0a9187bc3a9..b12f61507f9f 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -181,8 +181,6 @@ typedef unsigned __bitwise__ ieee80211_rx_result;
/**
* enum ieee80211_packet_rx_flags - packet RX flags
- * @IEEE80211_RX_RA_MATCH: frame is destined to interface currently processed
- * (incl. multicast frames)
* @IEEE80211_RX_FRAGMENTED: fragmented frame
* @IEEE80211_RX_AMSDU: a-MSDU packet
* @IEEE80211_RX_MALFORMED_ACTION_FRM: action frame is malformed
@@ -192,7 +190,6 @@ typedef unsigned __bitwise__ ieee80211_rx_result;
* @rx_flags field of &struct ieee80211_rx_status.
*/
enum ieee80211_packet_rx_flags {
- IEEE80211_RX_RA_MATCH = BIT(1),
IEEE80211_RX_FRAGMENTED = BIT(2),
IEEE80211_RX_AMSDU = BIT(3),
IEEE80211_RX_MALFORMED_ACTION_FRM = BIT(4),
@@ -722,7 +719,6 @@ struct ieee80211_if_mesh {
* enum ieee80211_sub_if_data_flags - virtual interface flags
*
* @IEEE80211_SDATA_ALLMULTI: interface wants all multicast packets
- * @IEEE80211_SDATA_PROMISC: interface is promisc
* @IEEE80211_SDATA_OPERATING_GMODE: operating in G-only mode
* @IEEE80211_SDATA_DONT_BRIDGE_PACKETS: bridge packets between
* associated stations and deliver multicast frames both
@@ -732,7 +728,6 @@ struct ieee80211_if_mesh {
*/
enum ieee80211_sub_if_data_flags {
IEEE80211_SDATA_ALLMULTI = BIT(0),
- IEEE80211_SDATA_PROMISC = BIT(1),
IEEE80211_SDATA_OPERATING_GMODE = BIT(2),
IEEE80211_SDATA_DONT_BRIDGE_PACKETS = BIT(3),
IEEE80211_SDATA_DISCONNECT_RESUME = BIT(4),
@@ -1040,7 +1035,6 @@ enum queue_stop_reason {
#ifdef CONFIG_MAC80211_LEDS
struct tpt_led_trigger {
- struct led_trigger trig;
char name[32];
const struct ieee80211_tpt_blink *blink_table;
unsigned int blink_table_len;
@@ -1208,8 +1202,8 @@ struct ieee80211_local {
atomic_t agg_queue_stop[IEEE80211_MAX_QUEUES];
- /* number of interfaces with corresponding IFF_ flags */
- atomic_t iff_allmultis, iff_promiscs;
+ /* number of interfaces with allmulti RX */
+ atomic_t iff_allmultis;
struct rate_control_ref *rate_ctrl;
@@ -1261,6 +1255,15 @@ struct ieee80211_local {
struct list_head chanctx_list;
struct mutex chanctx_mtx;
+#ifdef CONFIG_MAC80211_LEDS
+ struct led_trigger tx_led, rx_led, assoc_led, radio_led;
+ struct led_trigger tpt_led;
+ atomic_t tx_led_active, rx_led_active, assoc_led_active;
+ atomic_t radio_led_active, tpt_led_active;
+ struct tpt_led_trigger *tpt_led_trigger;
+#endif
+
+#ifdef CONFIG_MAC80211_DEBUG_COUNTERS
/* SNMP counters */
/* dot11CountersTable */
u32 dot11TransmittedFragmentCount;
@@ -1273,18 +1276,9 @@ struct ieee80211_local {
u32 dot11MulticastReceivedFrameCount;
u32 dot11TransmittedFrameCount;
-#ifdef CONFIG_MAC80211_LEDS
- struct led_trigger *tx_led, *rx_led, *assoc_led, *radio_led;
- struct tpt_led_trigger *tpt_led_trigger;
- char tx_led_name[32], rx_led_name[32],
- assoc_led_name[32], radio_led_name[32];
-#endif
-
-#ifdef CONFIG_MAC80211_DEBUG_COUNTERS
/* TX/RX handler statistics */
unsigned int tx_handlers_drop;
unsigned int tx_handlers_queued;
- unsigned int tx_handlers_drop_fragment;
unsigned int tx_handlers_drop_wep;
unsigned int tx_handlers_drop_not_assoc;
unsigned int tx_handlers_drop_unauth_port;
@@ -1295,8 +1289,7 @@ struct ieee80211_local {
unsigned int rx_handlers_drop_short;
unsigned int tx_expand_skb_head;
unsigned int tx_expand_skb_head_cloned;
- unsigned int rx_expand_skb_head;
- unsigned int rx_expand_skb_head2;
+ unsigned int rx_expand_skb_head_defrag;
unsigned int rx_handlers_fragments;
unsigned int tx_status_drop;
#define I802_DEBUG_INC(c) (c)++
@@ -1648,6 +1641,11 @@ struct sk_buff *
ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb, u32 info_flags);
+void ieee80211_check_fast_xmit(struct sta_info *sta);
+void ieee80211_check_fast_xmit_all(struct ieee80211_local *local);
+void ieee80211_check_fast_xmit_iface(struct ieee80211_sub_if_data *sdata);
+void ieee80211_clear_fast_xmit(struct sta_info *sta);
+
/* HT */
void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
struct ieee80211_sta_ht_cap *ht_cap);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 84cef600c573..ed1edac14372 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -338,7 +338,7 @@ static int ieee80211_check_queues(struct ieee80211_sub_if_data *sdata,
if ((iftype != NL80211_IFTYPE_AP &&
iftype != NL80211_IFTYPE_P2P_GO &&
iftype != NL80211_IFTYPE_MESH_POINT) ||
- !(sdata->local->hw.flags & IEEE80211_HW_QUEUE_CONTROL)) {
+ !ieee80211_hw_check(&sdata->local->hw, QUEUE_CONTROL)) {
sdata->vif.cab_queue = IEEE80211_INVAL_HW_QUEUE;
return 0;
}
@@ -378,7 +378,7 @@ static void ieee80211_set_default_queues(struct ieee80211_sub_if_data *sdata)
int i;
for (i = 0; i < IEEE80211_NUM_ACS; i++) {
- if (local->hw.flags & IEEE80211_HW_QUEUE_CONTROL)
+ if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL))
sdata->vif.hw_queue[i] = IEEE80211_INVAL_HW_QUEUE;
else if (local->hw.queues >= IEEE80211_NUM_ACS)
sdata->vif.hw_queue[i] = i;
@@ -393,7 +393,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
struct ieee80211_sub_if_data *sdata;
int ret;
- if (!(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF))
+ if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
return 0;
ASSERT_RTNL();
@@ -454,7 +454,7 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local)
{
struct ieee80211_sub_if_data *sdata;
- if (!(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF))
+ if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
return;
ASSERT_RTNL();
@@ -703,9 +703,6 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
if (sdata->flags & IEEE80211_SDATA_ALLMULTI)
atomic_inc(&local->iff_allmultis);
- if (sdata->flags & IEEE80211_SDATA_PROMISC)
- atomic_inc(&local->iff_promiscs);
-
if (coming_up)
local->open_count++;
@@ -835,13 +832,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) ||
(sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1)));
- /* don't count this interface for promisc/allmulti while it is down */
+ /* don't count this interface for allmulti while it is down */
if (sdata->flags & IEEE80211_SDATA_ALLMULTI)
atomic_dec(&local->iff_allmultis);
- if (sdata->flags & IEEE80211_SDATA_PROMISC)
- atomic_dec(&local->iff_promiscs);
-
if (sdata->vif.type == NL80211_IFTYPE_AP) {
local->fif_pspoll--;
local->fif_probe_req--;
@@ -1055,12 +1049,10 @@ static void ieee80211_set_multicast_list(struct net_device *dev)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct ieee80211_local *local = sdata->local;
- int allmulti, promisc, sdata_allmulti, sdata_promisc;
+ int allmulti, sdata_allmulti;
allmulti = !!(dev->flags & IFF_ALLMULTI);
- promisc = !!(dev->flags & IFF_PROMISC);
sdata_allmulti = !!(sdata->flags & IEEE80211_SDATA_ALLMULTI);
- sdata_promisc = !!(sdata->flags & IEEE80211_SDATA_PROMISC);
if (allmulti != sdata_allmulti) {
if (dev->flags & IFF_ALLMULTI)
@@ -1070,13 +1062,6 @@ static void ieee80211_set_multicast_list(struct net_device *dev)
sdata->flags ^= IEEE80211_SDATA_ALLMULTI;
}
- if (promisc != sdata_promisc) {
- if (dev->flags & IFF_PROMISC)
- atomic_inc(&local->iff_promiscs);
- else
- atomic_dec(&local->iff_promiscs);
- sdata->flags ^= IEEE80211_SDATA_PROMISC;
- }
spin_lock_bh(&local->filter_lock);
__hw_addr_sync(&local->mc_list, &dev->mc, dev->addr_len);
spin_unlock_bh(&local->filter_lock);
@@ -1117,6 +1102,35 @@ static u16 ieee80211_netdev_select_queue(struct net_device *dev,
return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
}
+static struct rtnl_link_stats64 *
+ieee80211_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ const struct pcpu_sw_netstats *tstats;
+ u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
+ unsigned int start;
+
+ tstats = per_cpu_ptr(dev->tstats, i);
+
+ do {
+ start = u64_stats_fetch_begin_irq(&tstats->syncp);
+ rx_packets = tstats->rx_packets;
+ tx_packets = tstats->tx_packets;
+ rx_bytes = tstats->rx_bytes;
+ tx_bytes = tstats->tx_bytes;
+ } while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
+
+ stats->rx_packets += rx_packets;
+ stats->tx_packets += tx_packets;
+ stats->rx_bytes += rx_bytes;
+ stats->tx_bytes += tx_bytes;
+ }
+
+ return stats;
+}
+
static const struct net_device_ops ieee80211_dataif_ops = {
.ndo_open = ieee80211_open,
.ndo_stop = ieee80211_stop,
@@ -1126,6 +1140,7 @@ static const struct net_device_ops ieee80211_dataif_ops = {
.ndo_change_mtu = ieee80211_change_mtu,
.ndo_set_mac_address = ieee80211_change_mac,
.ndo_select_queue = ieee80211_netdev_select_queue,
+ .ndo_get_stats64 = ieee80211_get_stats64,
};
static u16 ieee80211_monitor_select_queue(struct net_device *dev,
@@ -1159,14 +1174,21 @@ static const struct net_device_ops ieee80211_monitorif_ops = {
.ndo_change_mtu = ieee80211_change_mtu,
.ndo_set_mac_address = ieee80211_change_mac,
.ndo_select_queue = ieee80211_monitor_select_queue,
+ .ndo_get_stats64 = ieee80211_get_stats64,
};
+static void ieee80211_if_free(struct net_device *dev)
+{
+ free_percpu(dev->tstats);
+ free_netdev(dev);
+}
+
static void ieee80211_if_setup(struct net_device *dev)
{
ether_setup(dev);
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
dev->netdev_ops = &ieee80211_dataif_ops;
- dev->destructor = free_netdev;
+ dev->destructor = ieee80211_if_free;
}
static void ieee80211_iface_work(struct work_struct *work)
@@ -1564,7 +1586,7 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local,
break;
case NL80211_IFTYPE_P2P_CLIENT:
case NL80211_IFTYPE_P2P_GO:
- if (local->hw.flags & IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF) {
+ if (ieee80211_hw_check(&local->hw, P2P_DEV_ADDR_FOR_INTF)) {
list_for_each_entry(sdata, &local->interfaces, list) {
if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE)
continue;
@@ -1707,6 +1729,12 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
return -ENOMEM;
dev_net_set(ndev, wiphy_net(local->hw.wiphy));
+ ndev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!ndev->tstats) {
+ free_netdev(ndev);
+ return -ENOMEM;
+ }
+
ndev->needed_headroom = local->tx_headroom +
4*6 /* four MAC addresses */
+ 2 + 2 + 2 + 2 /* ctl, dur, seq, qos */
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index a907f2d5c12d..8abc31ebcf61 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -147,7 +147,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
* is supported; if not, return.
*/
if (sta && !(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE) &&
- !(key->local->hw.flags & IEEE80211_HW_SUPPORTS_PER_STA_GTK))
+ !ieee80211_hw_check(&key->local->hw, SUPPORTS_PER_STA_GTK))
goto out_unsupported;
if (sta && !sta->uploaded)
@@ -201,7 +201,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
/* all of these we can do in software - if driver can */
if (ret == 1)
return 0;
- if (key->local->hw.flags & IEEE80211_HW_SW_CRYPTO_CONTROL)
+ if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL))
return -EINVAL;
return 0;
default:
@@ -256,6 +256,7 @@ static void __ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata,
if (uni) {
rcu_assign_pointer(sdata->default_unicast_key, key);
+ ieee80211_check_fast_xmit_iface(sdata);
drv_set_default_unicast_key(sdata->local, sdata, idx);
}
@@ -325,6 +326,7 @@ static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata,
if (pairwise) {
rcu_assign_pointer(sta->ptk[idx], new);
sta->ptk_idx = idx;
+ ieee80211_check_fast_xmit(sta);
} else {
rcu_assign_pointer(sta->gtk[idx], new);
sta->gtk_idx = idx;
@@ -510,15 +512,17 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
break;
default:
if (cs) {
- size_t len = (seq_len > MAX_PN_LEN) ?
- MAX_PN_LEN : seq_len;
+ if (seq_len && seq_len != cs->pn_len) {
+ kfree(key);
+ return ERR_PTR(-EINVAL);
+ }
key->conf.iv_len = cs->hdr_len;
key->conf.icv_len = cs->mic_len;
for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++)
- for (j = 0; j < len; j++)
+ for (j = 0; j < seq_len; j++)
key->u.gen.rx_pn[i][j] =
- seq[len - j - 1];
+ seq[seq_len - j - 1];
key->flags |= KEY_FLAG_CIPHER_SCHEME;
}
}
@@ -892,27 +896,19 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf,
break;
case WLAN_CIPHER_SUITE_CCMP:
case WLAN_CIPHER_SUITE_CCMP_256:
- pn64 = atomic64_read(&key->u.ccmp.tx_pn);
- seq->ccmp.pn[5] = pn64;
- seq->ccmp.pn[4] = pn64 >> 8;
- seq->ccmp.pn[3] = pn64 >> 16;
- seq->ccmp.pn[2] = pn64 >> 24;
- seq->ccmp.pn[1] = pn64 >> 32;
- seq->ccmp.pn[0] = pn64 >> 40;
- break;
case WLAN_CIPHER_SUITE_AES_CMAC:
case WLAN_CIPHER_SUITE_BIP_CMAC_256:
- pn64 = atomic64_read(&key->u.aes_cmac.tx_pn);
- seq->ccmp.pn[5] = pn64;
- seq->ccmp.pn[4] = pn64 >> 8;
- seq->ccmp.pn[3] = pn64 >> 16;
- seq->ccmp.pn[2] = pn64 >> 24;
- seq->ccmp.pn[1] = pn64 >> 32;
- seq->ccmp.pn[0] = pn64 >> 40;
- break;
+ BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) !=
+ offsetof(typeof(*seq), aes_cmac));
case WLAN_CIPHER_SUITE_BIP_GMAC_128:
case WLAN_CIPHER_SUITE_BIP_GMAC_256:
- pn64 = atomic64_read(&key->u.aes_gmac.tx_pn);
+ BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) !=
+ offsetof(typeof(*seq), aes_gmac));
+ case WLAN_CIPHER_SUITE_GCMP:
+ case WLAN_CIPHER_SUITE_GCMP_256:
+ BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) !=
+ offsetof(typeof(*seq), gcmp));
+ pn64 = atomic64_read(&key->conf.tx_pn);
seq->ccmp.pn[5] = pn64;
seq->ccmp.pn[4] = pn64 >> 8;
seq->ccmp.pn[3] = pn64 >> 16;
@@ -920,16 +916,6 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf,
seq->ccmp.pn[1] = pn64 >> 32;
seq->ccmp.pn[0] = pn64 >> 40;
break;
- case WLAN_CIPHER_SUITE_GCMP:
- case WLAN_CIPHER_SUITE_GCMP_256:
- pn64 = atomic64_read(&key->u.gcmp.tx_pn);
- seq->gcmp.pn[5] = pn64;
- seq->gcmp.pn[4] = pn64 >> 8;
- seq->gcmp.pn[3] = pn64 >> 16;
- seq->gcmp.pn[2] = pn64 >> 24;
- seq->gcmp.pn[1] = pn64 >> 32;
- seq->gcmp.pn[0] = pn64 >> 40;
- break;
default:
WARN_ON(1);
}
@@ -1004,43 +990,25 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf,
break;
case WLAN_CIPHER_SUITE_CCMP:
case WLAN_CIPHER_SUITE_CCMP_256:
- pn64 = (u64)seq->ccmp.pn[5] |
- ((u64)seq->ccmp.pn[4] << 8) |
- ((u64)seq->ccmp.pn[3] << 16) |
- ((u64)seq->ccmp.pn[2] << 24) |
- ((u64)seq->ccmp.pn[1] << 32) |
- ((u64)seq->ccmp.pn[0] << 40);
- atomic64_set(&key->u.ccmp.tx_pn, pn64);
- break;
case WLAN_CIPHER_SUITE_AES_CMAC:
case WLAN_CIPHER_SUITE_BIP_CMAC_256:
- pn64 = (u64)seq->aes_cmac.pn[5] |
- ((u64)seq->aes_cmac.pn[4] << 8) |
- ((u64)seq->aes_cmac.pn[3] << 16) |
- ((u64)seq->aes_cmac.pn[2] << 24) |
- ((u64)seq->aes_cmac.pn[1] << 32) |
- ((u64)seq->aes_cmac.pn[0] << 40);
- atomic64_set(&key->u.aes_cmac.tx_pn, pn64);
- break;
+ BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) !=
+ offsetof(typeof(*seq), aes_cmac));
case WLAN_CIPHER_SUITE_BIP_GMAC_128:
case WLAN_CIPHER_SUITE_BIP_GMAC_256:
- pn64 = (u64)seq->aes_gmac.pn[5] |
- ((u64)seq->aes_gmac.pn[4] << 8) |
- ((u64)seq->aes_gmac.pn[3] << 16) |
- ((u64)seq->aes_gmac.pn[2] << 24) |
- ((u64)seq->aes_gmac.pn[1] << 32) |
- ((u64)seq->aes_gmac.pn[0] << 40);
- atomic64_set(&key->u.aes_gmac.tx_pn, pn64);
- break;
+ BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) !=
+ offsetof(typeof(*seq), aes_gmac));
case WLAN_CIPHER_SUITE_GCMP:
case WLAN_CIPHER_SUITE_GCMP_256:
- pn64 = (u64)seq->gcmp.pn[5] |
- ((u64)seq->gcmp.pn[4] << 8) |
- ((u64)seq->gcmp.pn[3] << 16) |
- ((u64)seq->gcmp.pn[2] << 24) |
- ((u64)seq->gcmp.pn[1] << 32) |
- ((u64)seq->gcmp.pn[0] << 40);
- atomic64_set(&key->u.gcmp.tx_pn, pn64);
+ BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) !=
+ offsetof(typeof(*seq), gcmp));
+ pn64 = (u64)seq->ccmp.pn[5] |
+ ((u64)seq->ccmp.pn[4] << 8) |
+ ((u64)seq->ccmp.pn[3] << 16) |
+ ((u64)seq->ccmp.pn[2] << 24) |
+ ((u64)seq->ccmp.pn[1] << 32) |
+ ((u64)seq->ccmp.pn[0] << 40);
+ atomic64_set(&key->conf.tx_pn, pn64);
break;
default:
WARN_ON(1);
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index 96557dd1e77d..3f4f9eaac140 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -18,7 +18,6 @@
#define NUM_DEFAULT_KEYS 4
#define NUM_DEFAULT_MGMT_KEYS 2
-#define MAX_PN_LEN 16
struct ieee80211_local;
struct ieee80211_sub_if_data;
@@ -78,7 +77,6 @@ struct ieee80211_key {
u32 mic_failures;
} tkip;
struct {
- atomic64_t tx_pn;
/*
* Last received packet number. The first
* IEEE80211_NUM_TIDS counters are used with Data
@@ -90,21 +88,18 @@ struct ieee80211_key {
u32 replays; /* dot11RSNAStatsCCMPReplays */
} ccmp;
struct {
- atomic64_t tx_pn;
u8 rx_pn[IEEE80211_CMAC_PN_LEN];
struct crypto_cipher *tfm;
u32 replays; /* dot11RSNAStatsCMACReplays */
u32 icverrors; /* dot11RSNAStatsCMACICVErrors */
} aes_cmac;
struct {
- atomic64_t tx_pn;
u8 rx_pn[IEEE80211_GMAC_PN_LEN];
struct crypto_aead *tfm;
u32 replays; /* dot11RSNAStatsCMACReplays */
u32 icverrors; /* dot11RSNAStatsCMACICVErrors */
} aes_gmac;
struct {
- atomic64_t tx_pn;
/* Last received packet number. The first
* IEEE80211_NUM_TIDS counters are used with Data
* frames and the last counter is used with Robust
@@ -116,7 +111,7 @@ struct ieee80211_key {
} gcmp;
struct {
/* generic cipher scheme */
- u8 rx_pn[IEEE80211_NUM_TIDS + 1][MAX_PN_LEN];
+ u8 rx_pn[IEEE80211_NUM_TIDS + 1][IEEE80211_MAX_PN_LEN];
} gen;
} u;
diff --git a/net/mac80211/led.c b/net/mac80211/led.c
index e2b836446af3..0505845b7ab8 100644
--- a/net/mac80211/led.c
+++ b/net/mac80211/led.c
@@ -12,96 +12,175 @@
#include <linux/export.h>
#include "led.h"
-#define MAC80211_BLINK_DELAY 50 /* ms */
-
-void ieee80211_led_rx(struct ieee80211_local *local)
-{
- unsigned long led_delay = MAC80211_BLINK_DELAY;
- if (unlikely(!local->rx_led))
- return;
- led_trigger_blink_oneshot(local->rx_led, &led_delay, &led_delay, 0);
-}
-
-void ieee80211_led_tx(struct ieee80211_local *local)
-{
- unsigned long led_delay = MAC80211_BLINK_DELAY;
- if (unlikely(!local->tx_led))
- return;
- led_trigger_blink_oneshot(local->tx_led, &led_delay, &led_delay, 0);
-}
-
void ieee80211_led_assoc(struct ieee80211_local *local, bool associated)
{
- if (unlikely(!local->assoc_led))
+ if (!atomic_read(&local->assoc_led_active))
return;
if (associated)
- led_trigger_event(local->assoc_led, LED_FULL);
+ led_trigger_event(&local->assoc_led, LED_FULL);
else
- led_trigger_event(local->assoc_led, LED_OFF);
+ led_trigger_event(&local->assoc_led, LED_OFF);
}
void ieee80211_led_radio(struct ieee80211_local *local, bool enabled)
{
- if (unlikely(!local->radio_led))
+ if (!atomic_read(&local->radio_led_active))
return;
if (enabled)
- led_trigger_event(local->radio_led, LED_FULL);
+ led_trigger_event(&local->radio_led, LED_FULL);
else
- led_trigger_event(local->radio_led, LED_OFF);
+ led_trigger_event(&local->radio_led, LED_OFF);
+}
+
+void ieee80211_alloc_led_names(struct ieee80211_local *local)
+{
+ local->rx_led.name = kasprintf(GFP_KERNEL, "%srx",
+ wiphy_name(local->hw.wiphy));
+ local->tx_led.name = kasprintf(GFP_KERNEL, "%stx",
+ wiphy_name(local->hw.wiphy));
+ local->assoc_led.name = kasprintf(GFP_KERNEL, "%sassoc",
+ wiphy_name(local->hw.wiphy));
+ local->radio_led.name = kasprintf(GFP_KERNEL, "%sradio",
+ wiphy_name(local->hw.wiphy));
+}
+
+void ieee80211_free_led_names(struct ieee80211_local *local)
+{
+ kfree(local->rx_led.name);
+ kfree(local->tx_led.name);
+ kfree(local->assoc_led.name);
+ kfree(local->radio_led.name);
+}
+
+static void ieee80211_tx_led_activate(struct led_classdev *led_cdev)
+{
+ struct ieee80211_local *local = container_of(led_cdev->trigger,
+ struct ieee80211_local,
+ tx_led);
+
+ atomic_inc(&local->tx_led_active);
+}
+
+static void ieee80211_tx_led_deactivate(struct led_classdev *led_cdev)
+{
+ struct ieee80211_local *local = container_of(led_cdev->trigger,
+ struct ieee80211_local,
+ tx_led);
+
+ atomic_dec(&local->tx_led_active);
+}
+
+static void ieee80211_rx_led_activate(struct led_classdev *led_cdev)
+{
+ struct ieee80211_local *local = container_of(led_cdev->trigger,
+ struct ieee80211_local,
+ rx_led);
+
+ atomic_inc(&local->rx_led_active);
+}
+
+static void ieee80211_rx_led_deactivate(struct led_classdev *led_cdev)
+{
+ struct ieee80211_local *local = container_of(led_cdev->trigger,
+ struct ieee80211_local,
+ rx_led);
+
+ atomic_dec(&local->rx_led_active);
+}
+
+static void ieee80211_assoc_led_activate(struct led_classdev *led_cdev)
+{
+ struct ieee80211_local *local = container_of(led_cdev->trigger,
+ struct ieee80211_local,
+ assoc_led);
+
+ atomic_inc(&local->assoc_led_active);
+}
+
+static void ieee80211_assoc_led_deactivate(struct led_classdev *led_cdev)
+{
+ struct ieee80211_local *local = container_of(led_cdev->trigger,
+ struct ieee80211_local,
+ assoc_led);
+
+ atomic_dec(&local->assoc_led_active);
+}
+
+static void ieee80211_radio_led_activate(struct led_classdev *led_cdev)
+{
+ struct ieee80211_local *local = container_of(led_cdev->trigger,
+ struct ieee80211_local,
+ radio_led);
+
+ atomic_inc(&local->radio_led_active);
+}
+
+static void ieee80211_radio_led_deactivate(struct led_classdev *led_cdev)
+{
+ struct ieee80211_local *local = container_of(led_cdev->trigger,
+ struct ieee80211_local,
+ radio_led);
+
+ atomic_dec(&local->radio_led_active);
+}
+
+static void ieee80211_tpt_led_activate(struct led_classdev *led_cdev)
+{
+ struct ieee80211_local *local = container_of(led_cdev->trigger,
+ struct ieee80211_local,
+ tpt_led);
+
+ atomic_inc(&local->tpt_led_active);
}
-void ieee80211_led_names(struct ieee80211_local *local)
+static void ieee80211_tpt_led_deactivate(struct led_classdev *led_cdev)
{
- snprintf(local->rx_led_name, sizeof(local->rx_led_name),
- "%srx", wiphy_name(local->hw.wiphy));
- snprintf(local->tx_led_name, sizeof(local->tx_led_name),
- "%stx", wiphy_name(local->hw.wiphy));
- snprintf(local->assoc_led_name, sizeof(local->assoc_led_name),
- "%sassoc", wiphy_name(local->hw.wiphy));
- snprintf(local->radio_led_name, sizeof(local->radio_led_name),
- "%sradio", wiphy_name(local->hw.wiphy));
+ struct ieee80211_local *local = container_of(led_cdev->trigger,
+ struct ieee80211_local,
+ tpt_led);
+
+ atomic_dec(&local->tpt_led_active);
}
void ieee80211_led_init(struct ieee80211_local *local)
{
- local->rx_led = kzalloc(sizeof(struct led_trigger), GFP_KERNEL);
- if (local->rx_led) {
- local->rx_led->name = local->rx_led_name;
- if (led_trigger_register(local->rx_led)) {
- kfree(local->rx_led);
- local->rx_led = NULL;
- }
+ atomic_set(&local->rx_led_active, 0);
+ local->rx_led.activate = ieee80211_rx_led_activate;
+ local->rx_led.deactivate = ieee80211_rx_led_deactivate;
+ if (local->rx_led.name && led_trigger_register(&local->rx_led)) {
+ kfree(local->rx_led.name);
+ local->rx_led.name = NULL;
}
- local->tx_led = kzalloc(sizeof(struct led_trigger), GFP_KERNEL);
- if (local->tx_led) {
- local->tx_led->name = local->tx_led_name;
- if (led_trigger_register(local->tx_led)) {
- kfree(local->tx_led);
- local->tx_led = NULL;
- }
+ atomic_set(&local->tx_led_active, 0);
+ local->tx_led.activate = ieee80211_tx_led_activate;
+ local->tx_led.deactivate = ieee80211_tx_led_deactivate;
+ if (local->tx_led.name && led_trigger_register(&local->tx_led)) {
+ kfree(local->tx_led.name);
+ local->tx_led.name = NULL;
}
- local->assoc_led = kzalloc(sizeof(struct led_trigger), GFP_KERNEL);
- if (local->assoc_led) {
- local->assoc_led->name = local->assoc_led_name;
- if (led_trigger_register(local->assoc_led)) {
- kfree(local->assoc_led);
- local->assoc_led = NULL;
- }
+ atomic_set(&local->assoc_led_active, 0);
+ local->assoc_led.activate = ieee80211_assoc_led_activate;
+ local->assoc_led.deactivate = ieee80211_assoc_led_deactivate;
+ if (local->assoc_led.name && led_trigger_register(&local->assoc_led)) {
+ kfree(local->assoc_led.name);
+ local->assoc_led.name = NULL;
}
- local->radio_led = kzalloc(sizeof(struct led_trigger), GFP_KERNEL);
- if (local->radio_led) {
- local->radio_led->name = local->radio_led_name;
- if (led_trigger_register(local->radio_led)) {
- kfree(local->radio_led);
- local->radio_led = NULL;
- }
+ atomic_set(&local->radio_led_active, 0);
+ local->radio_led.activate = ieee80211_radio_led_activate;
+ local->radio_led.deactivate = ieee80211_radio_led_deactivate;
+ if (local->radio_led.name && led_trigger_register(&local->radio_led)) {
+ kfree(local->radio_led.name);
+ local->radio_led.name = NULL;
}
+ atomic_set(&local->tpt_led_active, 0);
if (local->tpt_led_trigger) {
- if (led_trigger_register(&local->tpt_led_trigger->trig)) {
+ local->tpt_led.activate = ieee80211_tpt_led_activate;
+ local->tpt_led.deactivate = ieee80211_tpt_led_deactivate;
+ if (led_trigger_register(&local->tpt_led)) {
kfree(local->tpt_led_trigger);
local->tpt_led_trigger = NULL;
}
@@ -110,58 +189,50 @@ void ieee80211_led_init(struct ieee80211_local *local)
void ieee80211_led_exit(struct ieee80211_local *local)
{
- if (local->radio_led) {
- led_trigger_unregister(local->radio_led);
- kfree(local->radio_led);
- }
- if (local->assoc_led) {
- led_trigger_unregister(local->assoc_led);
- kfree(local->assoc_led);
- }
- if (local->tx_led) {
- led_trigger_unregister(local->tx_led);
- kfree(local->tx_led);
- }
- if (local->rx_led) {
- led_trigger_unregister(local->rx_led);
- kfree(local->rx_led);
- }
+ if (local->radio_led.name)
+ led_trigger_unregister(&local->radio_led);
+ if (local->assoc_led.name)
+ led_trigger_unregister(&local->assoc_led);
+ if (local->tx_led.name)
+ led_trigger_unregister(&local->tx_led);
+ if (local->rx_led.name)
+ led_trigger_unregister(&local->rx_led);
if (local->tpt_led_trigger) {
- led_trigger_unregister(&local->tpt_led_trigger->trig);
+ led_trigger_unregister(&local->tpt_led);
kfree(local->tpt_led_trigger);
}
}
-char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw)
+const char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw)
{
struct ieee80211_local *local = hw_to_local(hw);
- return local->radio_led_name;
+ return local->radio_led.name;
}
EXPORT_SYMBOL(__ieee80211_get_radio_led_name);
-char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw)
+const char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw)
{
struct ieee80211_local *local = hw_to_local(hw);
- return local->assoc_led_name;
+ return local->assoc_led.name;
}
EXPORT_SYMBOL(__ieee80211_get_assoc_led_name);
-char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw)
+const char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw)
{
struct ieee80211_local *local = hw_to_local(hw);
- return local->tx_led_name;
+ return local->tx_led.name;
}
EXPORT_SYMBOL(__ieee80211_get_tx_led_name);
-char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw)
+const char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw)
{
struct ieee80211_local *local = hw_to_local(hw);
- return local->rx_led_name;
+ return local->rx_led.name;
}
EXPORT_SYMBOL(__ieee80211_get_rx_led_name);
@@ -205,16 +276,17 @@ static void tpt_trig_timer(unsigned long data)
}
}
- read_lock(&tpt_trig->trig.leddev_list_lock);
- list_for_each_entry(led_cdev, &tpt_trig->trig.led_cdevs, trig_list)
+ read_lock(&local->tpt_led.leddev_list_lock);
+ list_for_each_entry(led_cdev, &local->tpt_led.led_cdevs, trig_list)
led_blink_set(led_cdev, &on, &off);
- read_unlock(&tpt_trig->trig.leddev_list_lock);
+ read_unlock(&local->tpt_led.leddev_list_lock);
}
-char *__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw,
- unsigned int flags,
- const struct ieee80211_tpt_blink *blink_table,
- unsigned int blink_table_len)
+const char *
+__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw,
+ unsigned int flags,
+ const struct ieee80211_tpt_blink *blink_table,
+ unsigned int blink_table_len)
{
struct ieee80211_local *local = hw_to_local(hw);
struct tpt_led_trigger *tpt_trig;
@@ -229,7 +301,7 @@ char *__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw,
snprintf(tpt_trig->name, sizeof(tpt_trig->name),
"%stpt", wiphy_name(local->hw.wiphy));
- tpt_trig->trig.name = tpt_trig->name;
+ local->tpt_led.name = tpt_trig->name;
tpt_trig->blink_table = blink_table;
tpt_trig->blink_table_len = blink_table_len;
@@ -269,10 +341,10 @@ static void ieee80211_stop_tpt_led_trig(struct ieee80211_local *local)
tpt_trig->running = false;
del_timer_sync(&tpt_trig->timer);
- read_lock(&tpt_trig->trig.leddev_list_lock);
- list_for_each_entry(led_cdev, &tpt_trig->trig.led_cdevs, trig_list)
+ read_lock(&local->tpt_led.leddev_list_lock);
+ list_for_each_entry(led_cdev, &local->tpt_led.led_cdevs, trig_list)
led_set_brightness(led_cdev, LED_OFF);
- read_unlock(&tpt_trig->trig.leddev_list_lock);
+ read_unlock(&local->tpt_led.leddev_list_lock);
}
void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local,
diff --git a/net/mac80211/led.h b/net/mac80211/led.h
index 89f4344f13b9..a7893a1ac98b 100644
--- a/net/mac80211/led.h
+++ b/net/mac80211/led.h
@@ -11,25 +11,42 @@
#include <linux/leds.h>
#include "ieee80211_i.h"
+#define MAC80211_BLINK_DELAY 50 /* ms */
+
+static inline void ieee80211_led_rx(struct ieee80211_local *local)
+{
+#ifdef CONFIG_MAC80211_LEDS
+ unsigned long led_delay = MAC80211_BLINK_DELAY;
+
+ if (!atomic_read(&local->rx_led_active))
+ return;
+ led_trigger_blink_oneshot(&local->rx_led, &led_delay, &led_delay, 0);
+#endif
+}
+
+static inline void ieee80211_led_tx(struct ieee80211_local *local)
+{
+#ifdef CONFIG_MAC80211_LEDS
+ unsigned long led_delay = MAC80211_BLINK_DELAY;
+
+ if (!atomic_read(&local->tx_led_active))
+ return;
+ led_trigger_blink_oneshot(&local->tx_led, &led_delay, &led_delay, 0);
+#endif
+}
+
#ifdef CONFIG_MAC80211_LEDS
-void ieee80211_led_rx(struct ieee80211_local *local);
-void ieee80211_led_tx(struct ieee80211_local *local);
void ieee80211_led_assoc(struct ieee80211_local *local,
bool associated);
void ieee80211_led_radio(struct ieee80211_local *local,
bool enabled);
-void ieee80211_led_names(struct ieee80211_local *local);
+void ieee80211_alloc_led_names(struct ieee80211_local *local);
+void ieee80211_free_led_names(struct ieee80211_local *local);
void ieee80211_led_init(struct ieee80211_local *local);
void ieee80211_led_exit(struct ieee80211_local *local);
void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local,
unsigned int types_on, unsigned int types_off);
#else
-static inline void ieee80211_led_rx(struct ieee80211_local *local)
-{
-}
-static inline void ieee80211_led_tx(struct ieee80211_local *local)
-{
-}
static inline void ieee80211_led_assoc(struct ieee80211_local *local,
bool associated)
{
@@ -38,7 +55,10 @@ static inline void ieee80211_led_radio(struct ieee80211_local *local,
bool enabled)
{
}
-static inline void ieee80211_led_names(struct ieee80211_local *local)
+static inline void ieee80211_alloc_led_names(struct ieee80211_local *local)
+{
+}
+static inline void ieee80211_free_led_names(struct ieee80211_local *local)
{
}
static inline void ieee80211_led_init(struct ieee80211_local *local)
@@ -58,7 +78,7 @@ static inline void
ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, __le16 fc, int bytes)
{
#ifdef CONFIG_MAC80211_LEDS
- if (local->tpt_led_trigger && ieee80211_is_data(fc))
+ if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active))
local->tpt_led_trigger->tx_bytes += bytes;
#endif
}
@@ -67,7 +87,7 @@ static inline void
ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, __le16 fc, int bytes)
{
#ifdef CONFIG_MAC80211_LEDS
- if (local->tpt_led_trigger && ieee80211_is_data(fc))
+ if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active))
local->tpt_led_trigger->rx_bytes += bytes;
#endif
}
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index df3051d96aff..3c63468b4dfb 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -41,9 +41,6 @@ void ieee80211_configure_filter(struct ieee80211_local *local)
unsigned int changed_flags;
unsigned int new_flags = 0;
- if (atomic_read(&local->iff_promiscs))
- new_flags |= FIF_PROMISC_IN_BSS;
-
if (atomic_read(&local->iff_allmultis))
new_flags |= FIF_ALLMULTI;
@@ -249,6 +246,7 @@ static void ieee80211_restart_work(struct work_struct *work)
{
struct ieee80211_local *local =
container_of(work, struct ieee80211_local, restart_work);
+ struct ieee80211_sub_if_data *sdata;
/* wait for scan work complete */
flush_workqueue(local->workqueue);
@@ -257,6 +255,8 @@ static void ieee80211_restart_work(struct work_struct *work)
"%s called with hardware scan in progress\n", __func__);
rtnl_lock();
+ list_for_each_entry(sdata, &local->interfaces, list)
+ flush_delayed_work(&sdata->dec_tailroom_needed_wk);
ieee80211_scan_cancel(local);
ieee80211_reconfig(local);
rtnl_unlock();
@@ -646,7 +646,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
skb_queue_head_init(&local->skb_queue);
skb_queue_head_init(&local->skb_queue_unreliable);
- ieee80211_led_names(local);
+ ieee80211_alloc_led_names(local);
ieee80211_roc_setup(local);
@@ -661,7 +661,7 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
{
bool have_wep = !(IS_ERR(local->wep_tx_tfm) ||
IS_ERR(local->wep_rx_tfm));
- bool have_mfp = local->hw.flags & IEEE80211_HW_MFP_CAPABLE;
+ bool have_mfp = ieee80211_hw_check(&local->hw, MFP_CAPABLE);
int n_suites = 0, r = 0, w = 0;
u32 *suites;
static const u32 cipher_suites[] = {
@@ -681,7 +681,7 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
WLAN_CIPHER_SUITE_BIP_GMAC_256,
};
- if (local->hw.flags & IEEE80211_HW_SW_CRYPTO_CONTROL ||
+ if (ieee80211_hw_check(&local->hw, SW_CRYPTO_CONTROL) ||
local->hw.wiphy->cipher_suites) {
/* If the driver advertises, or doesn't support SW crypto,
* we only need to remove WEP if necessary.
@@ -771,8 +771,13 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
suites[w++] = WLAN_CIPHER_SUITE_BIP_GMAC_256;
}
- for (r = 0; r < local->hw.n_cipher_schemes; r++)
+ for (r = 0; r < local->hw.n_cipher_schemes; r++) {
suites[w++] = cs[r].cipher;
+ if (WARN_ON(cs[r].pn_len > IEEE80211_MAX_PN_LEN)) {
+ kfree(suites);
+ return -EINVAL;
+ }
+ }
}
local->hw.wiphy->cipher_suites = suites;
@@ -792,7 +797,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
netdev_features_t feature_whitelist;
struct cfg80211_chan_def dflt_chandef = {};
- if (hw->flags & IEEE80211_HW_QUEUE_CONTROL &&
+ if (ieee80211_hw_check(hw, QUEUE_CONTROL) &&
(local->hw.offchannel_tx_hw_queue == IEEE80211_INVAL_HW_QUEUE ||
local->hw.offchannel_tx_hw_queue >= local->hw.queues))
return -EINVAL;
@@ -840,7 +845,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
/* Only HW csum features are currently compatible with mac80211 */
feature_whitelist = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_HW_CSUM;
+ NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA |
+ NETIF_F_GSO_SOFTWARE;
if (WARN_ON(hw->netdev_features & ~feature_whitelist))
return -EINVAL;
@@ -939,9 +945,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
/* mac80211 supports control port protocol changing */
local->hw.wiphy->flags |= WIPHY_FLAG_CONTROL_PORT_PROTOCOL;
- if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM) {
+ if (ieee80211_hw_check(&local->hw, SIGNAL_DBM)) {
local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM;
- } else if (local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC) {
+ } else if (ieee80211_hw_check(&local->hw, SIGNAL_UNSPEC)) {
local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC;
if (hw->max_signal <= 0) {
result = -EINVAL;
@@ -995,7 +1001,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
local->hw.wiphy->flags |= WIPHY_FLAG_TDLS_EXTERNAL_SETUP;
/* mac80211 supports eCSA, if the driver supports STA CSA at all */
- if (local->hw.flags & IEEE80211_HW_CHANCTX_STA_CSA)
+ if (ieee80211_hw_check(&local->hw, CHANCTX_STA_CSA))
local->ext_capa[0] |= WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING;
local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM;
@@ -1063,7 +1069,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
/* add one default STA interface if supported */
if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) &&
- !(hw->flags & IEEE80211_HW_NO_AUTO_VIF)) {
+ !ieee80211_hw_check(hw, NO_AUTO_VIF)) {
result = ieee80211_if_add(local, "wlan%d", NET_NAME_ENUM, NULL,
NL80211_IFTYPE_STATION, NULL);
if (result)
@@ -1209,6 +1215,8 @@ void ieee80211_free_hw(struct ieee80211_hw *hw)
sta_info_stop(local);
+ ieee80211_free_led_names(local);
+
wiphy_free(local->hw.wiphy);
}
EXPORT_SYMBOL(ieee80211_free_hw);
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index d4684242e78b..817098add1d6 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -680,6 +680,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
*pos++ = 0x0;
*pos++ = ieee80211_frequency_to_channel(
csa->settings.chandef.chan->center_freq);
+ bcn->csa_current_counter = csa->settings.count;
bcn->csa_counter_offsets[0] = hdr_len + 6;
*pos++ = csa->settings.count;
*pos++ = WLAN_EID_CHAN_SWITCH_PARAM;
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 214e63b84e5c..085edc1d056b 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -510,14 +510,14 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata,
static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
struct ieee80211_mgmt *mgmt,
- const u8 *preq_elem, u32 metric)
+ const u8 *preq_elem, u32 orig_metric)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
struct mesh_path *mpath = NULL;
const u8 *target_addr, *orig_addr;
const u8 *da;
u8 target_flags, ttl, flags;
- u32 orig_sn, target_sn, lifetime, orig_metric;
+ u32 orig_sn, target_sn, lifetime, target_metric;
bool reply = false;
bool forward = true;
bool root_is_gate;
@@ -528,7 +528,6 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
target_sn = PREQ_IE_TARGET_SN(preq_elem);
orig_sn = PREQ_IE_ORIG_SN(preq_elem);
target_flags = PREQ_IE_TARGET_F(preq_elem);
- orig_metric = metric;
/* Proactive PREQ gate announcements */
flags = PREQ_IE_FLAGS(preq_elem);
root_is_gate = !!(flags & RANN_FLAG_IS_GATE);
@@ -539,7 +538,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
mhwmp_dbg(sdata, "PREQ is for us\n");
forward = false;
reply = true;
- metric = 0;
+ target_metric = 0;
if (time_after(jiffies, ifmsh->last_sn_update +
net_traversal_jiffies(sdata)) ||
time_before(jiffies, ifmsh->last_sn_update)) {
@@ -556,7 +555,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
reply = true;
target_addr = sdata->vif.addr;
target_sn = ++ifmsh->sn;
- metric = 0;
+ target_metric = 0;
ifmsh->last_sn_update = jiffies;
}
if (root_is_gate)
@@ -574,7 +573,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
} else if ((!(target_flags & MP_F_DO)) &&
(mpath->flags & MESH_PATH_ACTIVE)) {
reply = true;
- metric = mpath->metric;
+ target_metric = mpath->metric;
target_sn = mpath->sn;
if (target_flags & MP_F_RF)
target_flags |= MP_F_DO;
@@ -593,7 +592,8 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
mesh_path_sel_frame_tx(MPATH_PREP, 0, orig_addr,
orig_sn, 0, target_addr,
target_sn, mgmt->sa, 0, ttl,
- lifetime, metric, 0, sdata);
+ lifetime, target_metric, 0,
+ sdata);
} else {
ifmsh->mshstats.dropped_frames_ttl++;
}
@@ -619,13 +619,12 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
if (flags & IEEE80211_PREQ_PROACTIVE_PREP_FLAG) {
target_addr = PREQ_IE_TARGET_ADDR(preq_elem);
target_sn = PREQ_IE_TARGET_SN(preq_elem);
- metric = orig_metric;
}
mesh_path_sel_frame_tx(MPATH_PREQ, flags, orig_addr,
orig_sn, target_flags, target_addr,
target_sn, da, hopcount, ttl, lifetime,
- metric, preq_id, sdata);
+ orig_metric, preq_id, sdata);
if (!is_multicast_ether_addr(da))
ifmsh->mshstats.fwded_unicast++;
else
@@ -854,7 +853,7 @@ void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata,
{
struct ieee802_11_elems elems;
size_t baselen;
- u32 last_hop_metric;
+ u32 path_metric;
struct sta_info *sta;
/* need action_code */
@@ -877,21 +876,21 @@ void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata,
if (elems.preq_len != 37)
/* Right now we support just 1 destination and no AE */
return;
- last_hop_metric = hwmp_route_info_get(sdata, mgmt, elems.preq,
- MPATH_PREQ);
- if (last_hop_metric)
+ path_metric = hwmp_route_info_get(sdata, mgmt, elems.preq,
+ MPATH_PREQ);
+ if (path_metric)
hwmp_preq_frame_process(sdata, mgmt, elems.preq,
- last_hop_metric);
+ path_metric);
}
if (elems.prep) {
if (elems.prep_len != 31)
/* Right now we support no AE */
return;
- last_hop_metric = hwmp_route_info_get(sdata, mgmt, elems.prep,
- MPATH_PREP);
- if (last_hop_metric)
+ path_metric = hwmp_route_info_get(sdata, mgmt, elems.prep,
+ MPATH_PREP);
+ if (path_metric)
hwmp_prep_frame_process(sdata, mgmt, elems.prep,
- last_hop_metric);
+ path_metric);
}
if (elems.perr) {
if (elems.perr_len != 15)
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 60d737f144e3..5438d13e2f00 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -72,10 +72,11 @@ static bool rssi_threshold_check(struct ieee80211_sub_if_data *sdata,
*
* @sta: mesh peer link to restart
*
- * Locking: this function must be called holding sta->lock
+ * Locking: this function must be called holding sta->plink_lock
*/
static inline void mesh_plink_fsm_restart(struct sta_info *sta)
{
+ lockdep_assert_held(&sta->plink_lock);
sta->plink_state = NL80211_PLINK_LISTEN;
sta->llid = sta->plid = sta->reason = 0;
sta->plink_retries = 0;
@@ -105,9 +106,7 @@ static u32 mesh_set_short_slot_time(struct ieee80211_sub_if_data *sdata)
/* (IEEE 802.11-2012 19.4.5) */
short_slot = true;
goto out;
- } else if (band != IEEE80211_BAND_2GHZ ||
- (band == IEEE80211_BAND_2GHZ &&
- local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE))
+ } else if (band != IEEE80211_BAND_2GHZ)
goto out;
for (i = 0; i < sband->n_bitrates; i++)
@@ -213,13 +212,15 @@ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata)
* All mesh paths with this peer as next hop will be flushed
* Returns beacon changed flag if the beacon content changed.
*
- * Locking: the caller must hold sta->lock
+ * Locking: the caller must hold sta->plink_lock
*/
static u32 __mesh_plink_deactivate(struct sta_info *sta)
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
u32 changed = 0;
+ lockdep_assert_held(&sta->plink_lock);
+
if (sta->plink_state == NL80211_PLINK_ESTAB)
changed = mesh_plink_dec_estab_count(sdata);
sta->plink_state = NL80211_PLINK_BLOCKED;
@@ -244,13 +245,13 @@ u32 mesh_plink_deactivate(struct sta_info *sta)
struct ieee80211_sub_if_data *sdata = sta->sdata;
u32 changed;
- spin_lock_bh(&sta->lock);
+ spin_lock_bh(&sta->plink_lock);
changed = __mesh_plink_deactivate(sta);
sta->reason = WLAN_REASON_MESH_PEER_CANCELED;
mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE,
sta->sta.addr, sta->llid, sta->plid,
sta->reason);
- spin_unlock_bh(&sta->lock);
+ spin_unlock_bh(&sta->plink_lock);
return changed;
}
@@ -387,12 +388,13 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
sband = local->hw.wiphy->bands[band];
rates = ieee80211_sta_get_rates(sdata, elems, band, &basic_rates);
- spin_lock_bh(&sta->lock);
+ spin_lock_bh(&sta->plink_lock);
sta->last_rx = jiffies;
/* rates and capabilities don't change during peering */
- if (sta->plink_state == NL80211_PLINK_ESTAB)
+ if (sta->plink_state == NL80211_PLINK_ESTAB && sta->processed_beacon)
goto out;
+ sta->processed_beacon = true;
if (sta->sta.supp_rates[band] != rates)
changed |= IEEE80211_RC_SUPP_RATES_CHANGED;
@@ -419,7 +421,7 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
else
rate_control_rate_update(local, sband, sta, changed);
out:
- spin_unlock_bh(&sta->lock);
+ spin_unlock_bh(&sta->plink_lock);
}
static struct sta_info *
@@ -552,7 +554,7 @@ static void mesh_plink_timer(unsigned long data)
if (sta->sdata->local->quiescing)
return;
- spin_lock_bh(&sta->lock);
+ spin_lock_bh(&sta->plink_lock);
/* If a timer fires just before a state transition on another CPU,
* we may have already extended the timeout and changed state by the
@@ -563,7 +565,7 @@ static void mesh_plink_timer(unsigned long data)
mpl_dbg(sta->sdata,
"Ignoring timer for %pM in state %s (timer adjusted)",
sta->sta.addr, mplstates[sta->plink_state]);
- spin_unlock_bh(&sta->lock);
+ spin_unlock_bh(&sta->plink_lock);
return;
}
@@ -573,7 +575,7 @@ static void mesh_plink_timer(unsigned long data)
mpl_dbg(sta->sdata,
"Ignoring timer for %pM in state %s (timer deleted)",
sta->sta.addr, mplstates[sta->plink_state]);
- spin_unlock_bh(&sta->lock);
+ spin_unlock_bh(&sta->plink_lock);
return;
}
@@ -619,7 +621,7 @@ static void mesh_plink_timer(unsigned long data)
default:
break;
}
- spin_unlock_bh(&sta->lock);
+ spin_unlock_bh(&sta->plink_lock);
if (action)
mesh_plink_frame_tx(sdata, action, sta->sta.addr,
sta->llid, sta->plid, reason);
@@ -674,16 +676,16 @@ u32 mesh_plink_open(struct sta_info *sta)
if (!test_sta_flag(sta, WLAN_STA_AUTH))
return 0;
- spin_lock_bh(&sta->lock);
+ spin_lock_bh(&sta->plink_lock);
sta->llid = mesh_get_new_llid(sdata);
if (sta->plink_state != NL80211_PLINK_LISTEN &&
sta->plink_state != NL80211_PLINK_BLOCKED) {
- spin_unlock_bh(&sta->lock);
+ spin_unlock_bh(&sta->plink_lock);
return 0;
}
sta->plink_state = NL80211_PLINK_OPN_SNT;
mesh_plink_timer_set(sta, sdata->u.mesh.mshcfg.dot11MeshRetryTimeout);
- spin_unlock_bh(&sta->lock);
+ spin_unlock_bh(&sta->plink_lock);
mpl_dbg(sdata,
"Mesh plink: starting establishment with %pM\n",
sta->sta.addr);
@@ -700,10 +702,10 @@ u32 mesh_plink_block(struct sta_info *sta)
{
u32 changed;
- spin_lock_bh(&sta->lock);
+ spin_lock_bh(&sta->plink_lock);
changed = __mesh_plink_deactivate(sta);
sta->plink_state = NL80211_PLINK_BLOCKED;
- spin_unlock_bh(&sta->lock);
+ spin_unlock_bh(&sta->plink_lock);
return changed;
}
@@ -758,7 +760,7 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata,
mpl_dbg(sdata, "peer %pM in state %s got event %s\n", sta->sta.addr,
mplstates[sta->plink_state], mplevents[event]);
- spin_lock_bh(&sta->lock);
+ spin_lock_bh(&sta->plink_lock);
switch (sta->plink_state) {
case NL80211_PLINK_LISTEN:
switch (event) {
@@ -872,7 +874,7 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata,
*/
break;
}
- spin_unlock_bh(&sta->lock);
+ spin_unlock_bh(&sta->plink_lock);
if (action) {
mesh_plink_frame_tx(sdata, action, sta->sta.addr,
sta->llid, sta->plid, sta->reason);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 26053bf2faa8..9b2cc278ac2a 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -118,7 +118,7 @@ void ieee80211_sta_reset_beacon_monitor(struct ieee80211_sub_if_data *sdata)
if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)
return;
- if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR)
+ if (ieee80211_hw_check(&sdata->local->hw, CONNECTION_MONITOR))
return;
mod_timer(&sdata->u.mgd.bcn_mon_timer,
@@ -134,7 +134,7 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata)
ifmgd->probe_send_count = 0;
- if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR)
+ if (ieee80211_hw_check(&sdata->local->hw, CONNECTION_MONITOR))
return;
mod_timer(&sdata->u.mgd.conn_mon_timer,
@@ -669,17 +669,15 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
capab = WLAN_CAPABILITY_ESS;
if (sband->band == IEEE80211_BAND_2GHZ) {
- if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE))
- capab |= WLAN_CAPABILITY_SHORT_SLOT_TIME;
- if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE))
- capab |= WLAN_CAPABILITY_SHORT_PREAMBLE;
+ capab |= WLAN_CAPABILITY_SHORT_SLOT_TIME;
+ capab |= WLAN_CAPABILITY_SHORT_PREAMBLE;
}
if (assoc_data->capability & WLAN_CAPABILITY_PRIVACY)
capab |= WLAN_CAPABILITY_PRIVACY;
if ((assoc_data->capability & WLAN_CAPABILITY_SPECTRUM_MGMT) &&
- (local->hw.flags & IEEE80211_HW_SPECTRUM_MGMT))
+ ieee80211_hw_check(&local->hw, SPECTRUM_MGMT))
capab |= WLAN_CAPABILITY_SPECTRUM_MGMT;
if (ifmgd->flags & IEEE80211_STA_ENABLE_RRM)
@@ -887,7 +885,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
drv_mgd_prepare_tx(local, sdata);
IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;
- if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
+ if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS))
IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS |
IEEE80211_TX_INTFL_MLME_CONN_TX;
ieee80211_tx_skb(sdata, skb);
@@ -929,7 +927,7 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local,
IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT |
IEEE80211_TX_INTFL_OFFCHAN_TX_OK;
- if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
+ if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS))
IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
if (ifmgd->flags & IEEE80211_STA_CONNECTION_POLL)
@@ -1098,6 +1096,24 @@ static void ieee80211_chswitch_timer(unsigned long data)
ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.chswitch_work);
}
+static void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata)
+{
+ struct sta_info *sta;
+ u16 reason = WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) {
+ if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded ||
+ !test_sta_flag(sta, WLAN_STA_AUTHORIZED))
+ continue;
+
+ ieee80211_tdls_oper_request(&sdata->vif, sta->sta.addr,
+ NL80211_TDLS_TEARDOWN, reason,
+ GFP_ATOMIC);
+ }
+ rcu_read_unlock();
+}
+
static void
ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
u64 timestamp, u32 device_timestamp,
@@ -1161,6 +1177,14 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
return;
}
+ /*
+ * Drop all TDLS peers - either we disconnect or move to a different
+ * channel from this point on. There's no telling what our peer will do.
+ * The TDLS WIDER_BW scenario is also problematic, as peers might now
+ * have an incompatible wider chandef.
+ */
+ ieee80211_teardown_tdls_peers(sdata);
+
mutex_lock(&local->mtx);
mutex_lock(&local->chanctx_mtx);
conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
@@ -1174,7 +1198,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
chanctx = container_of(conf, struct ieee80211_chanctx, conf);
if (local->use_chanctx &&
- !(local->hw.flags & IEEE80211_HW_CHANCTX_STA_CSA)) {
+ !ieee80211_hw_check(&local->hw, CHANCTX_STA_CSA)) {
sdata_info(sdata,
"driver doesn't support chan-switch with channel contexts\n");
goto drop_connection;
@@ -1383,15 +1407,15 @@ static void ieee80211_enable_ps(struct ieee80211_local *local,
return;
if (conf->dynamic_ps_timeout > 0 &&
- !(local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS)) {
+ !ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS)) {
mod_timer(&local->dynamic_ps_timer, jiffies +
msecs_to_jiffies(conf->dynamic_ps_timeout));
} else {
- if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK)
+ if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK))
ieee80211_send_nullfunc(local, sdata, 1);
- if ((local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) &&
- (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS))
+ if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK) &&
+ ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS))
return;
conf->flags |= IEEE80211_CONF_PS;
@@ -1450,7 +1474,7 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency)
int count = 0;
int timeout;
- if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS)) {
+ if (!ieee80211_hw_check(&local->hw, SUPPORTS_PS)) {
local->ps_sdata = NULL;
return;
}
@@ -1596,7 +1620,7 @@ void ieee80211_dynamic_ps_enable_work(struct work_struct *work)
spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
}
- if ((local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) &&
+ if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK) &&
!(ifmgd->flags & IEEE80211_STA_NULLFUNC_ACKED)) {
if (drv_tx_frames_pending(local)) {
mod_timer(&local->dynamic_ps_timer, jiffies +
@@ -1609,8 +1633,8 @@ void ieee80211_dynamic_ps_enable_work(struct work_struct *work)
}
}
- if (!((local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) &&
- (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK)) ||
+ if (!(ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) &&
+ ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK)) ||
(ifmgd->flags & IEEE80211_STA_NULLFUNC_ACKED)) {
ifmgd->flags &= ~IEEE80211_STA_NULLFUNC_ACKED;
local->hw.conf.flags |= IEEE80211_CONF_PS;
@@ -2135,7 +2159,7 @@ static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata)
ieee80211_recalc_ps(local, -1);
mutex_unlock(&local->iflist_mtx);
- if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR)
+ if (ieee80211_hw_check(&sdata->local->hw, CONNECTION_MONITOR))
goto out;
/*
@@ -2233,7 +2257,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
*/
ifmgd->probe_send_count++;
- if (sdata->local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) {
+ if (ieee80211_hw_check(&sdata->local->hw, REPORTS_TX_ACK_STATUS)) {
ifmgd->nullfunc_failed = false;
ieee80211_send_nullfunc(sdata->local, sdata, 0);
} else {
@@ -2495,6 +2519,34 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata,
sdata->u.mgd.auth_data = NULL;
}
+static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
+ bool assoc)
+{
+ struct ieee80211_mgd_assoc_data *assoc_data = sdata->u.mgd.assoc_data;
+
+ sdata_assert_lock(sdata);
+
+ if (!assoc) {
+ /*
+ * we are not associated yet, the only timer that could be
+ * running is the timeout for the association response which
+ * which is not relevant anymore.
+ */
+ del_timer_sync(&sdata->u.mgd.timer);
+ sta_info_destroy_addr(sdata, assoc_data->bss->bssid);
+
+ eth_zero_addr(sdata->u.mgd.bssid);
+ ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID);
+ sdata->u.mgd.flags = 0;
+ mutex_lock(&sdata->local->mtx);
+ ieee80211_vif_release_channel(sdata);
+ mutex_unlock(&sdata->local->mtx);
+ }
+
+ kfree(assoc_data);
+ sdata->u.mgd.assoc_data = NULL;
+}
+
static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata,
struct ieee80211_mgmt *mgmt, size_t len)
{
@@ -2510,7 +2562,7 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata,
return;
auth_data->expected_transaction = 4;
drv_mgd_prepare_tx(sdata->local, sdata);
- if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
+ if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS))
tx_flags = IEEE80211_TX_CTL_REQ_TX_STATUS |
IEEE80211_TX_INTFL_MLME_CONN_TX;
ieee80211_send_auth(sdata, 3, auth_data->algorithm, 0,
@@ -2687,28 +2739,42 @@ static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata,
struct ieee80211_mgmt *mgmt, size_t len)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
- const u8 *bssid = NULL;
- u16 reason_code;
+ u16 reason_code = le16_to_cpu(mgmt->u.deauth.reason_code);
sdata_assert_lock(sdata);
if (len < 24 + 2)
return;
- if (!ifmgd->associated ||
- !ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid))
- return;
+ if (ifmgd->associated &&
+ ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid)) {
+ const u8 *bssid = ifmgd->associated->bssid;
- bssid = ifmgd->associated->bssid;
+ sdata_info(sdata, "deauthenticated from %pM (Reason: %u=%s)\n",
+ bssid, reason_code,
+ ieee80211_get_reason_code_string(reason_code));
- reason_code = le16_to_cpu(mgmt->u.deauth.reason_code);
+ ieee80211_set_disassoc(sdata, 0, 0, false, NULL);
- sdata_info(sdata, "deauthenticated from %pM (Reason: %u=%s)\n",
- bssid, reason_code, ieee80211_get_reason_code_string(reason_code));
+ ieee80211_report_disconnect(sdata, (u8 *)mgmt, len, false,
+ reason_code);
+ return;
+ }
- ieee80211_set_disassoc(sdata, 0, 0, false, NULL);
+ if (ifmgd->assoc_data &&
+ ether_addr_equal(mgmt->bssid, ifmgd->assoc_data->bss->bssid)) {
+ const u8 *bssid = ifmgd->assoc_data->bss->bssid;
- ieee80211_report_disconnect(sdata, (u8 *)mgmt, len, false, reason_code);
+ sdata_info(sdata,
+ "deauthenticated from %pM while associating (Reason: %u=%s)\n",
+ bssid, reason_code,
+ ieee80211_get_reason_code_string(reason_code));
+
+ ieee80211_destroy_assoc_data(sdata, false);
+
+ cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
+ return;
+ }
}
@@ -2788,34 +2854,6 @@ static void ieee80211_get_rates(struct ieee80211_supported_band *sband,
}
}
-static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
- bool assoc)
-{
- struct ieee80211_mgd_assoc_data *assoc_data = sdata->u.mgd.assoc_data;
-
- sdata_assert_lock(sdata);
-
- if (!assoc) {
- /*
- * we are not associated yet, the only timer that could be
- * running is the timeout for the association response which
- * which is not relevant anymore.
- */
- del_timer_sync(&sdata->u.mgd.timer);
- sta_info_destroy_addr(sdata, assoc_data->bss->bssid);
-
- eth_zero_addr(sdata->u.mgd.bssid);
- ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID);
- sdata->u.mgd.flags = 0;
- mutex_lock(&sdata->local->mtx);
- ieee80211_vif_release_channel(sdata);
- mutex_unlock(&sdata->local->mtx);
- }
-
- kfree(assoc_data);
- sdata->u.mgd.assoc_data = NULL;
-}
-
static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
struct cfg80211_bss *cbss,
struct ieee80211_mgmt *mgmt, size_t len)
@@ -3299,7 +3337,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
}
ifmgd->have_beacon = true;
ifmgd->assoc_data->need_beacon = false;
- if (local->hw.flags & IEEE80211_HW_TIMING_BEACON_ONLY) {
<