aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/6lowpan/6lowpan_i.h4
-rw-r--r--net/6lowpan/Makefile2
-rw-r--r--net/6lowpan/core.c50
-rw-r--r--net/6lowpan/debugfs.c39
-rw-r--r--net/6lowpan/iphc.c167
-rw-r--r--net/6lowpan/ndisc.c241
-rw-r--r--net/8021q/vlan.c2
-rw-r--r--net/8021q/vlan_dev.c2
-rw-r--r--net/9p/trans_virtio.c4
-rw-r--r--net/Kconfig1
-rw-r--r--net/Makefile1
-rw-r--r--net/atm/clip.c2
-rw-r--r--net/batman-adv/Kconfig2
-rw-r--r--net/batman-adv/Makefile5
-rw-r--r--net/batman-adv/bat_algo.c140
-rw-r--r--net/batman-adv/bat_algo.h32
-rw-r--r--net/batman-adv/bat_iv_ogm.c106
-rw-r--r--net/batman-adv/bat_iv_ogm.h25
-rw-r--r--net/batman-adv/bat_v.c58
-rw-r--r--net/batman-adv/bat_v.h52
-rw-r--r--net/batman-adv/bat_v_elp.c7
-rw-r--r--net/batman-adv/bat_v_elp.h4
-rw-r--r--net/batman-adv/bat_v_ogm.c9
-rw-r--r--net/batman-adv/bat_v_ogm.h4
-rw-r--r--net/batman-adv/bitarray.c2
-rw-r--r--net/batman-adv/bridge_loop_avoidance.c1
-rw-r--r--net/batman-adv/debugfs.c240
-rw-r--r--net/batman-adv/distributed-arp-table.c2
-rw-r--r--net/batman-adv/fragmentation.c53
-rw-r--r--net/batman-adv/fragmentation.h6
-rw-r--r--net/batman-adv/gateway_client.c16
-rw-r--r--net/batman-adv/gateway_common.c10
-rw-r--r--net/batman-adv/hard-interface.c25
-rw-r--r--net/batman-adv/icmp_socket.c1
-rw-r--r--net/batman-adv/log.c231
-rw-r--r--net/batman-adv/log.h111
-rw-r--r--net/batman-adv/main.c709
-rw-r--r--net/batman-adv/main.h121
-rw-r--r--net/batman-adv/multicast.c501
-rw-r--r--net/batman-adv/multicast.h3
-rw-r--r--net/batman-adv/netlink.c424
-rw-r--r--net/batman-adv/netlink.h32
-rw-r--r--net/batman-adv/network-coding.c2
-rw-r--r--net/batman-adv/originator.c91
-rw-r--r--net/batman-adv/originator.h6
-rw-r--r--net/batman-adv/packet.h61
-rw-r--r--net/batman-adv/routing.c45
-rw-r--r--net/batman-adv/send.c102
-rw-r--r--net/batman-adv/send.h4
-rw-r--r--net/batman-adv/soft-interface.c13
-rw-r--r--net/batman-adv/sysfs.c29
-rw-r--r--net/batman-adv/tp_meter.c1507
-rw-r--r--net/batman-adv/tp_meter.h34
-rw-r--r--net/batman-adv/translation-table.c10
-rw-r--r--net/batman-adv/tvlv.c632
-rw-r--r--net/batman-adv/tvlv.h61
-rw-r--r--net/batman-adv/types.h258
-rw-r--r--net/bluetooth/6lowpan.c13
-rw-r--r--net/bluetooth/af_bluetooth.c5
-rw-r--r--net/bluetooth/hci_conn.c2
-rw-r--r--net/bluetooth/hci_core.c52
-rw-r--r--net/bluetooth/hci_debugfs.c35
-rw-r--r--net/bluetooth/hci_event.c18
-rw-r--r--net/bluetooth/hci_request.c2
-rw-r--r--net/bluetooth/hci_sock.c7
-rw-r--r--net/bluetooth/hci_sysfs.c99
-rw-r--r--net/bluetooth/l2cap_core.c10
-rw-r--r--net/bluetooth/l2cap_sock.c16
-rw-r--r--net/bluetooth/mgmt.c18
-rw-r--r--net/bluetooth/smp.c67
-rw-r--r--net/bridge/br_device.c34
-rw-r--r--net/bridge/br_fdb.c52
-rw-r--r--net/bridge/br_forward.c203
-rw-r--r--net/bridge/br_if.c9
-rw-r--r--net/bridge/br_input.c80
-rw-r--r--net/bridge/br_multicast.c245
-rw-r--r--net/bridge/br_netlink.c148
-rw-r--r--net/bridge/br_private.h73
-rw-r--r--net/bridge/br_stp.c2
-rw-r--r--net/bridge/br_stp_if.c2
-rw-r--r--net/bridge/br_sysfs_br.c25
-rw-r--r--net/bridge/netfilter/ebt_802_3.c6
-rw-r--r--net/bridge/netfilter/ebt_arp.c43
-rw-r--r--net/bridge/netfilter/ebt_ip.c28
-rw-r--r--net/bridge/netfilter/ebt_ip6.c41
-rw-r--r--net/bridge/netfilter/ebt_stp.c97
-rw-r--r--net/bridge/netfilter/ebtables.c34
-rw-r--r--net/bridge/netfilter/nft_meta_bridge.c1
-rw-r--r--net/bridge/netfilter/nft_reject_bridge.c8
-rw-r--r--net/caif/chnl_net.c1
-rw-r--r--net/can/Makefile3
-rw-r--r--net/can/af_can.c22
-rw-r--r--net/can/bcm.c309
-rw-r--r--net/can/proc.c3
-rw-r--r--net/ceph/Makefile2
-rw-r--r--net/ceph/ceph_common.c2
-rw-r--r--net/ceph/ceph_fs.c30
-rw-r--r--net/ceph/debugfs.c12
-rw-r--r--net/ceph/mon_client.c6
-rw-r--r--net/ceph/msgpool.c1
-rw-r--r--net/ceph/osd_client.c51
-rw-r--r--net/ceph/osdmap.c214
-rw-r--r--net/ceph/string_table.c105
-rw-r--r--net/core/dev.c214
-rw-r--r--net/core/devlink.c91
-rw-r--r--net/core/drop_monitor.c3
-rw-r--r--net/core/ethtool.c1
-rw-r--r--net/core/fib_rules.c82
-rw-r--r--net/core/filter.c593
-rw-r--r--net/core/flow_dissector.c6
-rw-r--r--net/core/gen_estimator.c24
-rw-r--r--net/core/gen_stats.c35
-rw-r--r--net/core/neighbour.c13
-rw-r--r--net/core/net-sysfs.c15
-rw-r--r--net/core/netpoll.c2
-rw-r--r--net/core/pktgen.c43
-rw-r--r--net/core/rtnetlink.c156
-rw-r--r--net/core/skbuff.c46
-rw-r--r--net/core/utils.c8
-rw-r--r--net/dccp/ipv6.c12
-rw-r--r--net/dsa/Makefile2
-rw-r--r--net/dsa/dsa.c259
-rw-r--r--net/dsa/dsa2.c695
-rw-r--r--net/dsa/dsa_priv.h9
-rw-r--r--net/dsa/slave.c121
-rw-r--r--net/dsa/tag_brcm.c4
-rw-r--r--net/dsa/tag_dsa.c10
-rw-r--r--net/dsa/tag_edsa.c10
-rw-r--r--net/dsa/tag_trailer.c4
-rw-r--r--net/ieee802154/6lowpan/core.c30
-rw-r--r--net/ieee802154/6lowpan/rx.c2
-rw-r--r--net/ieee802154/6lowpan/tx.c113
-rw-r--r--net/ieee802154/core.c70
-rw-r--r--net/ieee802154/core.h2
-rw-r--r--net/ieee802154/nl802154.c54
-rw-r--r--net/ipv4/Kconfig16
-rw-r--r--net/ipv4/Makefile1
-rw-r--r--net/ipv4/af_inet.c5
-rw-r--r--net/ipv4/cipso_ipv4.c88
-rw-r--r--net/ipv4/devinet.c23
-rw-r--r--net/ipv4/fib_frontend.c3
-rw-r--r--net/ipv4/fib_rules.c6
-rw-r--r--net/ipv4/fib_semantics.c8
-rw-r--r--net/ipv4/fib_trie.c12
-rw-r--r--net/ipv4/fou.c81
-rw-r--r--net/ipv4/gre_demux.c1
-rw-r--r--net/ipv4/inet_connection_sock.c7
-rw-r--r--net/ipv4/inet_diag.c25
-rw-r--r--net/ipv4/inet_fragment.c2
-rw-r--r--net/ipv4/inet_timewait_sock.c5
-rw-r--r--net/ipv4/ip_forward.c4
-rw-r--r--net/ipv4/ip_gre.c52
-rw-r--r--net/ipv4/ip_output.c8
-rw-r--r--net/ipv4/ip_tunnel.c2
-rw-r--r--net/ipv4/ip_tunnel_core.c11
-rw-r--r--net/ipv4/ip_vti.c31
-rw-r--r--net/ipv4/ipip.c137
-rw-r--r--net/ipv4/ipmr.c15
-rw-r--r--net/ipv4/netfilter/arp_tables.c88
-rw-r--r--net/ipv4/netfilter/ip_tables.c65
-rw-r--r--net/ipv4/netfilter/iptable_mangle.c4
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c14
-rw-r--r--net/ipv4/netfilter/nf_reject_ipv4.c3
-rw-r--r--net/ipv4/netfilter/nft_reject_ipv4.c1
-rw-r--r--net/ipv4/tcp.c69
-rw-r--r--net/ipv4/tcp_dctcp.c4
-rw-r--r--net/ipv4/tcp_diag.c7
-rw-r--r--net/ipv4/tcp_fastopen.c1
-rw-r--r--net/ipv4/tcp_input.c34
-rw-r--r--net/ipv4/tcp_ipv4.c39
-rw-r--r--net/ipv4/tcp_nv.c476
-rw-r--r--net/ipv4/tcp_output.c7
-rw-r--r--net/ipv4/tcp_timer.c81
-rw-r--r--net/ipv4/tunnel4.c72
-rw-r--r--net/ipv4/udp.c17
-rw-r--r--net/ipv4/udp_tunnel.c61
-rw-r--r--net/ipv4/udplite.c1
-rw-r--r--net/ipv4/xfrm4_policy.c8
-rw-r--r--net/ipv6/Makefile1
-rw-r--r--net/ipv6/addrconf.c335
-rw-r--r--net/ipv6/af_inet6.c15
-rw-r--r--net/ipv6/calipso.c1475
-rw-r--r--net/ipv6/exthdrs.c76
-rw-r--r--net/ipv6/exthdrs_core.c2
-rw-r--r--net/ipv6/fib6_rules.c6
-rw-r--r--net/ipv6/icmp.c78
-rw-r--r--net/ipv6/ila/ila.h3
-rw-r--r--net/ipv6/ila/ila_common.c16
-rw-r--r--net/ipv6/ila/ila_lwt.c4
-rw-r--r--net/ipv6/ila/ila_xlat.c8
-rw-r--r--net/ipv6/ip6_gre.c2
-rw-r--r--net/ipv6/ip6_icmp.c2
-rw-r--r--net/ipv6/ip6_input.c1
-rw-r--r--net/ipv6/ip6_output.c14
-rw-r--r--net/ipv6/ip6_tunnel.c2
-rw-r--r--net/ipv6/ip6mr.c26
-rw-r--r--net/ipv6/ipv6_sockglue.c1
-rw-r--r--net/ipv6/ndisc.c123
-rw-r--r--net/ipv6/netfilter/ip6_tables.c61
-rw-r--r--net/ipv6/netfilter/ip6table_mangle.c4
-rw-r--r--net/ipv6/netfilter/nft_reject_ipv6.c1
-rw-r--r--net/ipv6/ping.c44
-rw-r--r--net/ipv6/raw.c8
-rw-r--r--net/ipv6/route.c32
-rw-r--r--net/ipv6/sit.c140
-rw-r--r--net/ipv6/sysctl_net_ipv6.c19
-rw-r--r--net/ipv6/tcp_ipv6.c49
-rw-r--r--net/ipv6/udp.c13
-rw-r--r--net/ipv6/udplite.c1
-rw-r--r--net/ipv6/xfrm6_policy.c4
-rw-r--r--net/irda/af_irda.c7
-rw-r--r--net/irda/ircomm/ircomm_tty_ioctl.c8
-rw-r--r--net/irda/iriap.c8
-rw-r--r--net/iucv/af_iucv.c228
-rw-r--r--net/iucv/iucv.c36
-rw-r--r--net/kcm/kcmproc.c6
-rw-r--r--net/kcm/kcmsock.c11
-rw-r--r--net/l2tp/l2tp_core.c3
-rw-r--r--net/l2tp/l2tp_eth.c4
-rw-r--r--net/l2tp/l2tp_ip6.c8
-rw-r--r--net/l2tp/l2tp_ppp.c9
-rw-r--r--net/l3mdev/l3mdev.c64
-rw-r--r--net/mac80211/agg-rx.c18
-rw-r--r--net/mac80211/agg-tx.c8
-rw-r--r--net/mac80211/cfg.c3
-rw-r--r--net/mac80211/debugfs.c173
-rw-r--r--net/mac80211/debugfs_sta.c78
-rw-r--r--net/mac80211/driver-ops.h2
-rw-r--r--net/mac80211/ieee80211_i.h32
-rw-r--r--net/mac80211/iface.c26
-rw-r--r--net/mac80211/main.c10
-rw-r--r--net/mac80211/mesh.c30
-rw-r--r--net/mac80211/mesh_plink.c16
-rw-r--r--net/mac80211/rx.c9
-rw-r--r--net/mac80211/scan.c42
-rw-r--r--net/mac80211/spectmgmt.c45
-rw-r--r--net/mac80211/sta_info.c14
-rw-r--r--net/mac80211/status.c14
-rw-r--r--net/mac80211/tdls.c8
-rw-r--r--net/mac80211/tx.c308
-rw-r--r--net/mac80211/util.c34
-rw-r--r--net/mpls/af_mpls.c11
-rw-r--r--net/ncsi/Kconfig12
-rw-r--r--net/ncsi/Makefile4
-rw-r--r--net/ncsi/internal.h328
-rw-r--r--net/ncsi/ncsi-aen.c193
-rw-r--r--net/ncsi/ncsi-cmd.c367
-rw-r--r--net/ncsi/ncsi-manage.c1205
-rw-r--r--net/ncsi/ncsi-pkt.h415
-rw-r--r--net/ncsi/ncsi-rsp.c1035
-rw-r--r--net/netfilter/Kconfig10
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_tcp.c25
-rw-r--r--net/netfilter/nf_conntrack_core.c214
-rw-r--r--net/netfilter/nf_conntrack_expect.c2
-rw-r--r--net/netfilter/nf_conntrack_extend.c15
-rw-r--r--net/netfilter/nf_conntrack_ftp.c58
-rw-r--r--net/netfilter/nf_conntrack_h323_asn1.c3
-rw-r--r--net/netfilter/nf_conntrack_h323_main.c16
-rw-r--r--net/netfilter/nf_conntrack_helper.c127
-rw-r--r--net/netfilter/nf_conntrack_irc.c36
-rw-r--r--net/netfilter/nf_conntrack_labels.c28
-rw-r--r--net/netfilter/nf_conntrack_netlink.c20
-rw-r--r--net/netfilter/nf_conntrack_sane.c57
-rw-r--r--net/netfilter/nf_conntrack_sip.c79
-rw-r--r--net/netfilter/nf_conntrack_standalone.c54
-rw-r--r--net/netfilter/nf_conntrack_tftp.c48
-rw-r--r--net/netfilter/nf_log.c33
-rw-r--r--net/netfilter/nf_nat_core.c149
-rw-r--r--net/netfilter/nf_tables_api.c414
-rw-r--r--net/netfilter/nf_tables_netdev.c1
-rw-r--r--net/netfilter/nfnetlink_acct.c23
-rw-r--r--net/netfilter/nfnetlink_cttimeout.c85
-rw-r--r--net/netfilter/nfnetlink_log.c10
-rw-r--r--net/netfilter/nfnetlink_queue.c6
-rw-r--r--net/netfilter/nft_compat.c75
-rw-r--r--net/netfilter/nft_ct.c41
-rw-r--r--net/netfilter/nft_dynset.c7
-rw-r--r--net/netfilter/nft_exthdr.c11
-rw-r--r--net/netfilter/nft_hash.c24
-rw-r--r--net/netfilter/nft_log.c51
-rw-r--r--net/netfilter/nft_lookup.c43
-rw-r--r--net/netfilter/nft_meta.c26
-rw-r--r--net/netfilter/nft_rbtree.c36
-rw-r--r--net/netfilter/nft_reject.c16
-rw-r--r--net/netfilter/nft_reject_inet.c7
-rw-r--r--net/netfilter/x_tables.c53
-rw-r--r--net/netfilter/xt_NFLOG.c3
-rw-r--r--net/netfilter/xt_RATEEST.c2
-rw-r--r--net/netfilter/xt_TPROXY.c4
-rw-r--r--net/netfilter/xt_TRACE.c25
-rw-r--r--net/netfilter/xt_connlabel.c29
-rw-r--r--net/netfilter/xt_nfacct.c2
-rw-r--r--net/netfilter/xt_owner.c41
-rw-r--r--net/netfilter/xt_physdev.c8
-rw-r--r--net/netfilter/xt_tcpudp.c7
-rw-r--r--net/netlabel/Kconfig1
-rw-r--r--net/netlabel/Makefile2
-rw-r--r--net/netlabel/netlabel_calipso.c740
-rw-r--r--net/netlabel/netlabel_calipso.h151
-rw-r--r--net/netlabel/netlabel_domainhash.c293
-rw-r--r--net/netlabel/netlabel_domainhash.h17
-rw-r--r--net/netlabel/netlabel_kapi.c394
-rw-r--r--net/netlabel/netlabel_mgmt.c85
-rw-r--r--net/netlabel/netlabel_mgmt.h27
-rw-r--r--net/netlabel/netlabel_unlabeled.c5
-rw-r--r--net/netlabel/netlabel_user.c5
-rw-r--r--net/netlink/af_netlink.h14
-rw-r--r--net/nfc/digital_core.c28
-rw-r--r--net/nfc/digital_dep.c316
-rw-r--r--net/nfc/digital_technology.c11
-rw-r--r--net/nfc/hci/llc.c17
-rw-r--r--net/nfc/llcp_commands.c23
-rw-r--r--net/nfc/llcp_core.c9
-rw-r--r--net/openvswitch/actions.c40
-rw-r--r--net/openvswitch/conntrack.c81
-rw-r--r--net/openvswitch/datapath.c42
-rw-r--r--net/openvswitch/datapath.h5
-rw-r--r--net/openvswitch/flow_netlink.c9
-rw-r--r--net/openvswitch/vport-geneve.c9
-rw-r--r--net/openvswitch/vport-gre.c11
-rw-r--r--net/openvswitch/vport-internal_dev.c4
-rw-r--r--net/openvswitch/vport-vxlan.c9
-rw-r--r--net/openvswitch/vport.c1
-rw-r--r--net/packet/af_packet.c52
-rw-r--r--net/rds/bind.c6
-rw-r--r--net/rds/cong.c3
-rw-r--r--net/rds/connection.c329
-rw-r--r--net/rds/ib.c9
-rw-r--r--net/rds/ib.h8
-rw-r--r--net/rds/ib_cm.c9
-rw-r--r--net/rds/ib_rdma.c3
-rw-r--r--net/rds/ib_recv.c4
-rw-r--r--net/rds/ib_send.c4
-rw-r--r--net/rds/loop.c15
-rw-r--r--net/rds/message.c1
-rw-r--r--net/rds/rdma_transport.c1
-rw-r--r--net/rds/rds.h178
-rw-r--r--net/rds/rds_single_path.h30
-rw-r--r--net/rds/recv.c106
-rw-r--r--net/rds/send.c356
-rw-r--r--net/rds/tcp.c160
-rw-r--r--net/rds/tcp.h23
-rw-r--r--net/rds/tcp_connect.c43
-rw-r--r--net/rds/tcp_listen.c76
-rw-r--r--net/rds/tcp_recv.c38
-rw-r--r--net/rds/tcp_send.c39
-rw-r--r--net/rds/threads.c105
-rw-r--r--net/rxrpc/Makefile37
-rw-r--r--net/rxrpc/af_rxrpc.c287
-rw-r--r--net/rxrpc/ar-connection.c927
-rw-r--r--net/rxrpc/ar-error.c230
-rw-r--r--net/rxrpc/ar-internal.h516
-rw-r--r--net/rxrpc/ar-local.c415
-rw-r--r--net/rxrpc/ar-peer.c303
-rw-r--r--net/rxrpc/ar-transport.c284
-rw-r--r--net/rxrpc/call_accept.c (renamed from net/rxrpc/ar-accept.c)77
-rw-r--r--net/rxrpc/call_event.c (renamed from net/rxrpc/ar-ack.c)58
-rw-r--r--net/rxrpc/call_object.c (renamed from net/rxrpc/ar-call.c)569
-rw-r--r--net/rxrpc/conn_client.c372
-rw-r--r--net/rxrpc/conn_event.c (renamed from net/rxrpc/ar-connevent.c)73
-rw-r--r--net/rxrpc/conn_object.c340
-rw-r--r--net/rxrpc/conn_service.c230
-rw-r--r--net/rxrpc/input.c (renamed from net/rxrpc/ar-input.c)133
-rw-r--r--net/rxrpc/insecure.c7
-rw-r--r--net/rxrpc/key.c (renamed from net/rxrpc/ar-key.c)6
-rw-r--r--net/rxrpc/local_event.c116
-rw-r--r--net/rxrpc/local_object.c390
-rw-r--r--net/rxrpc/misc.c6
-rw-r--r--net/rxrpc/output.c (renamed from net/rxrpc/ar-output.c)233
-rw-r--r--net/rxrpc/peer_event.c281
-rw-r--r--net/rxrpc/peer_object.c315
-rw-r--r--net/rxrpc/proc.c (renamed from net/rxrpc/ar-proc.c)62
-rw-r--r--net/rxrpc/recvmsg.c (renamed from net/rxrpc/ar-recvmsg.c)35
-rw-r--r--net/rxrpc/rxkad.c263
-rw-r--r--net/rxrpc/security.c (renamed from net/rxrpc/ar-security.c)8
-rw-r--r--net/rxrpc/skbuff.c (renamed from net/rxrpc/ar-skbuff.c)43
-rw-r--r--net/rxrpc/sysctl.c12
-rw-r--r--net/rxrpc/utils.c46
-rw-r--r--net/sched/Kconfig10
-rw-r--r--net/sched/Makefile1
-rw-r--r--net/sched/act_api.c306
-rw-r--r--net/sched/act_bpf.c41
-rw-r--r--net/sched/act_connmark.c30
-rw-r--r--net/sched/act_csum.c29
-rw-r--r--net/sched/act_gact.c31
-rw-r--r--net/sched/act_ife.c69
-rw-r--r--net/sched/act_ipt.c67
-rw-r--r--net/sched/act_mirred.c35
-rw-r--r--net/sched/act_nat.c29
-rw-r--r--net/sched/act_pedit.c36
-rw-r--r--net/sched/act_police.c105
-rw-r--r--net/sched/act_simple.c39
-rw-r--r--net/sched/act_skbedit.c62
-rw-r--r--net/sched/act_vlan.c41
-rw-r--r--net/sched/cls_api.c99
-rw-r--r--net/sched/cls_bpf.c7
-rw-r--r--net/sched/cls_flower.c65
-rw-r--r--net/sched/cls_matchall.c318
-rw-r--r--net/sched/sch_api.c30
-rw-r--r--net/sched/sch_atm.c33
-rw-r--r--net/sched/sch_blackhole.c5
-rw-r--r--net/sched/sch_cbq.c305
-rw-r--r--net/sched/sch_choke.c41
-rw-r--r--net/sched/sch_codel.c10
-rw-r--r--net/sched/sch_drr.c38
-rw-r--r--net/sched/sch_dsmark.c27
-rw-r--r--net/sched/sch_fifo.c18
-rw-r--r--net/sched/sch_fq.c29
-rw-r--r--net/sched/sch_fq_codel.c64
-rw-r--r--net/sched/sch_generic.c99
-rw-r--r--net/sched/sch_gred.c42
-rw-r--r--net/sched/sch_hfsc.c108
-rw-r--r--net/sched/sch_hhf.c24
-rw-r--r--net/sched/sch_htb.c74
-rw-r--r--net/sched/sch_mq.c2
-rw-r--r--net/sched/sch_mqprio.c11
-rw-r--r--net/sched/sch_multiq.c32
-rw-r--r--net/sched/sch_netem.c73
-rw-r--r--net/sched/sch_pie.c7
-rw-r--r--net/sched/sch_plug.c19
-rw-r--r--net/sched/sch_prio.c27
-rw-r--r--net/sched/sch_qfq.c63
-rw-r--r--net/sched/sch_red.c28
-rw-r--r--net/sched/sch_sfb.c7
-rw-r--r--net/sched/sch_sfq.c11
-rw-r--r--net/sched/sch_tbf.c34
-rw-r--r--net/sched/sch_teql.c4
-rw-r--r--net/sctp/Makefile3
-rw-r--r--net/sctp/associola.c1
-rw-r--r--net/sctp/chunk.c25
-rw-r--r--net/sctp/endpointola.c1
-rw-r--r--net/sctp/input.c74
-rw-r--r--net/sctp/inqueue.c74
-rw-r--r--net/sctp/ipv6.c15
-rw-r--r--net/sctp/offload.c119
-rw-r--r--net/sctp/output.c379
-rw-r--r--net/sctp/outqueue.c99
-rw-r--r--net/sctp/proc.c1
-rw-r--r--net/sctp/protocol.c9
-rw-r--r--net/sctp/sctp_diag.c24
-rw-r--r--net/sctp/sm_make_chunk.c47
-rw-r--r--net/sctp/sm_sideeffect.c4
-rw-r--r--net/sctp/sm_statefuns.c9
-rw-r--r--net/sctp/socket.c293
-rw-r--r--net/sctp/ulpevent.c17
-rw-r--r--net/sctp/ulpqueue.c4
-rw-r--r--net/sunrpc/auth.c8
-rw-r--r--net/sunrpc/auth_generic.c9
-rw-r--r--net/sunrpc/auth_gss/auth_gss.c11
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_mech.c2
-rw-r--r--net/sunrpc/auth_gss/gss_mech_switch.c12
-rw-r--r--net/sunrpc/auth_gss/svcauth_gss.c5
-rw-r--r--net/sunrpc/auth_null.c1
-rw-r--r--net/sunrpc/auth_unix.c1
-rw-r--r--net/sunrpc/cache.c2
-rw-r--r--net/sunrpc/clnt.c26
-rw-r--r--net/sunrpc/rpc_pipe.c8
-rw-r--r--net/sunrpc/sched.c67
-rw-r--r--net/sunrpc/svc.c8
-rw-r--r--net/sunrpc/svc_xprt.c51
-rw-r--r--net/sunrpc/svcsock.c150
-rw-r--r--net/sunrpc/xprt.c40
-rw-r--r--net/sunrpc/xprtmultipath.c8
-rw-r--r--net/sunrpc/xprtrdma/Makefile2
-rw-r--r--net/sunrpc/xprtrdma/fmr_ops.c378
-rw-r--r--net/sunrpc/xprtrdma/frwr_ops.c369
-rw-r--r--net/sunrpc/xprtrdma/physical_ops.c122
-rw-r--r--net/sunrpc/xprtrdma/rpc_rdma.c274
-rw-r--r--net/sunrpc/xprtrdma/transport.c40
-rw-r--r--net/sunrpc/xprtrdma/verbs.c242
-rw-r--r--net/sunrpc/xprtrdma/xprt_rdma.h118
-rw-r--r--net/sunrpc/xprtsock.c181
-rw-r--r--net/switchdev/switchdev.c5
-rw-r--r--net/sysctl_net.c2
-rw-r--r--net/tipc/Makefile2
-rw-r--r--net/tipc/addr.h6
-rw-r--r--net/tipc/bearer.c33
-rw-r--r--net/tipc/bearer.h3
-rw-r--r--net/tipc/core.c1
-rw-r--r--net/tipc/core.h15
-rw-r--r--net/tipc/discover.c5
-rw-r--r--net/tipc/link.c51
-rw-r--r--net/tipc/monitor.c804
-rw-r--r--net/tipc/monitor.h82
-rw-r--r--net/tipc/name_distr.c8
-rw-r--r--net/tipc/netlink.c27
-rw-r--r--net/tipc/netlink.h1
-rw-r--r--net/tipc/node.c213
-rw-r--r--net/tipc/node.h5
-rw-r--r--net/tipc/server.c3
-rw-r--r--net/tipc/socket.c3
-rw-r--r--net/tipc/udp_media.c29
-rw-r--r--net/unix/af_unix.c112
-rw-r--r--net/vmw_vsock/Kconfig20
-rw-r--r--net/vmw_vsock/Makefile6
-rw-r--r--net/vmw_vsock/af_vsock.c25
-rw-r--r--net/vmw_vsock/virtio_transport.c620
-rw-r--r--net/vmw_vsock/virtio_transport_common.c992
-rw-r--r--net/vmw_vsock/vmci_transport.c2
-rw-r--r--net/wireless/chan.c3
-rw-r--r--net/wireless/core.c34
-rw-r--r--net/wireless/core.h16
-rw-r--r--net/wireless/nl80211.c437
-rw-r--r--net/wireless/nl80211.h2
-rw-r--r--net/wireless/scan.c18
-rw-r--r--net/wireless/sme.c8
-rw-r--r--net/wireless/trace.h33
-rw-r--r--net/wireless/wext-core.c25
508 files changed, 30570 insertions, 12004 deletions
diff --git a/net/6lowpan/6lowpan_i.h b/net/6lowpan/6lowpan_i.h
index 97ecc27aeca6..a67caee11929 100644
--- a/net/6lowpan/6lowpan_i.h
+++ b/net/6lowpan/6lowpan_i.h
@@ -12,6 +12,10 @@ static inline bool lowpan_is_ll(const struct net_device *dev,
return lowpan_dev(dev)->lltype == lltype;
}
+extern const struct ndisc_ops lowpan_ndisc_ops;
+
+int addrconf_ifid_802154_6lowpan(u8 *eui, struct net_device *dev);
+
#ifdef CONFIG_6LOWPAN_DEBUGFS
int lowpan_dev_debugfs_init(struct net_device *dev);
void lowpan_dev_debugfs_exit(struct net_device *dev);
diff --git a/net/6lowpan/Makefile b/net/6lowpan/Makefile
index e44f3bf2dd42..12d131ab2324 100644
--- a/net/6lowpan/Makefile
+++ b/net/6lowpan/Makefile
@@ -1,6 +1,6 @@
obj-$(CONFIG_6LOWPAN) += 6lowpan.o
-6lowpan-y := core.o iphc.o nhc.o
+6lowpan-y := core.o iphc.o nhc.o ndisc.o
6lowpan-$(CONFIG_6LOWPAN_DEBUGFS) += debugfs.o
#rfc6282 nhcs
diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c
index 7a240b3eaed1..5945f7e19c67 100644
--- a/net/6lowpan/core.c
+++ b/net/6lowpan/core.c
@@ -14,6 +14,7 @@
#include <linux/module.h>
#include <net/6lowpan.h>
+#include <net/addrconf.h>
#include "6lowpan_i.h"
@@ -33,6 +34,8 @@ int lowpan_register_netdevice(struct net_device *dev,
for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++)
lowpan_dev(dev)->ctx.table[i].id = i;
+ dev->ndisc_ops = &lowpan_ndisc_ops;
+
ret = register_netdevice(dev);
if (ret < 0)
return ret;
@@ -72,16 +75,61 @@ void lowpan_unregister_netdev(struct net_device *dev)
}
EXPORT_SYMBOL(lowpan_unregister_netdev);
+int addrconf_ifid_802154_6lowpan(u8 *eui, struct net_device *dev)
+{
+ struct wpan_dev *wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr;
+
+ /* Set short_addr autoconfiguration if short_addr is present only */
+ if (!lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr))
+ return -1;
+
+ /* For either address format, all zero addresses MUST NOT be used */
+ if (wpan_dev->pan_id == cpu_to_le16(0x0000) &&
+ wpan_dev->short_addr == cpu_to_le16(0x0000))
+ return -1;
+
+ /* Alternatively, if no PAN ID is known, 16 zero bits may be used */
+ if (wpan_dev->pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST))
+ memset(eui, 0, 2);
+ else
+ ieee802154_le16_to_be16(eui, &wpan_dev->pan_id);
+
+ /* The "Universal/Local" (U/L) bit shall be set to zero */
+ eui[0] &= ~2;
+ eui[2] = 0;
+ eui[3] = 0xFF;
+ eui[4] = 0xFE;
+ eui[5] = 0;
+ ieee802154_le16_to_be16(&eui[6], &wpan_dev->short_addr);
+ return 0;
+}
+
static int lowpan_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct inet6_dev *idev;
+ struct in6_addr addr;
int i;
if (dev->type != ARPHRD_6LOWPAN)
return NOTIFY_DONE;
+ idev = __in6_dev_get(dev);
+ if (!idev)
+ return NOTIFY_DONE;
+
switch (event) {
+ case NETDEV_UP:
+ case NETDEV_CHANGE:
+ /* (802.15.4 6LoWPAN short address slaac handling */
+ if (lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154) &&
+ addrconf_ifid_802154_6lowpan(addr.s6_addr + 8, dev) == 0) {
+ __ipv6_addr_set_half(&addr.s6_addr32[0],
+ htonl(0xFE800000), 0);
+ addrconf_add_linklocal(idev, &addr, 0);
+ }
+ break;
case NETDEV_DOWN:
for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++)
clear_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE,
@@ -112,8 +160,6 @@ static int __init lowpan_module_init(void)
return ret;
}
- request_module_nowait("ipv6");
-
request_module_nowait("nhc_dest");
request_module_nowait("nhc_fragment");
request_module_nowait("nhc_hop");
diff --git a/net/6lowpan/debugfs.c b/net/6lowpan/debugfs.c
index acbaa3db493b..24915e0bb9ea 100644
--- a/net/6lowpan/debugfs.c
+++ b/net/6lowpan/debugfs.c
@@ -245,6 +245,41 @@ static const struct file_operations lowpan_context_fops = {
.release = single_release,
};
+static int lowpan_short_addr_get(void *data, u64 *val)
+{
+ struct wpan_dev *wdev = data;
+
+ rtnl_lock();
+ *val = le16_to_cpu(wdev->short_addr);
+ rtnl_unlock();
+
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(lowpan_short_addr_fops, lowpan_short_addr_get,
+ NULL, "0x%04llx\n");
+
+static int lowpan_dev_debugfs_802154_init(const struct net_device *dev,
+ struct lowpan_dev *ldev)
+{
+ struct dentry *dentry, *root;
+
+ if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+ return 0;
+
+ root = debugfs_create_dir("ieee802154", ldev->iface_debugfs);
+ if (!root)
+ return -EINVAL;
+
+ dentry = debugfs_create_file("short_addr", 0444, root,
+ lowpan_802154_dev(dev)->wdev->ieee802154_ptr,
+ &lowpan_short_addr_fops);
+ if (!dentry)
+ return -EINVAL;
+
+ return 0;
+}
+
int lowpan_dev_debugfs_init(struct net_device *dev)
{
struct lowpan_dev *ldev = lowpan_dev(dev);
@@ -272,6 +307,10 @@ int lowpan_dev_debugfs_init(struct net_device *dev)
goto remove_root;
}
+ ret = lowpan_dev_debugfs_802154_init(dev, ldev);
+ if (ret < 0)
+ goto remove_root;
+
return 0;
remove_root:
diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c
index 8501dd532fe1..79f1fa22509a 100644
--- a/net/6lowpan/iphc.c
+++ b/net/6lowpan/iphc.c
@@ -761,22 +761,75 @@ static const u8 lowpan_iphc_dam_to_sam_value[] = {
[LOWPAN_IPHC_DAM_11] = LOWPAN_IPHC_SAM_11,
};
-static u8 lowpan_compress_ctx_addr(u8 **hc_ptr, const struct in6_addr *ipaddr,
+static inline bool
+lowpan_iphc_compress_ctx_802154_lladdr(const struct in6_addr *ipaddr,
+ const struct lowpan_iphc_ctx *ctx,
+ const void *lladdr)
+{
+ const struct ieee802154_addr *addr = lladdr;
+ unsigned char extended_addr[EUI64_ADDR_LEN];
+ bool lladdr_compress = false;
+ struct in6_addr tmp = {};
+
+ switch (addr->mode) {
+ case IEEE802154_ADDR_LONG:
+ ieee802154_le64_to_be64(&extended_addr, &addr->extended_addr);
+ /* check for SAM/DAM = 11 */
+ memcpy(&tmp.s6_addr[8], &extended_addr, EUI64_ADDR_LEN);
+ /* second bit-flip (Universe/Local) is done according RFC2464 */
+ tmp.s6_addr[8] ^= 0x02;
+ /* context information are always used */
+ ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
+ if (ipv6_addr_equal(&tmp, ipaddr))
+ lladdr_compress = true;
+ break;
+ case IEEE802154_ADDR_SHORT:
+ tmp.s6_addr[11] = 0xFF;
+ tmp.s6_addr[12] = 0xFE;
+ ieee802154_le16_to_be16(&tmp.s6_addr16[7],
+ &addr->short_addr);
+ /* context information are always used */
+ ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
+ if (ipv6_addr_equal(&tmp, ipaddr))
+ lladdr_compress = true;
+ break;
+ default:
+ /* should never handled and filtered by 802154 6lowpan */
+ WARN_ON_ONCE(1);
+ break;
+ }
+
+ return lladdr_compress;
+}
+
+static u8 lowpan_compress_ctx_addr(u8 **hc_ptr, const struct net_device *dev,
+ const struct in6_addr *ipaddr,
const struct lowpan_iphc_ctx *ctx,
const unsigned char *lladdr, bool sam)
{
struct in6_addr tmp = {};
u8 dam;
- /* check for SAM/DAM = 11 */
- memcpy(&tmp.s6_addr[8], lladdr, 8);
- /* second bit-flip (Universe/Local) is done according RFC2464 */
- tmp.s6_addr[8] ^= 0x02;
- /* context information are always used */
- ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
- if (ipv6_addr_equal(&tmp, ipaddr)) {
- dam = LOWPAN_IPHC_DAM_11;
- goto out;
+ switch (lowpan_dev(dev)->lltype) {
+ case LOWPAN_LLTYPE_IEEE802154:
+ if (lowpan_iphc_compress_ctx_802154_lladdr(ipaddr, ctx,
+ lladdr)) {
+ dam = LOWPAN_IPHC_DAM_11;
+ goto out;
+ }
+ break;
+ default:
+ /* check for SAM/DAM = 11 */
+ memcpy(&tmp.s6_addr[8], lladdr, EUI64_ADDR_LEN);
+ /* second bit-flip (Universe/Local) is done according RFC2464 */
+ tmp.s6_addr[8] ^= 0x02;
+ /* context information are always used */
+ ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
+ if (ipv6_addr_equal(&tmp, ipaddr)) {
+ dam = LOWPAN_IPHC_DAM_11;
+ goto out;
+ }
+ break;
}
memset(&tmp, 0, sizeof(tmp));
@@ -813,28 +866,85 @@ out:
return dam;
}
-static u8 lowpan_compress_addr_64(u8 **hc_ptr, const struct in6_addr *ipaddr,
+static inline bool
+lowpan_iphc_compress_802154_lladdr(const struct in6_addr *ipaddr,
+ const void *lladdr)
+{
+ const struct ieee802154_addr *addr = lladdr;
+ unsigned char extended_addr[EUI64_ADDR_LEN];
+ bool lladdr_compress = false;
+ struct in6_addr tmp = {};
+
+ switch (addr->mode) {
+ case IEEE802154_ADDR_LONG:
+ ieee802154_le64_to_be64(&extended_addr, &addr->extended_addr);
+ if (is_addr_mac_addr_based(ipaddr, extended_addr))
+ lladdr_compress = true;
+ break;
+ case IEEE802154_ADDR_SHORT:
+ /* fe:80::ff:fe00:XXXX
+ * \__/
+ * short_addr
+ *
+ * Universe/Local bit is zero.
+ */
+ tmp.s6_addr[0] = 0xFE;
+ tmp.s6_addr[1] = 0x80;
+ tmp.s6_addr[11] = 0xFF;
+ tmp.s6_addr[12] = 0xFE;
+ ieee802154_le16_to_be16(&tmp.s6_addr16[7],
+ &addr->short_addr);
+ if (ipv6_addr_equal(&tmp, ipaddr))
+ lladdr_compress = true;
+ break;
+ default:
+ /* should never handled and filtered by 802154 6lowpan */
+ WARN_ON_ONCE(1);
+ break;
+ }
+
+ return lladdr_compress;
+}
+
+static u8 lowpan_compress_addr_64(u8 **hc_ptr, const struct net_device *dev,
+ const struct in6_addr *ipaddr,
const unsigned char *lladdr, bool sam)
{
- u8 dam = LOWPAN_IPHC_DAM_00;
+ u8 dam = LOWPAN_IPHC_DAM_01;
- if (is_addr_mac_addr_based(ipaddr, lladdr)) {
- dam = LOWPAN_IPHC_DAM_11; /* 0-bits */
- pr_debug("address compression 0 bits\n");
- } else if (lowpan_is_iid_16_bit_compressable(ipaddr)) {
+ switch (lowpan_dev(dev)->lltype) {
+ case LOWPAN_LLTYPE_IEEE802154:
+ if (lowpan_iphc_compress_802154_lladdr(ipaddr, lladdr)) {
+ dam = LOWPAN_IPHC_DAM_11; /* 0-bits */
+ pr_debug("address compression 0 bits\n");
+ goto out;
+ }
+ break;
+ default:
+ if (is_addr_mac_addr_based(ipaddr, lladdr)) {
+ dam = LOWPAN_IPHC_DAM_11; /* 0-bits */
+ pr_debug("address compression 0 bits\n");
+ goto out;
+ }
+ break;
+ }
+
+ if (lowpan_is_iid_16_bit_compressable(ipaddr)) {
/* compress IID to 16 bits xxxx::XXXX */
lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[7], 2);
dam = LOWPAN_IPHC_DAM_10; /* 16-bits */
raw_dump_inline(NULL, "Compressed ipv6 addr is (16 bits)",
*hc_ptr - 2, 2);
- } else {
- /* do not compress IID => xxxx::IID */
- lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[4], 8);
- dam = LOWPAN_IPHC_DAM_01; /* 64-bits */
- raw_dump_inline(NULL, "Compressed ipv6 addr is (64 bits)",
- *hc_ptr - 8, 8);
+ goto out;
}
+ /* do not compress IID => xxxx::IID */
+ lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[4], 8);
+ raw_dump_inline(NULL, "Compressed ipv6 addr is (64 bits)",
+ *hc_ptr - 8, 8);
+
+out:
+
if (sam)
return lowpan_iphc_dam_to_sam_value[dam];
else
@@ -1013,9 +1123,6 @@ int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev,
iphc0 = LOWPAN_DISPATCH_IPHC;
iphc1 = 0;
- raw_dump_inline(__func__, "saddr", saddr, EUI64_ADDR_LEN);
- raw_dump_inline(__func__, "daddr", daddr, EUI64_ADDR_LEN);
-
raw_dump_table(__func__, "sending raw skb network uncompressed packet",
skb->data, skb->len);
@@ -1088,14 +1195,15 @@ int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev,
iphc1 |= LOWPAN_IPHC_SAC;
} else {
if (sci) {
- iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, &hdr->saddr,
+ iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, dev,
+ &hdr->saddr,
&sci_entry, saddr,
true);
iphc1 |= LOWPAN_IPHC_SAC;
} else {
if (ipv6_saddr_type & IPV6_ADDR_LINKLOCAL &&
lowpan_is_linklocal_zero_padded(hdr->saddr)) {
- iphc1 |= lowpan_compress_addr_64(&hc_ptr,
+ iphc1 |= lowpan_compress_addr_64(&hc_ptr, dev,
&hdr->saddr,
saddr, true);
pr_debug("source address unicast link-local %pI6c iphc1 0x%02x\n",
@@ -1123,14 +1231,15 @@ int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev,
}
} else {
if (dci) {
- iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, &hdr->daddr,
+ iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, dev,
+ &hdr->daddr,
&dci_entry, daddr,
false);
iphc1 |= LOWPAN_IPHC_DAC;
} else {
if (ipv6_daddr_type & IPV6_ADDR_LINKLOCAL &&
lowpan_is_linklocal_zero_padded(hdr->daddr)) {
- iphc1 |= lowpan_compress_addr_64(&hc_ptr,
+ iphc1 |= lowpan_compress_addr_64(&hc_ptr, dev,
&hdr->daddr,
daddr, false);
pr_debug("dest address unicast link-local %pI6c iphc1 0x%02x\n",
diff --git a/net/6lowpan/ndisc.c b/net/6lowpan/ndisc.c
new file mode 100644
index 000000000000..86450b7e2899
--- /dev/null
+++ b/net/6lowpan/ndisc.c
@@ -0,0 +1,241 @@
+/* This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * 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.
+ *
+ * Authors:
+ * (C) 2016 Pengutronix, Alexander Aring <aar@pengutronix.de>
+ */
+
+#include <net/6lowpan.h>
+#include <net/addrconf.h>
+#include <net/ndisc.h>
+
+#include "6lowpan_i.h"
+
+static int lowpan_ndisc_is_useropt(u8 nd_opt_type)
+{
+ return nd_opt_type == ND_OPT_6CO;
+}
+
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+#define NDISC_802154_SHORT_ADDR_LENGTH 1
+static int lowpan_ndisc_parse_802154_options(const struct net_device *dev,
+ struct nd_opt_hdr *nd_opt,
+ struct ndisc_options *ndopts)
+{
+ switch (nd_opt->nd_opt_len) {
+ case NDISC_802154_SHORT_ADDR_LENGTH:
+ if (ndopts->nd_802154_opt_array[nd_opt->nd_opt_type])
+ ND_PRINTK(2, warn,
+ "%s: duplicated short addr ND6 option found: type=%d\n",
+ __func__, nd_opt->nd_opt_type);
+ else
+ ndopts->nd_802154_opt_array[nd_opt->nd_opt_type] = nd_opt;
+ return 1;
+ default:
+ /* all others will be handled by ndisc IPv6 option parsing */
+ return 0;
+ }
+}
+
+static int lowpan_ndisc_parse_options(const struct net_device *dev,
+ struct nd_opt_hdr *nd_opt,
+ struct ndisc_options *ndopts)
+{
+ if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+ return 0;
+
+ switch (nd_opt->nd_opt_type) {
+ case ND_OPT_SOURCE_LL_ADDR:
+ case ND_OPT_TARGET_LL_ADDR:
+ return lowpan_ndisc_parse_802154_options(dev, nd_opt, ndopts);
+ default:
+ return 0;
+ }
+}
+
+static void lowpan_ndisc_802154_update(struct neighbour *n, u32 flags,
+ u8 icmp6_type,
+ const struct ndisc_options *ndopts)
+{
+ struct lowpan_802154_neigh *neigh = lowpan_802154_neigh(neighbour_priv(n));
+ u8 *lladdr_short = NULL;
+
+ switch (icmp6_type) {
+ case NDISC_ROUTER_SOLICITATION:
+ case NDISC_ROUTER_ADVERTISEMENT:
+ case NDISC_NEIGHBOUR_SOLICITATION:
+ if (ndopts->nd_802154_opts_src_lladdr) {
+ lladdr_short = __ndisc_opt_addr_data(ndopts->nd_802154_opts_src_lladdr,
+ IEEE802154_SHORT_ADDR_LEN, 0);
+ if (!lladdr_short) {
+ ND_PRINTK(2, warn,
+ "NA: invalid short link-layer address length\n");
+ return;
+ }
+ }
+ break;
+ case NDISC_REDIRECT:
+ case NDISC_NEIGHBOUR_ADVERTISEMENT:
+ if (ndopts->nd_802154_opts_tgt_lladdr) {
+ lladdr_short = __ndisc_opt_addr_data(ndopts->nd_802154_opts_tgt_lladdr,
+ IEEE802154_SHORT_ADDR_LEN, 0);
+ if (!lladdr_short) {
+ ND_PRINTK(2, warn,
+ "NA: invalid short link-layer address length\n");
+ return;
+ }
+ }
+ break;
+ default:
+ break;
+ }
+
+ write_lock_bh(&n->lock);
+ if (lladdr_short) {
+ ieee802154_be16_to_le16(&neigh->short_addr, lladdr_short);
+ if (!lowpan_802154_is_valid_src_short_addr(neigh->short_addr))
+ neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+ } else {
+ neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+ }
+ write_unlock_bh(&n->lock);
+}
+
+static void lowpan_ndisc_update(const struct net_device *dev,
+ struct neighbour *n, u32 flags, u8 icmp6_type,
+ const struct ndisc_options *ndopts)
+{
+ if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+ return;
+
+ /* react on overrides only. TODO check if this is really right. */
+ if (flags & NEIGH_UPDATE_F_OVERRIDE)
+ lowpan_ndisc_802154_update(n, flags, icmp6_type, ndopts);
+}
+
+static int lowpan_ndisc_opt_addr_space(const struct net_device *dev,
+ u8 icmp6_type, struct neighbour *neigh,
+ u8 *ha_buf, u8 **ha)
+{
+ struct lowpan_802154_neigh *n;
+ struct wpan_dev *wpan_dev;
+ int addr_space = 0;
+
+ if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+ return 0;
+
+ switch (icmp6_type) {
+ case NDISC_REDIRECT:
+ n = lowpan_802154_neigh(neighbour_priv(neigh));
+
+ read_lock_bh(&neigh->lock);
+ if (lowpan_802154_is_valid_src_short_addr(n->short_addr)) {
+ memcpy(ha_buf, &n->short_addr,
+ IEEE802154_SHORT_ADDR_LEN);
+ read_unlock_bh(&neigh->lock);
+ addr_space += __ndisc_opt_addr_space(IEEE802154_SHORT_ADDR_LEN, 0);
+ *ha = ha_buf;
+ } else {
+ read_unlock_bh(&neigh->lock);
+ }
+ break;
+ case NDISC_NEIGHBOUR_ADVERTISEMENT:
+ case NDISC_NEIGHBOUR_SOLICITATION:
+ case NDISC_ROUTER_SOLICITATION:
+ wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr;
+
+ if (lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr))
+ addr_space = __ndisc_opt_addr_space(IEEE802154_SHORT_ADDR_LEN, 0);
+ break;
+ default:
+ break;
+ }
+
+ return addr_space;
+}
+
+static void lowpan_ndisc_fill_addr_option(const struct net_device *dev,
+ struct sk_buff *skb, u8 icmp6_type,
+ const u8 *ha)
+{
+ struct wpan_dev *wpan_dev;
+ __be16 short_addr;
+ u8 opt_type;
+
+ if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+ return;
+
+ switch (icmp6_type) {
+ case NDISC_REDIRECT:
+ if (ha) {
+ ieee802154_le16_to_be16(&short_addr, ha);
+ __ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR,
+ &short_addr,
+ IEEE802154_SHORT_ADDR_LEN, 0);
+ }
+ return;
+ case NDISC_NEIGHBOUR_ADVERTISEMENT:
+ opt_type = ND_OPT_TARGET_LL_ADDR;
+ break;
+ case NDISC_ROUTER_SOLICITATION:
+ case NDISC_NEIGHBOUR_SOLICITATION:
+ opt_type = ND_OPT_SOURCE_LL_ADDR;
+ break;
+ default:
+ return;
+ }
+
+ wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr;
+
+ if (lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr)) {
+ ieee802154_le16_to_be16(&short_addr,
+ &wpan_dev->short_addr);
+ __ndisc_fill_addr_option(skb, opt_type, &short_addr,
+ IEEE802154_SHORT_ADDR_LEN, 0);
+ }
+}
+
+static void lowpan_ndisc_prefix_rcv_add_addr(struct net *net,
+ struct net_device *dev,
+ const struct prefix_info *pinfo,
+ struct inet6_dev *in6_dev,
+ struct in6_addr *addr,
+ int addr_type, u32 addr_flags,
+ bool sllao, bool tokenized,
+ __u32 valid_lft,
+ u32 prefered_lft,
+ bool dev_addr_generated)
+{
+ int err;
+
+ /* generates short based address for RA PIO's */
+ if (lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154) && dev_addr_generated &&
+ !addrconf_ifid_802154_6lowpan(addr->s6_addr + 8, dev)) {
+ err = addrconf_prefix_rcv_add_addr(net, dev, pinfo, in6_dev,
+ addr, addr_type, addr_flags,
+ sllao, tokenized, valid_lft,
+ prefered_lft);
+ if (err)
+ ND_PRINTK(2, warn,
+ "RA: could not add a short address based address for prefix: %pI6c\n",
+ &pinfo->prefix);
+ }
+}
+#endif
+
+const struct ndisc_ops lowpan_ndisc_ops = {
+ .is_useropt = lowpan_ndisc_is_useropt,
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+ .parse_options = lowpan_ndisc_parse_options,
+ .update = lowpan_ndisc_update,
+ .opt_addr_space = lowpan_ndisc_opt_addr_space,
+ .fill_addr_option = lowpan_ndisc_fill_addr_option,
+ .prefix_rcv_add_addr = lowpan_ndisc_prefix_rcv_add_addr,
+#endif
+};
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 82a116ba590e..8de138d3306b 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -169,7 +169,7 @@ int register_vlan_dev(struct net_device *dev)
if (err < 0)
goto out_uninit_mvrp;
- vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1;
+ vlan->nest_level = dev_get_nest_level(real_dev) + 1;
err = register_netdevice(dev);
if (err < 0)
goto out_uninit_mvrp;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 516b0e73263c..fbfacd51aa34 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -792,6 +792,8 @@ static const struct net_device_ops vlan_netdev_ops = {
.ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup,
#endif
.ndo_fix_features = vlan_dev_fix_features,
+ .ndo_neigh_construct = netdev_default_l2upper_neigh_construct,
+ .ndo_neigh_destroy = netdev_default_l2upper_neigh_destroy,
.ndo_fdb_add = switchdev_port_fdb_add,
.ndo_fdb_del = switchdev_port_fdb_del,
.ndo_fdb_dump = switchdev_port_fdb_dump,
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 4acb1d5417aa..f24b25c25106 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -507,8 +507,8 @@ err_out:
/* wakeup anybody waiting for slots to pin pages */
wake_up(&vp_wq);
}
- kfree(in_pages);
- kfree(out_pages);
+ kvfree(in_pages);
+ kvfree(out_pages);
return err;
}
diff --git a/net/Kconfig b/net/Kconfig
index ff40562a782c..c2cdbce629bd 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -237,6 +237,7 @@ source "net/hsr/Kconfig"
source "net/switchdev/Kconfig"
source "net/l3mdev/Kconfig"
source "net/qrtr/Kconfig"
+source "net/ncsi/Kconfig"
config RPS
bool
diff --git a/net/Makefile b/net/Makefile
index bdd14553a774..9bd20bb86cc6 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -79,3 +79,4 @@ ifneq ($(CONFIG_NET_L3_MASTER_DEV),)
obj-y += l3mdev/
endif
obj-$(CONFIG_QRTR) += qrtr/
+obj-$(CONFIG_NET_NCSI) += ncsi/
diff --git a/net/atm/clip.c b/net/atm/clip.c
index e07f551a863c..53b4ac09e7b7 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -286,7 +286,7 @@ static const struct neigh_ops clip_neigh_ops = {
.connected_output = neigh_direct_output,
};
-static int clip_constructor(struct neighbour *neigh)
+static int clip_constructor(struct net_device *dev, struct neighbour *neigh)
{
struct atmarp_entry *entry = neighbour_priv(neigh);
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index f66930ee3c0b..833bb145ba3c 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -66,7 +66,7 @@ config BATMAN_ADV_NC
config BATMAN_ADV_MCAST
bool "Multicast optimisation"
- depends on BATMAN_ADV
+ depends on BATMAN_ADV && INET && !(BRIDGE=m && BATMAN_ADV=y)
default n
help
This option enables the multicast optimisation which aims to
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index 797cf2fc88c1..a83fc6c58d19 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -17,6 +17,7 @@
#
obj-$(CONFIG_BATMAN_ADV) += batman-adv.o
+batman-adv-y += bat_algo.o
batman-adv-y += bat_iv_ogm.o
batman-adv-$(CONFIG_BATMAN_ADV_BATMAN_V) += bat_v.o
batman-adv-$(CONFIG_BATMAN_ADV_BATMAN_V) += bat_v_elp.o
@@ -31,12 +32,16 @@ batman-adv-y += gateway_common.o
batman-adv-y += hard-interface.o
batman-adv-y += hash.o
batman-adv-y += icmp_socket.o
+batman-adv-$(CONFIG_BATMAN_ADV_DEBUG) += log.o
batman-adv-y += main.o
batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o
+batman-adv-y += netlink.o
batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o
batman-adv-y += originator.o
batman-adv-y += routing.o
batman-adv-y += send.o
batman-adv-y += soft-interface.o
batman-adv-y += sysfs.o
+batman-adv-y += tp_meter.o
batman-adv-y += translation-table.o
+batman-adv-y += tvlv.o
diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c
new file mode 100644
index 000000000000..81dbbf569bd4
--- /dev/null
+++ b/net/batman-adv/bat_algo.c
@@ -0,0 +1,140 @@
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ *
+ * 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/>.
+ */
+
+#include "main.h"
+
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/moduleparam.h>
+#include <linux/printk.h>
+#include <linux/seq_file.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+
+#include "bat_algo.h"
+
+char batadv_routing_algo[20] = "BATMAN_IV";
+static struct hlist_head batadv_algo_list;
+
+/**
+ * batadv_algo_init - Initialize batman-adv algorithm management data structures
+ */
+void batadv_algo_init(void)
+{
+ INIT_HLIST_HEAD(&batadv_algo_list);
+}
+
+static struct batadv_algo_ops *batadv_algo_get(char *name)
+{
+ struct batadv_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp;
+
+ hlist_for_each_entry(bat_algo_ops_tmp, &batadv_algo_list, list) {
+ if (strcmp(bat_algo_ops_tmp->name, name) != 0)
+ continue;
+
+ bat_algo_ops = bat_algo_ops_tmp;
+ break;
+ }
+
+ return bat_algo_ops;
+}
+
+int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops)
+{
+ struct batadv_algo_ops *bat_algo_ops_tmp;
+
+ 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);
+ return -EEXIST;
+ }
+
+ /* all algorithms must implement all ops (for now) */
+ if (!bat_algo_ops->iface.enable ||
+ !bat_algo_ops->iface.disable ||
+ !bat_algo_ops->iface.update_mac ||
+ !bat_algo_ops->iface.primary_set ||
+ !bat_algo_ops->neigh.cmp ||
+ !bat_algo_ops->neigh.is_similar_or_better) {
+ pr_info("Routing algo '%s' does not implement required ops\n",
+ bat_algo_ops->name);
+ return -EINVAL;
+ }
+
+ INIT_HLIST_NODE(&bat_algo_ops->list);
+ hlist_add_head(&bat_algo_ops->list, &batadv_algo_list);
+
+ return 0;
+}
+
+int batadv_algo_select(struct batadv_priv *bat_priv, char *name)
+{
+ struct batadv_algo_ops *bat_algo_ops;
+
+ bat_algo_ops = batadv_algo_get(name);
+ if (!bat_algo_ops)
+ return -EINVAL;
+
+ bat_priv->algo_ops = bat_algo_ops;
+
+ return 0;
+}
+
+int batadv_algo_seq_print_text(struct seq_file *seq, void *offset)
+{
+ struct batadv_algo_ops *bat_algo_ops;
+
+ seq_puts(seq, "Available routing algorithms:\n");
+
+ hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) {
+ seq_printf(seq, " * %s\n", bat_algo_ops->name);
+ }
+
+ return 0;
+}
+
+static int batadv_param_set_ra(const char *val, const struct kernel_param *kp)
+{
+ struct batadv_algo_ops *bat_algo_ops;
+ char *algo_name = (char *)val;
+ size_t name_len = strlen(algo_name);
+
+ if (name_len > 0 && algo_name[name_len - 1] == '\n')
+ algo_name[name_len - 1] = '\0';
+
+ bat_algo_ops = batadv_algo_get(algo_name);
+ if (!bat_algo_ops) {
+ pr_err("Routing algorithm '%s' is not supported\n", algo_name);
+ return -EINVAL;
+ }
+
+ return param_set_copystring(algo_name, kp);
+}
+
+static const struct kernel_param_ops batadv_param_ops_ra = {
+ .set = batadv_param_set_ra,
+ .get = param_get_string,
+};
+
+static struct kparam_string batadv_param_string_ra = {
+ .maxlen = sizeof(batadv_routing_algo),
+ .string = batadv_routing_algo,
+};
+
+module_param_cb(routing_algo, &batadv_param_ops_ra, &batadv_param_string_ra,
+ 0644);
diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h
index 03dafd33d23b..860d773dd8fa 100644
--- a/net/batman-adv/bat_algo.h
+++ b/net/batman-adv/bat_algo.h
@@ -18,32 +18,18 @@
#ifndef _NET_BATMAN_ADV_BAT_ALGO_H_
#define _NET_BATMAN_ADV_BAT_ALGO_H_
-struct batadv_priv;
+#include "main.h"
-int batadv_iv_init(void);
+#include <linux/types.h>
-#ifdef CONFIG_BATMAN_ADV_BATMAN_V
+struct seq_file;
-int batadv_v_init(void);
-int batadv_v_mesh_init(struct batadv_priv *bat_priv);
-void batadv_v_mesh_free(struct batadv_priv *bat_priv);
+extern char batadv_routing_algo[];
+extern struct list_head batadv_hardif_list;
-#else
-
-static inline int batadv_v_init(void)
-{
- return 0;
-}
-
-static inline int batadv_v_mesh_init(struct batadv_priv *bat_priv)
-{
- return 0;
-}
-
-static inline void batadv_v_mesh_free(struct batadv_priv *bat_priv)
-{
-}
-
-#endif /* CONFIG_BATMAN_ADV_BATMAN_V */
+void batadv_algo_init(void);
+int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops);
+int batadv_algo_select(struct batadv_priv *bat_priv, char *name);
+int batadv_algo_seq_print_text(struct seq_file *seq, void *offset);
#endif /* _NET_BATMAN_ADV_BAT_ALGO_H_ */
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index ce2f203048d3..19b0abd6c640 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -15,7 +15,7 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "bat_algo.h"
+#include "bat_iv_ogm.h"
#include "main.h"
#include <linux/atomic.h>
@@ -30,8 +30,9 @@
#include <linux/if_ether.h>
#include <linux/init.h>
#include <linux/jiffies.h>
-#include <linux/list.h>
+#include <linux/kernel.h>
#include <linux/kref.h>
+#include <linux/list.h>
#include <linux/lockdep.h>
#include <linux/netdevice.h>
#include <linux/pkt_sched.h>
@@ -48,15 +49,20 @@
#include <linux/types.h>
#include <linux/workqueue.h>
+#include "bat_algo.h"
#include "bitarray.h"
#include "hard-interface.h"
#include "hash.h"
+#include "log.h"
#include "network-coding.h"
#include "originator.h"
#include "packet.h"
#include "routing.h"
#include "send.h"
#include "translation-table.h"
+#include "tvlv.h"
+
+static void batadv_iv_send_outstanding_bat_ogm_packet(struct work_struct *work);
/**
* enum batadv_dup_status - duplicate status
@@ -336,7 +342,8 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface,
{
struct batadv_neigh_node *neigh_node;
- neigh_node = batadv_neigh_node_new(orig_node, hard_iface, neigh_addr);
+ neigh_node = batadv_neigh_node_get_or_create(orig_node,
+ hard_iface, neigh_addr);
if (!neigh_node)
goto out;
@@ -730,7 +737,7 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
/* start timer for this packet */
INIT_DELAYED_WORK(&forw_packet_aggr->delayed_work,
- batadv_send_outstanding_bat_ogm_packet);
+ batadv_iv_send_outstanding_bat_ogm_packet);
queue_delayed_work(batadv_event_workqueue,
&forw_packet_aggr->delayed_work,
send_time - jiffies);
@@ -937,6 +944,19 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
u16 tvlv_len = 0;
unsigned long send_time;
+ if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) ||
+ (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED))
+ return;
+
+ /* the interface gets activated here to avoid race conditions between
+ * the moment of activating the interface in
+ * hardif_activate_interface() where the originator mac is set and
+ * outdated packets (especially uninitialized mac addresses) in the
+ * packet queue
+ */
+ if (hard_iface->if_status == BATADV_IF_TO_BE_ACTIVATED)
+ hard_iface->if_status = BATADV_IF_ACTIVE;
+
primary_if = batadv_primary_if_get_selected(bat_priv);
if (hard_iface == primary_if) {
@@ -1778,6 +1798,45 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset,
batadv_orig_node_put(orig_node);
}
+static void batadv_iv_send_outstanding_bat_ogm_packet(struct work_struct *work)
+{
+ struct delayed_work *delayed_work;
+ struct batadv_forw_packet *forw_packet;
+ struct batadv_priv *bat_priv;
+
+ delayed_work = to_delayed_work(work);
+ forw_packet = container_of(delayed_work, struct batadv_forw_packet,
+ delayed_work);
+ bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface);
+ spin_lock_bh(&bat_priv->forw_bat_list_lock);
+ hlist_del(&forw_packet->list);
+ spin_unlock_bh(&bat_priv->forw_bat_list_lock);
+
+ if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING)
+ goto out;
+
+ batadv_iv_ogm_emit(forw_packet);
+
+ /* we have to have at least one packet in the queue to determine the
+ * queues wake up time unless we are shutting down.
+ *
+ * only re-schedule if this is the "original" copy, e.g. the OGM of the
+ * primary interface should only be rescheduled once per period, but
+ * this function will be called for the forw_packet instances of the
+ * other secondary interfaces as well.
+ */
+ if (forw_packet->own &&
+ forw_packet->if_incoming == forw_packet->if_outgoing)
+ batadv_iv_ogm_schedule(forw_packet->if_incoming);
+
+out:
+ /* don't count own packet */
+ if (!forw_packet->own)
+ atomic_inc(&bat_priv->batman_queue_left);
+
+ batadv_forw_packet_free(forw_packet);
+}
+
static int batadv_iv_ogm_receive(struct sk_buff *skb,
struct batadv_hard_iface *if_incoming)
{
@@ -1794,7 +1853,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb,
/* did we receive a B.A.T.M.A.N. IV OGM packet on an interface
* that does not have B.A.T.M.A.N. IV enabled ?
*/
- if (bat_priv->bat_algo_ops->bat_ogm_emit != batadv_iv_ogm_emit)
+ if (bat_priv->algo_ops->iface.enable != batadv_iv_ogm_iface_enable)
return NET_RX_DROP;
batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_RX);
@@ -2052,21 +2111,32 @@ out:
return ret;
}
+static void batadv_iv_iface_activate(struct batadv_hard_iface *hard_iface)
+{
+ /* begin scheduling originator messages on that interface */
+ batadv_iv_ogm_schedule(hard_iface);
+}
+
static struct batadv_algo_ops batadv_batman_iv __read_mostly = {
.name = "BATMAN_IV",
- .bat_iface_enable = batadv_iv_ogm_iface_enable,
- .bat_iface_disable = batadv_iv_ogm_iface_disable,
- .bat_iface_update_mac = batadv_iv_ogm_iface_update_mac,
- .bat_primary_iface_set = batadv_iv_ogm_primary_iface_set,
- .bat_ogm_schedule = batadv_iv_ogm_schedule,
- .bat_ogm_emit = batadv_iv_ogm_emit,
- .bat_neigh_cmp = batadv_iv_ogm_neigh_cmp,
- .bat_neigh_is_similar_or_better = batadv_iv_ogm_neigh_is_sob,
- .bat_neigh_print = batadv_iv_neigh_print,
- .bat_orig_print = batadv_iv_ogm_orig_print,
- .bat_orig_free = batadv_iv_ogm_orig_free,
- .bat_orig_add_if = batadv_iv_ogm_orig_add_if,
- .bat_orig_del_if = batadv_iv_ogm_orig_del_if,
+ .iface = {
+ .activate = batadv_iv_iface_activate,
+ .enable = batadv_iv_ogm_iface_enable,
+ .disable = batadv_iv_ogm_iface_disable,
+ .update_mac = batadv_iv_ogm_iface_update_mac,
+ .primary_set = batadv_iv_ogm_primary_iface_set,
+ },
+ .neigh = {
+ .cmp = batadv_iv_ogm_neigh_cmp,
+ .is_similar_or_better = batadv_iv_ogm_neigh_is_sob,
+ .print = batadv_iv_neigh_print,
+ },
+ .orig = {
+ .print = batadv_iv_ogm_orig_print,
+ .free = batadv_iv_ogm_orig_free,
+ .add_if = batadv_iv_ogm_orig_add_if,
+ .del_if = batadv_iv_ogm_orig_del_if,
+ },
};
int __init batadv_iv_init(void)
diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h
new file mode 100644
index 000000000000..b9f3550faaf7
--- /dev/null
+++ b/net/batman-adv/bat_iv_ogm.h
@@ -0,0 +1,25 @@
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ *
+ * 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/>.
+ */
+
+#ifndef _BATMAN_ADV_BATADV_IV_OGM_H_
+#define _BATMAN_ADV_BATADV_IV_OGM_H_
+
+#include "main.h"
+
+int batadv_iv_init(void);
+
+#endif /* _BATMAN_ADV_BATADV_IV_OGM_H_ */
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 0a12e5cdd65d..0366cbf5e444 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -15,7 +15,7 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "bat_algo.h"
+#include "bat_v.h"
#include "main.h"
#include <linux/atomic.h>
@@ -31,6 +31,7 @@
#include <linux/types.h>
#include <linux/workqueue.h>
+#include "bat_algo.h"
#include "bat_v_elp.h"
#include "bat_v_ogm.h"
#include "hard-interface.h"
@@ -70,11 +71,6 @@ static int batadv_v_iface_enable(struct batadv_hard_iface *hard_iface)
if (ret < 0)
batadv_v_elp_iface_disable(hard_iface);
- /* enable link throughput auto-detection by setting the throughput
- * override to zero
- */
- atomic_set(&hard_iface->bat_v.throughput_override, 0);
-
return ret;
}
@@ -119,14 +115,6 @@ batadv_v_hardif_neigh_init(struct batadv_hardif_neigh_node *hardif_neigh)
batadv_v_elp_throughput_metric_update);
}
-static void batadv_v_ogm_schedule(struct batadv_hard_iface *hard_iface)
-{
-}
-
-static void batadv_v_ogm_emit(struct batadv_forw_packet *forw_packet)
-{
-}
-
/**
* batadv_v_orig_print_neigh - print neighbors for the originator table
* @orig_node: the orig_node for which the neighbors are printed
@@ -334,21 +322,39 @@ err_ifinfo1:
static struct batadv_algo_ops batadv_batman_v __read_mostly = {
.name = "BATMAN_V",
- .bat_iface_activate = batadv_v_iface_activate,
- .bat_iface_enable = batadv_v_iface_enable,
- .bat_iface_disable = batadv_v_iface_disable,
- .bat_iface_update_mac = batadv_v_iface_update_mac,
- .bat_primary_iface_set = batadv_v_primary_iface_set,
- .bat_hardif_neigh_init = batadv_v_hardif_neigh_init,
- .bat_ogm_emit = batadv_v_ogm_emit,
- .bat_ogm_schedule = batadv_v_ogm_schedule,
- .bat_orig_print = batadv_v_orig_print,
- .bat_neigh_cmp = batadv_v_neigh_cmp,
- .bat_neigh_is_similar_or_better = batadv_v_neigh_is_sob,
- .bat_neigh_print = batadv_v_neigh_print,
+ .iface = {
+ .activate = batadv_v_iface_activate,
+ .enable = batadv_v_iface_enable,
+ .disable = batadv_v_iface_disable,
+ .update_mac = batadv_v_iface_update_mac,
+ .primary_set = batadv_v_primary_iface_set,
+ },
+ .neigh = {
+ .hardif_init = batadv_v_hardif_neigh_init,
+ .cmp = batadv_v_neigh_cmp,
+ .is_similar_or_better = batadv_v_neigh_is_sob,
+ .print = batadv_v_neigh_print,
+ },
+ .orig = {
+ .print = batadv_v_orig_print,
+ },
};
/**
+ * batadv_v_hardif_init - initialize the algorithm specific fields in the
+ * hard-interface object
+ * @hard_iface: the hard-interface to initialize
+ */
+void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface)
+{
+ /* enable link throughput auto-detection by setting the throughput
+ * override to zero
+ */
+ atomic_set(&hard_iface->bat_v.throughput_override, 0);
+ atomic_set(&hard_iface->bat_v.elp_interval, 500);
+}
+
+/**
* batadv_v_mesh_init - initialize the B.A.T.M.A.N. V private resources for a
* mesh
* @bat_priv: the object representing the mesh interface to initialise
diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h
new file mode 100644
index 000000000000..83b77639729e
--- /dev/null
+++ b/net/batman-adv/bat_v.h
@@ -0,0 +1,52 @@
+/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Linus Lüssing
+ *
+ * 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/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_BAT_V_H_
+#define _NET_BATMAN_ADV_BAT_V_H_
+
+#include "main.h"
+
+#ifdef CONFIG_BATMAN_ADV_BATMAN_V
+
+int batadv_v_init(void);
+void batadv_v_hardif_init(struct batadv_hard_iface *hardif);
+int batadv_v_mesh_init(struct batadv_priv *bat_priv);
+void batadv_v_mesh_free(struct batadv_priv *bat_priv);
+
+#else
+
+static inline int batadv_v_init(void)
+{
+ return 0;
+}
+
+static inline void batadv_v_hardif_init(struct batadv_hard_iface *hardif)
+{
+}
+
+static inline int batadv_v_mesh_init(struct batadv_priv *bat_priv)
+{
+ return 0;
+}
+
+static inline void batadv_v_mesh_free(struct batadv_priv *bat_priv)
+{
+}
+
+#endif /* CONFIG_BATMAN_ADV_BATMAN_V */
+
+#endif /* _NET_BATMAN_ADV_BAT_V_H_ */
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index df42eb1365a0..7d170010beb9 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -43,6 +43,7 @@
#include "bat_algo.h"
#include "bat_v_ogm.h"
#include "hard-interface.h"
+#include "log.h"
#include "originator.h"
#include "packet.h"
#include "routing.h"
@@ -344,7 +345,6 @@ int batadv_v_elp_iface_enable(struct batadv_hard_iface *hard_iface)
/* randomize initial seqno to avoid collision */
get_random_bytes(&random_seqno, sizeof(random_seqno));
atomic_set(&hard_iface->bat_v.elp_seqno, random_seqno);
- atomic_set(&hard_iface->bat_v.elp_interval, 500);
/* assume full-duplex by default */
hard_iface->bat_v.flags |= BATADV_FULL_DUPLEX;
@@ -443,7 +443,8 @@ static void batadv_v_elp_neigh_update(struct batadv_priv *bat_priv,
if (!orig_neigh)
return;
- neigh = batadv_neigh_node_new(orig_neigh, if_incoming, neigh_addr);
+ neigh = batadv_neigh_node_get_or_create(orig_neigh,
+ if_incoming, neigh_addr);
if (!neigh)
goto orig_free;
@@ -503,7 +504,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb,
/* did we receive a B.A.T.M.A.N. V ELP packet on an interface
* that does not have B.A.T.M.A.N. V ELP enabled ?
*/
- if (strcmp(bat_priv->bat_algo_ops->name, "BATMAN_V") != 0)
+ if (strcmp(bat_priv->algo_ops->name, "BATMAN_V") != 0)
return NET_RX_DROP;
elp_packet = (struct batadv_elp_packet *)skb->data;
diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h
index cc130b2d05e5..be17c0b1369e 100644
--- a/net/batman-adv/bat_v_elp.h
+++ b/net/batman-adv/bat_v_elp.h
@@ -15,11 +15,11 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
-#include "main.h"
-
#ifndef _NET_BATMAN_ADV_BAT_V_ELP_H_
#define _NET_BATMAN_ADV_BAT_V_ELP_H_
+#include "main.h"
+
struct sk_buff;
struct work_struct;
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 473ebb9a0e73..6fbba4eb0617 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -39,13 +39,16 @@
#include <linux/types.h>
#include <linux/workqueue.h>
+#include "bat_algo.h"
#include "hard-interface.h"
#include "hash.h"
+#include "log.h"
#include "originator.h"
#include "packet.h"
#include "routing.h"
#include "send.h"
#include "translation-table.h"
+#include "tvlv.h"
/**
* batadv_v_ogm_orig_get - retrieve and possibly create an originator node
@@ -683,8 +686,8 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset,
if (!orig_node)
return;
- neigh_node = batadv_neigh_node_new(orig_node, if_incoming,
- ethhdr->h_source);
+ neigh_node = batadv_neigh_node_get_or_create(orig_node, if_incoming,
+ ethhdr->h_source);
if (!neigh_node)
goto out;
@@ -751,7 +754,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb,
/* did we receive a OGM2 packet on an interface that does not have
* B.A.T.M.A.N. V enabled ?
*/
- if (strcmp(bat_priv->bat_algo_ops->name, "BATMAN_V") != 0)
+ if (strcmp(bat_priv->algo_ops->name, "BATMAN_V") != 0)
return NET_RX_DROP;
if (!batadv_check_management_packet(skb, if_incoming, BATADV_OGM2_HLEN))
diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h
index d849c75ada0e..4c4d45caa422 100644
--- a/net/batman-adv/bat_v_ogm.h
+++ b/net/batman-adv/bat_v_ogm.h
@@ -18,10 +18,10 @@
#ifndef _BATMAN_ADV_BATADV_V_OGM_H_
#define _BATMAN_ADV_BATADV_V_OGM_H_
+#include "main.h"
+
#include <linux/types.h>
-struct batadv_hard_iface;
-struct batadv_priv;
struct sk_buff;
int batadv_v_ogm_init(struct batadv_priv *bat_priv);
diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c
index a0c7913837a5..032271421a20 100644
--- a/net/batman-adv/bitarray.c
+++ b/net/batman-adv/bitarray.c
@@ -20,6 +20,8 @@
#include <linux/bitmap.h>
+#include "log.h"
+
/* shift the packet array by n places. */
static void batadv_bitmap_shift_left(unsigned long *seq_bits, s32 n)
{
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 825a5cdf4382..ad2ffe16d29f 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -48,6 +48,7 @@
#include "hard-interface.h"
#include "hash.h"
+#include "log.h"
#include "originator.h"
#include "packet.h"
#include "sysfs.h"
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index 952900466d88..1d68b6e63b96 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -18,245 +18,33 @@
#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 "bat_algo.h"
#include "bridge_loop_avoidance.h"
#include "distributed-arp-table.h"
#include "gateway_client.h"
#include "icmp_socket.h"
+#include "log.h"
+#include "multicast.h"
#include "network-coding.h"
#include "originator.h"
#include "translation-table.h"
static struct dentry *batadv_debugfs;
-#ifdef CONFIG_BATMAN_ADV_DEBUG
-#define BATADV_LOG_BUFF_MASK (batadv_log_buff_len - 1)
-
-static const int batadv_log_buff_len = BATADV_LOG_BUF_LEN;
-
-static char *batadv_log_char_addr(struct batadv_priv_debug_log *debug_log,
- size_t idx)
-{
- return &debug_log->log_buff[idx & BATADV_LOG_BUFF_MASK];
-}
-
-static void batadv_emit_log_char(struct batadv_priv_debug_log *debug_log,
- char c)
-{
- char *char_addr;
-
- char_addr = batadv_log_char_addr(debug_log, debug_log->log_end);
- *char_addr = c;
- debug_log->log_end++;
-
- if (debug_log->log_end - debug_log->log_start > batadv_log_buff_len)
- debug_log->log_start = debug_log->log_end - batadv_log_buff_len;
-}
-
-__printf(2, 3)
-static int batadv_fdebug_log(struct batadv_priv_debug_log *debug_log,
- const char *fmt, ...)
-{
- va_list args;
- static char debug_log_buf[256];
- char *p;
-
- if (!debug_log)
- return 0;
-
- spin_lock_bh(&debug_log->lock);
- va_start(args, fmt);
- vscnprintf(debug_log_buf, sizeof(debug_log_buf), fmt, args);
- va_end(args);
-
- for (p = debug_log_buf; *p != 0; p++)
- batadv_emit_log_char(debug_log, *p);
-
- spin_unlock_bh(&debug_log->lock);
-
- wake_up(&debug_log->queue_wait);
-
- return 0;
-}
-
-int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
-{
- va_list args;
- char tmp_log_buf[256];
-
- va_start(args, fmt);
- vscnprintf(tmp_log_buf, sizeof(tmp_log_buf), fmt, args);
- batadv_fdebug_log(bat_priv->debug_log, "[%10u] %s",
- jiffies_to_msecs(jiffies), tmp_log_buf);
- va_end(args);
-
- return 0;
-}
-
-static int batadv_log_open(struct inode *inode, struct file *file)
-{
- if (!try_module_get(THIS_MODULE))
- return -EBUSY;
-
- nonseekable_open(inode, file);
- file->private_data = inode->i_private;
- return 0;
-}
-
-static int batadv_log_release(struct inode *inode, struct file *file)
-{
- module_put(THIS_MODULE);
- return 0;
-}
-
-static bool batadv_log_empty(struct batadv_priv_debug_log *debug_log)
-{
- return !(debug_log->log_start - debug_log->log_end);
-}
-
-static ssize_t batadv_log_read(struct file *file, char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct batadv_priv *bat_priv = file->private_data;
- struct batadv_priv_debug_log *debug_log = bat_priv->debug_log;
- int error, i = 0;
- char *char_addr;
- char c;
-
- if ((file->f_flags & O_NONBLOCK) && batadv_log_empty(debug_log))
- return -EAGAIN;
-
- if (!buf)
- return -EINVAL;
-
- if (count == 0)
- return 0;
-
- if (!access_ok(VERIFY_WRITE, buf, count))
- return -EFAULT;
-
- error = wait_event_interruptible(debug_log->queue_wait,
- (!batadv_log_empty(debug_log)));
-
- if (error)
- return error;
-
- spin_lock_bh(&debug_log->lock);
-
- while ((!error) && (i < count) &&
- (debug_log->log_start != debug_log->log_end)) {
- char_addr = batadv_log_char_addr(debug_log,
- debug_log->log_start);
- c = *char_addr;
-
- debug_log->log_start++;
-
- spin_unlock_bh(&debug_log->lock);
-
- error = __put_user(c, buf);
-
- spin_lock_bh(&debug_log->lock);
-
- buf++;
- i++;
- }
-
- spin_unlock_bh(&debug_log->lock);
-
- if (!error)
- return i;
-
- return error;
-}
-
-static unsigned int batadv_log_poll(struct file *file, poll_table *wait)
-{
- struct batadv_priv *bat_priv = file->private_data;
- struct batadv_priv_debug_log *debug_log = bat_priv->debug_log;
-
- poll_wait(file, &debug_log->queue_wait, wait);
-
- if (!batadv_log_empty(debug_log))
- return POLLIN | POLLRDNORM;
-
- return 0;
-}
-
-static const struct file_operations batadv_log_fops = {
- .open = batadv_log_open,
- .release = batadv_log_release,
- .read = batadv_log_read,
- .poll = batadv_log_poll,
- .llseek = no_llseek,
-};
-
-static int batadv_debug_log_setup(struct batadv_priv *bat_priv)
-{
- struct dentry *d;
-
- if (!bat_priv->debug_dir)
- goto err;
-
- bat_priv->debug_log = kzalloc(sizeof(*bat_priv->debug_log), GFP_ATOMIC);
- if (!bat_priv->debug_log)
- goto err;
-
- spin_lock_init(&bat_priv->debug_log->lock);
- init_waitqueue_head(&bat_priv->debug_log->queue_wait);
-
- d = debugfs_create_file("log", S_IFREG | S_IRUSR,
- bat_priv->debug_dir, bat_priv,
- &batadv_log_fops);
- if (!d)
- goto err;
-
- return 0;
-
-err:
- return -ENOMEM;
-}
-
-static void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
-{
- kfree(bat_priv->debug_log);
- bat_priv->debug_log = NULL;
-}
-#else /* CONFIG_BATMAN_ADV_DEBUG */
-static int batadv_debug_log_setup(struct batadv_priv *bat_priv)
-{
- return 0;
-}
-
-static void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
-{
-}
-#endif
-
static int batadv_algorithms_open(struct inode *inode, struct file *file)
{
return single_open(file, batadv_algo_seq_print_text, NULL);
@@ -363,6 +151,22 @@ static int batadv_nc_nodes_open(struct inode *inode, struct file *file)
}
#endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+/**
+ * batadv_mcast_flags_open - prepare file handler for reads from mcast_flags
+ * @inode: inode which was opened
+ * @file: file handle to be initialized
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+static int batadv_mcast_flags_open(struct inode *inode, struct file *file)
+{
+ struct net_device *net_dev = (struct net_device *)inode->i_private;
+
+ return single_open(file, batadv_mcast_flags_seq_print_text, net_dev);
+}
+#endif
+
#define BATADV_DEBUGINFO(_name, _mode, _open) \
struct batadv_debuginfo batadv_debuginfo_##_name = { \
.attr = { \
@@ -407,6 +211,9 @@ static BATADV_DEBUGINFO(transtable_local, S_IRUGO,
#ifdef CONFIG_BATMAN_ADV_NC
static BATADV_DEBUGINFO(nc_nodes, S_IRUGO, batadv_nc_nodes_open);
#endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+static BATADV_DEBUGINFO(mcast_flags, S_IRUGO, batadv_mcast_flags_open);
+#endif
static struct batadv_debuginfo *batadv_mesh_debuginfos[] = {
&batadv_debuginfo_neighbors,
@@ -424,6 +231,9 @@ static struct batadv_debuginfo *batadv_mesh_debuginfos[] = {
#ifdef CONFIG_BATMAN_ADV_NC
&batadv_debuginfo_nc_nodes,
#endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+ &batadv_debuginfo_mcast_flags,
+#endif
NULL,
};
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index aee3b3991471..b1cc8bfe11ac 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -45,9 +45,11 @@
#include "hard-interface.h"
#include "hash.h"
+#include "log.h"
#include "originator.h"
#include "send.h"
#include "translation-table.h"
+#include "tvlv.h"
static void batadv_dat_purge(struct work_struct *work);
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 65536db1bff7..0934730fb7ff 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -27,7 +27,6 @@
#include <linux/kernel.h>
#include <linux/lockdep.h>
#include <linux/netdevice.h>
-#include <linux/pkt_sched.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
@@ -414,7 +413,7 @@ static struct sk_buff *batadv_frag_create(struct sk_buff *skb,
if (!skb_fragment)
goto err;
- skb->priority = TC_PRIO_CONTROL;
+ skb_fragment->priority = skb->priority;
/* Eat the last mtu-bytes of the skb */
skb_reserve(skb_fragment, header_size + ETH_HLEN);
@@ -434,11 +433,12 @@ err:
* @orig_node: final destination of the created fragments
* @neigh_node: next-hop of the created fragments
*
- * Return: true on success, false otherwise.
+ * Return: the netdev tx status or -1 in case of error.
+ * When -1 is returned the skb is not consumed.
*/
-bool batadv_frag_send_packet(struct sk_buff *skb,
- struct batadv_orig_node *orig_node,
- struct batadv_neigh_node *neigh_node)
+int batadv_frag_send_packet(struct sk_buff *skb,
+ struct batadv_orig_node *orig_node,
+ struct batadv_neigh_node *neigh_node)
{
struct batadv_priv *bat_priv;
struct batadv_hard_iface *primary_if = NULL;
@@ -447,7 +447,7 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
unsigned int mtu = neigh_node->if_incoming->net_dev->mtu;
unsigned int header_size = sizeof(frag_header);
unsigned int max_fragment_size, max_packet_size;
- bool ret = false;
+ int ret = -1;
/* To avoid merge and refragmentation at next-hops we never send
* fragments larger than BATADV_FRAG_MAX_FRAG_SIZE
@@ -458,12 +458,12 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
/* Don't even try to fragment, if we need more than 16 fragments */
if (skb->len > max_packet_size)
- goto out_err;
+ goto out;
bat_priv = orig_node->bat_priv;
primary_if = batadv_primary_if_get_selected(bat_priv);
if (!primary_if)
- goto out_err;
+ goto out;
/* Create one header to be copied to all fragments */
frag_header.packet_type = BATADV_UNICAST_FRAG;
@@ -473,6 +473,15 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
frag_header.reserved = 0;
frag_header.no = 0;
frag_header.total_size = htons(skb->len);
+
+ /* skb->priority values from 256->263 are magic values to
+ * directly indicate a specific 802.1d priority. This is used
+ * to allow 802.1d priority to be passed directly in from VLAN
+ * tags, etc.
+ */
+ if (skb->priority >= 256 && skb->priority <= 263)
+ frag_header.priority = skb->priority - 256;
+
ether_addr_copy(frag_header.orig, primary_if->net_dev->dev_addr);
ether_addr_copy(frag_header.dest, orig_node->orig);
@@ -480,23 +489,33 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
while (skb->len > max_fragment_size) {
skb_fragment = batadv_frag_create(skb, &frag_header, mtu);
if (!skb_fragment)
- goto out_err;
+ goto out;
batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_TX);
batadv_add_counter(bat_priv, BATADV_CNT_FRAG_TX_BYTES,
skb_fragment->len + ETH_HLEN);
- batadv_send_unicast_skb(skb_fragment, neigh_node);
+ ret = batadv_send_unicast_skb(skb_fragment, neigh_node);
+ if (ret != NET_XMIT_SUCCESS) {
+ /* return -1 so that the caller can free the original
+ * skb
+ */
+ ret = -1;
+ goto out;
+ }
+
frag_header.no++;
/* The initial check in this function should cover this case */
- if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1)
- goto out_err;
+ if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1) {
+ ret = -1;
+ goto out;
+ }
}
/* Make room for the fragment header. */
if (batadv_skb_head_push(skb, header_size) < 0 ||
pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0)
- goto out_err;
+ goto out;
memcpy(skb->data, &frag_header, header_size);
@@ -504,11 +523,9 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_TX);
batadv_add_counter(bat_priv, BATADV_CNT_FRAG_TX_BYTES,
skb->len + ETH_HLEN);
- batadv_send_unicast_skb(skb, neigh_node);
-
- ret = true;
+ ret = batadv_send_unicast_skb(skb, neigh_node);
-out_err:
+out:
if (primary_if)
batadv_hardif_put(primary_if);
diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h
index 9ff77c7ef7c7..3202fe329e63 100644
--- a/net/batman-adv/fragmentation.h
+++ b/net/batman-adv/fragmentation.h
@@ -34,9 +34,9 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
struct batadv_orig_node *orig_node_src);
bool batadv_frag_skb_buffer(struct sk_buff **skb,
struct batadv_orig_node *orig_node);
-bool batadv_frag_send_packet(struct sk_buff *skb,
- struct batadv_orig_node *orig_node,
- struct batadv_neigh_node *neigh_node);
+int batadv_frag_send_packet(struct sk_buff *skb,
+ struct batadv_orig_node *orig_node,
+ struct batadv_neigh_node *neigh_node);
/**
* batadv_frag_check_entry - check if a list of fragments has timed out
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 5839c569f769..63a805d3f96e 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -42,6 +42,7 @@
#include "gateway_common.h"
#include "hard-interface.h"
+#include "log.h"
#include "originator.h"
#include "packet.h"
#include "routing.h"
@@ -192,7 +193,7 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv)
tq_avg = router_ifinfo->bat_iv.tq_avg;
- switch (atomic_read(&bat_priv->gw_sel_class)) {
+ switch (atomic_read(&bat_priv->gw.sel_class)) {
case 1: /* fast connection */
tmp_gw_factor = tq_avg * tq_avg;
tmp_gw_factor *= gw_node->bandwidth_down;
@@ -255,7 +256,7 @@ void batadv_gw_check_client_stop(struct batadv_priv *bat_priv)
{
struct batadv_gw_node *curr_gw;
- if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_CLIENT)
+ if (atomic_read(&bat_priv->gw.mode) != BATADV_GW_MODE_CLIENT)
return;
curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
@@ -283,7 +284,7 @@ void batadv_gw_election(struct batadv_priv *bat_priv)
struct batadv_neigh_ifinfo *router_ifinfo = NULL;
char gw_addr[18] = { '\0' };
- if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_CLIENT)
+ if (atomic_read(&bat_priv->gw.mode) != BATADV_GW_MODE_CLIENT)
goto out;
curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
@@ -402,8 +403,8 @@ void batadv_gw_check_election(struct batadv_priv *bat_priv,
/* if the routing class is greater than 3 the value tells us how much
* greater the TQ value of the new gateway must be
*/
- if ((atomic_read(&bat_priv->gw_sel_class) > 3) &&
- (orig_tq_avg - gw_tq_avg < atomic_read(&bat_priv->gw_sel_class)))
+ if ((atomic_read(&bat_priv->gw.sel_class) > 3) &&
+ (orig_tq_avg - gw_tq_avg < atomic_read(&bat_priv->gw.sel_class)))
goto out;
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
@@ -638,8 +639,7 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset)
goto out;
seq_printf(seq,
- " %-12s (%s/%i) %17s [%10s]: advertised uplink bandwidth ... [B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n",
- "Gateway", "#", BATADV_TQ_MAX_VALUE, "Nexthop", "outgoingIF",
+ " Gateway (#/255) Nexthop [outgoingIF]: advertised uplink bandwidth ... [B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n",
BATADV_SOURCE_VERSION, primary_if->net_dev->name,
primary_if->net_dev->dev_addr, net_dev->name);
@@ -821,7 +821,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
if (!gw_node)
goto out;
- switch (atomic_read(&bat_priv->gw_mode)) {
+ switch (atomic_read(&bat_priv->gw.mode)) {
case BATADV_GW_MODE_SERVER:
/* If we are a GW then we are our best GW. We can artificially
* set the tq towards ourself as the maximum value
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 4423047889e1..d7bc6a87bcc9 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -19,8 +19,8 @@
#include "main.h"
#include <linux/atomic.h>
-#include <linux/errno.h>
#include <linux/byteorder/generic.h>
+#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/math64.h>
#include <linux/netdevice.h>
@@ -28,7 +28,9 @@
#include <linux/string.h>
#include "gateway_client.h"
+#include "log.h"
#include "packet.h"
+#include "tvlv.h"
/**
* batadv_parse_throughput - parse supplied string buffer to extract throughput
@@ -144,7 +146,7 @@ void batadv_gw_tvlv_container_update(struct batadv_priv *bat_priv)
u32 down, up;
char gw_mode;
- gw_mode = atomic_read(&bat_priv->gw_mode);
+ gw_mode = atomic_read(&bat_priv->gw.mode);
switch (gw_mode) {
case BATADV_GW_MODE_OFF:
@@ -241,8 +243,8 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
/* restart gateway selection if fast or late switching was enabled */
if ((gateway.bandwidth_down != 0) &&
- (atomic_read(&bat_priv->gw_mode) == BATADV_GW_MODE_CLIENT) &&
- (atomic_read(&bat_priv->gw_sel_class) > 2))
+ (atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT) &&
+ (atomic_read(&bat_priv->gw.sel_class) > 2))
batadv_gw_check_election(bat_priv, orig);
}
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 8c2f39962fa5..1f9080840566 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -23,9 +23,9 @@
#include <linux/byteorder/generic.h>
#include <linux/errno.h>
#include <linux/fs.h>
+#include <linux/if.h>
#include <linux/if_arp.h>
#include <linux/if_ether.h>
-#include <linux/if.h>
#include <linux/kernel.h>
#include <linux/kref.h>
#include <linux/list.h>
@@ -37,10 +37,12 @@
#include <linux/spinlock.h>
#include <linux/workqueue.h>
+#include "bat_v.h"
#include "bridge_loop_avoidance.h"
#include "debugfs.h"
#include "distributed-arp-table.h"
#include "gateway_client.h"
+#include "log.h"
#include "originator.h"
#include "packet.h"
#include "send.h"
@@ -245,7 +247,7 @@ static void batadv_primary_if_select(struct batadv_priv *bat_priv,
if (!new_hard_iface)
goto out;
- bat_priv->bat_algo_ops->bat_primary_iface_set(new_hard_iface);
+ bat_priv->algo_ops->iface.primary_set(new_hard_iface);
batadv_primary_if_update_addr(bat_priv, curr_hard_iface);
out:
@@ -392,7 +394,7 @@ batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface)
bat_priv = netdev_priv(hard_iface->soft_iface);
- bat_priv->bat_algo_ops->bat_iface_update_mac(hard_iface);
+ bat_priv->algo_ops->iface.update_mac(hard_iface);
hard_iface->if_status = BATADV_IF_TO_BE_ACTIVATED;
/* the first active interface becomes our primary interface or
@@ -407,8 +409,8 @@ batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface)
batadv_update_min_mtu(hard_iface->soft_iface);
- if (bat_priv->bat_algo_ops->bat_iface_activate)
- bat_priv->bat_algo_ops->bat_iface_activate(hard_iface);
+ if (bat_priv->algo_ops->iface.activate)
+ bat_priv->algo_ops->iface.activate(hard_iface);
out:
if (primary_if)
@@ -506,7 +508,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
if (ret)
goto err_dev;
- ret = bat_priv->bat_algo_ops->bat_iface_enable(hard_iface);
+ ret = bat_priv->algo_ops->iface.enable(hard_iface);
if (ret < 0)
goto err_upper;
@@ -515,7 +517,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
hard_iface->if_status = BATADV_IF_INACTIVE;
ret = batadv_orig_hash_add_if(hard_iface, bat_priv->num_ifaces);
if (ret < 0) {
- bat_priv->bat_algo_ops->bat_iface_disable(hard_iface);
+ bat_priv->algo_ops->iface.disable(hard_iface);
bat_priv->num_ifaces--;
hard_iface->if_status = BATADV_IF_NOT_IN_USE;
goto err_upper;
@@ -553,9 +555,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
batadv_hardif_recalc_extra_skbroom(soft_iface);
- /* begin scheduling originator messages on that interface */
- batadv_schedule_bat_ogm(hard_iface);
-
out:
return 0;
@@ -599,7 +598,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface,
batadv_hardif_put(new_if);
}
- bat_priv->bat_algo_ops->bat_iface_disable(hard_iface);
+ bat_priv->algo_ops->iface.disable(hard_iface);
hard_iface->if_status = BATADV_IF_NOT_IN_USE;
/* delete all references to this hard_iface */
@@ -686,6 +685,8 @@ batadv_hardif_add_interface(struct net_device *net_dev)
if (batadv_is_wifi_netdev(net_dev))
hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS;
+ batadv_v_hardif_init(hard_iface);
+
/* extra reference for return */
kref_init(&hard_iface->refcount);
kref_get(&hard_iface->refcount);
@@ -782,7 +783,7 @@ static int batadv_hard_if_event(struct notifier_block *this,
batadv_check_known_mac_addr(hard_iface->net_dev);
bat_priv = netdev_priv(hard_iface->soft_iface);
- bat_priv->bat_algo_ops->bat_iface_update_mac(hard_iface);
+ bat_priv->algo_ops->iface.update_mac(hard_iface);
primary_if = batadv_primary_if_get_selected(bat_priv);
if (!primary_if)
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 777aea10cd8f..378cc1119d66 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -45,6 +45,7 @@
#include <linux/wait.h>
#include "hard-interface.h"
+#include "log.h"
#include "originator.h"
#include "packet.h"
#include "send.h"
diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c
new file mode 100644
index 000000000000..56dc532f7a2c
--- /dev/null
+++ b/net/batman-adv/log.c
@@ -0,0 +1,231 @@
+/* Copyright (C) 2010-2016 B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner
+ *
+ * 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/>.
+ */
+
+#include "log.h"
+#include "main.h"
+
+#include <linux/compiler.h>
+#include <linux/debugfs.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/poll.h>
+#include <linux/sched.h> /* for linux/wait.h */
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/wait.h>
+#include <stdarg.h>
+
+#define BATADV_LOG_BUFF_MASK (batadv_log_buff_len - 1)
+
+static const int batadv_log_buff_len = BATADV_LOG_BUF_LEN;
+
+static char *batadv_log_char_addr(struct batadv_priv_debug_log *debug_log,
+ size_t idx)
+{
+ return &debug_log->log_buff[idx & BATADV_LOG_BUFF_MASK];
+}
+
+static void batadv_emit_log_char(struct batadv_priv_debug_log *debug_log,
+ char c)
+{
+ char *char_addr;
+
+ char_addr = batadv_log_char_addr(debug_log, debug_log->log_end);
+ *char_addr = c;
+ debug_log->log_end++;
+
+ if (debug_log->log_end - debug_log->log_start > batadv_log_buff_len)
+ debug_log->log_start = debug_log->log_end - batadv_log_buff_len;
+}
+
+__printf(2, 3)
+static int batadv_fdebug_log(struct batadv_priv_debug_log *debug_log,
+ const char *fmt, ...)
+{
+ va_list args;
+ static char debug_log_buf[256];
+ char *p;
+
+ if (!debug_log)
+ return 0;
+
+ spin_lock_bh(&debug_log->lock);
+ va_start(args, fmt);
+ vscnprintf(debug_log_buf, sizeof(debug_log_buf), fmt, args);
+ va_end(args);
+
+ for (p = debug_log_buf; *p != 0; p++)
+ batadv_emit_log_char(debug_log, *p);
+
+ spin_unlock_bh(&debug_log->lock);
+
+ wake_up(&debug_log->queue_wait);
+
+ return 0;
+}
+
+int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
+{
+ va_list args;
+ char tmp_log_buf[256];
+
+ va_start(args, fmt);
+ vscnprintf(tmp_log_buf, sizeof(tmp_log_buf), fmt, args);
+ batadv_fdebug_log(bat_priv->debug_log, "[%10u] %s",
+ jiffies_to_msecs(jiffies), tmp_log_buf);
+ va_end(args);
+
+ return 0;
+}
+
+static int batadv_log_open(struct inode *inode, struct file *file)
+{
+ if (!try_module_get(THIS_MODULE))
+ return -EBUSY;
+
+ nonseekable_open(inode, file);
+ file->private_data = inode->i_private;
+ return 0;
+}
+
+static int batadv_log_release(struct inode *inode, struct file *file)
+{
+ module_put(THIS_MODULE);
+ return 0;
+}
+
+static bool batadv_log_empty(struct batadv_priv_debug_log *debug_log)
+{
+ return !(debug_log->log_start - debug_log->log_end);
+}
+
+static ssize_t batadv_log_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct batadv_priv *bat_priv = file->private_data;
+ struct batadv_priv_debug_log *debug_log = bat_priv->debug_log;
+ int error, i = 0;
+ char *char_addr;
+ char c;
+
+ if ((file->f_flags & O_NONBLOCK) && batadv_log_empty(debug_log))
+ return -EAGAIN;
+
+ if (!buf)
+ return -EINVAL;
+
+ if (count == 0)
+ return 0;
+
+ if (!access_ok(VERIFY_WRITE, buf, count))
+ return -EFAULT;
+
+ error = wait_event_interruptible(debug_log->queue_wait,
+ (!batadv_log_empty(debug_log)));
+
+ if (error)
+ return error;
+
+ spin_lock_bh(&debug_log->lock);
+
+ while ((!error) && (i < count) &&
+ (debug_log->log_start != debug_log->log_end)) {
+ char_addr = batadv_log_char_addr(debug_log,
+ debug_log->log_start);
+ c = *char_addr;
+
+ debug_log->log_start++;
+
+ spin_unlock_bh(&debug_log->lock);
+
+ error = __put_user(c, buf);
+
+ spin_lock_bh(&debug_log->lock);
+
+ buf++;
+ i++;
+ }
+
+ spin_unlock_bh(&debug_log->lock);
+
+ if (!error)
+ return i;
+
+ return error;
+}
+
+static unsigned int batadv_log_poll(struct file *file, poll_table *wait)
+{
+ struct batadv_priv *bat_priv = file->private_data;
+ struct batadv_priv_debug_log *debug_log = bat_priv->debug_log;
+
+ poll_wait(file, &debug_log->queue_wait, wait);
+
+ if (!batadv_log_empty(debug_log))
+ return POLLIN | POLLRDNORM;
+
+ return 0;
+}
+
+static const struct file_operations batadv_log_fops = {
+ .open = batadv_log_open,
+ .release = batadv_log_release,
+ .read = batadv_log_read,
+ .poll = batadv_log_poll,
+ .llseek = no_llseek,
+};
+
+int batadv_debug_log_setup(struct batadv_priv *bat_priv)
+{
+ struct dentry *d;
+
+ if (!bat_priv->debug_dir)
+ goto err;
+
+ bat_priv->debug_log = kzalloc(sizeof(*bat_priv->debug_log), GFP_ATOMIC);
+ if (!bat_priv->debug_log)
+ goto err;
+
+ spin_lock_init(&bat_priv->debug_log->lock);
+ init_waitqueue_head(&bat_priv->debug_log->queue_wait);
+
+ d = debugfs_create_file("log", S_IFREG | S_IRUSR,
+ bat_priv->debug_dir, bat_priv,
+ &batadv_log_fops);
+ if (!d)
+ goto err;
+
+ return 0;
+
+err:
+ return -ENOMEM;
+}
+
+void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
+{
+ kfree(bat_priv->debug_log);
+ bat_priv->debug_log = NULL;
+}
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
new file mode 100644
index 000000000000..e0e1a88c3e58
--- /dev/null
+++ b/net/batman-adv/log.h
@@ -0,0 +1,111 @@
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ *
+ * 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/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_LOG_H_
+#define _NET_BATMAN_ADV_LOG_H_
+
+#include "main.h"
+
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/printk.h>
+
+#ifdef CONFIG_BATMAN_ADV_DEBUG
+
+int batadv_debug_log_setup(struct batadv_priv *bat_priv);
+void batadv_debug_log_cleanup(struct batadv_priv *bat_priv);
+
+#else
+
+static inline int batadv_debug_log_setup(struct batadv_priv *bat_priv)
+{
+ return 0;
+}
+
+static inline void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
+{
+}
+
+#endif
+
+/**
+ * enum batadv_dbg_level - available log levels
+ * @BATADV_DBG_BATMAN: OGM and TQ computations related messages
+ * @BATADV_DBG_ROUTES: route added / changed / deleted
+ * @BATADV_DBG_TT: translation table messages
+ * @BATADV_DBG_BLA: bridge loop avoidance messages
+ * @BATADV_DBG_DAT: ARP snooping and DAT related messages
+ * @BATADV_DBG_NC: network coding related messages
+ * @BATADV_DBG_MCAST: multicast related messages
+ * @BATADV_DBG_TP_METER: throughput meter messages
+ * @BATADV_DBG_ALL: the union of all the above log levels
+ */
+enum batadv_dbg_level {
+ BATADV_DBG_BATMAN = BIT(0),
+ BATADV_DBG_ROUTES = BIT(1),
+ BATADV_DBG_TT = BIT(2),
+ BATADV_DBG_BLA = BIT(3),
+ BATADV_DBG_DAT = BIT(4),
+ BATADV_DBG_NC = BIT(5),
+ BATADV_DBG_MCAST = BIT(6),
+ BATADV_DBG_TP_METER = BIT(7),
+ BATADV_DBG_ALL = 127,
+};
+
+#ifdef CONFIG_BATMAN_ADV_DEBUG
+int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
+__printf(2, 3);
+
+/* possibly ratelimited debug output */
+#define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...) \
+ do { \
+ if (atomic_read(&bat_priv->log_level) & type && \
+ (!ratelimited || net_ratelimit())) \
+ batadv_debug_log(bat_priv, fmt, ## arg);\
+ } \
+ while (0)
+#else /* !CONFIG_BATMAN_ADV_DEBUG */
+__printf(4, 5)
+static inline void _batadv_dbg(int type __always_unused,
+ struct batadv_priv *bat_priv __always_unused,
+ int ratelimited __always_unused,
+ const char *fmt __always_unused, ...)
+{
+}
+#endif
+
+#define batadv_dbg(type, bat_priv, arg...) \
+ _batadv_dbg(type, bat_priv, 0, ## arg)
+#define batadv_dbg_ratelimited(type, bat_priv, arg...) \
+ _batadv_dbg(type, bat_priv, 1, ## arg)
+
+#define batadv_info(net_dev, fmt, arg...) \
+ do { \
+ struct net_device *_netdev = (net_dev); \
+ struct batadv_priv *_batpriv = netdev_priv(_netdev); \
+ batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg); \
+ pr_info("%s: " fmt, _netdev->name, ## arg); \
+ } while (0)
+#define batadv_err(net_dev, fmt, arg...) \
+ do { \
+ struct net_device *_netdev = (net_dev); \
+ struct batadv_priv *_batpriv = netdev_priv(_netdev); \
+ batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg); \
+ pr_err("%s: " fmt, _netdev->name, ## arg); \
+ } while (0)
+
+#endif /* _NET_BATMAN_ADV_LOG_H_ */
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 5f2974bd1227..fe4c5e29f96b 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -31,16 +31,13 @@
#include <linux/kernel.h>
#include <linux/kref.h>
#include <linux/list.h>
-#include <linux/lockdep.h>
#include <linux/module.h>
-#include <linux/moduleparam.h>
#include <linux/netdevice.h>
-#include <linux/pkt_sched.h>
+#include <linux/printk.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>
@@ -49,6 +46,8 @@
#include <net/rtnetlink.h>
#include "bat_algo.h"
+#include "bat_iv_ogm.h"
+#include "bat_v.h"
#include "bridge_loop_avoidance.h"
#include "debugfs.h"
#include "distributed-arp-table.h"
@@ -56,13 +55,16 @@
#include "gateway_common.h"
#include "hard-interface.h"
#include "icmp_socket.h"
+#include "log.h"
#include "multicast.h"
+#include "netlink.h"
#include "network-coding.h"
#include "originator.h"
#include "packet.h"
#include "routing.h"
#include "send.h"
#include "soft-interface.h"
+#include "tp_meter.h"
#include "translation-table.h"
/* List manipulations on hardif_list have to be rtnl_lock()'ed,
@@ -71,8 +73,6 @@
struct list_head batadv_hardif_list;
static int (*batadv_rx_handler[256])(struct sk_buff *,
struct batadv_hard_iface *);
-char batadv_routing_algo[20] = "BATMAN_IV";
-static struct hlist_head batadv_algo_list;
unsigned char batadv_broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
@@ -83,13 +83,14 @@ static void batadv_recv_handler_init(void);
static int __init batadv_init(void)
{
INIT_LIST_HEAD(&batadv_hardif_list);
- INIT_HLIST_HEAD(&batadv_algo_list);
+ batadv_algo_init();
batadv_recv_handler_init();
batadv_v_init();
batadv_iv_init();
batadv_nc_init();
+ batadv_tp_meter_init();
batadv_event_workqueue = create_singlethread_workqueue("bat_events");
@@ -101,6 +102,7 @@ static int __init batadv_init(void)
register_netdevice_notifier(&batadv_hard_if_notifier);
rtnl_link_register(&batadv_link_ops);
+ batadv_netlink_register();
pr_info("B.A.T.M.A.N. advanced %s (compatibility version %i) loaded\n",
BATADV_SOURCE_VERSION, BATADV_COMPAT_VERSION);
@@ -111,6 +113,7 @@ static int __init batadv_init(void)
static void __exit batadv_exit(void)
{
batadv_debugfs_destroy();
+ batadv_netlink_unregister();
rtnl_link_unregister(&batadv_link_ops);
unregister_netdevice_notifier(&batadv_hard_if_notifier);
batadv_hardif_remove_interfaces();
@@ -141,6 +144,7 @@ int batadv_mesh_init(struct net_device *soft_iface)
spin_lock_init(&bat_priv->tvlv.container_list_lock);
spin_lock_init(&bat_priv->tvlv.handler_list_lock);
spin_lock_init(&bat_priv->softif_vlan_list_lock);
+ spin_lock_init(&bat_priv->tp_list_lock);
INIT_HLIST_HEAD(&bat_priv->forw_bat_list);
INIT_HLIST_HEAD(&bat_priv->forw_bcast_list);
@@ -159,6 +163,7 @@ int batadv_mesh_init(struct net_device *soft_iface)
INIT_HLIST_HEAD(&bat_priv->tvlv.container_list);
INIT_HLIST_HEAD(&bat_priv->tvlv.handler_list);
INIT_HLIST_HEAD(&bat_priv->softif_vlan_list);
+ INIT_HLIST_HEAD(&bat_priv->tp_list);
ret = batadv_v_mesh_init(bat_priv);
if (ret < 0)
@@ -538,78 +543,6 @@ void batadv_recv_handler_unregister(u8 packet_type)
batadv_rx_handler[packet_type] = batadv_recv_unhandled_packet;
}
-static struct batadv_algo_ops *batadv_algo_get(char *name)
-{
- struct batadv_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp;
-
- hlist_for_each_entry(bat_algo_ops_tmp, &batadv_algo_list, list) {
- if (strcmp(bat_algo_ops_tmp->name, name) != 0)
- continue;
-
- bat_algo_ops = bat_algo_ops_tmp;
- break;
- }
-
- return bat_algo_ops;
-}
-
-int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops)
-{
- struct batadv_algo_ops *bat_algo_ops_tmp;
-
- 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);
- return -EEXIST;
- }
-
- /* all algorithms must implement all ops (for now) */
- if (!bat_algo_ops->bat_iface_enable ||
- !bat_algo_ops->bat_iface_disable ||
- !bat_algo_ops->bat_iface_update_mac ||
- !bat_algo_ops->bat_primary_iface_set ||
- !bat_algo_ops->bat_ogm_schedule ||
- !bat_algo_ops->bat_ogm_emit ||
- !bat_algo_ops->bat_neigh_cmp ||
- !bat_algo_ops->bat_neigh_is_similar_or_better) {
- pr_info("Routing algo '%s' does not implement required ops\n",
- bat_algo_ops->name);
- return -EINVAL;
- }
-
- INIT_HLIST_NODE(&bat_algo_ops->list);
- hlist_add_head(&bat_algo_ops->list, &batadv_algo_list);
-
- return 0;
-}
-
-int batadv_algo_select(struct batadv_priv *bat_priv, char *name)
-{
- struct batadv_algo_ops *bat_algo_ops;
-
- bat_algo_ops = batadv_algo_get(name);
- if (!bat_algo_ops)
- return -EINVAL;
-
- bat_priv->bat_algo_ops = bat_algo_ops;
-
- return 0;
-}
-
-int batadv_algo_seq_print_text(struct seq_file *seq, void *offset)
-{
- struct batadv_algo_ops *bat_algo_ops;
-
- seq_puts(seq, "Available routing algorithms:\n");
-
- hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) {
- seq_printf(seq, " * %s\n", bat_algo_ops->name);
- }
-
- return 0;
-}
-
/**
* batadv_skb_crc32 - calculate CRC32 of the whole packet and skip bytes in
* the header
@@ -644,594 +577,6 @@ __be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr)
}
/**
- * batadv_tvlv_handler_release - release tvlv handler from lists and queue for
- * free after rcu grace period
- * @ref: kref pointer of the tvlv
- */
-static void batadv_tvlv_handler_release(struct kref *ref)
-{
- struct batadv_tvlv_handler *tvlv_handler;
-
- tvlv_handler = container_of(ref, struct batadv_tvlv_handler, refcount);
- kfree_rcu(tvlv_handler, rcu);
-}
-
-/**
- * batadv_tvlv_handler_put - decrement the tvlv container refcounter and
- * possibly release it
- * @tvlv_handler: the tvlv handler to free
- */
-static void batadv_tvlv_handler_put(struct batadv_tvlv_handler *tvlv_handler)
-{
- kref_put(&tvlv_handler->refcount, batadv_tvlv_handler_release);
-}
-
-/**
- * batadv_tvlv_handler_get - retrieve tvlv handler from the tvlv handler list
- * based on the provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
- * @type: tvlv handler type to look for
- * @version: tvlv handler version to look for
- *
- * Return: tvlv handler if found or NULL otherwise.
- */
-static struct batadv_tvlv_handler *
-batadv_tvlv_handler_get(struct batadv_priv *bat_priv, u8 type, u8 version)
-{
- struct batadv_tvlv_handler *tvlv_handler_tmp, *tvlv_handler = NULL;
-
- rcu_read_lock();
- hlist_for_each_entry_rcu(tvlv_handler_tmp,
- &bat_priv->tvlv.handler_list, list) {
- if (tvlv_handler_tmp->type != type)
- continue;
-
- if (tvlv_handler_tmp->version != version)
- continue;
-
- if (!kref_get_unless_zero(&tvlv_handler_tmp->refcount))
- continue;
-
- tvlv_handler = tvlv_handler_tmp;
- break;
- }
- rcu_read_unlock();
-
- return tvlv_handler;
-}
-
-/**
- * batadv_tvlv_container_release - release tvlv from lists and free
- * @ref: kref pointer of the tvlv
- */
-static void batadv_tvlv_container_release(struct kref *ref)
-{
- struct batadv_tvlv_container *tvlv;
-
- tvlv = container_of(ref, struct batadv_tvlv_container, refcount);
- kfree(tvlv);
-}
-
-/**
- * batadv_tvlv_container_put - decrement the tvlv container refcounter and
- * possibly release it
- * @tvlv: the tvlv container to free
- */
-static void batadv_tvlv_container_put(struct batadv_tvlv_container *tvlv)
-{
- kref_put(&tvlv->refcount, batadv_tvlv_container_release);
-}
-
-/**
- * batadv_tvlv_container_get - retrieve tvlv container from the tvlv container
- * list based on the provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
- * @type: tvlv container type to look for
- * @version: tvlv container version to look for
- *
- * Has to be called with the appropriate locks being acquired
- * (tvlv.container_list_lock).
- *
- * Return: tvlv container if found or NULL otherwise.
- */
-static struct batadv_tvlv_container *
-batadv_tvlv_container_get(struct batadv_priv *bat_priv, u8 type, u8 version)
-{
- struct batadv_tvlv_container *tvlv_tmp, *tvlv = NULL;
-
- lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
-
- hlist_for_each_entry(tvlv_tmp, &bat_priv->tvlv.container_list, list) {
- if (tvlv_tmp->tvlv_hdr.type != type)
- continue;
-
- if (tvlv_tmp->tvlv_hdr.version != version)
- continue;
-
- kref_get(&tvlv_tmp->refcount);
- tvlv = tvlv_tmp;
- break;
- }
-
- return tvlv;
-}
-
-/**
- * batadv_tvlv_container_list_size - calculate the size of the tvlv container
- * list entries
- * @bat_priv: the bat priv with all the soft interface information
- *
- * Has to be called with the appropriate locks being acquired
- * (tvlv.container_list_lock).
- *
- * Return: size of all currently registered tvlv containers in bytes.
- */
-static u16 batadv_tvlv_container_list_size(struct batadv_priv *bat_priv)
-{
- struct batadv_tvlv_container *tvlv;
- u16 tvlv_len = 0;
-
- lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
-
- hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) {
- tvlv_len += sizeof(struct batadv_tvlv_hdr);
- tvlv_len += ntohs(tvlv->tvlv_hdr.len);
- }
-
- return tvlv_len;
-}
-
-/**
- * batadv_tvlv_container_remove - remove tvlv container from the tvlv container
- * list
- * @bat_priv: the bat priv with all the soft interface information
- * @tvlv: the to be removed tvlv container
- *
- * Has to be called with the appropriate locks being acquired
- * (tvlv.container_list_lock).
- */
-static void batadv_tvlv_container_remove(struct batadv_priv *bat_priv,
- struct batadv_tvlv_container *tvlv)
-{
- lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
-
- if (!tvlv)
- return;
-
- hlist_del(&tvlv->list);
-
- /* first call to decrement the counter, second call to free */
- batadv_tvlv_container_put(tvlv);
- batadv_tvlv_container_put(tvlv);
-}
-
-/**
- * batadv_tvlv_container_unregister - unregister tvlv container based on the
- * provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
- * @type: tvlv container type to unregister
- * @version: tvlv container type to unregister
- */
-void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv,
- u8 type, u8 version)
-{
- struct batadv_tvlv_container *tvlv;
-
- spin_lock_bh(&bat_priv->tvlv.container_list_lock);
- tvlv = batadv_tvlv_container_get(bat_priv, type, version);
- batadv_tvlv_container_remove(bat_priv, tvlv);
- spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
-}
-
-/**
- * batadv_tvlv_container_register - register tvlv type, version and content
- * to be propagated with each (primary interface) OGM
- * @bat_priv: the bat priv with all the soft interface information
- * @type: tvlv container type
- * @version: tvlv container version
- * @tvlv_value: tvlv container content
- * @tvlv_value_len: tvlv container content length
- *
- * If a container of the same type and version was already registered the new
- * content is going to replace the old one.
- */
-void batadv_tvlv_container_register(struct batadv_priv *bat_priv,
- u8 type, u8 version,
- void *tvlv_value, u16 tvlv_value_len)
-{
- struct batadv_tvlv_container *tvlv_old, *tvlv_new;
-
- if (!tvlv_value)
- tvlv_value_len = 0;
-
- tvlv_new = kzalloc(sizeof(*tvlv_new) + tvlv_value_len, GFP_ATOMIC);
- if (!tvlv_new)
- return;
-
- tvlv_new->tvlv_hdr.version = version;
- tvlv_new->tvlv_hdr.type = type;
- tvlv_new->tvlv_hdr.len = htons(tvlv_value_len);
-
- memcpy(tvlv_new + 1, tvlv_value, ntohs(tvlv_new->tvlv_hdr.len));
- INIT_HLIST_NODE(&tvlv_new->list);
- kref_init(&tvlv_new->refcount);
-
- spin_lock_bh(&bat_priv->tvlv.container_list_lock);
- tvlv_old = batadv_tvlv_container_get(bat_priv, type, version);
- batadv_tvlv_container_remove(bat_priv, tvlv_old);
- hlist_add_head(&tvlv_new->list, &bat_priv->tvlv.container_list);
- spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
-}
-
-/**
- * batadv_tvlv_realloc_packet_buff - reallocate packet buffer to accommodate
- * requested packet size
- * @packet_buff: packet buffer
- * @packet_buff_len: packet buffer size
- * @min_packet_len: requested packet minimum size
- * @additional_packet_len: requested additional packet size on top of minimum
- * size
- *
- * Return: true of the packet buffer could be changed to the requested size,
- * false otherwise.
- */
-static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff,
- int *packet_buff_len,
- int min_packet_len,
- int additional_packet_len)
-{
- unsigned char *new_buff;
-
- new_buff = kmalloc(min_packet_len + additional_packet_len, GFP_ATOMIC);
-
- /* keep old buffer if kmalloc should fail */
- 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 true;
-}
-
-/**
- * batadv_tvlv_container_ogm_append - append tvlv container content to given
- * OGM packet buffer
- * @bat_priv: the bat priv with all the soft interface information
- * @packet_buff: ogm packet buffer
- * @packet_buff_len: ogm packet buffer size including ogm header and tvlv
- * content
- * @packet_min_len: ogm header size to be preserved for the OGM itself
- *
- * The ogm packet might be enlarged or shrunk depending on the current size
- * and the size of the to-be-appended tvlv containers.
- *
- * Return: size of all appended tvlv containers in bytes.
- */
-u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv,
- unsigned char **packet_buff,
- int *packet_buff_len, int packet_min_len)
-{
- struct batadv_tvlv_container *tvlv;
- struct batadv_tvlv_hdr *tvlv_hdr;
- u16 tvlv_value_len;
- void *tvlv_value;
- bool ret;
-
- spin_lock_bh(&bat_priv->tvlv.container_list_lock);
- tvlv_value_len = batadv_tvlv_container_list_size(bat_priv);
-
- ret = batadv_tvlv_realloc_packet_buff(packet_buff, packet_buff_len,
- packet_min_len, tvlv_value_len);
-
- if (!ret)
- goto end;
-
- if (!tvlv_value_len)
- goto end;
-
- tvlv_value = (*packet_buff) + packet_min_len;
-
- hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) {
- tvlv_hdr = tvlv_value;
- tvlv_hdr->type = tvlv->tvlv_hdr.type;
- tvlv_hdr->version = tvlv->tvlv_hdr.version;
- tvlv_hdr->len = tvlv->tvlv_hdr.len;
- tvlv_value = tvlv_hdr + 1;
- memcpy(tvlv_value, tvlv + 1, ntohs(tvlv->tvlv_hdr.len));
- tvlv_value = (u8 *)tvlv_value + ntohs(tvlv->tvlv_hdr.len);
- }
-
-end:
- spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
- return tvlv_value_len;
-}
-
-/**
- * batadv_tvlv_call_handler - parse the given tvlv buffer to call the
- * appropriate handlers
- * @bat_priv: the bat priv with all the soft interface information
- * @tvlv_handler: tvlv callback function handling the tvlv content
- * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet
- * @orig_node: orig node emitting the ogm packet
- * @src: source mac address of the unicast packet
- * @dst: destination mac address of the unicast packet
- * @tvlv_value: tvlv content
- * @tvlv_value_len: tvlv content length
- *
- * Return: success if handler was not found or the return value of the handler
- * callback.
- */
-static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv,
- struct batadv_tvlv_handler *tvlv_handler,
- bool ogm_source,
- struct batadv_orig_node *orig_node,
- u8 *src, u8 *dst,
- void *tvlv_value, u16 tvlv_value_len)
-{
- if (!tvlv_handler)
- return NET_RX_SUCCESS;
-
- if (ogm_source) {
- if (!tvlv_handler->ogm_handler)
- return NET_RX_SUCCESS;
-
- if (!orig_node)
- return NET_RX_SUCCESS;
-
- tvlv_handler->ogm_handler(bat_priv, orig_node,
- BATADV_NO_FLAGS,
- tvlv_value, tvlv_value_len);
- tvlv_handler->flags |= BATADV_TVLV_HANDLER_OGM_CALLED;
- } else {
- if (!src)
- return NET_RX_SUCCESS;
-
- if (!dst)
- return NET_RX_SUCCESS;
-
- if (!tvlv_handler->unicast_handler)
- return NET_RX_SUCCESS;
-
- return tvlv_handler->unicast_handler(bat_priv, src,
- dst, tvlv_value,
- tvlv_value_len);
- }
-
- return NET_RX_SUCCESS;
-}
-
-/**
- * batadv_tvlv_containers_process - parse the given tvlv buffer to call the
- * appropriate handlers
- * @bat_priv: the bat priv with all the soft interface information
- * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet
- * @orig_node: orig node emitting the ogm packet
- * @src: source mac address of the unicast packet
- * @dst: destination mac address of the unicast packet
- * @tvlv_value: tvlv content
- * @tvlv_value_len: tvlv content length
- *
- * Return: success when processing an OGM or the return value of all called
- * handler callbacks.
- */
-int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
- bool ogm_source,
- struct batadv_orig_node *orig_node,
- u8 *src, u8 *dst,
- void *tvlv_value, u16 tvlv_value_len)
-{
- struct batadv_tvlv_handler *tvlv_handler;
- struct batadv_tvlv_hdr *tvlv_hdr;
- u16 tvlv_value_cont_len;
- u8 cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND;
- int ret = NET_RX_SUCCESS;
-
- while (tvlv_value_len >= sizeof(*tvlv_hdr)) {
- tvlv_hdr = tvlv_value;
- tvlv_value_cont_len = ntohs(tvlv_hdr->len);
- tvlv_value = tvlv_hdr + 1;
- tvlv_value_len -= sizeof(*tvlv_hdr);
-
- if (tvlv_value_cont_len > tvlv_value_len)
- break;
-
- tvlv_handler = batadv_tvlv_handler_get(bat_priv,
- tvlv_hdr->type,
- tvlv_hdr->version);
-
- ret |= batadv_tvlv_call_handler(bat_priv, tvlv_handler,
- ogm_source, orig_node,
- src, dst, tvlv_value,
- tvlv_value_cont_len);
- if (tvlv_handler)
- batadv_tvlv_handler_put(tvlv_handler);
- tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len;
- tvlv_value_len -= tvlv_value_cont_len;
- }
-
- if (!ogm_source)
- return ret;
-
- rcu_read_lock();
- hlist_for_each_entry_rcu(tvlv_handler,
- &bat_priv->tvlv.handler_list, list) {
- if ((tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) &&
- !(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CALLED))
- tvlv_handler->ogm_handler(bat_priv, orig_node,
- cifnotfound, NULL, 0);
-
- tvlv_handler->flags &= ~BATADV_TVLV_HANDLER_OGM_CALLED;
- }
- rcu_read_unlock();
-
- return NET_RX_SUCCESS;
-}
-
-/**
- * batadv_tvlv_ogm_receive - process an incoming ogm and call the appropriate
- * handlers
- * @bat_priv: the bat priv with all the soft interface information
- * @batadv_ogm_packet: ogm packet containing the tvlv containers
- * @orig_node: orig node emitting the ogm packet
- */
-void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv,
- struct batadv_ogm_packet *batadv_ogm_packet,
- struct batadv_orig_node *orig_node)
-{
- void *tvlv_value;
- u16 tvlv_value_len;
-
- if (!batadv_ogm_packet)
- return;
-
- tvlv_value_len = ntohs(batadv_ogm_packet->tvlv_len);
- if (!tvlv_value_len)
- return;
-
- tvlv_value = batadv_ogm_packet + 1;
-
- batadv_tvlv_containers_process(bat_priv, true, orig_node, NULL, NULL,
- tvlv_value, tvlv_value_len);
-}
-
-/**
- * batadv_tvlv_handler_register - register tvlv handler based on the provided
- * type and version (both need to match) for ogm tvlv payload and/or unicast
- * payload
- * @bat_priv: the bat priv with all the soft interface information
- * @optr: ogm tvlv handler callback function. This function receives the orig
- * node, flags and the tvlv content as argument to process.
- * @uptr: unicast tvlv handler callback function. This function receives the
- * source & destination of the unicast packet as well as the tvlv content
- * to process.
- * @type: tvlv handler type to be registered
- * @version: tvlv handler version to be registered
- * @flags: flags to enable or disable TVLV API behavior
- */
-void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
- void (*optr)(struct batadv_priv *bat_priv,
- struct batadv_orig_node *orig,
- u8 flags,
- void *tvlv_value,
- u16 tvlv_value_len),
- int (*uptr)(struct batadv_priv *bat_priv,
- u8 *src, u8 *dst,
- void *tvlv_value,
- u16 tvlv_value_len),
- u8 type, u8 version, u8 flags)
-{
- struct batadv_tvlv_handler *tvlv_handler;
-
- tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version);
- if (tvlv_handler) {
- batadv_tvlv_handler_put(tvlv_handler);
- return;
- }
-
- tvlv_handler = kzalloc(sizeof(*tvlv_handler), GFP_ATOMIC);
- if (!tvlv_handler)
- return;
-
- tvlv_handler->ogm_handler = optr;
- tvlv_handler->unicast_handler = uptr;
- tvlv_handler->type = type;
- tvlv_handler->version = version;
- tvlv_handler->flags = flags;
- kref_init(&tvlv_handler->refcount);
- INIT_HLIST_NODE(&tvlv_handler->list);
-
- spin_lock_bh(&bat_priv->tvlv.handler_list_lock);
- hlist_add_head_rcu(&tvlv_handler->list, &bat_priv->tvlv.handler_list);
- spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
-}
-
-/**
- * batadv_tvlv_handler_unregister - unregister tvlv handler based on the
- * provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
- * @type: tvlv handler type to be unregistered
- * @version: tvlv handler version to be unregistered
- */
-void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv,
- u8 type, u8 version)
-{
- struct batadv_tvlv_handler *tvlv_handler;
-
- tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version);
- if (!tvlv_handler)
- return;
-
- batadv_tvlv_handler_put(tvlv_handler);
- spin_lock_bh(&bat_priv->tvlv.handler_list_lock);
- hlist_del_rcu(&tvlv_handler->list);
- spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
- batadv_tvlv_handler_put(tvlv_handler);
-}
-
-/**
- * batadv_tvlv_unicast_send - send a unicast packet with tvlv payload to the
- * specified host
- * @bat_priv: the bat priv with all the soft interface information
- * @src: source mac address of the unicast packet
- * @dst: destination mac address of the unicast packet
- * @type: tvlv type
- * @version: tvlv version
- * @tvlv_value: tvlv content
- * @tvlv_value_len: tvlv content length
- */
-void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src,
- u8 *dst, u8 type, u8 version,
- void *tvlv_value, u16 tvlv_value_len)
-{
- struct batadv_unicast_tvlv_packet *unicast_tvlv_packet;
- struct batadv_tvlv_hdr *tvlv_hdr;
- struct batadv_orig_node *orig_node;
- struct sk_buff *skb;
- unsigned char *tvlv_buff;
- unsigned int tvlv_len;
- ssize_t hdr_len = sizeof(*unicast_tvlv_packet);
-
- orig_node = batadv_orig_hash_find(bat_priv, dst);
- if (!orig_node)
- return;
-
- tvlv_len = sizeof(*tvlv_hdr) + tvlv_value_len;
-
- skb = netdev_alloc_skb_ip_align(NULL, ETH_HLEN + hdr_len + tvlv_len);
- if (!skb)
- goto out;
-
- skb->priority = TC_PRIO_CONTROL;
- skb_reserve(skb, ETH_HLEN);
- tvlv_buff = skb_put(skb, sizeof(*unicast_tvlv_packet) + tvlv_len);
- unicast_tvlv_packet = (struct batadv_unicast_tvlv_packet *)tvlv_buff;
- unicast_tvlv_packet->packet_type = BATADV_UNICAST_TVLV;
- unicast_tvlv_packet->version = BATADV_COMPAT_VERSION;
- unicast_tvlv_packet->ttl = BATADV_TTL;
- unicast_tvlv_packet->reserved = 0;
- unicast_tvlv_packet->tvlv_len = htons(tvlv_len);
- unicast_tvlv_packet->align = 0;
- ether_addr_copy(unicast_tvlv_packet->src, src);
- ether_addr_copy(unicast_tvlv_packet->dst, dst);
-
- tvlv_buff = (unsigned char *)(unicast_tvlv_packet + 1);
- tvlv_hdr = (struct batadv_tvlv_hdr *)tvlv_buff;
- tvlv_hdr->version = version;
- tvlv_hdr->type = type;
- tvlv_hdr->len = htons(tvlv_value_len);
- tvlv_buff += sizeof(*tvlv_hdr);
- memcpy(tvlv_buff, tvlv_value, tvlv_value_len);
-
- if (batadv_send_skb_to_orig(skb, orig_node, NULL) == NET_XMIT_DROP)
- kfree_skb(skb);
-out:
- batadv_orig_node_put(orig_node);
-}
-
-/**
* batadv_get_vid - extract the VLAN identifier from skb if any
* @skb: the buffer containing the packet
* @header_len: length of the batman header preceding the ethernet header
@@ -1284,36 +629,6 @@ bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid)
return ap_isolation_enabled;
}
-static int batadv_param_set_ra(const char *val, const struct kernel_param *kp)
-{
- struct batadv_algo_ops *bat_algo_ops;
- char *algo_name = (char *)val;
- size_t name_len = strlen(algo_name);
-
- if (name_len > 0 && algo_name[name_len - 1] == '\n')
- algo_name[name_len - 1] = '\0';
-
- bat_algo_ops = batadv_algo_get(algo_name);
- if (!bat_algo_ops) {
- pr_err("Routing algorithm '%s' is not supported\n", algo_name);
- return -EINVAL;
- }
-
- return param_set_copystring(algo_name, kp);
-}
-
-static const struct kernel_param_ops batadv_param_ops_ra = {
- .set = batadv_param_set_ra,
- .get = param_get_string,
-};
-
-static struct kparam_string batadv_param_string_ra = {
- .maxlen = sizeof(batadv_routing_algo),
- .string = batadv_routing_algo,
-};
-
-module_param_cb(routing_algo, &batadv_param_ops_ra, &batadv_param_string_ra,
- 0644);
module_init(batadv_init);
module_exit(batadv_exit);
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 76925266deed..06a860845434 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -24,7 +24,7 @@
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2016.2"
+#define BATADV_SOURCE_VERSION "2016.3"
#endif
/* B.A.T.M.A.N. parameters */
@@ -100,6 +100,9 @@
#define BATADV_NUM_BCASTS_WIRELESS 3
#define BATADV_NUM_BCASTS_MAX 3
+/* length of the single packet used by the TP meter */
+#define BATADV_TP_PACKET_LEN ETH_DATA_LEN
+
/* msecs after which an ARP_REQUEST is sent in broadcast as fallback */
#define ARP_REQ_DELAY 250
/* numbers of originator to contact for any PUT/GET DHT operation */
@@ -131,6 +134,11 @@
#define BATADV_NC_NODE_TIMEOUT 10000 /* Milliseconds */
+/**
+ * BATADV_TP_MAX_NUM - maximum number of simultaneously active tp sessions
+ */
+#define BATADV_TP_MAX_NUM 5
+
enum batadv_mesh_state {
BATADV_MESH_INACTIVE,
BATADV_MESH_ACTIVE,
@@ -175,29 +183,26 @@ enum batadv_uev_type {
/* Kernel headers */
-#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/jiffies.h>
#include <linux/if_vlan.h>
+#include <linux/jiffies.h>
+#include <linux/percpu.h>
+#include <linux/types.h>
#include "types.h"
-struct batadv_ogm_packet;
+struct net_device;
+struct packet_type;
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[];
extern struct list_head batadv_hardif_list;
extern unsigned char batadv_broadcast_addr[];
@@ -218,74 +223,9 @@ batadv_recv_handler_register(u8 packet_type,
int (*recv_handler)(struct sk_buff *,
struct batadv_hard_iface *));
void batadv_recv_handler_unregister(u8 packet_type);
-int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops);
-int batadv_algo_select(struct batadv_priv *bat_priv, char *name);
-int batadv_algo_seq_print_text(struct seq_file *seq, void *offset);
__be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr);
/**
- * enum batadv_dbg_level - available log levels
- * @BATADV_DBG_BATMAN: OGM and TQ computations related messages
- * @BATADV_DBG_ROUTES: route added / changed / deleted
- * @BATADV_DBG_TT: translation table messages
- * @BATADV_DBG_BLA: bridge loop avoidance messages
- * @BATADV_DBG_DAT: ARP snooping and DAT related messages
- * @BATADV_DBG_NC: network coding related messages
- * @BATADV_DBG_ALL: the union of all the above log levels
- */
-enum batadv_dbg_level {
- BATADV_DBG_BATMAN = BIT(0),
- BATADV_DBG_ROUTES = BIT(1),
- BATADV_DBG_TT = BIT(2),
- BATADV_DBG_BLA = BIT(3),
- BATADV_DBG_DAT = BIT(4),
- BATADV_DBG_NC = BIT(5),
- BATADV_DBG_ALL = 63,
-};
-
-#ifdef CONFIG_BATMAN_ADV_DEBUG
-int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
-__printf(2, 3);
-
-/* possibly ratelimited debug output */
-#define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...) \
- do { \
- if (atomic_read(&bat_priv->log_level) & type && \
- (!ratelimited || net_ratelimit())) \
- batadv_debug_log(bat_priv, fmt, ## arg);\
- } \
- while (0)
-#else /* !CONFIG_BATMAN_ADV_DEBUG */
-__printf(4, 5)
-static inline void _batadv_dbg(int type __always_unused,
- struct batadv_priv *bat_priv __always_unused,
- int ratelimited __always_unused,
- const char *fmt __always_unused, ...)
-{
-}
-#endif
-
-#define batadv_dbg(type, bat_priv, arg...) \
- _batadv_dbg(type, bat_priv, 0, ## arg)
-#define batadv_dbg_ratelimited(type, bat_priv, arg...) \
- _batadv_dbg(type, bat_priv, 1, ## arg)
-
-#define batadv_info(net_dev, fmt, arg...) \
- do { \
- struct net_device *_netdev = (net_dev); \
- struct batadv_priv *_batpriv = netdev_priv(_netdev); \
- batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg); \
- pr_info("%s: " fmt, _netdev->name, ## arg); \
- } while (0)
-#define batadv_err(net_dev, fmt, arg...) \
- do { \
- struct net_device *_netdev = (net_dev); \
- struct batadv_priv *_batpriv = netdev_priv(_netdev); \
- batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg); \
- pr_err("%s: " fmt, _netdev->name, ## arg); \
- } while (0)
-
-/**
* batadv_compare_eth - Compare two not u16 aligned Ethernet addresses
* @data1: Pointer to a six-byte array containing the Ethernet address
* @data2: Pointer other six-byte array containing the Ethernet address
@@ -370,39 +310,6 @@ static inline u64 batadv_sum_counter(struct batadv_priv *bat_priv, size_t idx)
*/
#define BATADV_SKB_CB(__skb) ((struct batadv_skb_cb *)&((__skb)->cb[0]))
-void batadv_tvlv_container_register(struct batadv_priv *bat_priv,
- u8 type, u8 version,
- void *tvlv_value, u16 tvlv_value_len);
-u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv,
- unsigned char **packet_buff,
- int *packet_buff_len, int packet_min_len);
-void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv,
- struct batadv_ogm_packet *batadv_ogm_packet,
- struct batadv_orig_node *orig_node);
-void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv,
- u8 type, u8 version);
-
-void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
- void (*optr)(struct batadv_priv *bat_priv,
- struct batadv_orig_node *orig,
- u8 flags,
- void *tvlv_value,
- u16 tvlv_value_len),
- int (*uptr)(struct batadv_priv *bat_priv,
- u8 *src, u8 *dst,
- void *tvlv_value,
- u16 tvlv_value_len),
- u8 type, u8 version, u8 flags);
-void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv,
- u8 type, u8 version);
-int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
- bool ogm_source,
- struct batadv_orig_node *orig_node,
- u8 *src, u8 *dst,
- void *tvlv_buff, u16 tvlv_buff_len);
-void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src,
- u8 *dst, u8 type, u8 version,
- void *tvlv_value, u16 tvlv_value_len);
unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len);
bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid);
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index c32f24fafe67..cc915073a753 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -25,17 +25,23 @@
#include <linux/errno.h>
#include <linux/etherdevice.h>
#include <linux/fs.h>
+#include <linux/icmpv6.h>
+#include <linux/if_bridge.h>
#include <linux/if_ether.h>
-#include <linux/in6.h>
+#include <linux/igmp.h>
#include <linux/in.h>
+#include <linux/in6.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/kernel.h>
#include <linux/kref.h>
#include <linux/list.h>
#include <linux/lockdep.h>
#include <linux/netdevice.h>
+#include <linux/printk.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>
@@ -43,18 +49,57 @@
#include <linux/string.h>
#include <linux/types.h>
#include <net/addrconf.h>
+#include <net/if_inet6.h>
+#include <net/ip.h>
#include <net/ipv6.h>
+#include "hard-interface.h"
+#include "hash.h"
+#include "log.h"
#include "packet.h"
#include "translation-table.h"
+#include "tvlv.h"
+
+/**
+ * batadv_mcast_get_bridge - get the bridge on top of the softif if it exists
+ * @soft_iface: netdev struct of the mesh interface
+ *
+ * If the given soft interface has a bridge on top then the refcount
+ * of the according net device is increased.
+ *
+ * Return: NULL if no such bridge exists. Otherwise the net device of the
+ * bridge.
+ */
+static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface)
+{
+ struct net_device *upper = soft_iface;
+
+ rcu_read_lock();
+ do {
+ upper = netdev_master_upper_dev_get_rcu(upper);
+ } while (upper && !(upper->priv_flags & IFF_EBRIDGE));
+
+ if (upper)
+ dev_hold(upper);
+ rcu_read_unlock();
+
+ return upper;
+}
/**
* batadv_mcast_mla_softif_get - get softif multicast listeners
* @dev: the device to collect multicast addresses from
* @mcast_list: a list to put found addresses into
*
- * Collect multicast addresses of the local multicast listeners
- * on the given soft interface, dev, in the given mcast_list.
+ * Collects multicast addresses of multicast listeners residing
+ * on this kernel on the given soft interface, dev, in
+ * the given mcast_list. In general, multicast listeners provided by
+ * your multicast receiving applications run directly on this node.
+ *
+ * If there is a bridge interface on top of dev, collects from that one
+ * instead. Just like with IP addresses and routes, multicast listeners
+ * will(/should) register to the bridge interface instead of an
+ * enslaved bat0.
*
* Return: -ENOMEM on memory allocation error or the number of
* items added to the mcast_list otherwise.
@@ -62,12 +107,13 @@
static int batadv_mcast_mla_softif_get(struct net_device *dev,
struct hlist_head *mcast_list)
{
+ struct net_device *bridge = batadv_mcast_get_bridge(dev);
struct netdev_hw_addr *mc_list_entry;
struct batadv_hw_addr *new;
int ret = 0;
- netif_addr_lock_bh(dev);
- netdev_for_each_mc_addr(mc_list_entry, dev) {
+ netif_addr_lock_bh(bridge ? bridge : dev);
+ netdev_for_each_mc_addr(mc_list_entry, bridge ? bridge : dev) {
new = kmalloc(sizeof(*new), GFP_ATOMIC);
if (!new) {
ret = -ENOMEM;
@@ -78,7 +124,10 @@ static int batadv_mcast_mla_softif_get(struct net_device *dev,
hlist_add_head(&new->list, mcast_list);
ret++;
}
- netif_addr_unlock_bh(dev);
+ netif_addr_unlock_bh(bridge ? bridge : dev);
+
+ if (bridge)
+ dev_put(bridge);
return ret;
}
@@ -104,6 +153,83 @@ static bool batadv_mcast_mla_is_duplicate(u8 *mcast_addr,
}
/**
+ * batadv_mcast_mla_br_addr_cpy - copy a bridge multicast address
+ * @dst: destination to write to - a multicast MAC address
+ * @src: source to read from - a multicast IP address
+ *
+ * Converts a given multicast IPv4/IPv6 address from a bridge
+ * to its matching multicast MAC address and copies it into the given
+ * destination buffer.
+ *
+ * Caller needs to make sure the destination buffer can hold
+ * at least ETH_ALEN bytes.
+ */
+static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src)
+{
+ if (src->proto == htons(ETH_P_IP))
+ ip_eth_mc_map(src->u.ip4, dst);
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (src->proto == htons(ETH_P_IPV6))
+ ipv6_eth_mc_map(&src->u.ip6, dst);
+#endif
+ else
+ eth_zero_addr(dst);
+}
+
+/**
+ * batadv_mcast_mla_bridge_get - get bridged-in multicast listeners
+ * @dev: a bridge slave whose bridge to collect multicast addresses from
+ * @mcast_list: a list to put found addresses into
+ *
+ * Collects multicast addresses of multicast listeners residing
+ * on foreign, non-mesh devices which we gave access to our mesh via
+ * a bridge on top of the given soft interface, dev, in the given
+ * mcast_list.
+ *
+ * Return: -ENOMEM on memory allocation error or the number of
+ * items added to the mcast_list otherwise.
+ */
+static int batadv_mcast_mla_bridge_get(struct net_device *dev,
+ struct hlist_head *mcast_list)
+{
+ struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list);
+ struct br_ip_list *br_ip_entry, *tmp;
+ struct batadv_hw_addr *new;
+ u8 mcast_addr[ETH_ALEN];
+ int ret;
+
+ /* we don't need to detect these devices/listeners, the IGMP/MLD
+ * snooping code of the Linux bridge already does that for us
+ */
+ ret = br_multicast_list_adjacent(dev, &bridge_mcast_list);
+ if (ret < 0)
+ goto out;
+
+ list_for_each_entry(br_ip_entry, &bridge_mcast_list, list) {
+ batadv_mcast_mla_br_addr_cpy(mcast_addr, &br_ip_entry->addr);
+ if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list))
+ continue;
+
+ new = kmalloc(sizeof(*new), GFP_ATOMIC);
+ if (!new) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ ether_addr_copy(new->addr, mcast_addr);
+ hlist_add_head(&new->list, mcast_list);
+ }
+
+out:
+ list_for_each_entry_safe(br_ip_entry, tmp, &bridge_mcast_list, list) {
+ list_del(&br_ip_entry->list);
+ kfree(br_ip_entry);
+ }
+
+ return ret;
+}
+
+/**
* batadv_mcast_mla_list_free - free a list of multicast addresses
* @bat_priv: the bat priv with all the soft interface information
* @mcast_list: the list to free
@@ -214,44 +340,195 @@ static bool batadv_mcast_has_bridge(struct batadv_priv *bat_priv)
}
/**
+ * batadv_mcast_querier_log - debug output regarding the querier status on link
+ * @bat_priv: the bat priv with all the soft interface information
+ * @str_proto: a string for the querier protocol (e.g. "IGMP" or "MLD")
+ * @old_state: the previous querier state on our link
+ * @new_state: the new querier state on our link
+ *
+ * Outputs debug messages to the logging facility with log level 'mcast'
+ * regarding changes to the querier status on the link which are relevant
+ * to our multicast optimizations.
+ *
+ * Usually this is about whether a querier appeared or vanished in
+ * our mesh or whether the querier is in the suboptimal position of being
+ * behind our local bridge segment: Snooping switches will directly
+ * forward listener reports to the querier, therefore batman-adv and
+ * the bridge will potentially not see these listeners - the querier is
+ * potentially shadowing listeners from us then.
+ *
+ * This is only interesting for nodes with a bridge on top of their
+ * soft interface.
+ */
+static void
+batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto,
+ struct batadv_mcast_querier_state *old_state,
+ struct batadv_mcast_querier_state *new_state)
+{
+ if (!old_state->exists && new_state->exists)
+ batadv_info(bat_priv->soft_iface, "%s Querier appeared\n",
+ str_proto);
+ else if (old_state->exists && !new_state->exists)
+ batadv_info(bat_priv->soft_iface,
+ "%s Querier disappeared - multicast optimizations disabled\n",
+ str_proto);
+ else if (!bat_priv->mcast.bridged && !new_state->exists)
+ batadv_info(bat_priv->soft_iface,
+ "No %s Querier present - multicast optimizations disabled\n",
+ str_proto);
+
+ if (new_state->exists) {
+ if ((!old_state->shadowing && new_state->shadowing) ||
+ (!old_state->exists && new_state->shadowing))
+ batadv_dbg(BATADV_DBG_MCAST, bat_priv,
+ "%s Querier is behind our bridged segment: Might shadow listeners\n",
+ str_proto);
+ else if (old_state->shadowing && !new_state->shadowing)
+ batadv_dbg(BATADV_DBG_MCAST, bat_priv,
+ "%s Querier is not behind our bridged segment\n",
+ str_proto);
+ }
+}
+
+/**
+ * batadv_mcast_bridge_log - debug output for topology changes in bridged setups
+ * @bat_priv: the bat priv with all the soft interface information
+ * @bridged: a flag about whether the soft interface is currently bridged or not
+ * @querier_ipv4: (maybe) new status of a potential, selected IGMP querier
+ * @querier_ipv6: (maybe) new status of a potential, selected MLD querier
+ *
+ * If no bridges are ever used on this node, then this function does nothing.
+ *
+ * Otherwise this function outputs debug information to the 'mcast' log level
+ * which might be relevant to our multicast optimizations.
+ *
+ * More precisely, it outputs information when a bridge interface is added or
+ * removed from a soft interface. And when a bridge is present, it further
+ * outputs information about the querier state which is relevant for the
+ * multicast flags this node is going to set.
+ */
+static void
+batadv_mcast_bridge_log(struct batadv_priv *bat_priv, bool bridged,
+ struct batadv_mcast_querier_state *querier_ipv4,
+ struct batadv_mcast_querier_state *querier_ipv6)
+{
+ if (!bat_priv->mcast.bridged && bridged)
+ batadv_dbg(BATADV_DBG_MCAST, bat_priv,
+ "Bridge added: Setting Unsnoopables(U)-flag\n");
+ else if (bat_priv->mcast.bridged && !bridged)
+ batadv_dbg(BATADV_DBG_MCAST, bat_priv,
+ "Bridge removed: Unsetting Unsnoopables(U)-flag\n");
+
+ if (bridged) {
+ batadv_mcast_querier_log(bat_priv, "IGMP",
+ &bat_priv->mcast.querier_ipv4,
+ querier_ipv4);
+ batadv_mcast_querier_log(bat_priv, "MLD",
+ &bat_priv->mcast.querier_ipv6,
+ querier_ipv6);
+ }
+}
+
+/**
+ * batadv_mcast_flags_logs - output debug information about mcast flag changes
+ * @bat_priv: the bat priv with all the soft interface information
+ * @flags: flags indicating the new multicast state
+ *
+ * Whenever the multicast flags this nodes announces changes (@mcast_flags vs.
+ * bat_priv->mcast.flags), this notifies userspace via the 'mcast' log level.
+ */
+static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags)
+{
+ u8 old_flags = bat_priv->mcast.flags;
+ char str_old_flags[] = "[...]";
+
+ sprintf(str_old_flags, "[%c%c%c]",
+ (old_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
+ (old_flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
+ (old_flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.');
+
+ batadv_dbg(BATADV_DBG_MCAST, bat_priv,
+ "Changing multicast flags from '%s' to '[%c%c%c]'\n",
+ bat_priv->mcast.enabled ? str_old_flags : "<undefined>",
+ (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
+ (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
+ (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.');
+}
+
+/**
* batadv_mcast_mla_tvlv_update - update multicast tvlv
* @bat_priv: the bat priv with all the soft interface information
*
* Updates the own multicast tvlv with our current multicast related settings,
* capabilities and inabilities.
*
- * Return: true if the tvlv container is registered afterwards. Otherwise
- * returns false.
+ * Return: false if we want all IPv4 && IPv6 multicast traffic and true
+ * otherwise.
*/
static bool batadv_mcast_mla_tvlv_update(struct batadv_priv *bat_priv)
{
struct batadv_tvlv_mcast_data mcast_data;
+ struct batadv_mcast_querier_state querier4 = {false, false};
+ struct batadv_mcast_querier_state querier6 = {false, false};
+ struct net_device *dev = bat_priv->soft_iface;
+ bool bridged;
mcast_data.flags = BATADV_NO_FLAGS;
memset(mcast_data.reserved, 0, sizeof(mcast_data.reserved));
- /* Avoid attaching MLAs, if there is a bridge on top of our soft
- * interface, we don't support that yet (TODO)
+ bridged = batadv_mcast_has_bridge(bat_priv);
+ if (!bridged)
+ goto update;
+
+#if !IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
+ pr_warn_once("No bridge IGMP snooping compiled - multicast optimizations disabled\n");
+#endif
+
+ querier4.exists = br_multicast_has_querier_anywhere(dev, ETH_P_IP);
+ querier4.shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IP);
+
+ querier6.exists = br_multicast_has_querier_anywhere(dev, ETH_P_IPV6);
+ querier6.shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IPV6);
+
+ mcast_data.flags |= BATADV_MCAST_WANT_ALL_UNSNOOPABLES;
+
+ /* 1) If no querier exists at all, then multicast listeners on
+ * our local TT clients behind the bridge will keep silent.
+ * 2) If the selected querier is on one of our local TT clients,
+ * behind the bridge, then this querier might shadow multicast
+ * listeners on our local TT clients, behind this bridge.
+ *
+ * In both cases, we will signalize other batman nodes that
+ * we need all multicast traffic of the according protocol.
*/
- if (batadv_mcast_has_bridge(bat_priv)) {
- if (bat_priv->mcast.enabled) {
- batadv_tvlv_container_unregister(bat_priv,
- BATADV_TVLV_MCAST, 1);
- bat_priv->mcast.enabled = false;
- }
+ if (!querier4.exists || querier4.shadowing)
+ mcast_data.flags |= BATADV_MCAST_WANT_ALL_IPV4;
- return false;
- }
+ if (!querier6.exists || querier6.shadowing)
+ mcast_data.flags |= BATADV_MCAST_WANT_ALL_IPV6;
+
+update:
+ batadv_mcast_bridge_log(bat_priv, bridged, &querier4, &querier6);
+
+ bat_priv->mcast.querier_ipv4.exists = querier4.exists;
+ bat_priv->mcast.querier_ipv4.shadowing = querier4.shadowing;
+
+ bat_priv->mcast.querier_ipv6.exists = querier6.exists;
+ bat_priv->mcast.querier_ipv6.shadowing = querier6.shadowing;
+
+ bat_priv->mcast.bridged = bridged;
if (!bat_priv->mcast.enabled ||
mcast_data.flags != bat_priv->mcast.flags) {
- batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 1,
+ batadv_mcast_flags_log(bat_priv, mcast_data.flags);
+ batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 2,
&mcast_data, sizeof(mcast_data));
bat_priv->mcast.flags = mcast_data.flags;
bat_priv->mcast.enabled = true;
}
- return true;
+ return !(mcast_data.flags &
+ (BATADV_MCAST_WANT_ALL_IPV4 + BATADV_MCAST_WANT_ALL_IPV6));
}
/**
@@ -274,6 +551,10 @@ void batadv_mcast_mla_update(struct batadv_priv *bat_priv)
if (ret < 0)
goto out;
+ ret = batadv_mcast_mla_bridge_get(soft_iface, &mcast_list);
+ if (ret < 0)
+ goto out;
+
update:
batadv_mcast_mla_tt_retract(bat_priv, &mcast_list);
batadv_mcast_mla_tt_add(bat_priv, &mcast_list);
@@ -283,6 +564,31 @@ out:
}
/**
+ * batadv_mcast_is_report_ipv4 - check for IGMP reports
+ * @skb: the ethernet frame destined for the mesh
+ *
+ * This call might reallocate skb data.
+ *
+ * Checks whether the given frame is a valid IGMP report.
+ *
+ * Return: If so then true, otherwise false.
+ */
+static bool batadv_mcast_is_report_ipv4(struct sk_buff *skb)
+{
+ if (ip_mc_check_igmp(skb, NULL) < 0)
+ return false;
+
+ switch (igmp_hdr(skb)->type) {
+ case IGMP_HOST_MEMBERSHIP_REPORT:
+ case IGMPV2_HOST_MEMBERSHIP_REPORT:
+ case IGMPV3_HOST_MEMBERSHIP_REPORT:
+ return true;
+ }
+
+ return false;
+}
+
+/**
* batadv_mcast_forw_mode_check_ipv4 - check for optimized forwarding potential
* @bat_priv: the bat priv with all the soft interface information
* @skb: the IPv4 packet to check
@@ -304,6 +610,9 @@ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*iphdr)))
return -ENOMEM;
+ if (batadv_mcast_is_report_ipv4(skb))
+ return -EINVAL;
+
iphdr = ip_hdr(skb);
/* TODO: Implement Multicast Router Discovery (RFC4286),
@@ -320,6 +629,31 @@ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
return 0;
}
+#if IS_ENABLED(CONFIG_IPV6)
+/**
+ * batadv_mcast_is_report_ipv6 - check for MLD reports
+ * @skb: the ethernet frame destined for the mesh
+ *
+ * This call might reallocate skb data.
+ *
+ * Checks whether the given frame is a valid MLD report.
+ *
+ * Return: If so then true, otherwise false.
+ */
+static bool batadv_mcast_is_report_ipv6(struct sk_buff *skb)
+{
+ if (ipv6_mc_check_mld(skb, NULL) < 0)
+ return false;
+
+ switch (icmp6_hdr(skb)->icmp6_type) {
+ case ICMPV6_MGM_REPORT:
+ case ICMPV6_MLD2_REPORT:
+ return true;
+ }
+
+ return false;
+}
+
/**
* batadv_mcast_forw_mode_check_ipv6 - check for optimized forwarding potential
* @bat_priv: the bat priv with all the soft interface information
@@ -341,6 +675,9 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*ip6hdr)))
return -ENOMEM;
+ if (batadv_mcast_is_report_ipv6(skb))
+ return -EINVAL;
+
ip6hdr = ipv6_hdr(skb);
/* TODO: Implement Multicast Router Discovery (RFC4286),
@@ -357,6 +694,7 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
return 0;
}
+#endif
/**
* batadv_mcast_forw_mode_check - check for optimized forwarding potential
@@ -385,9 +723,11 @@ static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv,
case ETH_P_IP:
return batadv_mcast_forw_mode_check_ipv4(bat_priv, skb,
is_unsnoopable);
+#if IS_ENABLED(CONFIG_IPV6)
case ETH_P_IPV6:
return batadv_mcast_forw_mode_check_ipv6(bat_priv, skb,
is_unsnoopable);
+#endif
default:
return -EINVAL;
}
@@ -728,18 +1068,18 @@ static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv,
}
/**
- * batadv_mcast_tvlv_ogm_handler_v1 - process incoming multicast tvlv container
+ * batadv_mcast_tvlv_ogm_handler - process incoming multicast tvlv container
* @bat_priv: the bat priv with all the soft interface information
* @orig: the orig_node of the ogm
* @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags)
* @tvlv_value: tvlv buffer containing the multicast data
* @tvlv_value_len: tvlv buffer length
*/
-static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
- struct batadv_orig_node *orig,
- u8 flags,
- void *tvlv_value,
- u16 tvlv_value_len)
+static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig,
+ u8 flags,
+ void *tvlv_value,
+ u16 tvlv_value_len)
{
bool orig_mcast_enabled = !(flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
u8 mcast_flags = BATADV_NO_FLAGS;
@@ -789,19 +1129,120 @@ static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
*/
void batadv_mcast_init(struct batadv_priv *bat_priv)
{
- batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler_v1,
- NULL, BATADV_TVLV_MCAST, 1,
+ batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler,
+ NULL, BATADV_TVLV_MCAST, 2,
BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
}
/**
+ * batadv_mcast_flags_print_header - print own mcast flags to debugfs table
+ * @bat_priv: the bat priv with all the soft interface information
+ * @seq: debugfs table seq_file struct
+ *
+ * Prints our own multicast flags including a more specific reason why
+ * they are set, that is prints the bridge and querier state too, to
+ * the debugfs table specified via @seq.
+ */
+static void batadv_mcast_flags_print_header(struct batadv_priv *bat_priv,
+ struct seq_file *seq)
+{
+ u8 flags = bat_priv->mcast.flags;
+ char querier4, querier6, shadowing4, shadowing6;
+ bool bridged = bat_priv->mcast.bridged;
+
+ if (bridged) {
+ querier4 = bat_priv->mcast.querier_ipv4.exists ? '.' : '4';
+ querier6 = bat_priv->mcast.querier_ipv6.exists ? '.' : '6';
+ shadowing4 = bat_priv->mcast.querier_ipv4.shadowing ? '4' : '.';
+ shadowing6 = bat_priv->mcast.querier_ipv6.shadowing ? '6' : '.';
+ } else {
+ querier4 = '?';
+ querier6 = '?';
+ shadowing4 = '?';
+ shadowing6 = '?';
+ }
+
+ seq_printf(seq, "Multicast flags (own flags: [%c%c%c])\n",
+ (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
+ (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
+ (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.');
+ seq_printf(seq, "* Bridged [U]\t\t\t\t%c\n", bridged ? 'U' : '.');
+ seq_printf(seq, "* No IGMP/MLD Querier [4/6]:\t\t%c/%c\n",
+ querier4, querier6);
+ seq_printf(seq, "* Shadowing IGMP/MLD Querier [4/6]:\t%c/%c\n",
+ shadowing4, shadowing6);
+ seq_puts(seq, "-------------------------------------------\n");
+ seq_printf(seq, " %-10s %s\n", "Originator", "Flags");
+}
+
+/**
+ * batadv_mcast_flags_seq_print_text - print the mcast flags of other nodes
+ * @seq: seq file to print on
+ * @offset: not used
+ *
+ * This prints a table of (primary) originators and their according
+ * multicast flags, including (in the header) our own.
+ *
+ * Return: always 0
+ */
+int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset)
+{
+ struct net_device *net_dev = (struct net_device *)seq->private;
+ struct batadv_priv *bat_priv = netdev_priv(net_dev);
+ struct batadv_hard_iface *primary_if;
+ struct batadv_hashtable *hash = bat_priv->orig_hash;
+ struct batadv_orig_node *orig_node;
+ struct hlist_head *head;
+ u8 flags;
+ u32 i;
+
+ primary_if = batadv_seq_print_text_primary_if_get(seq);
+ if (!primary_if)
+ return 0;
+
+ batadv_mcast_flags_print_header(bat_priv, seq);
+
+ for (i = 0; i < hash->size; i++) {
+ head = &hash->table[i];
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
+ if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST,
+ &orig_node->capa_initialized))
+ continue;
+
+ if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST,
+ &orig_node->capabilities)) {
+ seq_printf(seq, "%pM -\n", orig_node->orig);
+ continue;
+ }
+
+ flags = orig_node->mcast_flags;
+
+ seq_printf(seq, "%pM [%c%c%c]\n", orig_node->orig,
+ (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)
+ ? 'U' : '.',
+ (flags & BATADV_MCAST_WANT_ALL_IPV4)
+ ? '4' : '.',
+ (flags & BATADV_MCAST_WANT_ALL_IPV6)
+ ? '6' : '.');
+ }
+ rcu_read_unlock();
+ }
+
+ batadv_hardif_put(primary_if);
+
+ return 0;
+}
+
+/**
* batadv_mcast_free - free the multicast optimizations structures
* @bat_priv: the bat priv with all the soft interface information
*/
void batadv_mcast_free(struct batadv_priv *bat_priv)
{
- batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 1);
- batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 1);
+ batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
+ batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
spin_lock_bh(&bat_priv->tt.commit_lock);
batadv_mcast_mla_tt_retract(bat_priv, NULL);
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index 80bceec55592..1fb00ba84907 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -20,6 +20,7 @@
#include "main.h"
+struct seq_file;
struct sk_buff;
/**
@@ -46,6 +47,8 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
void batadv_mcast_init(struct batadv_priv *bat_priv);
+int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset);
+
void batadv_mcast_free(struct batadv_priv *bat_priv);
void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node);
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
new file mode 100644
index 000000000000..231f8eaf075b
--- /dev/null
+++ b/net/batman-adv/netlink.c
@@ -0,0 +1,424 @@
+/* Copyright (C) 2016 B.A.T.M.A.N. contributors:
+ *
+ * Matthias Schiffer
+ *
+ * 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/>.
+ */
+
+#include "netlink.h"
+#include "main.h"
+
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/genetlink.h>
+#include <linux/if_ether.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/netlink.h>
+#include <linux/printk.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <net/genetlink.h>
+#include <net/netlink.h>
+#include <uapi/linux/batman_adv.h>
+
+#include "hard-interface.h"
+#include "soft-interface.h"
+#include "tp_meter.h"
+
+struct sk_buff;
+
+static struct genl_family batadv_netlink_family = {
+ .id = GENL_ID_GENERATE,
+ .hdrsize = 0,
+ .name = BATADV_NL_NAME,
+ .version = 1,
+ .maxattr = BATADV_ATTR_MAX,
+};
+
+/* multicast groups */
+enum batadv_netlink_multicast_groups {
+ BATADV_NL_MCGRP_TPMETER,
+};
+
+static struct genl_multicast_group batadv_netlink_mcgrps[] = {
+ [BATADV_NL_MCGRP_TPMETER] = { .name = BATADV_NL_MCAST_GROUP_TPMETER },
+};
+
+static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = {
+ [BATADV_ATTR_VERSION] = { .type = NLA_STRING },
+ [BATADV_ATTR_ALGO_NAME] = { .type = NLA_STRING },
+ [BATADV_ATTR_MESH_IFINDEX] = { .type = NLA_U32 },
+ [BATADV_ATTR_MESH_IFNAME] = { .type = NLA_STRING },
+ [BATADV_ATTR_MESH_ADDRESS] = { .len = ETH_ALEN },
+ [BATADV_ATTR_HARD_IFINDEX] = { .type = NLA_U32 },
+ [BATADV_ATTR_HARD_IFNAME] = { .type = NLA_STRING },
+ [BATADV_ATTR_HARD_ADDRESS] = { .len = ETH_ALEN },
+ [BATADV_ATTR_ORIG_ADDRESS] = { .len = ETH_ALEN },
+ [BATADV_ATTR_TPMETER_RESULT] = { .type = NLA_U8 },
+ [BATADV_ATTR_TPMETER_TEST_TIME] = { .type = NLA_U32 },
+ [BATADV_ATTR_TPMETER_BYTES] = { .type = NLA_U64 },
+ [BATADV_ATTR_TPMETER_COOKIE] = { .type = NLA_U32 },
+};
+
+/**
+ * batadv_netlink_mesh_info_put - fill in generic information about mesh
+ * interface
+ * @msg: netlink message to be sent back
+ * @soft_iface: interface for which the data should be taken
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int
+batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface)
+{
+ struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+ struct batadv_hard_iface *primary_if = NULL;
+ struct net_device *hard_iface;
+ int ret = -ENOBUFS;
+
+ if (nla_put_string(msg, BATADV_ATTR_VERSION, BATADV_SOURCE_VERSION) ||
+ nla_put_string(msg, BATADV_ATTR_ALGO_NAME,
+ bat_priv->algo_ops->name) ||
+ nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, soft_iface->ifindex) ||
+ nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, soft_iface->name) ||
+ nla_put(msg, BATADV_ATTR_MESH_ADDRESS, ETH_ALEN,
+ soft_iface->dev_addr))
+ goto out;
+
+ primary_if = batadv_primary_if_get_selected(bat_priv);
+ if (primary_if && primary_if->if_status == BATADV_IF_ACTIVE) {
+ hard_iface = primary_if->net_dev;
+
+ if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
+ hard_iface->ifindex) ||
+ nla_put_string(msg, BATADV_ATTR_HARD_IFNAME,
+ hard_iface->name) ||
+ nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN,
+ hard_iface->dev_addr))
+ goto out;
+ }
+
+ ret = 0;
+
+ out:
+ if (primary_if)
+ batadv_hardif_put(primary_if);
+
+ return ret;
+}
+
+/**
+ * batadv_netlink_get_mesh_info - handle incoming BATADV_CMD_GET_MESH_INFO
+ * netlink request
+ * @skb: received netlink message
+ * @info: receiver information
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int
+batadv_netlink_get_mesh_info(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct net_device *soft_iface;
+ struct sk_buff *msg = NULL;
+ void *msg_head;
+ int ifindex;
+ int ret;
+
+ if (!info->attrs[BATADV_ATTR_MESH_IFINDEX])
+ return -EINVAL;
+
+ ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
+ if (!ifindex)
+ return -EINVAL;
+
+ soft_iface = dev_get_by_index(net, ifindex);
+ if (!soft_iface || !batadv_softif_is_valid(soft_iface)) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ msg_head = genlmsg_put(msg, info->snd_portid, info->snd_seq,
+ &batadv_netlink_family, 0,
+ BATADV_CMD_GET_MESH_INFO);
+ if (!msg_head) {
+ ret = -ENOBUFS;
+ goto out;
+ }
+
+ ret = batadv_netlink_mesh_info_put(msg, soft_iface);
+
+ out:
+ if (soft_iface)
+ dev_put(soft_iface);
+
+ if (ret) {
+ if (msg)
+ nlmsg_free(msg);
+ return ret;
+ }
+
+ genlmsg_end(msg, msg_head);
+ return genlmsg_reply(msg, info);
+}
+
+/**
+ * batadv_netlink_tp_meter_put - Fill information of started tp_meter session
+ * @msg: netlink message to be sent back
+ * @cookie: tp meter session cookie
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int
+batadv_netlink_tp_meter_put(struct sk_buff *msg, u32 cookie)
+{
+ if (nla_put_u32(msg, BATADV_ATTR_TPMETER_COOKIE, cookie))
+ return -ENOBUFS;
+
+ return 0;
+}
+
+/**
+ * batadv_netlink_tpmeter_notify - send tp_meter result via netlink to client
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: destination of tp_meter session
+ * @result: reason for tp meter session stop
+ * @test_time: total time ot the tp_meter session
+ * @total_bytes: bytes acked to the receiver
+ * @cookie: cookie of tp_meter session
+ *
+ * Return: 0 on success, < 0 on error
+ */
+int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst,
+ u8 result, u32 test_time, u64 total_bytes,
+ u32 cookie)
+{
+ struct sk_buff *msg;
+ void *hdr;
+ int ret;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ hdr = genlmsg_put(msg, 0, 0, &batadv_netlink_family, 0,
+ BATADV_CMD_TP_METER);
+ if (!hdr) {
+ ret = -ENOBUFS;
+ goto err_genlmsg;
+ }
+
+ if (nla_put_u32(msg, BATADV_ATTR_TPMETER_COOKIE, cookie))
+ goto nla_put_failure;
+
+ if (nla_put_u32(msg, BATADV_ATTR_TPMETER_TEST_TIME, test_time))
+ goto nla_put_failure;
+
+ if (nla_put_u64_64bit(msg, BATADV_ATTR_TPMETER_BYTES, total_bytes,
+ BATADV_ATTR_PAD))
+ goto nla_put_failure;
+
+ if (nla_put_u8(msg, BATADV_ATTR_TPMETER_RESULT, result))
+ goto nla_put_failure;
+
+ if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, dst))
+ goto nla_put_failure;
+
+ genlmsg_end(msg, hdr);
+
+ genlmsg_multicast_netns(&batadv_netlink_family,
+ dev_net(bat_priv->soft_iface), msg, 0,
+ BATADV_NL_MCGRP_TPMETER, GFP_KERNEL);
+
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ ret = -EMSGSIZE;
+
+err_genlmsg:
+ nlmsg_free(msg);
+ return ret;
+}
+
+/**
+ * batadv_netlink_tp_meter_start - Start a new tp_meter session
+ * @skb: received netlink message
+ * @info: receiver information
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int
+batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct net_device *soft_iface;
+ struct batadv_priv *bat_priv;
+ struct sk_buff *msg = NULL;
+ u32 test_length;
+ void *msg_head;
+ int ifindex;
+ u32 cookie;
+ u8 *dst;
+ int ret;
+
+ if (!info->attrs[BATADV_ATTR_MESH_IFINDEX])
+ return -EINVAL;
+
+ if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS])
+ return -EINVAL;
+
+ if (!info->attrs[BATADV_ATTR_TPMETER_TEST_TIME])
+ return -EINVAL;
+
+ ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
+ if (!ifindex)
+ return -EINVAL;
+
+ dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]);
+
+ test_length = nla_get_u32(info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]);
+
+ soft_iface = dev_get_by_index(net, ifindex);
+ if (!soft_iface || !batadv_softif_is_valid(soft_iface)) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ msg_head = genlmsg_put(msg, info->snd_portid, info->snd_seq,
+ &batadv_netlink_family, 0,
+ BATADV_CMD_TP_METER);
+ if (!msg_head) {
+ ret = -ENOBUFS;
+ goto out;
+ }
+
+ bat_priv = netdev_priv(soft_iface);
+ batadv_tp_start(bat_priv, dst, test_length, &cookie);
+
+ ret = batadv_netlink_tp_meter_put(msg, cookie);
+
+ out:
+ if (soft_iface)
+ dev_put(soft_iface);
+
+ if (ret) {
+ if (msg)
+ nlmsg_free(msg);
+ return ret;
+ }
+
+ genlmsg_end(msg, msg_head);
+ return genlmsg_reply(msg, info);
+}
+
+/**
+ * batadv_netlink_tp_meter_start - Cancel a running tp_meter session
+ * @skb: received netlink message
+ * @info: receiver information
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int
+batadv_netlink_tp_meter_cancel(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct net_device *soft_iface;
+ struct batadv_priv *bat_priv;
+ int ifindex;
+ u8 *dst;
+ int ret = 0;
+
+ if (!info->attrs[BATADV_ATTR_MESH_IFINDEX])
+ return -EINVAL;
+
+ if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS])
+ return -EINVAL;
+
+ ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
+ if (!ifindex)
+ return -EINVAL;
+
+ dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]);
+
+ soft_iface = dev_get_by_index(net, ifindex);
+ if (!soft_iface || !batadv_softif_is_valid(soft_iface)) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ bat_priv = netdev_priv(soft_iface);
+ batadv_tp_stop(bat_priv, dst, BATADV_TP_REASON_CANCEL);
+
+out:
+ if (soft_iface)
+ dev_put(soft_iface);
+
+ return ret;
+}
+
+static struct genl_ops batadv_netlink_ops[] = {
+ {
+ .cmd = BATADV_CMD_GET_MESH_INFO,
+ .flags = GENL_ADMIN_PERM,
+ .policy = batadv_netlink_policy,
+ .doit = batadv_netlink_get_mesh_info,
+ },
+ {
+ .cmd = BATADV_CMD_TP_METER,
+ .flags = GENL_ADMIN_PERM,
+ .policy = batadv_netlink_policy,
+ .doit = batadv_netlink_tp_meter_start,
+ },
+ {
+ .cmd = BATADV_CMD_TP_METER_CANCEL,
+ .flags = GENL_ADMIN_PERM,
+ .policy = batadv_netlink_policy,
+ .doit = batadv_netlink_tp_meter_cancel,
+ },
+};
+
+/**
+ * batadv_netlink_register - register batadv genl netlink family
+ */
+void __init batadv_netlink_register(void)
+{
+ int ret;
+
+ ret = genl_register_family_with_ops_groups(&batadv_netlink_family,
+ batadv_netlink_ops,
+ batadv_netlink_mcgrps);
+ if (ret)
+ pr_warn("unable to register netlink family");
+}
+
+/**
+ * batadv_netlink_unregister - unregister batadv genl netlink family
+ */
+void batadv_netlink_unregister(void)
+{
+ genl_unregister_family(&batadv_netlink_family);
+}
diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h
new file mode 100644
index 000000000000..945653ab58c6
--- /dev/null
+++ b/net/batman-adv/netlink.h
@@ -0,0 +1,32 @@
+/* Copyright (C) 2016 B.A.T.M.A.N. contributors:
+ *
+ * Matthias Schiffer
+ *
+ * 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/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_NETLINK_H_
+#define _NET_BATMAN_ADV_NETLINK_H_
+
+#include "main.h"
+
+#include <linux/types.h>
+
+void batadv_netlink_register(void);
+void batadv_netlink_unregister(void);
+
+int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst,
+ u8 result, u32 test_time, u64 total_bytes,
+ u32 cookie);
+
+#endif /* _NET_BATMAN_ADV_NETLINK_H_ */
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 678f06865312..293ef4ffd4e1 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -51,10 +51,12 @@
#include "hard-interface.h"
#include "hash.h"
+#include "log.h"
#include "originator.h"
#include "packet.h"
#include "routing.h"
#include "send.h"
+#include "tvlv.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;
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index ab8c4f9738fe..3940b5d24421 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -34,11 +34,13 @@
#include <linux/spinlock.h>
#include <linux/workqueue.h>
+#include "bat_algo.h"
#include "distributed-arp-table.h"
#include "fragmentation.h"
#include "gateway_client.h"
#include "hard-interface.h"
#include "hash.h"
+#include "log.h"
#include "multicast.h"
#include "network-coding.h"
#include "routing.h"
@@ -251,10 +253,8 @@ static void batadv_neigh_node_release(struct kref *ref)
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(ref, struct batadv_neigh_node, refcount);
- bao = neigh_node->orig_node->bat_priv->bat_algo_ops;
hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
&neigh_node->ifinfo_list, list) {
@@ -263,9 +263,6 @@ static void batadv_neigh_node_release(struct kref *ref)
batadv_hardif_neigh_put(neigh_node->hardif_neigh);
- if (bao->bat_neigh_free)
- bao->bat_neigh_free(neigh_node);
-
batadv_hardif_put(neigh_node->if_incoming);
kfree_rcu(neigh_node, rcu);
@@ -537,8 +534,8 @@ batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface,
kref_init(&hardif_neigh->refcount);
- if (bat_priv->bat_algo_ops->bat_hardif_neigh_init)
- bat_priv->bat_algo_ops->bat_hardif_neigh_init(hardif_neigh);
+ if (bat_priv->algo_ops->neigh.hardif_init)
+ bat_priv->algo_ops->neigh.hardif_init(hardif_neigh);
hlist_add_head(&hardif_neigh->list, &hard_iface->neigh_list);
@@ -602,19 +599,19 @@ batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface,
}
/**
- * batadv_neigh_node_new - create and init a new neigh_node object
+ * batadv_neigh_node_create - create a neigh node object
* @orig_node: originator object representing the neighbour
* @hard_iface: the interface where the neighbour is connected to
* @neigh_addr: the mac address of the neighbour interface
*
* Allocates a new neigh_node object and initialises all the generic fields.
*
- * Return: neighbor when found. Othwerwise NULL
+ * Return: the neighbour node if found or created or NULL otherwise.
*/
-struct batadv_neigh_node *
-batadv_neigh_node_new(struct batadv_orig_node *orig_node,
- struct batadv_hard_iface *hard_iface,
- const u8 *neigh_addr)
+static struct batadv_neigh_node *
+batadv_neigh_node_create(struct batadv_orig_node *orig_node,
+ struct batadv_hard_iface *hard_iface,
+ const u8 *neigh_addr)
{
struct batadv_neigh_node *neigh_node;
struct batadv_hardif_neigh_node *hardif_neigh = NULL;
@@ -667,6 +664,29 @@ out:
}
/**
+ * batadv_neigh_node_get_or_create - retrieve or create a neigh node object
+ * @orig_node: originator object representing the neighbour
+ * @hard_iface: the interface where the neighbour is connected to
+ * @neigh_addr: the mac address of the neighbour interface
+ *
+ * Return: the neighbour node if found or created or NULL otherwise.
+ */
+struct batadv_neigh_node *
+batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node,
+ struct batadv_hard_iface *hard_iface,
+ const u8 *neigh_addr)
+{
+ struct batadv_neigh_node *neigh_node = NULL;
+
+ /* first check without locking to avoid the overhead */
+ neigh_node = batadv_neigh_node_get(orig_node, hard_iface, neigh_addr);
+ if (neigh_node)
+ return neigh_node;
+
+ return batadv_neigh_node_create(orig_node, hard_iface, neigh_addr);
+}
+
+/**
* batadv_hardif_neigh_seq_print_text - print the single hop neighbour list
* @seq: neighbour table seq_file struct
* @offset: not used
@@ -686,17 +706,17 @@ int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset)
seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s %s)]\n",
BATADV_SOURCE_VERSION, primary_if->net_dev->name,
primary_if->net_dev->dev_addr, net_dev->name,
- bat_priv->bat_algo_ops->name);
+ bat_priv->algo_ops->name);
batadv_hardif_put(primary_if);
- if (!bat_priv->bat_algo_ops->bat_neigh_print) {
+ if (!bat_priv->algo_ops->neigh.print) {
seq_puts(seq,
"No printing function for this routing protocol\n");
return 0;
}
- bat_priv->bat_algo_ops->bat_neigh_print(bat_priv, seq);
+ bat_priv->algo_ops->neigh.print(bat_priv, seq);
return 0;
}
@@ -747,8 +767,8 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
batadv_frag_purge_orig(orig_node, NULL);
- if (orig_node->bat_priv->bat_algo_ops->bat_orig_free)
- orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node);
+ if (orig_node->bat_priv->algo_ops->orig.free)
+ orig_node->bat_priv->algo_ops->orig.free(orig_node);
kfree(orig_node->tt_buff);
kfree(orig_node);
@@ -1092,12 +1112,12 @@ batadv_find_best_neighbor(struct batadv_priv *bat_priv,
struct batadv_hard_iface *if_outgoing)
{
struct batadv_neigh_node *best = NULL, *neigh;
- struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+ struct batadv_algo_ops *bao = bat_priv->algo_ops;
rcu_read_lock();
hlist_for_each_entry_rcu(neigh, &orig_node->neigh_list, list) {
- if (best && (bao->bat_neigh_cmp(neigh, if_outgoing,
- best, if_outgoing) <= 0))
+ if (best && (bao->neigh.cmp(neigh, if_outgoing, best,
+ if_outgoing) <= 0))
continue;
if (!kref_get_unless_zero(&neigh->refcount))
@@ -1249,18 +1269,17 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset)
seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s %s)]\n",
BATADV_SOURCE_VERSION, primary_if->net_dev->name,
primary_if->net_dev->dev_addr, net_dev->name,
- bat_priv->bat_algo_ops->name);
+ bat_priv->algo_ops->name);
batadv_hardif_put(primary_if);
- if (!bat_priv->bat_algo_ops->bat_orig_print) {
+ if (!bat_priv->algo_ops->orig.print) {
seq_puts(seq,
"No printing function for this routing protocol\n");
return 0;
}
- bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq,
- BATADV_IF_DEFAULT);
+ bat_priv->algo_ops->orig.print(bat_priv, seq, BATADV_IF_DEFAULT);
return 0;
}
@@ -1287,7 +1306,7 @@ int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
}
bat_priv = netdev_priv(hard_iface->soft_iface);
- if (!bat_priv->bat_algo_ops->bat_orig_print) {
+ if (!bat_priv->algo_ops->orig.print) {
seq_puts(seq,
"No printing function for this routing protocol\n");
goto out;
@@ -1301,9 +1320,9 @@ int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
seq_printf(seq, "[B.A.T.M.A.N. adv %s, IF/MAC: %s/%pM (%s %s)]\n",
BATADV_SOURCE_VERSION, hard_iface->net_dev->name,
hard_iface->net_dev->dev_addr,
- hard_iface->soft_iface->name, bat_priv->bat_algo_ops->name);
+ hard_iface->soft_iface->name, bat_priv->algo_ops->name);
- bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface);
+ bat_priv->algo_ops->orig.print(bat_priv, seq, hard_iface);
out:
if (hard_iface)
@@ -1315,7 +1334,7 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface,
int max_if_num)
{
struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
- struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+ struct batadv_algo_ops *bao = bat_priv->algo_ops;
struct batadv_hashtable *hash = bat_priv->orig_hash;
struct hlist_head *head;
struct batadv_orig_node *orig_node;
@@ -1331,9 +1350,8 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface,
rcu_read_lock();
hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
ret = 0;
- if (bao->bat_orig_add_if)
- ret = bao->bat_orig_add_if(orig_node,
- max_if_num);
+ if (bao->orig.add_if)
+ ret = bao->orig.add_if(orig_node, max_if_num);
if (ret == -ENOMEM)
goto err;
}
@@ -1355,7 +1373,7 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface,
struct hlist_head *head;
struct batadv_hard_iface *hard_iface_tmp;
struct batadv_orig_node *orig_node;
- struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+ struct batadv_algo_ops *bao = bat_priv->algo_ops;
u32 i;
int ret;
@@ -1368,10 +1386,9 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface,
rcu_read_lock();
hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
ret = 0;
- if (bao->bat_orig_del_if)
- ret = bao->bat_orig_del_if(orig_node,
- max_if_num,
- hard_iface->if_num);
+ if (bao->orig.del_if)
+ ret = bao->orig.del_if(orig_node, max_if_num,
+ hard_iface->if_num);
if (ret == -ENOMEM)
goto err;
}
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index 64a8951e5844..566306bf05dc 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -46,9 +46,9 @@ batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface,
void
batadv_hardif_neigh_put(struct batadv_hardif_neigh_node *hardif_neigh);
struct batadv_neigh_node *
-batadv_neigh_node_new(struct batadv_orig_node *orig_node,
- struct batadv_hard_iface *hard_iface,
- const u8 *neigh_addr);
+batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node,
+ struct batadv_hard_iface *hard_iface,
+ const u8 *neigh_addr);
void batadv_neigh_node_put(struct batadv_neigh_node *neigh_node);
struct batadv_neigh_node *
batadv_orig_router_get(struct batadv_orig_node *orig_node,
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 372128ddb474..6b011ff64dd8 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -21,6 +21,8 @@
#include <asm/byteorder.h>
#include <linux/types.h>
+#define batadv_tp_is_error(n) ((u8)n > 127 ? 1 : 0)
+
/**
* enum batadv_packettype - types for batman-adv encapsulated packets
* @BATADV_IV_OGM: originator messages for B.A.T.M.A.N. IV
@@ -93,6 +95,7 @@ enum batadv_icmp_packettype {
BATADV_ECHO_REQUEST = 8,
BATADV_TTL_EXCEEDED = 11,
BATADV_PARAMETER_PROBLEM = 12,
+ BATADV_TP = 15,
};
/**
@@ -285,6 +288,16 @@ struct batadv_elp_packet {
#define BATADV_ELP_HLEN sizeof(struct batadv_elp_packet)
/**
+ * enum batadv_icmp_user_cmd_type - types for batman-adv icmp cmd modes
+ * @BATADV_TP_START: start a throughput meter run
+ * @BATADV_TP_STOP: stop a throughput meter run
+ */
+enum batadv_icmp_user_cmd_type {
+ BATADV_TP_START = 0,
+ BATADV_TP_STOP = 2,
+};
+
+/**
* struct batadv_icmp_header - common members among all the ICMP packets
* @packet_type: batman-adv packet type, part of the general header
* @version: batman-adv protocol version, part of the genereal header
@@ -334,6 +347,47 @@ struct batadv_icmp_packet {
__be16 seqno;
};
+/**
+ * struct batadv_icmp_tp_packet - ICMP TP Meter packet
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @msg_type: ICMP packet type
+ * @dst: address of the destination node
+ * @orig: address of the source node
+ * @uid: local ICMP socket identifier
+ * @subtype: TP packet subtype (see batadv_icmp_tp_subtype)
+ * @session: TP session identifier
+ * @seqno: the TP sequence number
+ * @timestamp: time when the packet has been sent. This value is filled in a
+ * TP_MSG and echoed back in the next TP_ACK so that the sender can compute the
+ * RTT. Since it is read only by the host which wrote it, there is no need to
+ * store it using network order
+ */
+struct batadv_icmp_tp_packet {
+ u8 packet_type;
+ u8 version;
+ u8 ttl;
+ u8 msg_type; /* see ICMP message types above */
+ u8 dst[ETH_ALEN];
+ u8 orig[ETH_ALEN];
+ u8 uid;
+ u8 subtype;
+ u8 session[2];
+ __be32 seqno;
+ __be32 timestamp;
+};
+
+/**
+ * enum batadv_icmp_tp_subtype - ICMP TP Meter packet subtypes
+ * @BATADV_TP_MSG: Msg from sender to receiver
+ * @BATADV_TP_ACK: acknowledgment from receiver to sender
+ */
+enum batadv_icmp_tp_subtype {
+ BATADV_TP_MSG = 0,
+ BATADV_TP_ACK,
+};
+
#define BATADV_RR_LEN 16
/**
@@ -420,6 +474,7 @@ struct batadv_unicast_4addr_packet {
* @dest: final destination used when routing fragments
* @orig: originator of the fragment used when merging the packet
* @no: fragment number within this sequence
+ * @priority: priority of frame, from ToS IP precedence or 802.1p
* @reserved: reserved byte for alignment
* @seqno: sequence identification
* @total_size: size of the merged packet
@@ -430,9 +485,11 @@ struct batadv_frag_packet {
u8 ttl;
#if defined(__BIG_ENDIAN_BITFIELD)
u8 no:4;
- u8 reserved:4;
+ u8 priority:3;
+ u8 reserved:1;
#elif defined(__LITTLE_ENDIAN_BITFIELD)
- u8 reserved:4;
+ u8 reserved:1;
+ u8 priority:3;
u8 no:4;
#else
#error "unknown bitfield endianness"
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index bfac086b4d01..7602c001e92b 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -40,12 +40,15 @@
#include "fragmentation.h"
#include "hard-interface.h"
#include "icmp_socket.h"
+#include "log.h"
#include "network-coding.h"
#include "originator.h"
#include "packet.h"
#include "send.h"
#include "soft-interface.h"
+#include "tp_meter.h"
#include "translation-table.h"
+#include "tvlv.h"
static int batadv_route_unicast_packet(struct sk_buff *skb,
struct batadv_hard_iface *recv_if);
@@ -268,10 +271,19 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv,
icmph->ttl = BATADV_TTL;
res = batadv_send_skb_to_orig(skb, orig_node, NULL);
- if (res != NET_XMIT_DROP)
- ret = NET_RX_SUCCESS;
+ if (res == -1)
+ goto out;
+
+ ret = NET_RX_SUCCESS;
break;
+ case BATADV_TP:
+ if (!pskb_may_pull(skb, sizeof(struct batadv_icmp_tp_packet)))
+ goto out;
+
+ batadv_tp_meter_recv(bat_priv, skb);
+ ret = NET_RX_SUCCESS;
+ goto out;
default:
/* drop unknown type */
goto out;
@@ -290,7 +302,7 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
struct batadv_hard_iface *primary_if = NULL;
struct batadv_orig_node *orig_node = NULL;
struct batadv_icmp_packet *icmp_packet;
- int ret = NET_RX_DROP;
+ int res, ret = NET_RX_DROP;
icmp_packet = (struct batadv_icmp_packet *)skb->data;
@@ -321,7 +333,8 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
icmp_packet->msg_type = BATADV_TTL_EXCEEDED;
icmp_packet->ttl = BATADV_TTL;
- if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
+ res = batadv_send_skb_to_orig(skb, orig_node, NULL);
+ if (res != -1)
ret = NET_RX_SUCCESS;
out:
@@ -341,7 +354,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
struct ethhdr *ethhdr;
struct batadv_orig_node *orig_node = NULL;
int hdr_size = sizeof(struct batadv_icmp_header);
- int ret = NET_RX_DROP;
+ int res, ret = NET_RX_DROP;
/* drop packet if it has not necessary minimum size */
if (unlikely(!pskb_may_pull(skb, hdr_size)))
@@ -408,7 +421,8 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
icmph->ttl--;
/* route it */
- if (batadv_send_skb_to_orig(skb, orig_node, recv_if) != NET_XMIT_DROP)
+ res = batadv_send_skb_to_orig(skb, orig_node, recv_if);
+ if (res != -1)
ret = NET_RX_SUCCESS;
out:
@@ -492,7 +506,7 @@ batadv_find_router(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
struct batadv_hard_iface *recv_if)
{
- struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+ struct batadv_algo_ops *bao = bat_priv->algo_ops;
struct batadv_neigh_node *first_candidate_router = NULL;
struct batadv_neigh_node *next_candidate_router = NULL;
struct batadv_neigh_node *router, *cand_router = NULL;
@@ -546,9 +560,9 @@ batadv_find_router(struct batadv_priv *bat_priv,
/* alternative candidate should be good enough to be
* considered
*/
- if (!bao->bat_neigh_is_similar_or_better(cand_router,
- cand->if_outgoing,
- router, recv_if))
+ if (!bao->neigh.is_similar_or_better(cand_router,
+ cand->if_outgoing, router,
+ recv_if))
goto next;
/* don't use the same router twice */
@@ -671,6 +685,8 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
len = skb->len;
res = batadv_send_skb_to_orig(skb, orig_node, recv_if);
+ if (res == -1)
+ goto out;
/* translate transmit result into receive result */
if (res == NET_XMIT_SUCCESS) {
@@ -678,13 +694,10 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD);
batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES,
len + ETH_HLEN);
-
- ret = NET_RX_SUCCESS;
- } else if (res == NET_XMIT_POLICED) {
- /* skb was buffered and consumed */
- ret = NET_RX_SUCCESS;
}
+ ret = NET_RX_SUCCESS;
+
out:
if (orig_node)
batadv_orig_node_put(orig_node);
@@ -1033,6 +1046,8 @@ int batadv_recv_frag_packet(struct sk_buff *skb,
if (!orig_node_src)
goto out;
+ skb->priority = frag_packet->priority + 256;
+
/* Route the fragment if it is not for us and too big to be merged. */
if (!batadv_is_my_mac(bat_priv, frag_packet->dest) &&
batadv_frag_skb_fwd(skb, recv_if, orig_node_src)) {
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 010397650fa5..6191159484df 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -20,10 +20,11 @@
#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/if.h>
+#include <linux/if_ether.h>
#include <linux/jiffies.h>
#include <linux/kernel.h>
#include <linux/kref.h>
@@ -42,6 +43,7 @@
#include "fragmentation.h"
#include "gateway_client.h"
#include "hard-interface.h"
+#include "log.h"
#include "network-coding.h"
#include "originator.h"
#include "routing.h"
@@ -71,6 +73,7 @@ int batadv_send_skb_packet(struct sk_buff *skb,
{
struct batadv_priv *bat_priv;
struct ethhdr *ethhdr;
+ int ret;
bat_priv = netdev_priv(hard_iface->soft_iface);
@@ -108,8 +111,15 @@ int batadv_send_skb_packet(struct sk_buff *skb,
/* dev_queue_xmit() returns a negative result on error. However on
* congestion and traffic shaping, it drops and returns NET_XMIT_DROP
* (which is > 0). This will not be treated as an error.
+ *
+ * a negative value cannot be returned because it could be interepreted
+ * as not consumed skb by callers of batadv_send_skb_to_orig.
*/
- return dev_queue_xmit(skb);
+ ret = dev_queue_xmit(skb);
+ if (ret < 0)
+ ret = NET_XMIT_DROP;
+
+ return ret;
send_skb_err:
kfree_skb(skb);
return NET_XMIT_DROP;
@@ -155,8 +165,11 @@ int batadv_send_unicast_skb(struct sk_buff *skb,
* host, NULL can be passed as recv_if and no interface alternating is
* attempted.
*
- * Return: NET_XMIT_SUCCESS on success, NET_XMIT_DROP on failure, or
- * NET_XMIT_POLICED if the skb is buffered for later transmit.
+ * Return: -1 on failure (and the skb is not consumed), -EINPROGRESS if the
+ * skb is buffered for later transmit or the NET_XMIT status returned by the
+ * lower routine if the packet has been passed down.
+ *
+ * If the returning value is not -1 the skb has been consumed.
*/
int batadv_send_skb_to_orig(struct sk_buff *skb,
struct batadv_orig_node *orig_node,
@@ -164,7 +177,7 @@ int batadv_send_skb_to_orig(struct sk_buff *skb,
{
struct batadv_priv *bat_priv = orig_node->bat_priv;
struct batadv_neigh_node *neigh_node;
- int ret = NET_XMIT_DROP;
+ int ret = -1;
/* batadv_find_router() increases neigh_nodes refcount if found. */
neigh_node = batadv_find_router(bat_priv, orig_node, recv_if);
@@ -177,8 +190,7 @@ int batadv_send_skb_to_orig(struct sk_buff *skb,
if (atomic_read(&bat_priv->fragmentation) &&
skb->len > neigh_node->if_incoming->net_dev->mtu) {
/* Fragment and send packet. */
- if (batadv_frag_send_packet(skb, orig_node, neigh_node))
- ret = NET_XMIT_SUCCESS;
+ ret = batadv_frag_send_packet(skb, orig_node, neigh_node);
goto out;
}
@@ -187,12 +199,10 @@ int batadv_send_skb_to_orig(struct sk_buff *skb,
* (i.e. being forwarded). If the packet originates from this node or if
* network coding fails, then send the packet as usual.
*/
- if (recv_if && batadv_nc_skb_forward(skb, neigh_node)) {
- ret = NET_XMIT_POLICED;
- } else {
- batadv_send_unicast_skb(skb, neigh_node);
- ret = NET_XMIT_SUCCESS;
- }
+ if (recv_if && batadv_nc_skb_forward(skb, neigh_node))
+ ret = -EINPROGRESS;
+ else
+ ret = batadv_send_unicast_skb(skb, neigh_node);
out:
if (neigh_node)
@@ -318,7 +328,7 @@ int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
{
struct batadv_unicast_packet *unicast_packet;
struct ethhdr *ethhdr;
- int ret = NET_XMIT_DROP;
+ int res, ret = NET_XMIT_DROP;
if (!orig_node)
goto out;
@@ -355,7 +365,8 @@ int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
if (batadv_tt_global_client_is_roaming(bat_priv, ethhdr->h_dest, vid))
unicast_packet->ttvn = unicast_packet->ttvn - 1;
- if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
+ res = batadv_send_skb_to_orig(skb, orig_node, NULL);
+ if (res != -1)
ret = NET_XMIT_SUCCESS;
out:
@@ -428,27 +439,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb,
BATADV_P_DATA, orig_node, vid);
}
-void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface)
-{
- struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
-
- if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) ||
- (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED))
- return;
-
- /* the interface gets activated here to avoid race conditions between
- * the moment of activating the interface in
- * hardif_activate_interface() where the originator mac is set and
- * outdated packets (especially uninitialized mac addresses) in the
- * packet queue
- */
- if (hard_iface->if_status == BATADV_IF_TO_BE_ACTIVATED)
- hard_iface->if_status = BATADV_IF_ACTIVE;
-
- bat_priv->bat_algo_ops->bat_ogm_schedule(hard_iface);
-}
-
-static void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet)
+void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet)
{
kfree_skb(forw_packet->skb);
if (forw_packet->if_incoming)
@@ -604,45 +595,6 @@ out:
atomic_inc(&bat_priv->bcast_queue_left);
}
-void batadv_send_outstanding_bat_ogm_packet(struct work_struct *work)
-{
- struct delayed_work *delayed_work;
- struct batadv_forw_packet *forw_packet;
- struct batadv_priv *bat_priv;
-
- delayed_work = to_delayed_work(work);
- forw_packet = container_of(delayed_work, struct batadv_forw_packet,
- delayed_work);
- bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface);
- spin_lock_bh(&bat_priv->forw_bat_list_lock);
- hlist_del(&forw_packet->list);
- spin_unlock_bh(&bat_priv->forw_bat_list_lock);
-
- if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING)
- goto out;
-
- bat_priv->bat_algo_ops->bat_ogm_emit(forw_packet);
-
- /* we have to have at least one packet in the queue to determine the
- * queues wake up time unless we are shutting down.
- *
- * only re-schedule if this is the "original" copy, e.g. the OGM of the
- * primary interface should only be rescheduled once per period, but
- * this function will be called for the forw_packet instances of the
- * other secondary interfaces as well.
- */
- if (forw_packet->own &&
- forw_packet->if_incoming == forw_packet->if_outgoing)
- batadv_schedule_bat_ogm(forw_packet->if_incoming);
-
-out:
- /* don't count own packet */
- if (!forw_packet->own)
- atomic_inc(&bat_priv->batman_queue_left);
-
- batadv_forw_packet_free(forw_packet);
-}
-
void
batadv_purge_outstanding_packets(struct batadv_priv *bat_priv,
const struct batadv_hard_iface *hard_iface)
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index 6fd7270d8ce6..7cecb7563b45 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -26,8 +26,8 @@
#include "packet.h"
struct sk_buff;
-struct work_struct;
+void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet);
int batadv_send_skb_to_orig(struct sk_buff *skb,
struct batadv_orig_node *orig_node,
struct batadv_hard_iface *recv_if);
@@ -38,11 +38,9 @@ int batadv_send_broadcast_skb(struct sk_buff *skb,
struct batadv_hard_iface *hard_iface);
int batadv_send_unicast_skb(struct sk_buff *skb,
struct batadv_neigh_node *neigh_node);
-void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface);
int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
const struct sk_buff *skb,
unsigned long delay);
-void batadv_send_outstanding_bat_ogm_packet(struct work_struct *work);
void
batadv_purge_outstanding_packets(struct batadv_priv *bat_priv,
const struct batadv_hard_iface *hard_iface);
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 287a3879ed7e..7527c0652dd5 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -48,6 +48,7 @@
#include <linux/types.h>
#include <linux/workqueue.h>
+#include "bat_algo.h"
#include "bridge_loop_avoidance.h"
#include "debugfs.h"
#include "distributed-arp-table.h"
@@ -255,7 +256,7 @@ static int batadv_interface_tx(struct sk_buff *skb,
if (batadv_compare_eth(ethhdr->h_dest, ectp_addr))
goto dropped;
- gw_mode = atomic_read(&bat_priv->gw_mode);
+ gw_mode = atomic_read(&bat_priv->gw.mode);
if (is_multicast_ether_addr(ethhdr->h_dest)) {
/* if gw mode is off, broadcast every packet */
if (gw_mode == BATADV_GW_MODE_OFF) {
@@ -808,6 +809,10 @@ static int batadv_softif_init_late(struct net_device *dev)
atomic_set(&bat_priv->distributed_arp_table, 1);
#endif
#ifdef CONFIG_BATMAN_ADV_MCAST
+ bat_priv->mcast.querier_ipv4.exists = false;
+ bat_priv->mcast.querier_ipv4.shadowing = false;
+ bat_priv->mcast.querier_ipv6.exists = false;
+ bat_priv->mcast.querier_ipv6.shadowing = false;
bat_priv->mcast.flags = BATADV_NO_FLAGS;
atomic_set(&bat_priv->multicast_mode, 1);
atomic_set(&bat_priv->mcast.num_disabled, 0);
@@ -815,8 +820,8 @@ static int batadv_softif_init_late(struct net_device *dev)
atomic_set(&bat_priv->mcast.num_want_all_ipv4, 0);
atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0);
#endif
- atomic_set(&bat_priv->gw_mode, BATADV_GW_MODE_OFF);
- atomic_set(&bat_priv->gw_sel_class, 20);
+ atomic_set(&bat_priv->gw.mode, BATADV_GW_MODE_OFF);
+ atomic_set(&bat_priv->gw.sel_class, 20);
atomic_set(&bat_priv->gw.bandwidth_down, 100);
atomic_set(&bat_priv->gw.bandwidth_up, 20);
atomic_set(&bat_priv->orig_interval, 1000);
@@ -837,6 +842,8 @@ static int batadv_softif_init_late(struct net_device *dev)
#ifdef CONFIG_BATMAN_ADV_BLA
atomic_set(&bat_priv->bla.num_requests, 0);
#endif
+ atomic_set(&bat_priv->tp_num, 0);
+
bat_priv->tt.last_changeset = NULL;
bat_priv->tt.last_changeset_len = 0;
bat_priv->isolation_mark = 0;
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 414b2074165f..fe9ca94ddee2 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -25,8 +25,8 @@
#include <linux/fs.h>
#include <linux/if.h>
#include <linux/if_vlan.h>
-#include <linux/kref.h>
#include <linux/kernel.h>
+#include <linux/kref.h>
#include <linux/netdevice.h>
#include <linux/printk.h>
#include <linux/rculist.h>
@@ -38,11 +38,12 @@
#include <linux/string.h>
#include <linux/stringify.h>
+#include "bridge_loop_avoidance.h"
#include "distributed-arp-table.h"
#include "gateway_client.h"
#include "gateway_common.h"
-#include "bridge_loop_avoidance.h"
#include "hard-interface.h"
+#include "log.h"
#include "network-coding.h"
#include "packet.h"
#include "soft-interface.h"
@@ -389,12 +390,12 @@ static int batadv_store_uint_attr(const char *buff, size_t count,
return count;
}
-static inline ssize_t
-__batadv_store_uint_attr(const char *buff, size_t count,
- int min, int max,
- void (*post_func)(struct net_device *),
- const struct attribute *attr,
- atomic_t *attr_store, struct net_device *net_dev)
+static ssize_t __batadv_store_uint_attr(const char *buff, size_t count,
+ int min, int max,
+ void (*post_func)(struct net_device *),
+ const struct attribute *attr,
+ atomic_t *attr_store,
+ struct net_device *net_dev)
{
int ret;
@@ -411,7 +412,7 @@ static ssize_t batadv_show_bat_algo(struct kobject *kobj,
{
struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
- return sprintf(buff, "%s\n", bat_priv->bat_algo_ops->name);
+ return sprintf(buff, "%s\n", bat_priv->algo_ops->name);
}
static void batadv_post_gw_reselect(struct net_device *net_dev)
@@ -427,7 +428,7 @@ static ssize_t batadv_show_gw_mode(struct kobject *kobj, struct attribute *attr,
struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
int bytes_written;
- switch (atomic_read(&bat_priv->gw_mode)) {
+ switch (atomic_read(&bat_priv->gw.mode)) {
case BATADV_GW_MODE_CLIENT:
bytes_written = sprintf(buff, "%s\n",
BATADV_GW_MODE_CLIENT_NAME);
@@ -476,10 +477,10 @@ static ssize_t batadv_store_gw_mode(struct kobject *kobj,
return -EINVAL;
}
- if (atomic_read(&bat_priv->gw_mode) == gw_mode_tmp)
+ if (atomic_read(&bat_priv->gw.mode) == gw_mode_tmp)
return count;
- switch (atomic_read(&bat_priv->gw_mode)) {
+ switch (atomic_read(&bat_priv->gw.mode)) {
case BATADV_GW_MODE_CLIENT:
curr_gw_mode_str = BATADV_GW_MODE_CLIENT_NAME;
break;
@@ -508,7 +509,7 @@ static ssize_t batadv_store_gw_mode(struct kobject *kobj,
* state
*/
batadv_gw_check_client_stop(bat_priv);
- atomic_set(&bat_priv->gw_mode, (unsigned int)gw_mode_tmp);
+ atomic_set(&bat_priv->gw.mode, (unsigned int)gw_mode_tmp);
batadv_gw_tvlv_container_update(bat_priv);
return count;
}
@@ -624,7 +625,7 @@ 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_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);
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
new file mode 100644
index 000000000000..2333777f919d
--- /dev/null
+++ b/net/batman-adv/tp_meter.c
@@ -0,0 +1,1507 @@
+/* Copyright (C) 2012-2016 B.A.T.M.A.N. contributors:
+ *
+ * Edo Monticelli, Antonio Quartulli
+ *
+ * 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/>.
+ */
+
+#include "tp_meter.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/byteorder/generic.h>
+#include <linux/cache.h>
+#include <linux/compiler.h>
+#include <linux/device.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/kref.h>
+#include <linux/kthread.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/param.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+#include <uapi/linux/batman_adv.h>
+
+#include "hard-interface.h"
+#include "log.h"
+#include "netlink.h"
+#include "originator.h"
+#include "packet.h"
+#include "send.h"
+
+/**
+ * BATADV_TP_DEF_TEST_LENGTH - Default test length if not specified by the user
+ * in milliseconds
+ */
+#define BATADV_TP_DEF_TEST_LENGTH 10000
+
+/**
+ * BATADV_TP_AWND - Advertised window by the receiver (in bytes)
+ */
+#define BATADV_TP_AWND 0x20000000
+
+/**
+ * BATADV_TP_RECV_TIMEOUT - Receiver activity timeout. If the receiver does not
+ * get anything for such amount of milliseconds, the connection is killed
+ */
+#define BATADV_TP_RECV_TIMEOUT 1000
+
+/**
+ * BATADV_TP_MAX_RTO - Maximum sender timeout. If the sender RTO gets beyond
+ * such amound of milliseconds, the receiver is considered unreachable and the
+ * connection is killed
+ */
+#define BATADV_TP_MAX_RTO 30000
+
+/**
+ * BATADV_TP_FIRST_SEQ - First seqno of each session. The number is rather high
+ * in order to immediately trigger a wrap around (test purposes)
+ */
+#define BATADV_TP_FIRST_SEQ ((u32)-1 - 2000)
+
+/**
+ * BATADV_TP_PLEN - length of the payload (data after the batadv_unicast header)
+ * to simulate
+ */
+#define BATADV_TP_PLEN (BATADV_TP_PACKET_LEN - ETH_HLEN - \
+ sizeof(struct batadv_unicast_packet))
+
+static u8 batadv_tp_prerandom[4096] __read_mostly;
+
+/**
+ * batadv_tp_session_cookie - generate session cookie based on session ids
+ * @session: TP session identifier
+ * @icmp_uid: icmp pseudo uid of the tp session
+ *
+ * Return: 32 bit tp_meter session cookie
+ */
+static u32 batadv_tp_session_cookie(const u8 session[2], u8 icmp_uid)
+{
+ u32 cookie;
+
+ cookie = icmp_uid << 16;
+ cookie |= session[0] << 8;
+ cookie |= session[1];
+
+ return cookie;
+}
+
+/**
+ * batadv_tp_cwnd - compute the new cwnd size
+ * @base: base cwnd size value
+ * @increment: the value to add to base to get the new size
+ * @min: minumim cwnd value (usually MSS)
+ *
+ * Return the new cwnd size and ensures it does not exceed the Advertised
+ * Receiver Window size. It is wrap around safe.
+ * For details refer to Section 3.1 of RFC5681
+ *
+ * Return: new congestion window size in bytes
+ */
+static u32 batadv_tp_cwnd(u32 base, u32 increment, u32 min)
+{
+ u32 new_size = base + increment;
+
+ /* check for wrap-around */
+ if (new_size < base)
+ new_size = (u32)ULONG_MAX;
+
+ new_size = min_t(u32, new_size, BATADV_TP_AWND);
+
+ return max_t(u32, new_size, min);
+}
+
+/**
+ * batadv_tp_updated_cwnd - update the Congestion Windows
+ * @tp_vars: the private data of the current TP meter session
+ * @mss: maximum segment size of transmission
+ *
+ * 1) if the session is in Slow Start, the CWND has to be increased by 1
+ * MSS every unique received ACK
+ * 2) if the session is in Congestion Avoidance, the CWND has to be
+ * increased by MSS * MSS / CWND for every unique received ACK
+ */
+static void batadv_tp_update_cwnd(struct batadv_tp_vars *tp_vars, u32 mss)
+{
+ spin_lock_bh(&tp_vars->cwnd_lock);
+
+ /* slow start... */
+ if (tp_vars->cwnd <= tp_vars->ss_threshold) {
+ tp_vars->dec_cwnd = 0;
+ tp_vars->cwnd = batadv_tp_cwnd(tp_vars->cwnd, mss, mss);
+ spin_unlock_bh(&tp_vars->cwnd_lock);
+ return;
+ }
+
+ /* increment CWND at least of 1 (section 3.1 of RFC5681) */
+ tp_vars->dec_cwnd += max_t(u32, 1U << 3,
+ ((mss * mss) << 6) / (tp_vars->cwnd << 3));
+ if (tp_vars->dec_cwnd < (mss << 3)) {
+ spin_unlock_bh(&tp_vars->cwnd_lock);
+ return;
+ }
+
+ tp_vars->cwnd = batadv_tp_cwnd(tp_vars->cwnd, mss, mss);
+ tp_vars->dec_cwnd = 0;
+
+ spin_unlock_bh(&tp_vars->cwnd_lock);
+}
+
+/**
+ * batadv_tp_update_rto - calculate new retransmission timeout
+ * @tp_vars: the private data of the current TP meter session
+ * @new_rtt: new roundtrip time in msec
+ */
+static void batadv_tp_update_rto(struct batadv_tp_vars *tp_vars,
+ u32 new_rtt)
+{
+ long m = new_rtt;
+
+ /* RTT update
+ * Details in Section 2.2 and 2.3 of RFC6298
+ *
+ * It's tricky to understand. Don't lose hair please.
+ * Inspired by tcp_rtt_estimator() tcp_input.c
+ */
+ if (tp_vars->srtt != 0) {
+ m -= (tp_vars->srtt >> 3); /* m is now error in rtt est */
+ tp_vars->srtt += m; /* rtt = 7/8 srtt + 1/8 new */
+ if (m < 0)
+ m = -m;
+
+ m -= (tp_vars->rttvar >> 2);
+ tp_vars->rttvar += m; /* mdev ~= 3/4 rttvar + 1/4 new */
+ } else {
+ /* first measure getting in */
+ tp_vars->srtt = m << 3; /* take the measured time to be srtt */
+ tp_vars->rttvar = m << 1; /* new_rtt / 2 */
+ }
+
+ /* rto = srtt + 4 * rttvar.
+ * rttvar is scaled by 4, therefore doesn't need to be multiplied
+ */
+ tp_vars->rto = (tp_vars->srtt >> 3) + tp_vars->rttvar;
+}
+
+/**
+ * batadv_tp_batctl_notify - send client status result to client
+ * @reason: reason for tp meter session stop
+ * @dst: destination of tp_meter session
+ * @bat_priv: the bat priv with all the soft interface information
+ * @start_time: start of transmission in jiffies
+ * @total_sent: bytes acked to the receiver
+ * @cookie: cookie of tp_meter session
+ */
+static void batadv_tp_batctl_notify(enum batadv_tp_meter_reason reason,
+ const u8 *dst, struct batadv_priv *bat_priv,
+ unsigned long start_time, u64 total_sent,
+ u32 cookie)
+{
+ u32 test_time;
+ u8 result;
+ u32 total_bytes;
+
+ if (!batadv_tp_is_error(reason)) {
+ result = BATADV_TP_REASON_COMPLETE;
+ test_time = jiffies_to_msecs(jiffies - start_time);
+ total_bytes = total_sent;
+ } else {
+ result = reason;
+ test_time = 0;
+ total_bytes = 0;
+ }
+
+ batadv_netlink_tpmeter_notify(bat_priv, dst, result, test_time,
+ total_bytes, cookie);
+}
+
+/**
+ * batadv_tp_batctl_error_notify - send client error result to client
+ * @reason: reason for tp meter session stop
+ * @dst: destination of tp_meter session
+ * @bat_priv: the bat priv with all the soft interface information
+ * @cookie: cookie of tp_meter session
+ */
+static void batadv_tp_batctl_error_notify(enum batadv_tp_meter_reason reason,
+ const u8 *dst,
+ struct batadv_priv *bat_priv,
+ u32 cookie)
+{
+ batadv_tp_batctl_notify(reason, dst, bat_priv, 0, 0, cookie);
+}
+
+/**
+ * batadv_tp_list_find - find a tp_vars object in the global list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: the other endpoint MAC address to look for
+ *
+ * Look for a tp_vars object matching dst as end_point and return it after
+ * having incremented the refcounter. Return NULL is not found
+ *
+ * Return: matching tp_vars or NULL when no tp_vars with @dst was found
+ */
+static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv,
+ const u8 *dst)
+{
+ struct batadv_tp_vars *pos, *tp_vars = NULL;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(pos, &bat_priv->tp_list, list) {
+ if (!batadv_compare_eth(pos->other_end, dst))
+ continue;
+
+ /* most of the time this function is invoked during the normal
+ * process..it makes sens to pay more when the session is
+ * finished and to speed the process up during the measurement
+ */
+ if (unlikely(!kref_get_unless_zero(&pos->refcount)))
+ continue;
+
+ tp_vars = pos;
+ break;
+ }
+ rcu_read_unlock();
+
+ return tp_vars;
+}
+
+/**
+ * batadv_tp_list_find_session - find tp_vars session object in the global list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: the other endpoint MAC address to look for
+ * @session: session identifier
+ *
+ * Look for a tp_vars object matching dst as end_point, session as tp meter
+ * session and return it after having incremented the refcounter. Return NULL
+ * is not found
+ *
+ * Return: matching tp_vars or NULL when no tp_vars was found
+ */
+static struct batadv_tp_vars *
+batadv_tp_list_find_session(struct batadv_priv *bat_priv, const u8 *dst,
+ const u8 *session)
+{
+ struct batadv_tp_vars *pos, *tp_vars = NULL;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(pos, &bat_priv->tp_list, list) {
+ if (!batadv_compare_eth(pos->other_end, dst))
+ continue;
+
+ if (memcmp(pos->session, session, sizeof(pos->session)) != 0)
+ continue;
+
+ /* most of the time this function is invoked during the normal
+ * process..it makes sense to pay more when the session is
+ * finished and to speed the process up during the measurement
+ */
+ if (unlikely(!kref_get_unless_zero(&pos->refcount)))
+ continue;
+
+ tp_vars = pos;
+ break;
+ }
+ rcu_read_unlock();
+
+ return tp_vars;
+}
+
+/**
+ * batadv_tp_vars_release - release batadv_tp_vars from lists and queue for
+ * free after rcu grace period
+ * @ref: kref pointer of the batadv_tp_vars
+ */
+static void batadv_tp_vars_release(struct kref *ref)
+{
+ struct batadv_tp_vars *tp_vars;
+ struct batadv_tp_unacked *un, *safe;
+
+ tp_vars = container_of(ref, struct batadv_tp_vars, refcount);
+
+ /* lock should not be needed because this object is now out of any
+ * context!
+ */
+ spin_lock_bh(&tp_vars->unacked_lock);
+ list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
+ list_del(&un->list);
+ kfree(un);
+ }
+ spin_unlock_bh(&tp_vars->unacked_lock);
+
+ kfree_rcu(tp_vars, rcu);
+}
+
+/**
+ * batadv_tp_vars_put - decrement the batadv_tp_vars refcounter and possibly
+ * release it
+ * @tp_vars: the private data of the current TP meter session to be free'd
+ */
+static void batadv_tp_vars_put(struct batadv_tp_vars *tp_vars)
+{
+ kref_put(&tp_vars->refcount, batadv_tp_vars_release);
+}
+
+/**
+ * batadv_tp_sender_cleanup - cleanup sender data and drop and timer
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tp_vars: the private data of the current TP meter session to cleanup
+ */
+static void batadv_tp_sender_cleanup(struct batadv_priv *bat_priv,
+ struct batadv_tp_vars *tp_vars)
+{
+ cancel_delayed_work(&tp_vars->finish_work);
+
+ spin_lock_bh(&tp_vars->bat_priv->tp_list_lock);
+ hlist_del_rcu(&tp_vars->list);
+ spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock);
+
+ /* drop list reference */
+ batadv_tp_vars_put(tp_vars);
+
+ atomic_dec(&tp_vars->bat_priv->tp_num);
+
+ /* kill the timer and remove its reference */
+ del_timer_sync(&tp_vars->timer);
+ /* the worker might have rearmed itself therefore we kill it again. Note
+ * that if the worker should run again before invoking the following
+ * del_timer(), it would not re-arm itself once again because the status
+ * is OFF now
+ */
+ del_timer(&tp_vars->timer);
+ batadv_tp_vars_put(tp_vars);
+}
+
+/**
+ * batadv_tp_sender_end - print info about ended session and inform client
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tp_vars: the private data of the current TP meter session
+ */
+static void batadv_tp_sender_end(struct batadv_priv *bat_priv,
+ struct batadv_tp_vars *tp_vars)
+{
+ u32 session_cookie;
+
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Test towards %pM finished..shutting down (reason=%d)\n",
+ tp_vars->other_end, tp_vars->reason);
+
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Last timing stats: SRTT=%ums RTTVAR=%ums RTO=%ums\n",
+ tp_vars->srtt >> 3, tp_vars->rttvar >> 2, tp_vars->rto);
+
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Final values: cwnd=%u ss_threshold=%u\n",
+ tp_vars->cwnd, tp_vars->ss_threshold);
+
+ session_cookie = batadv_tp_session_cookie(tp_vars->session,
+ tp_vars->icmp_uid);
+
+ batadv_tp_batctl_notify(tp_vars->reason,
+ tp_vars->other_end,
+ bat_priv,
+ tp_vars->start_time,
+ atomic64_read(&tp_vars->tot_sent),
+ session_cookie);
+}
+
+/**
+ * batadv_tp_sender_shutdown - let sender thread/timer stop gracefully
+ * @tp_vars: the private data of the current TP meter session
+ * @reason: reason for tp meter session stop
+ */
+static void batadv_tp_sender_shutdown(struct batadv_tp_vars *tp_vars,
+ enum batadv_tp_meter_reason reason)
+{
+ if (!atomic_dec_and_test(&tp_vars->sending))
+ return;
+
+ tp_vars->reason = reason;
+}
+
+/**
+ * batadv_tp_sender_finish - stop sender session after test_length was reached
+ * @work: delayed work reference of the related tp_vars
+ */
+static void batadv_tp_sender_finish(struct work_struct *work)
+{
+ struct delayed_work *delayed_work;
+ struct batadv_tp_vars *tp_vars;
+
+ delayed_work = to_delayed_work(work);
+ tp_vars = container_of(delayed_work, struct batadv_tp_vars,
+ finish_work);
+
+ batadv_tp_sender_shutdown(tp_vars, BATADV_TP_REASON_COMPLETE);
+}
+
+/**
+ * batadv_tp_reset_sender_timer - reschedule the sender timer
+ * @tp_vars: the private TP meter data for this session
+ *
+ * Reschedule the timer using tp_vars->rto as delay
+ */
+static void batadv_tp_reset_sender_timer(struct batadv_tp_vars *tp_vars)
+{
+ /* most of the time this function is invoked while normal packet
+ * reception...
+ */
+ if (unlikely(atomic_read(&tp_vars->sending) == 0))
+ /* timer ref will be dropped in batadv_tp_sender_cleanup */
+ return;
+
+ mod_timer(&tp_vars->timer, jiffies + msecs_to_jiffies(tp_vars->rto));
+}
+
+/**
+ * batadv_tp_sender_timeout - timer that fires in case of packet loss
+ * @arg: address of the related tp_vars
+ *
+ * If fired it means that there was packet loss.
+ * Switch to Slow Start, set the ss_threshold to half of the current cwnd and
+ * reset the cwnd to 3*MSS
+ */
+static void batadv_tp_sender_timeout(unsigned long arg)
+{
+ struct batadv_tp_vars *tp_vars = (struct batadv_tp_vars *)arg;
+ struct batadv_priv *bat_priv = tp_vars->bat_priv;
+
+ if (atomic_read(&tp_vars->sending) == 0)
+ return;
+
+ /* if the user waited long enough...shutdown the test */
+ if (unlikely(tp_vars->rto >= BATADV_TP_MAX_RTO)) {
+ batadv_tp_sender_shutdown(tp_vars,
+ BATADV_TP_REASON_DST_UNREACHABLE);
+ return;
+ }
+
+ /* RTO exponential backoff
+ * Details in Section 5.5 of RFC6298
+ */
+ tp_vars->rto <<= 1;
+
+ spin_lock_bh(&tp_vars->cwnd_lock);
+
+ tp_vars->ss_threshold = tp_vars->cwnd >> 1;
+ if (tp_vars->ss_threshold < BATADV_TP_PLEN * 2)
+ tp_vars->ss_threshold = BATADV_TP_PLEN * 2;
+
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: RTO fired during test towards %pM! cwnd=%u new ss_thr=%u, resetting last_sent to %u\n",
+ tp_vars->other_end, tp_vars->cwnd, tp_vars->ss_threshold,
+ atomic_read(&tp_vars->last_acked));
+
+ tp_vars->cwnd = BATADV_TP_PLEN * 3;
+
+ spin_unlock_bh(&tp_vars->cwnd_lock);
+
+ /* resend the non-ACKed packets.. */
+ tp_vars->last_sent = atomic_read(&tp_vars->last_acked);
+ wake_up(&tp_vars->more_bytes);
+
+ batadv_tp_reset_sender_timer(tp_vars);
+}
+
+/**
+ * batadv_tp_fill_prerandom - Fill buffer with prefetched random bytes
+ * @tp_vars: the private TP meter data for this session
+ * @buf: Buffer to fill with bytes
+ * @nbytes: amount of pseudorandom bytes
+ */
+static void batadv_tp_fill_prerandom(struct batadv_tp_vars *tp_vars,
+ u8 *buf, size_t nbytes)
+{
+ u32 local_offset;
+ size_t bytes_inbuf;
+ size_t to_copy;
+ size_t pos = 0;
+
+ spin_lock_bh(&tp_vars->prerandom_lock);
+ local_offset = tp_vars->prerandom_offset;
+ tp_vars->prerandom_offset += nbytes;
+ tp_vars->prerandom_offset %= sizeof(batadv_tp_prerandom);
+ spin_unlock_bh(&tp_vars->prerandom_lock);
+
+ while (nbytes) {
+ local_offset %= sizeof(batadv_tp_prerandom);
+ bytes_inbuf = sizeof(batadv_tp_prerandom) - local_offset;
+ to_copy = min(nbytes, bytes_inbuf);
+
+ memcpy(&buf[pos], &batadv_tp_prerandom[local_offset], to_copy);
+ pos += to_copy;
+ nbytes -= to_copy;
+ local_offset = 0;
+ }
+}
+
+/**
+ * batadv_tp_send_msg - send a single message
+ * @tp_vars: the private TP meter data for this session
+ * @src: source mac address
+ * @orig_node: the originator of the destination
+ * @seqno: sequence number of this packet
+ * @len: length of the entire packet
+ * @session: session identifier
+ * @uid: local ICMP "socket" index
+ * @timestamp: timestamp in jiffies which is replied in ack
+ *
+ * Create and send a single TP Meter message.
+ *
+ * Return: 0 on success, BATADV_TP_REASON_DST_UNREACHABLE if the destination is
+ * not reachable, BATADV_TP_REASON_MEMORY_ERROR if the packet couldn't be
+ * allocated
+ */
+static int batadv_tp_send_msg(struct batadv_tp_vars *tp_vars, const u8 *src,
+ struct batadv_orig_node *orig_node,
+ u32 seqno, size_t len, const u8 *session,
+ int uid, u32 timestamp)
+{
+ struct batadv_icmp_tp_packet *icmp;
+ struct sk_buff *skb;
+ int r;
+ u8 *data;
+ size_t data_len;
+
+ skb = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN);
+ if (unlikely(!skb))
+ return BATADV_TP_REASON_MEMORY_ERROR;
+
+ skb_reserve(skb, ETH_HLEN);
+ icmp = (struct batadv_icmp_tp_packet *)skb_put(skb, sizeof(*icmp));
+
+ /* fill the icmp header */
+ ether_addr_copy(icmp->dst, orig_node->orig);
+ ether_addr_copy(icmp->orig, src);
+ icmp->version = BATADV_COMPAT_VERSION;
+ icmp->packet_type = BATADV_ICMP;
+ icmp->ttl = BATADV_TTL;
+ icmp->msg_type = BATADV_TP;
+ icmp->uid = uid;
+
+ icmp->subtype = BATADV_TP_MSG;
+ memcpy(icmp->session, session, sizeof(icmp->session));
+ icmp->seqno = htonl(seqno);
+ icmp->timestamp = htonl(timestamp);
+
+ data_len = len - sizeof(*icmp);
+ data = (u8 *)skb_put(skb, data_len);
+ batadv_tp_fill_prerandom(tp_vars, data, data_len);
+
+ r = batadv_send_skb_to_orig(skb, orig_node, NULL);
+ if (r == -1)
+ kfree_skb(skb);
+
+ if (r == NET_XMIT_SUCCESS)
+ return 0;
+
+ return BATADV_TP_REASON_CANT_SEND;
+}
+
+/**
+ * batadv_tp_recv_ack - ACK receiving function
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the buffer containing the received packet
+ *
+ * Process a received TP ACK packet
+ */
+static void batadv_tp_recv_ack(struct batadv_priv *bat_priv,
+ const struct sk_buff *skb)
+{
+ struct batadv_hard_iface *primary_if = NULL;
+ struct batadv_orig_node *orig_node = NULL;
+ const struct batadv_icmp_tp_packet *icmp;
+ struct batadv_tp_vars *tp_vars;
+ size_t packet_len, mss;
+ u32 rtt, recv_ack, cwnd;
+ unsigned char *dev_addr;
+
+ packet_len = BATADV_TP_PLEN;
+ mss = BATADV_TP_PLEN;
+ packet_len += sizeof(struct batadv_unicast_packet);
+
+ icmp = (struct batadv_icmp_tp_packet *)skb->data;
+
+ /* find the tp_vars */
+ tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig,
+ icmp->session);
+ if (unlikely(!tp_vars))
+ return;
+
+ if (unlikely(atomic_read(&tp_vars->sending) == 0))
+ goto out;
+
+ /* old ACK? silently drop it.. */
+ if (batadv_seq_before(ntohl(icmp->seqno),
+ (u32)atomic_read(&tp_vars->last_acked)))
+ goto out;
+
+ primary_if = batadv_primary_if_get_selected(bat_priv);
+ if (unlikely(!primary_if))
+ goto out;
+
+ orig_node = batadv_orig_hash_find(bat_priv, icmp->orig);
+ if (unlikely(!orig_node))
+ goto out;
+
+ /* update RTO with the new sampled RTT, if any */
+ rtt = jiffies_to_msecs(jiffies) - ntohl(icmp->timestamp);
+ if (icmp->timestamp && rtt)
+ batadv_tp_update_rto(tp_vars, rtt);
+
+ /* ACK for new data... reset the timer */
+ batadv_tp_reset_sender_timer(tp_vars);
+
+ recv_ack = ntohl(icmp->seqno);
+
+ /* check if this ACK is a duplicate */
+ if (atomic_read(&tp_vars->last_acked) == recv_ack) {
+ atomic_inc(&tp_vars->dup_acks);
+ if (atomic_read(&tp_vars->dup_acks) != 3)
+ goto out;
+
+ if (recv_ack >= tp_vars->recover)
+ goto out;
+
+ /* if this is the third duplicate ACK do Fast Retransmit */
+ batadv_tp_send_msg(tp_vars, primary_if->net_dev->dev_addr,
+ orig_node, recv_ack, packet_len,
+ icmp->session, icmp->uid,
+ jiffies_to_msecs(jiffies));
+
+ spin_lock_bh(&tp_vars->cwnd_lock);
+
+ /* Fast Recovery */
+ tp_vars->fast_recovery = true;
+ /* Set recover to the last outstanding seqno when Fast Recovery
+ * is entered. RFC6582, Section 3.2, step 1
+ */
+ tp_vars->recover = tp_vars->last_sent;
+ tp_vars->ss_threshold = tp_vars->cwnd >> 1;
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: Fast Recovery, (cur cwnd=%u) ss_thr=%u last_sent=%u recv_ack=%u\n",
+ tp_vars->cwnd, tp_vars->ss_threshold,
+ tp_vars->last_sent, recv_ack);
+ tp_vars->cwnd = batadv_tp_cwnd(tp_vars->ss_threshold, 3 * mss,
+ mss);
+ tp_vars->dec_cwnd = 0;
+ tp_vars->last_sent = recv_ack;
+
+ spin_unlock_bh(&tp_vars->cwnd_lock);
+ } else {
+ /* count the acked data */
+ atomic64_add(recv_ack - atomic_read(&tp_vars->last_acked),
+ &tp_vars->tot_sent);
+ /* reset the duplicate ACKs counter */
+ atomic_set(&tp_vars->dup_acks, 0);
+
+ if (tp_vars->fast_recovery) {
+ /* partial ACK */
+ if (batadv_seq_before(recv_ack, tp_vars->recover)) {
+ /* this is another hole in the window. React
+ * immediately as specified by NewReno (see
+ * Section 3.2 of RFC6582 for details)
+ */
+ dev_addr = primary_if->net_dev->dev_addr;
+ batadv_tp_send_msg(tp_vars, dev_addr,
+ orig_node, recv_ack,
+ packet_len, icmp->session,
+ icmp->uid,
+ jiffies_to_msecs(jiffies));
+ tp_vars->cwnd = batadv_tp_cwnd(tp_vars->cwnd,
+ mss, mss);
+ } else {
+ tp_vars->fast_recovery = false;
+ /* set cwnd to the value of ss_threshold at the
+ * moment that Fast Recovery was entered.
+ * RFC6582, Section 3.2, step 3
+ */
+ cwnd = batadv_tp_cwnd(tp_vars->ss_threshold, 0,
+ mss);
+ tp_vars->cwnd = cwnd;
+ }
+ goto move_twnd;
+ }
+
+ if (recv_ack - atomic_read(&tp_vars->last_acked) >= mss)
+ batadv_tp_update_cwnd(tp_vars, mss);
+move_twnd:
+ /* move the Transmit Window */
+ atomic_set(&tp_vars->last_acked, recv_ack);
+ }
+
+ wake_up(&tp_vars->more_bytes);
+out:
+ if (likely(primary_if))
+ batadv_hardif_put(primary_if);
+ if (likely(orig_node))
+ batadv_orig_node_put(orig_node);
+ if (likely(tp_vars))
+ batadv_tp_vars_put(tp_vars);
+}
+
+/**
+ * batadv_tp_avail - check if congestion window is not full
+ * @tp_vars: the private data of the current TP meter session
+ * @payload_len: size of the payload of a single message
+ *
+ * Return: true when congestion window is not full, false otherwise
+ */
+static bool batadv_tp_avail(struct batadv_tp_vars *tp_vars,
+ size_t payload_len)
+{
+ u32 win_left, win_limit;
+
+ win_limit = atomic_read(&tp_vars->last_acked) + tp_vars->cwnd;
+ win_left = win_limit - tp_vars->last_sent;
+
+ return win_left >= payload_len;
+}
+
+/**
+ * batadv_tp_wait_available - wait until congestion window becomes free or
+ * timeout is reached
+ * @tp_vars: the private data of the current TP meter session
+ * @plen: size of the payload of a single message
+ *
+ * Return: 0 if the condition evaluated to false after the timeout elapsed,
+ * 1 if the condition evaluated to true after the timeout elapsed, the
+ * remaining jiffies (at least 1) if the condition evaluated to true before
+ * the timeout elapsed, or -ERESTARTSYS if it was interrupted by a signal.
+ */
+static int batadv_tp_wait_available(struct batadv_tp_vars *tp_vars, size_t plen)
+{
+ int ret;
+
+ ret = wait_event_interruptible_timeout(tp_vars->more_bytes,
+ batadv_tp_avail(tp_vars, plen),
+ HZ / 10);
+
+ return ret;
+}
+
+/**
+ * batadv_tp_send - main sending thread of a tp meter session
+ * @arg: address of the related tp_vars
+ *
+ * Return: nothing, this function never returns
+ */
+static int batadv_tp_send(void *arg)
+{
+ struct batadv_tp_vars *tp_vars = arg;
+ struct batadv_priv *bat_priv = tp_vars->bat_priv;
+ struct batadv_hard_iface *primary_if = NULL;
+ struct batadv_orig_node *orig_node = NULL;
+ size_t payload_len, packet_len;
+ int err = 0;
+
+ if (unlikely(tp_vars->role != BATADV_TP_SENDER)) {
+ err = BATADV_TP_REASON_DST_UNREACHABLE;
+ tp_vars->reason = err;
+ goto out;
+ }
+
+ orig_node = batadv_orig_hash_find(bat_priv, tp_vars->other_end);
+ if (unlikely(!orig_node)) {
+ err = BATADV_TP_REASON_DST_UNREACHABLE;
+ tp_vars->reason = err;
+ goto out;
+ }
+
+ primary_if = batadv_primary_if_get_selected(bat_priv);
+ if (unlikely(!primary_if)) {
+ err = BATADV_TP_REASON_DST_UNREACHABLE;
+ goto out;
+ }
+
+ /* assume that all the hard_interfaces have a correctly
+ * configured MTU, so use the soft_iface MTU as MSS.
+ * This might not be true and in that case the fragmentation
+ * should be used.
+ * Now, try to send the packet as it is
+ */
+ payload_len = BATADV_TP_PLEN;
+ BUILD_BUG_ON(sizeof(struct batadv_icmp_tp_packet) > BATADV_TP_PLEN);
+
+ batadv_tp_reset_sender_timer(tp_vars);
+
+ /* queue the worker in charge of terminating the test */
+ queue_delayed_work(batadv_event_workqueue, &tp_vars->finish_work,
+ msecs_to_jiffies(tp_vars->test_length));
+
+ while (atomic_read(&tp_vars->sending) != 0) {
+ if (unlikely(!batadv_tp_avail(tp_vars, payload_len))) {
+ batadv_tp_wait_available(tp_vars, payload_len);
+ continue;
+ }
+
+ /* to emulate normal unicast traffic, add to the payload len
+ * the size of the unicast header
+ */
+ packet_len = payload_len + sizeof(struct batadv_unicast_packet);
+
+ err = batadv_tp_send_msg(tp_vars, primary_if->net_dev->dev_addr,
+ orig_node, tp_vars->last_sent,
+ packet_len,
+ tp_vars->session, tp_vars->icmp_uid,
+ jiffies_to_msecs(jiffies));
+
+ /* something went wrong during the preparation/transmission */
+ if (unlikely(err && err != BATADV_TP_REASON_CANT_SEND)) {
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: batadv_tp_send() cannot send packets (%d)\n",
+ err);
+ /* ensure nobody else tries to stop the thread now */
+ if (atomic_dec_and_test(&tp_vars->sending))
+ tp_vars->reason = err;
+ break;
+ }
+
+ /* right-shift the TWND */
+ if (!err)
+ tp_vars->last_sent += payload_len;
+
+ cond_resched();
+ }
+
+out:
+ if (likely(primary_if))
+ batadv_hardif_put(primary_if);
+ if (likely(orig_node))
+ batadv_orig_node_put(orig_node);
+
+ batadv_tp_sender_end(bat_priv, tp_vars);
+ batadv_tp_sender_cleanup(bat_priv, tp_vars);
+
+ batadv_tp_vars_put(tp_vars);
+
+ do_exit(0);
+}
+
+/**
+ * batadv_tp_start_kthread - start new thread which manages the tp meter sender
+ * @tp_vars: the private data of the current TP meter session
+ */
+static void batadv_tp_start_kthread(struct batadv_tp_vars *tp_vars)
+{
+ struct task_struct *kthread;
+ struct batadv_priv *bat_priv = tp_vars->bat_priv;
+ u32 session_cookie;
+
+ kref_get(&tp_vars->refcount);
+ kthread = kthread_create(batadv_tp_send, tp_vars, "kbatadv_tp_meter");
+ if (IS_ERR(kthread)) {
+ session_cookie = batadv_tp_session_cookie(tp_vars->session,
+ tp_vars->icmp_uid);
+ pr_err("batadv: cannot create tp meter kthread\n");
+ batadv_tp_batctl_error_notify(BATADV_TP_REASON_MEMORY_ERROR,
+ tp_vars->other_end,
+ bat_priv, session_cookie);
+
+ /* drop reserved reference for kthread */
+ batadv_tp_vars_put(tp_vars);
+
+ /* cleanup of failed tp meter variables */
+ batadv_tp_sender_cleanup(bat_priv, tp_vars);
+ return;
+ }
+
+ wake_up_process(kthread);
+}
+
+/**
+ * batadv_tp_start - start a new tp meter session
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: the receiver MAC address
+ * @test_length: test length in milliseconds
+ * @cookie: session cookie
+ */
+void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
+ u32 test_length, u32 *cookie)
+{
+ struct batadv_tp_vars *tp_vars;
+ u8 session_id[2];
+ u8 icmp_uid;
+ u32 session_cookie;
+
+ get_random_bytes(session_id, sizeof(session_id));
+ get_random_bytes(&icmp_uid, 1);
+ session_cookie = batadv_tp_session_cookie(session_id, icmp_uid);
+ *cookie = session_cookie;
+
+ /* look for an already existing test towards this node */
+ spin_lock_bh(&bat_priv->tp_list_lock);
+ tp_vars = batadv_tp_list_find(bat_priv, dst);
+ if (tp_vars) {
+ spin_unlock_bh(&bat_priv->tp_list_lock);
+ batadv_tp_vars_put(tp_vars);
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: test to or from the same node already ongoing, aborting\n");
+ batadv_tp_batctl_error_notify(BATADV_TP_REASON_ALREADY_ONGOING,
+ dst, bat_priv, session_cookie);
+ return;
+ }
+
+ if (!atomic_add_unless(&bat_priv->tp_num, 1, BATADV_TP_MAX_NUM)) {
+ spin_unlock_bh(&bat_priv->tp_list_lock);
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: too many ongoing sessions, aborting (SEND)\n");
+ batadv_tp_batctl_error_notify(BATADV_TP_REASON_TOO_MANY, dst,
+ bat_priv, session_cookie);
+ return;
+ }
+
+ tp_vars = kmalloc(sizeof(*tp_vars), GFP_ATOMIC);
+ if (!tp_vars) {
+ spin_unlock_bh(&bat_priv->tp_list_lock);
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: batadv_tp_start cannot allocate list elements\n");
+ batadv_tp_batctl_error_notify(BATADV_TP_REASON_MEMORY_ERROR,
+ dst, bat_priv, session_cookie);
+ return;
+ }
+
+ /* initialize tp_vars */
+ ether_addr_copy(tp_vars->other_end, dst);
+ kref_init(&tp_vars->refcount);
+ tp_vars->role = BATADV_TP_SENDER;
+ atomic_set(&tp_vars->sending, 1);
+ memcpy(tp_vars->session, session_id, sizeof(session_id));
+ tp_vars->icmp_uid = icmp_uid;
+
+ tp_vars->last_sent = BATADV_TP_FIRST_SEQ;
+ atomic_set(&tp_vars->last_acked, BATADV_TP_FIRST_SEQ);
+ tp_vars->fast_recovery = false;
+ tp_vars->recover = BATADV_TP_FIRST_SEQ;
+
+ /* initialise the CWND to 3*MSS (Section 3.1 in RFC5681).
+ * For batman-adv the MSS is the size of the payload received by the
+ * soft_interface, hence its MTU
+ */
+ tp_vars->cwnd = BATADV_TP_PLEN * 3;
+ /* at the beginning initialise the SS threshold to the biggest possible
+ * window size, hence the AWND size
+ */
+ tp_vars->ss_threshold = BATADV_TP_AWND;
+
+ /* RTO initial value is 3 seconds.
+ * Details in Section 2.1 of RFC6298
+ */
+ tp_vars->rto = 1000;
+ tp_vars->srtt = 0;
+ tp_vars->rttvar = 0;
+
+ atomic64_set(&tp_vars->tot_sent, 0);
+
+ kref_get(&tp_vars->refcount);
+ setup_timer(&tp_vars->timer, batadv_tp_sender_timeout,
+ (unsigned long)tp_vars);
+
+ tp_vars->bat_priv = bat_priv;
+ tp_vars->start_time = jiffies;
+
+ init_waitqueue_head(&tp_vars->more_bytes);
+
+ spin_lock_init(&tp_vars->unacked_lock);
+ INIT_LIST_HEAD(&tp_vars->unacked_list);
+
+ spin_lock_init(&tp_vars->cwnd_lock);
+
+ tp_vars->prerandom_offset = 0;
+ spin_lock_init(&tp_vars->prerandom_lock);
+
+ kref_get(&tp_vars->refcount);
+ hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
+ spin_unlock_bh(&bat_priv->tp_list_lock);
+
+ tp_vars->test_length = test_length;
+ if (!tp_vars->test_length)
+ tp_vars->test_length = BATADV_TP_DEF_TEST_LENGTH;
+
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: starting throughput meter towards %pM (length=%ums)\n",
+ dst, test_length);
+
+ /* init work item for finished tp tests */
+ INIT_DELAYED_WORK(&tp_vars->finish_work, batadv_tp_sender_finish);
+
+ /* start tp kthread. This way the write() call issued from userspace can
+ * happily return and avoid to block
+ */
+ batadv_tp_start_kthread(tp_vars);
+
+ /* don't return reference to new tp_vars */
+ batadv_tp_vars_put(tp_vars);
+}
+
+/**
+ * batadv_tp_stop - stop currently running tp meter session
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: the receiver MAC address
+ * @return_value: reason for tp meter session stop
+ */
+void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst,
+ u8 return_value)
+{
+ struct batadv_orig_node *orig_node;
+ struct batadv_tp_vars *tp_vars;
+
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: stopping test towards %pM\n", dst);
+
+ orig_node = batadv_orig_hash_find(bat_priv, dst);
+ if (!orig_node)
+ return;
+
+ tp_vars = batadv_tp_list_find(bat_priv, orig_node->orig);
+ if (!tp_vars) {
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: trying to interrupt an already over connection\n");
+ goto out;
+ }
+
+ batadv_tp_sender_shutdown(tp_vars, return_value);
+ batadv_tp_vars_put(tp_vars);
+out:
+ batadv_orig_node_put(orig_node);
+}
+
+/**
+ * batadv_tp_reset_receiver_timer - reset the receiver shutdown timer
+ * @tp_vars: the private data of the current TP meter session
+ *
+ * start the receiver shutdown timer or reset it if already started
+ */
+static void batadv_tp_reset_receiver_timer(struct batadv_tp_vars *tp_vars)
+{
+ mod_timer(&tp_vars->timer,
+ jiffies + msecs_to_jiffies(BATADV_TP_RECV_TIMEOUT));
+}
+
+/**
+ * batadv_tp_receiver_shutdown - stop a tp meter receiver when timeout is
+ * reached without received ack
+ * @arg: address of the related tp_vars
+ */
+static void batadv_tp_receiver_shutdown(unsigned long arg)
+{
+ struct batadv_tp_vars *tp_vars = (struct batadv_tp_vars *)arg;
+ struct batadv_tp_unacked *un, *safe;
+ struct batadv_priv *bat_priv;
+
+ bat_priv = tp_vars->bat_priv;
+
+ /* if there is recent activity rearm the timer */
+ if (!batadv_has_timed_out(tp_vars->last_recv_time,
+ BATADV_TP_RECV_TIMEOUT)) {
+ /* reset the receiver shutdown timer */
+ batadv_tp_reset_receiver_timer(tp_vars);
+ return;
+ }
+
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Shutting down for inactivity (more than %dms) from %pM\n",
+ BATADV_TP_RECV_TIMEOUT, tp_vars->other_end);
+
+ spin_lock_bh(&tp_vars->bat_priv->tp_list_lock);
+ hlist_del_rcu(&tp_vars->list);
+ spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock);
+
+ /* drop list reference */
+ batadv_tp_vars_put(tp_vars);
+
+ atomic_dec(&bat_priv->tp_num);
+
+ spin_lock_bh(&tp_vars->unacked_lock);
+ list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
+ list_del(&un->list);
+ kfree(un);
+ }
+ spin_unlock_bh(&tp_vars->unacked_lock);
+
+ /* drop reference of timer */
+ batadv_tp_vars_put(tp_vars);
+}
+
+/**
+ * batadv_tp_send_ack - send an ACK packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: the mac address of the destination originator
+ * @seq: the sequence number to ACK
+ * @timestamp: the timestamp to echo back in the ACK
+ * @session: session identifier
+ * @socket_index: local ICMP socket identifier
+ *
+ * Return: 0 on success, a positive integer representing the reason of the
+ * failure otherwise
+ */
+static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst,
+ u32 seq, __be32 timestamp, const u8 *session,
+ int socket_index)
+{
+ struct batadv_hard_iface *primary_if = NULL;
+ struct batadv_orig_node *orig_node;
+ struct batadv_icmp_tp_packet *icmp;
+ struct sk_buff *skb;
+ int r, ret;
+
+ orig_node = batadv_orig_hash_find(bat_priv, dst);
+ if (unlikely(!orig_node)) {
+ ret = BATADV_TP_REASON_DST_UNREACHABLE;
+ goto out;
+ }
+
+ primary_if = batadv_primary_if_get_selected(bat_priv);
+ if (unlikely(!primary_if)) {
+ ret = BATADV_TP_REASON_DST_UNREACHABLE;
+ goto out;
+ }
+
+ skb = netdev_alloc_skb_ip_align(NULL, sizeof(*icmp) + ETH_HLEN);
+ if (unlikely(!skb)) {
+ ret = BATADV_TP_REASON_MEMORY_ERROR;
+ goto out;
+ }
+
+ skb_reserve(skb, ETH_HLEN);
+ icmp = (struct batadv_icmp_tp_packet *)skb_put(skb, sizeof(*icmp));
+ icmp->packet_type = BATADV_ICMP;
+ icmp->version = BATADV_COMPAT_VERSION;
+ icmp->ttl = BATADV_TTL;
+ icmp->msg_type = BATADV_TP;
+ ether_addr_copy(icmp->dst, orig_node->orig);
+ ether_addr_copy(icmp->orig, primary_if->net_dev->dev_addr);
+ icmp->uid = socket_index;
+
+ icmp->subtype = BATADV_TP_ACK;
+ memcpy(icmp->session, session, sizeof(icmp->session));
+ icmp->seqno = htonl(seq);
+ icmp->timestamp = timestamp;
+
+ /* send the ack */
+ r = batadv_send_skb_to_orig(skb, orig_node, NULL);
+ if (r == -1)
+ kfree_skb(skb);
+
+ if (unlikely(r < 0) || (r == NET_XMIT_DROP)) {
+ ret = BATADV_TP_REASON_DST_UNREACHABLE;
+ goto out;
+ }
+ ret = 0;
+
+out:
+ if (likely(orig_node))
+ batadv_orig_node_put(orig_node);
+ if (likely(primary_if))
+ batadv_hardif_put(primary_if);
+
+ return ret;
+}
+
+/**
+ * batadv_tp_handle_out_of_order - store an out of order packet
+ * @tp_vars: the private data of the current TP meter session
+ * @skb: the buffer containing the received packet
+ *
+ * Store the out of order packet in the unacked list for late processing. This
+ * packets are kept in this list so that they can be ACKed at once as soon as
+ * all the previous packets have been received
+ *
+ * Return: true if the packed has been successfully processed, false otherwise
+ */
+static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
+ const struct sk_buff *skb)
+{
+ const struct batadv_icmp_tp_packet *icmp;
+ struct batadv_tp_unacked *un, *new;
+ u32 payload_len;
+ bool added = false;
+
+ new = kmalloc(sizeof(*new), GFP_ATOMIC);
+ if (unlikely(!new))
+ return false;
+
+ icmp = (struct batadv_icmp_tp_packet *)skb->data;
+
+ new->seqno = ntohl(icmp->seqno);
+ payload_len = skb->len - sizeof(struct batadv_unicast_packet);
+ new->len = payload_len;
+
+ spin_lock_bh(&tp_vars->unacked_lock);
+ /* if the list is empty immediately attach this new object */
+ if (list_empty(&tp_vars->unacked_list)) {
+ list_add(&new->list, &tp_vars->unacked_list);
+ goto out;
+ }
+
+ /* otherwise loop over the list and either drop the packet because this
+ * is a duplicate or store it at the right position.
+ *
+ * The iteration is done in the reverse way because it is likely that
+ * the last received packet (the one being processed now) has a bigger
+ * seqno than all the others already stored.
+ */
+ list_for_each_entry_reverse(un, &tp_vars->unacked_list, list) {
+ /* check for duplicates */
+ if (new->seqno == un->seqno) {
+ if (new->len > un->len)
+ un->len = new->len;
+ kfree(new);
+ added = true;
+ break;
+ }
+
+ /* look for the right position */
+ if (batadv_seq_before(new->seqno, un->seqno))
+ continue;
+
+ /* as soon as an entry having a bigger seqno is found, the new
+ * one is attached _after_ it. In this way the list is kept in
+ * ascending order
+ */
+ list_add_tail(&new->list, &un->list);
+ added = true;
+ break;
+ }
+
+ /* received packet with smallest seqno out of order; add it to front */
+ if (!added)
+ list_add(&new->list, &tp_vars->unacked_list);
+
+out:
+ spin_unlock_bh(&tp_vars->unacked_lock);
+
+ return true;
+}
+
+/**
+ * batadv_tp_ack_unordered - update number received bytes in current stream
+ * without gaps
+ * @tp_vars: the private data of the current TP meter session
+ */
+static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars)
+{
+ struct batadv_tp_unacked *un, *safe;
+ u32 to_ack;
+
+ /* go through the unacked packet list and possibly ACK them as
+ * well
+ */
+ spin_lock_bh(&tp_vars->unacked_lock);
+ list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
+ /* the list is ordered, therefore it is possible to stop as soon
+ * there is a gap between the last acked seqno and the seqno of
+ * the packet under inspection
+ */
+ if (batadv_seq_before(tp_vars->last_recv, un->seqno))
+ break;
+
+ to_ack = un->seqno + un->len - tp_vars->last_recv;
+
+ if (batadv_seq_before(tp_vars->last_recv, un->seqno + un->len))
+ tp_vars->last_recv += to_ack;
+
+ list_del(&un->list);
+ kfree(un);
+ }
+ spin_unlock_bh(&tp_vars->unacked_lock);
+}
+
+/**
+ * batadv_tp_init_recv - return matching or create new receiver tp_vars
+ * @bat_priv: the bat priv with all the soft interface information
+ * @icmp: received icmp tp msg
+ *
+ * Return: corresponding tp_vars or NULL on errors
+ */
+static struct batadv_tp_vars *
+batadv_tp_init_recv(struct batadv_priv *bat_priv,
+ const struct batadv_icmp_tp_packet *icmp)
+{
+ struct batadv_tp_vars *tp_vars;
+
+ spin_lock_bh(&bat_priv->tp_list_lock);
+ tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig,
+ icmp->session);
+ if (tp_vars)
+ goto out_unlock;
+
+ if (!atomic_add_unless(&bat_priv->tp_num, 1, BATADV_TP_MAX_NUM)) {
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: too many ongoing sessions, aborting (RECV)\n");
+ goto out_unlock;
+ }
+
+ tp_vars = kmalloc(sizeof(*tp_vars), GFP_ATOMIC);
+ if (!tp_vars)
+ goto out_unlock;
+
+ ether_addr_copy(tp_vars->other_end, icmp->orig);
+ tp_vars->role = BATADV_TP_RECEIVER;
+ memcpy(tp_vars->session, icmp->session, sizeof(tp_vars->session));
+ tp_vars->last_recv = BATADV_TP_FIRST_SEQ;
+ tp_vars->bat_priv = bat_priv;
+ kref_init(&tp_vars->refcount);
+
+ spin_lock_init(&tp_vars->unacked_lock);
+ INIT_LIST_HEAD(&tp_vars->unacked_list);
+
+ kref_get(&tp_vars->refcount);
+ hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
+
+ kref_get(&tp_vars->refcount);
+ setup_timer(&tp_vars->timer, batadv_tp_receiver_shutdown,
+ (unsigned long)tp_vars);
+
+ batadv_tp_reset_receiver_timer(tp_vars);
+
+out_unlock:
+ spin_unlock_bh(&bat_priv->tp_list_lock);
+
+ return tp_vars;
+}
+
+/**
+ * batadv_tp_recv_msg - process a single data message
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the buffer containing the received packet
+ *
+ * Process a received TP MSG packet
+ */
+static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
+ const struct sk_buff *skb)
+{
+ const struct batadv_icmp_tp_packet *icmp;
+ struct batadv_tp_vars *tp_vars;
+ size_t packet_size;
+ u32 seqno;
+
+ icmp = (struct batadv_icmp_tp_packet *)skb->data;
+
+ seqno = ntohl(icmp->seqno);
+ /* check if this is the first seqno. This means that if the
+ * first packet is lost, the tp meter does not work anymore!
+ */
+ if (seqno == BATADV_TP_FIRST_SEQ) {
+ tp_vars = batadv_tp_init_recv(bat_priv, icmp);
+ if (!tp_vars) {
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: seqno != BATADV_TP_FIRST_SEQ cannot initiate connection\n");
+ goto out;
+ }
+ } else {
+ tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig,
+ icmp->session);
+ if (!tp_vars) {
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Unexpected packet from %pM!\n",
+ icmp->orig);
+ goto out;
+ }
+ }
+
+ if (unlikely(tp_vars->role != BATADV_TP_RECEIVER)) {
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Meter: dropping packet: not expected (role=%u)\n",
+ tp_vars->role);
+ goto out;
+ }
+
+ tp_vars->last_recv_time = jiffies;
+
+ /* if the packet is a duplicate, it may be the case that an ACK has been
+ * lost. Resend the ACK
+ */
+ if (batadv_seq_before(seqno, tp_vars->last_recv))
+ goto send_ack;
+
+ /* if the packet is out of order enqueue it */
+ if (ntohl(icmp->seqno) != tp_vars->last_recv) {
+ /* exit immediately (and do not send any ACK) if the packet has
+ * not been enqueued correctly
+ */
+ if (!batadv_tp_handle_out_of_order(tp_vars, skb))
+ goto out;
+
+ /* send a duplicate ACK */
+ goto send_ack;
+ }
+
+ /* if everything was fine count the ACKed bytes */
+ packet_size = skb->len - sizeof(struct batadv_unicast_packet);
+ tp_vars->last_recv += packet_size;
+
+ /* check if this ordered message filled a gap.... */
+ batadv_tp_ack_unordered(tp_vars);
+
+send_ack:
+ /* send the ACK. If the received packet was out of order, the ACK that
+ * is going to be sent is a duplicate (the sender will count them and
+ * possibly enter Fast Retransmit as soon as it has reached 3)
+ */
+ batadv_tp_send_ack(bat_priv, icmp->orig, tp_vars->last_recv,
+ icmp->timestamp, icmp->session, icmp->uid);
+out:
+ if (likely(tp_vars))
+ batadv_tp_vars_put(tp_vars);
+}
+
+/**
+ * batadv_tp_meter_recv - main TP Meter receiving function
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the buffer containing the received packet
+ */
+void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb)
+{
+ struct batadv_icmp_tp_packet *icmp;
+
+ icmp = (struct batadv_icmp_tp_packet *)skb->data;
+
+ switch (icmp->subtype) {
+ case BATADV_TP_MSG:
+ batadv_tp_recv_msg(bat_priv, skb);
+ break;
+ case BATADV_TP_ACK:
+ batadv_tp_recv_ack(bat_priv, skb);
+ break;
+ default:
+ batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+ "Received unknown TP Metric packet type %u\n",
+ icmp->subtype);
+ }
+ consume_skb(skb);
+}
+
+/**
+ * batadv_tp_meter_init - initialize global tp_meter structures
+ */
+void batadv_tp_meter_init(void)
+{
+ get_random_bytes(batadv_tp_prerandom, sizeof(batadv_tp_prerandom));
+}
diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h
new file mode 100644
index 000000000000..ba922c425e56
--- /dev/null
+++ b/net/batman-adv/tp_meter.h
@@ -0,0 +1,34 @@
+/* Copyright (C) 2012-2016 B.A.T.M.A.N. contributors:
+ *
+ * Edo Monticelli, Antonio Quartulli
+ *
+ * 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/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_TP_METER_H_
+#define _NET_BATMAN_ADV_TP_METER_H_
+
+#include "main.h"
+
+#include <linux/types.h>
+
+struct sk_buff;
+
+void batadv_tp_meter_init(void);
+void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
+ u32 test_length, u32 *cookie);
+void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst,
+ u8 return_value);
+void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb);
+
+#endif /* _NET_BATMAN_ADV_TP_METER_H_ */
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 57ec87f37050..7e6df7a4964a 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -47,10 +47,12 @@
#include "bridge_loop_avoidance.h"
#include "hard-interface.h"
#include "hash.h"
+#include "log.h"
#include "multicast.h"
#include "originator.h"
#include "packet.h"
#include "soft-interface.h"
+#include "tvlv.h"
/* hash class keys */
static struct lock_class_key batadv_tt_local_hash_lock_class_key;
@@ -996,7 +998,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
struct batadv_tt_local_entry *tt_local;
struct batadv_hard_iface *primary_if;
struct hlist_head *head;
- unsigned short vid;
u32 i;
int last_seen_secs;
int last_seen_msecs;
@@ -1023,7 +1024,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
tt_local = container_of(tt_common_entry,
struct batadv_tt_local_entry,
common);
- vid = tt_common_entry->vid;
last_seen_jiffies = jiffies - tt_local->last_seen;
last_seen_msecs = jiffies_to_msecs(last_seen_jiffies);
last_seen_secs = last_seen_msecs / 1000;
@@ -1547,7 +1547,7 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv,
struct batadv_tt_global_entry *tt_global_entry)
{
struct batadv_neigh_node *router, *best_router = NULL;
- struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+ struct batadv_algo_ops *bao = bat_priv->algo_ops;
struct hlist_head *head;
struct batadv_tt_orig_list_entry *orig_entry, *best_entry = NULL;
@@ -1559,8 +1559,8 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv,
continue;
if (best_router &&
- bao->bat_neigh_cmp(router, BATADV_IF_DEFAULT,
- best_router, BATADV_IF_DEFAULT) <= 0) {
+ bao->neigh.cmp(router, BATADV_IF_DEFAULT, best_router,
+ BATADV_IF_DEFAULT) <= 0) {
batadv_neigh_node_put(router);
continue;
}
diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c
new file mode 100644
index 000000000000..3d1cf0fb112d
--- /dev/null
+++ b/net/batman-adv/tvlv.c
@@ -0,0 +1,632 @@
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ *
+ * 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/>.
+ */
+
+#include "main.h"
+
+#include <linux/byteorder/generic.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/kernel.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+#include <linux/pkt_sched.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 "originator.h"
+#include "packet.h"
+#include "send.h"
+#include "tvlv.h"
+
+/**
+ * batadv_tvlv_handler_release - release tvlv handler from lists and queue for
+ * free after rcu grace period
+ * @ref: kref pointer of the tvlv
+ */
+static void batadv_tvlv_handler_release(struct kref *ref)
+{
+ struct batadv_tvlv_handler *tvlv_handler;
+
+ tvlv_handler = container_of(ref, struct batadv_tvlv_handler, refcount);
+ kfree_rcu(tvlv_handler, rcu);
+}
+
+/**
+ * batadv_tvlv_handler_put - decrement the tvlv container refcounter and
+ * possibly release it
+ * @tvlv_handler: the tvlv handler to free
+ */
+static void batadv_tvlv_handler_put(struct batadv_tvlv_handler *tvlv_handler)
+{
+ kref_put(&tvlv_handler->refcount, batadv_tvlv_handler_release);
+}
+
+/**
+ * batadv_tvlv_handler_get - retrieve tvlv handler from the tvlv handler list
+ * based on the provided type and version (both need to match)
+ * @bat_priv: the bat priv with all the soft interface information
+ * @type: tvlv handler type to look for
+ * @version: tvlv handler version to look for
+ *
+ * Return: tvlv handler if found or NULL otherwise.
+ */
+static struct batadv_tvlv_handler *
+batadv_tvlv_handler_get(struct batadv_priv *bat_priv, u8 type, u8 version)
+{
+ struct batadv_tvlv_handler *tvlv_handler_tmp, *tvlv_handler = NULL;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tvlv_handler_tmp,
+ &bat_priv->tvlv.handler_list, list) {
+ if (tvlv_handler_tmp->type != type)
+ continue;
+
+ if (tvlv_handler_tmp->version != version)
+ continue;
+
+ if (!kref_get_unless_zero(&tvlv_handler_tmp->refcount))
+ continue;
+
+ tvlv_handler = tvlv_handler_tmp;
+ break;
+ }
+ rcu_read_unlock();
+
+ return tvlv_handler;
+}
+
+/**
+ * batadv_tvlv_container_release - release tvlv from lists and free
+ * @ref: kref pointer of the tvlv
+ */
+static void batadv_tvlv_container_release(struct kref *ref)
+{
+ struct batadv_tvlv_container *tvlv;
+
+ tvlv = container_of(ref, struct batadv_tvlv_container, refcount);
+ kfree(tvlv);
+}
+
+/**
+ * batadv_tvlv_container_put - decrement the tvlv container refcounter and
+ * possibly release it
+ * @tvlv: the tvlv container to free
+ */
+static void batadv_tvlv_container_put(struct batadv_tvlv_container *tvlv)
+{
+ kref_put(&tvlv->refcount, batadv_tvlv_container_release);
+}
+
+/**
+ * batadv_tvlv_container_get - retrieve tvlv container from the tvlv container
+ * list based on the provided type and version (both need to match)
+ * @bat_priv: the bat priv with all the soft interface information
+ * @type: tvlv container type to look for
+ * @version: tvlv container version to look for
+ *
+ * Has to be called with the appropriate locks being acquired
+ * (tvlv.container_list_lock).
+ *
+ * Return: tvlv container if found or NULL otherwise.
+ */
+static struct batadv_tvlv_container *
+batadv_tvlv_container_get(struct batadv_priv *bat_priv, u8 type, u8 version)
+{
+ struct batadv_tvlv_container *tvlv_tmp, *tvlv = NULL;
+
+ lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
+
+ hlist_for_each_entry(tvlv_tmp, &bat_priv->tvlv.container_list, list) {
+ if (tvlv_tmp->tvlv_hdr.type != type)
+ continue;
+
+ if (tvlv_tmp->tvlv_hdr.version != version)
+ continue;
+
+ kref_get(&tvlv_tmp->refcount);
+ tvlv = tvlv_tmp;
+ break;
+ }
+
+ return tvlv;
+}
+
+/**
+ * batadv_tvlv_container_list_size - calculate the size of the tvlv container
+ * list entries
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Has to be called with the appropriate locks being acquired
+ * (tvlv.container_list_lock).
+ *
+ * Return: size of all currently registered tvlv containers in bytes.
+ */
+static u16 batadv_tvlv_container_list_size(struct batadv_priv *bat_priv)
+{
+ struct batadv_tvlv_container *tvlv;
+ u16 tvlv_len = 0;
+
+ lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
+
+ hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) {
+ tvlv_len += sizeof(struct batadv_tvlv_hdr);
+ tvlv_len += ntohs(tvlv->tvlv_hdr.len);
+ }
+
+ return tvlv_len;
+}
+
+/**
+ * batadv_tvlv_container_remove - remove tvlv container from the tvlv container
+ * list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tvlv: the to be removed tvlv container
+ *
+ * Has to be called with the appropriate locks being acquired
+ * (tvlv.container_list_lock).
+ */
+static void batadv_tvlv_container_remove(struct batadv_priv *bat_priv,
+ struct batadv_tvlv_container *tvlv)
+{
+ lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
+
+ if (!tvlv)
+ return;
+
+ hlist_del(&tvlv->list);
+
+ /* first call to decrement the counter, second call to free */
+ batadv_tvlv_container_put(tvlv);
+ batadv_tvlv_container_put(tvlv);
+}
+
+/**
+ * batadv_tvlv_container_unregister - unregister tvlv container based on the
+ * provided type and version (both need to match)
+ * @bat_priv: the bat priv with all the soft interface information
+ * @type: tvlv container type to unregister
+ * @version: tvlv container type to unregister
+ */
+void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv,
+ u8 type, u8 version)
+{
+ struct batadv_tvlv_container *tvlv;
+
+ spin_lock_bh(&bat_priv->tvlv.container_list_lock);
+ tvlv = batadv_tvlv_container_get(bat_priv, type, version);
+ batadv_tvlv_container_remove(bat_priv, tvlv);
+ spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
+}
+
+/**
+ * batadv_tvlv_container_register - register tvlv type, version and content
+ * to be propagated with each (primary interface) OGM
+ * @bat_priv: the bat priv with all the soft interface information
+ * @type: tvlv container type
+ * @version: tvlv container version
+ * @tvlv_value: tvlv container content
+ * @tvlv_value_len: tvlv container content length
+ *
+ * If a container of the same type and version was already registered the new
+ * content is going to replace the old one.
+ */
+void batadv_tvlv_container_register(struct batadv_priv *bat_priv,
+ u8 type, u8 version,
+ void *tvlv_value, u16 tvlv_value_len)
+{
+ struct batadv_tvlv_container *tvlv_old, *tvlv_new;
+
+ if (!tvlv_value)
+ tvlv_value_len = 0;
+
+ tvlv_new = kzalloc(sizeof(*tvlv_new) + tvlv_value_len, GFP_ATOMIC);
+ if (!tvlv_new)
+ return;
+
+ tvlv_new->tvlv_hdr.version = version;
+ tvlv_new->tvlv_hdr.type = type;
+ tvlv_new->tvlv_hdr.len = htons(tvlv_value_len);
+
+ memcpy(tvlv_new + 1, tvlv_value, ntohs(tvlv_new->tvlv_hdr.len));
+ INIT_HLIST_NODE(&tvlv_new->list);
+ kref_init(&tvlv_new->refcount);
+
+ spin_lock_bh(&bat_priv->tvlv.container_list_lock);
+ tvlv_old = batadv_tvlv_container_get(bat_priv, type, version);
+ batadv_tvlv_container_remove(bat_priv, tvlv_old);
+ hlist_add_head(&tvlv_new->list, &bat_priv->tvlv.container_list);
+ spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
+}
+
+/**
+ * batadv_tvlv_realloc_packet_buff - reallocate packet buffer to accommodate
+ * requested packet size
+ * @packet_buff: packet buffer
+ * @packet_buff_len: packet buffer size
+ * @min_packet_len: requested packet minimum size
+ * @additional_packet_len: requested additional packet size on top of minimum
+ * size
+ *
+ * Return: true of the packet buffer could be changed to the requested size,
+ * false otherwise.
+ */
+static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff,
+ int *packet_buff_len,
+ int min_packet_len,
+ int additional_packet_len)
+{
+ unsigned char *new_buff;
+
+ new_buff = kmalloc(min_packet_len + additional_packet_len, GFP_ATOMIC);
+
+ /* keep old buffer if kmalloc should fail */
+ 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 true;
+}
+
+/**
+ * batadv_tvlv_container_ogm_append - append tvlv container content to given
+ * OGM packet buffer
+ * @bat_priv: the bat priv with all the soft interface information
+ * @packet_buff: ogm packet buffer
+ * @packet_buff_len: ogm packet buffer size including ogm header and tvlv
+ * content
+ * @packet_min_len: ogm header size to be preserved for the OGM itself
+ *
+ * The ogm packet might be enlarged or shrunk depending on the current size
+ * and the size of the to-be-appended tvlv containers.
+ *
+ * Return: size of all appended tvlv containers in bytes.
+ */
+u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv,
+ unsigned char **packet_buff,
+ int *packet_buff_len, int packet_min_len)
+{
+ struct batadv_tvlv_container *tvlv;
+ struct batadv_tvlv_hdr *tvlv_hdr;
+ u16 tvlv_value_len;
+ void *tvlv_value;
+ bool ret;
+
+ spin_lock_bh(&bat_priv->tvlv.container_list_lock);
+ tvlv_value_len = batadv_tvlv_container_list_size(bat_priv);
+
+ ret = batadv_tvlv_realloc_packet_buff(packet_buff, packet_buff_len,
+ packet_min_len, tvlv_value_len);
+
+ if (!ret)
+ goto end;
+
+ if (!tvlv_value_len)
+ goto end;
+
+ tvlv_value = (*packet_buff) + packet_min_len;
+
+ hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) {
+ tvlv_hdr = tvlv_value;
+ tvlv_hdr->type = tvlv->tvlv_hdr.type;
+ tvlv_hdr->version = tvlv->tvlv_hdr.version;
+ tvlv_hdr->len = tvlv->tvlv_hdr.len;
+ tvlv_value = tvlv_hdr + 1;
+ memcpy(tvlv_value, tvlv + 1, ntohs(tvlv->tvlv_hdr.len));
+ tvlv_value = (u8 *)tvlv_value + ntohs(tvlv->tvlv_hdr.len);
+ }
+
+end:
+ spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
+ return tvlv_value_len;
+}
+
+/**
+ * batadv_tvlv_call_handler - parse the given tvlv buffer to call the
+ * appropriate handlers
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tvlv_handler: tvlv callback function handling the tvlv content
+ * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet
+ * @orig_node: orig node emitting the ogm packet
+ * @src: source mac address of the unicast packet
+ * @dst: destination mac address of the unicast packet
+ * @tvlv_value: tvlv content
+ * @tvlv_value_len: tvlv content length
+ *
+ * Return: success if handler was not found or the return value of the handler
+ * callback.
+ */
+static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv,
+ struct batadv_tvlv_handler *tvlv_handler,
+ bool ogm_source,
+ struct batadv_orig_node *orig_node,
+ u8 *src, u8 *dst,
+ void *tvlv_value, u16 tvlv_value_len)
+{
+ if (!tvlv_handler)
+ return NET_RX_SUCCESS;
+
+ if (ogm_source) {
+ if (!tvlv_handler->ogm_handler)
+ return NET_RX_SUCCESS;
+
+ if (!orig_node)
+ return NET_RX_SUCCESS;
+
+ tvlv_handler->ogm_handler(bat_priv, orig_node,
+ BATADV_NO_FLAGS,
+ tvlv_value, tvlv_value_len);
+ tvlv_handler->flags |= BATADV_TVLV_HANDLER_OGM_CALLED;
+ } else {
+ if (!src)
+ return NET_RX_SUCCESS;
+
+ if (!dst)
+ return NET_RX_SUCCESS;
+
+ if (!tvlv_handler->unicast_handler)
+ return NET_RX_SUCCESS;
+
+ return tvlv_handler->unicast_handler(bat_priv, src,
+ dst, tvlv_value,
+ tvlv_value_len);
+ }
+
+ return NET_RX_SUCCESS;
+}
+
+/**
+ * batadv_tvlv_containers_process - parse the given tvlv buffer to call the
+ * appropriate handlers
+ * @bat_priv: the bat priv with all the soft interface information
+ * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet
+ * @orig_node: orig node emitting the ogm packet
+ * @src: source mac address of the unicast packet
+ * @dst: destination mac address of the unicast packet
+ * @tvlv_value: tvlv content
+ * @tvlv_value_len: tvlv content length
+ *
+ * Return: success when processing an OGM or the return value of all called
+ * handler callbacks.
+ */
+int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
+ bool ogm_source,
+ struct batadv_orig_node *orig_node,
+ u8 *src, u8 *dst,
+ void *tvlv_value, u16 tvlv_value_len)
+{
+ struct batadv_tvlv_handler *tvlv_handler;
+ struct batadv_tvlv_hdr *tvlv_hdr;
+ u16 tvlv_value_cont_len;
+ u8 cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND;
+ int ret = NET_RX_SUCCESS;
+
+ while (tvlv_value_len >= sizeof(*tvlv_hdr)) {
+ tvlv_hdr = tvlv_value;
+ tvlv_value_cont_len = ntohs(tvlv_hdr->len);
+ tvlv_value = tvlv_hdr + 1;
+ tvlv_value_len -= sizeof(*tvlv_hdr);
+
+ if (tvlv_value_cont_len > tvlv_value_len)
+ break;
+
+ tvlv_handler = batadv_tvlv_handler_get(bat_priv,
+ tvlv_hdr->type,
+ tvlv_hdr->version);
+
+ ret |= batadv_tvlv_call_handler(bat_priv, tvlv_handler,
+ ogm_source, orig_node,
+ src, dst, tvlv_value,
+ tvlv_value_cont_len);
+ if (tvlv_handler)
+ batadv_tvlv_handler_put(tvlv_handler);
+ tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len;
+ tvlv_value_len -= tvlv_value_cont_len;
+ }
+
+ if (!ogm_source)
+ return ret;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tvlv_handler,
+ &bat_priv->tvlv.handler_list, list) {
+ if ((tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) &&
+ !(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CALLED))
+ tvlv_handler->ogm_handler(bat_priv, orig_node,
+ cifnotfound, NULL, 0);
+
+ tvlv_handler->flags &= ~BATADV_TVLV_HANDLER_OGM_CALLED;
+ }
+ rcu_read_unlock();
+
+ return NET_RX_SUCCESS;
+}
+
+/**
+ * batadv_tvlv_ogm_receive - process an incoming ogm and call the appropriate
+ * handlers
+ * @bat_priv: the bat priv with all the soft interface information
+ * @batadv_ogm_packet: ogm packet containing the tvlv containers
+ * @orig_node: orig node emitting the ogm packet
+ */
+void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv,
+ struct batadv_ogm_packet *batadv_ogm_packet,
+ struct batadv_orig_node *orig_node)
+{
+ void *tvlv_value;
+ u16 tvlv_value_len;
+
+ if (!batadv_ogm_packet)
+ return;
+
+ tvlv_value_len = ntohs(batadv_ogm_packet->tvlv_len);
+ if (!tvlv_value_len)
+ return;
+
+ tvlv_value = batadv_ogm_packet + 1;
+
+ batadv_tvlv_containers_process(bat_priv, true, orig_node, NULL, NULL,
+ tvlv_value, tvlv_value_len);
+}
+
+/**
+ * batadv_tvlv_handler_register - register tvlv handler based on the provided
+ * type and version (both need to match) for ogm tvlv payload and/or unicast
+ * payload
+ * @bat_priv: the bat priv with all the soft interface information
+ * @optr: ogm tvlv handler callback function. This function receives the orig
+ * node, flags and the tvlv content as argument to process.
+ * @uptr: unicast tvlv handler callback function. This function receives the
+ * source & destination of the unicast packet as well as the tvlv content
+ * to process.
+ * @type: tvlv handler type to be registered
+ * @version: tvlv handler version to be registered
+ * @flags: flags to enable or disable TVLV API behavior
+ */
+void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
+ void (*optr)(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig,
+ u8 flags,
+ void *tvlv_value,
+ u16 tvlv_value_len),
+ int (*uptr)(struct batadv_priv *bat_priv,
+ u8 *src, u8 *dst,
+ void *tvlv_value,
+ u16 tvlv_value_len),
+ u8 type, u8 version, u8 flags)
+{
+ struct batadv_tvlv_handler *tvlv_handler;
+
+ tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version);
+ if (tvlv_handler) {
+ batadv_tvlv_handler_put(tvlv_handler);
+ return;
+ }
+
+ tvlv_handler = kzalloc(sizeof(*tvlv_handler), GFP_ATOMIC);
+ if (!tvlv_handler)
+ return;
+
+ tvlv_handler->ogm_handler = optr;
+ tvlv_handler->unicast_handler = uptr;
+ tvlv_handler->type = type;
+ tvlv_handler->version = version;
+ tvlv_handler->flags = flags;
+ kref_init(&tvlv_handler->refcount);
+ INIT_HLIST_NODE(&tvlv_handler->list);
+
+ spin_lock_bh(&bat_priv->tvlv.handler_list_lock);
+ hlist_add_head_rcu(&tvlv_handler->list, &bat_priv->tvlv.handler_list);
+ spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
+}
+
+/**
+ * batadv_tvlv_handler_unregister - unregister tvlv handler based on the
+ * provided type and version (both need to match)
+ * @bat_priv: the bat priv with all the soft interface information
+ * @type: tvlv handler type to be unregistered
+ * @version: tvlv handler version to be unregistered
+ */
+void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv,
+ u8 type, u8 version)
+{
+ struct batadv_tvlv_handler *tvlv_handler;
+
+ tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version);
+ if (!tvlv_handler)
+ return;
+
+ batadv_tvlv_handler_put(tvlv_handler);
+ spin_lock_bh(&bat_priv->tvlv.handler_list_lock);
+ hlist_del_rcu(&tvlv_handler->list);
+ spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
+ batadv_tvlv_handler_put(tvlv_handler);
+}
+
+/**
+ * batadv_tvlv_unicast_send - send a unicast packet with tvlv payload to the
+ * specified host
+ * @bat_priv: the bat priv with all the soft interface information
+ * @src: source mac address of the unicast packet
+ * @dst: destination mac address of the unicast packet
+ * @type: tvlv type
+ * @version: tvlv version
+ * @tvlv_value: tvlv content
+ * @tvlv_value_len: tvlv content length
+ */
+void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src,
+ u8 *dst, u8 type, u8 version,
+ void *tvlv_value, u16 tvlv_value_len)
+{
+ struct batadv_unicast_tvlv_packet *unicast_tvlv_packet;
+ struct batadv_tvlv_hdr *tvlv_hdr;
+ struct batadv_orig_node *orig_node;
+ struct sk_buff *skb;
+ unsigned char *tvlv_buff;
+ unsigned int tvlv_len;
+ ssize_t hdr_len = sizeof(*unicast_tvlv_packet);
+ int res;
+
+ orig_node = batadv_orig_hash_find(bat_priv, dst);
+ if (!orig_node)
+ return;
+
+ tvlv_len = sizeof(*tvlv_hdr) + tvlv_value_len;
+
+ skb = netdev_alloc_skb_ip_align(NULL, ETH_HLEN + hdr_len + tvlv_len);
+ if (!skb)
+ goto out;
+
+ skb->priority = TC_PRIO_CONTROL;
+ skb_reserve(skb, ETH_HLEN);
+ tvlv_buff = skb_put(skb, sizeof(*unicast_tvlv_packet) + tvlv_len);
+ unicast_tvlv_packet = (struct batadv_unicast_tvlv_packet *)tvlv_buff;
+ unicast_tvlv_packet->packet_type = BATADV_UNICAST_TVLV;
+ unicast_tvlv_packet->version = BATADV_COMPAT_VERSION;
+ unicast_tvlv_packet->ttl = BATADV_TTL;
+ unicast_tvlv_packet->reserved = 0;
+ unicast_tvlv_packet->tvlv_len = htons(tvlv_len);
+ unicast_tvlv_packet->align = 0;
+ ether_addr_copy(unicast_tvlv_packet->src, src);
+ ether_addr_copy(unicast_tvlv_packet->dst, dst);
+
+ tvlv_buff = (unsigned char *)(unicast_tvlv_packet + 1);
+ tvlv_hdr = (struct batadv_tvlv_hdr *)tvlv_buff;
+ tvlv_hdr->version = version;
+ tvlv_hdr->type = type;
+ tvlv_hdr->len = htons(tvlv_value_len);
+ tvlv_buff += sizeof(*tvlv_hdr);
+ memcpy(tvlv_buff, tvlv_value, tvlv_value_len);
+
+ res = batadv_send_skb_to_orig(skb, orig_node, NULL);
+ if (res == -1)
+ kfree_skb(skb);
+out:
+ batadv_orig_node_put(orig_node);
+}
diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h
new file mode 100644
index 000000000000..e4369b547b43
--- /dev/null
+++ b/net/batman-adv/tvlv.h
@@ -0,0 +1,61 @@
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ *
+ * 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/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_TVLV_H_
+#define _NET_BATMAN_ADV_TVLV_H_
+
+#include "main.h"
+
+#include <linux/types.h>
+
+struct batadv_ogm_packet;
+
+void batadv_tvlv_container_register(struct batadv_priv *bat_priv,
+ u8 type, u8 version,
+ void *tvlv_value, u16 tvlv_value_len);
+u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv,
+ unsigned char **packet_buff,
+ int *packet_buff_len, int packet_min_len);
+void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv,
+ struct batadv_ogm_packet *batadv_ogm_packet,
+ struct batadv_orig_node *orig_node);
+void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv,
+ u8 type, u8 version);
+
+void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
+ void (*optr)(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig,
+ u8 flags,
+ void *tvlv_value,
+ u16 tvlv_value_len),
+ int (*uptr)(struct batadv_priv *bat_priv,
+ u8 *src, u8 *dst,
+ void *tvlv_value,
+ u16 tvlv_value_len),
+ u8 type, u8 version, u8 flags);
+void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv,
+ u8 type, u8 version);
+int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
+ bool ogm_source,
+ struct batadv_orig_node *orig_node,
+ u8 *src, u8 *dst,
+ void *tvlv_buff, u16 tvlv_buff_len);
+void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src,
+ u8 *dst, u8 type, u8 version,
+ void *tvlv_value, u16 tvlv_value_len);
+
+#endif /* _NET_BATMAN_ADV_TVLV_H_ */
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 74d865a4df46..a64522c3b45d 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -33,6 +33,7 @@
#include <linux/types.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
+#include <uapi/linux/batman_adv.h>
#include "packet.h"
@@ -709,6 +710,8 @@ struct batadv_priv_debug_log {
* @list: list of available gateway nodes
* @list_lock: lock protecting gw_list & curr_gw
* @curr_gw: pointer to currently selected gateway node
+ * @mode: gateway operation: off, client or server (see batadv_gw_modes)
+ * @sel_class: gateway selection class (applies if gw_mode client)
* @bandwidth_down: advertised uplink download bandwidth (if gw_mode server)
* @bandwidth_up: advertised uplink upload bandwidth (if gw_mode server)
* @reselect: bool indicating a gateway re-selection is in progress
@@ -717,6 +720,8 @@ struct batadv_priv_gw {
struct hlist_head list;
spinlock_t list_lock; /* protects gw_list & curr_gw */
struct batadv_gw_node __rcu *curr_gw; /* rcu protected pointer */
+ atomic_t mode;
+ atomic_t sel_class;
atomic_t bandwidth_down;
atomic_t bandwidth_up;
atomic_t reselect;
@@ -753,14 +758,28 @@ struct batadv_priv_dat {
#ifdef CONFIG_BATMAN_ADV_MCAST
/**
+ * struct batadv_mcast_querier_state - IGMP/MLD querier state when bridged
+ * @exists: whether a querier exists in the mesh
+ * @shadowing: if a querier exists, whether it is potentially shadowing
+ * multicast listeners (i.e. querier is behind our own bridge segment)
+ */
+struct batadv_mcast_querier_state {
+ bool exists;
+ bool shadowing;
+};
+
+/**
* struct batadv_priv_mcast - per mesh interface mcast data
* @mla_list: list of multicast addresses we are currently announcing via TT
* @want_all_unsnoopables_list: a list of orig_nodes wanting all unsnoopable
* multicast traffic
* @want_all_ipv4_list: a list of orig_nodes wanting all IPv4 multicast traffic
* @want_all_ipv6_list: a list of orig_nodes wanting all IPv6 multicast traffic
+ * @querier_ipv4: the current state of an IGMP querier in the mesh
+ * @querier_ipv6: the current state of an MLD querier in the mesh
* @flags: the flags we have last sent in our mcast tvlv
* @enabled: whether the multicast tvlv is currently enabled
+ * @bridged: whether the soft interface has a bridge on top
* @num_disabled: number of nodes that have no mcast tvlv
* @num_want_all_unsnoopables: number of nodes wanting unsnoopable IP traffic
* @num_want_all_ipv4: counter for items in want_all_ipv4_list
@@ -773,8 +792,11 @@ struct batadv_priv_mcast {
struct hlist_head want_all_unsnoopables_list;
struct hlist_head want_all_ipv4_list;
struct hlist_head want_all_ipv6_list;
+ struct batadv_mcast_querier_state querier_ipv4;
+ struct batadv_mcast_querier_state querier_ipv6;
u8 flags;
bool enabled;
+ bool bridged;
atomic_t num_disabled;
atomic_t num_want_all_unsnoopables;
atomic_t num_want_all_ipv4;
@@ -814,6 +836,111 @@ struct batadv_priv_nc {
};
/**
+ * struct batadv_tp_unacked - unacked packet meta-information
+ * @seqno: seqno of the unacked packet
+ * @len: length of the packet
+ * @list: list node for batadv_tp_vars::unacked_list
+ *
+ * This struct is supposed to represent a buffer unacked packet. However, since
+ * the purpose of the TP meter is to count the traffic only, there is no need to
+ * store the entire sk_buff, the starting offset and the length are enough
+ */
+struct batadv_tp_unacked {
+ u32 seqno;
+ u16 len;
+ struct list_head list;
+};
+
+/**
+ * enum batadv_tp_meter_role - Modus in tp meter session
+ * @BATADV_TP_RECEIVER: Initialized as receiver
+ * @BATADV_TP_SENDER: Initialized as sender
+ */
+enum batadv_tp_meter_role {
+ BATADV_TP_RECEIVER,
+ BATADV_TP_SENDER
+};
+
+/**
+ * struct batadv_tp_vars - tp meter private variables per session
+ * @list: list node for bat_priv::tp_list
+ * @timer: timer for ack (receiver) and retry (sender)
+ * @bat_priv: pointer to the mesh object
+ * @start_time: start time in jiffies
+ * @other_end: mac address of remote
+ * @role: receiver/sender modi
+ * @sending: sending binary semaphore: 1 if sending, 0 is not
+ * @reason: reason for a stopped session
+ * @finish_work: work item for the finishing procedure
+ * @test_length: test length in milliseconds
+ * @session: TP session identifier
+ * @icmp_uid: local ICMP "socket" index
+ * @dec_cwnd: decimal part of the cwnd used during linear growth
+ * @cwnd: current size of the congestion window
+ * @cwnd_lock: lock do protect @cwnd & @dec_cwnd
+ * @ss_threshold: Slow Start threshold. Once cwnd exceeds this value the
+ * connection switches to the Congestion Avoidance state
+ * @last_acked: last acked byte
+ * @last_sent: last sent byte, not yet acked
+ * @tot_sent: amount of data sent/ACKed so far
+ * @dup_acks: duplicate ACKs counter
+ * @fast_recovery: true if in Fast Recovery mode
+ * @recover: last sent seqno when entering Fast Recovery
+ * @rto: sender timeout
+ * @srtt: smoothed RTT scaled by 2^3
+ * @rttvar: RTT variation scaled by 2^2
+ * @more_bytes: waiting queue anchor when waiting for more ack/retry timeout
+ * @prerandom_offset: offset inside the prerandom buffer
+ * @prerandom_lock: spinlock protecting access to prerandom_offset
+ * @last_recv: last in-order received packet
+ * @unacked_list: list of unacked packets (meta-info only)
+ * @unacked_lock: protect unacked_list
+ * @last_recv_time: time time (jiffies) a msg was received
+ * @refcount: number of context where the object is used
+ * @rcu: struct used for freeing in an RCU-safe manner
+ */
+struct batadv_tp_vars {
+ struct hlist_node list;
+ struct timer_list timer;
+ struct batadv_priv *bat_priv;
+ unsigned long start_time;
+ u8 other_end[ETH_ALEN];
+ enum batadv_tp_meter_role role;
+ atomic_t sending;
+ enum batadv_tp_meter_reason reason;
+ struct delayed_work finish_work;
+ u32 test_length;
+ u8 session[2];
+ u8 icmp_uid;
+
+ /* sender variables */
+ u16 dec_cwnd;
+ u32 cwnd;
+ spinlock_t cwnd_lock; /* Protects cwnd & dec_cwnd */
+ u32 ss_threshold;
+ atomic_t last_acked;
+ u32 last_sent;
+ atomic64_t tot_sent;
+ atomic_t dup_acks;
+ bool fast_recovery;
+ u32 recover;
+ u32 rto;
+ u32 srtt;
+ u32 rttvar;
+ wait_queue_head_t more_bytes;
+ u32 prerandom_offset;
+ spinlock_t prerandom_lock; /* Protects prerandom_offset */
+
+ /* receiver variables */
+ u32 last_recv;
+ struct list_head unacked_list;
+ spinlock_t unacked_lock; /* Protects unacked_list */
+ unsigned long last_recv_time;
+ struct kref refcount;
+ struct rcu_head rcu;
+};
+
+/**
* struct batadv_softif_vlan - per VLAN attributes set
* @bat_priv: pointer to the mesh object
* @vid: VLAN identifier
@@ -867,8 +994,6 @@ struct batadv_priv_bat_v {
* enabled
* @multicast_mode: Enable or disable multicast optimizations on this node's
* sender/originating side
- * @gw_mode: gateway operation: off, client or server (see batadv_gw_modes)
- * @gw_sel_class: gateway selection class (applies if gw_mode client)
* @orig_interval: OGM broadcast interval in milliseconds
* @hop_penalty: penalty which will be applied to an OGM's tq-field on every hop
* @log_level: configured log level (see batadv_dbg_level)
@@ -883,14 +1008,17 @@ struct batadv_priv_bat_v {
* @debug_dir: dentry for debugfs batman-adv subdirectory
* @forw_bat_list: list of aggregated OGMs that will be forwarded
* @forw_bcast_list: list of broadcast packets that will be rebroadcasted
+ * @tp_list: list of tp sessions
+ * @tp_num: number of currently active tp sessions
* @orig_hash: hash table containing mesh participants (orig nodes)
* @forw_bat_list_lock: lock protecting forw_bat_list
* @forw_bcast_list_lock: lock protecting forw_bcast_list
+ * @tp_list_lock: spinlock protecting @tp_list
* @orig_work: work queue callback item for orig node purging
* @cleanup_work: work queue callback item for soft-interface deinit
* @primary_if: one of the hard-interfaces assigned to this mesh interface
* becomes the primary interface
- * @bat_algo_ops: routing algorithm used by this mesh interface
+ * @algo_ops: routing algorithm used by this mesh interface
* @softif_vlan_list: a list of softif_vlan structs, one per VLAN created on top
* of the mesh interface represented by this object
* @softif_vlan_list_lock: lock protecting softif_vlan_list
@@ -924,8 +1052,6 @@ struct batadv_priv {
#ifdef CONFIG_BATMAN_ADV_MCAST
atomic_t multicast_mode;
#endif
- atomic_t gw_mode;
- atomic_t gw_sel_class;
atomic_t orig_interval;
atomic_t hop_penalty;
#ifdef CONFIG_BATMAN_ADV_DEBUG
@@ -941,13 +1067,16 @@ struct batadv_priv {
struct dentry *debug_dir;
struct hlist_head forw_bat_list;
struct hlist_head forw_bcast_list;
+ struct hlist_head tp_list;
struct batadv_hashtable *orig_hash;
spinlock_t forw_bat_list_lock; /* protects forw_bat_list */
spinlock_t forw_bcast_list_lock; /* protects forw_bcast_list */
+ spinlock_t tp_list_lock; /* protects tp_list */
+ atomic_t tp_num;
struct delayed_work orig_work;
struct work_struct cleanup_work;
struct batadv_hard_iface __rcu *primary_if; /* rcu protected pointer */
- struct batadv_algo_ops *bat_algo_ops;
+ struct batadv_algo_ops *algo_ops;
struct hlist_head softif_vlan_list;
spinlock_t softif_vlan_list_lock; /* protects softif_vlan_list */
#ifdef CONFIG_BATMAN_ADV_BLA
@@ -1265,66 +1394,77 @@ struct batadv_forw_packet {
};
/**
+ * struct batadv_algo_iface_ops - mesh algorithm callbacks (interface specific)
+ * @activate: start routing mechanisms when hard-interface is brought up
+ * @enable: init routing info when hard-interface is enabled
+ * @disable: de-init routing info when hard-interface is disabled
+ * @update_mac: (re-)init mac addresses of the protocol information
+ * belonging to this hard-interface
+ * @primary_set: called when primary interface is selected / changed
+ */
+struct batadv_algo_iface_ops {
+ void (*activate)(struct batadv_hard_iface *hard_iface);
+ int (*enable)(struct batadv_hard_iface *hard_iface);
+ void (*disable)(struct batadv_hard_iface *hard_iface);
+ void (*update_mac)(struct batadv_hard_iface *hard_iface);
+ void (*primary_set)(struct batadv_hard_iface *hard_iface);
+};
+
+/**
+ * struct batadv_algo_neigh_ops - mesh algorithm callbacks (neighbour specific)
+ * @hardif_init: called on creation of single hop entry
+ * @cmp: compare the metrics of two neighbors for their respective outgoing
+ * interfaces
+ * @is_similar_or_better: check if neigh1 is equally similar or better than
+ * neigh2 for their respective outgoing interface from the metric prospective
+ * @print: print the single hop neighbor list (optional)
+ */
+struct batadv_algo_neigh_ops {
+ void (*hardif_init)(struct batadv_hardif_neigh_node *neigh);
+ int (*cmp)(struct batadv_neigh_node *neigh1,
+ struct batadv_hard_iface *if_outgoing1,
+ struct batadv_neigh_node *neigh2,
+ struct batadv_hard_iface *if_outgoing2);
+ bool (*is_similar_or_better)(struct batadv_neigh_node *neigh1,
+ struct batadv_hard_iface *if_outgoing1,
+ struct batadv_neigh_node *neigh2,
+ struct batadv_hard_iface *if_outgoing2);
+ void (*print)(struct batadv_priv *priv, struct seq_file *seq);
+};
+
+/**
+ * struct batadv_algo_orig_ops - mesh algorithm callbacks (originator specific)
+ * @free: free the resources allocated by the routing algorithm for an orig_node
+ * object
+ * @add_if: ask the routing algorithm to apply the needed changes to the
+ * orig_node due to a new hard-interface being added into the mesh
+ * @del_if: ask the routing algorithm to apply the needed changes to the
+ * orig_node due to an hard-interface being removed from the mesh
+ * @print: print the originator table (optional)
+ */
+struct batadv_algo_orig_ops {
+ void (*free)(struct batadv_orig_node *orig_node);
+ int (*add_if)(struct batadv_orig_node *orig_node, int max_if_num);
+ int (*del_if)(struct batadv_orig_node *orig_node, int max_if_num,
+ int del_if_num);
+ void (*print)(struct batadv_priv *priv, struct seq_file *seq,
+ struct batadv_hard_iface *hard_iface);
+};
+
+/**
* struct batadv_algo_ops - mesh algorithm callbacks
* @list: list node for the batadv_algo_list
* @name: name of the algorithm
- * @bat_iface_activate: start routing mechanisms when hard-interface is brought
- * up
- * @bat_iface_enable: init routing info when hard-interface is enabled
- * @bat_iface_disable: de-init routing info when hard-interface is disabled
- * @bat_iface_update_mac: (re-)init mac addresses of the protocol information
- * belonging to this hard-interface
- * @bat_primary_iface_set: called when primary interface is selected / changed
- * @bat_ogm_schedule: prepare a new outgoing OGM for the send queue
- * @bat_ogm_emit: send scheduled OGM
- * @bat_hardif_neigh_init: called on creation of single hop entry
- * @bat_neigh_cmp: compare the metrics of two neighbors for their respective
- * outgoing interfaces
- * @bat_neigh_is_similar_or_better: check if neigh1 is equally similar or
- * better than neigh2 for their respective outgoing interface from the metric
- * prospective
- * @bat_neigh_print: print the single hop neighbor list (optional)
- * @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
- * @bat_orig_add_if: ask the routing algorithm to apply the needed changes to
- * the orig_node due to a new hard-interface being added into the mesh
- * @bat_orig_del_if: ask the routing algorithm to apply the needed changes to
- * the orig_node due to an hard-interface being removed from the mesh
+ * @iface: callbacks related to interface handling
+ * @neigh: callbacks related to neighbors handling
+ * @orig: callbacks related to originators handling
*/
struct batadv_algo_ops {
struct hlist_node list;
char *name;
- void (*bat_iface_activate)(struct batadv_hard_iface *hard_iface);
- int (*bat_iface_enable)(struct batadv_hard_iface *hard_iface);
- void (*bat_iface_disable)(struct batadv_hard_iface *hard_iface);
- void (*bat_iface_update_mac)(struct batadv_hard_iface *hard_iface);
- 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 */
- void (*bat_hardif_neigh_init)(struct batadv_hardif_neigh_node *neigh);
- int (*bat_neigh_cmp)(struct batadv_neigh_node *neigh1,
- struct batadv_hard_iface *if_outgoing1,
- struct batadv_neigh_node *neigh2,
- struct batadv_hard_iface *if_outgoing2);
- bool (*bat_neigh_is_similar_or_better)
- (struct batadv_neigh_node *neigh1,
- struct batadv_hard_iface *if_outgoing1,
- struct batadv_neigh_node *neigh2,
- struct batadv_hard_iface *if_outgoing2);
- void (*bat_neigh_print)(struct batadv_priv *priv, struct seq_file *seq);
- 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);
- void (*bat_orig_free)(struct batadv_orig_node *orig_node);
- int (*bat_orig_add_if)(struct batadv_orig_node *orig_node,
- int max_if_num);
- int (*bat_orig_del_if)(struct batadv_orig_node *orig_node,
- int max_if_num, int del_if_num);
+ struct batadv_algo_iface_ops iface;
+ struct batadv_algo_neigh_ops neigh;
+ struct batadv_algo_orig_ops orig;
};
/**
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 780089d75915..d020299baba4 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -627,20 +627,9 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
return err < 0 ? NET_XMIT_DROP : err;
}
-static struct lock_class_key bt_tx_busylock;
-static struct lock_class_key bt_netdev_xmit_lock_key;
-
-static void bt_set_lockdep_class_one(struct net_device *dev,
- struct netdev_queue *txq,
- void *_unused)
-{
- lockdep_set_class(&txq->_xmit_lock, &bt_netdev_xmit_lock_key);
-}
-
static int bt_dev_init(struct net_device *dev)
{
- netdev_for_each_tx_queue(dev, bt_set_lockdep_class_one, NULL);
- dev->qdisc_tx_busylock = &bt_tx_busylock;
+ netdev_lockdep_set_classes(dev);
return 0;
}
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 3df7aefb7663..0b5f729d08d2 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -215,6 +215,7 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
struct sock *sk = sock->sk;
struct sk_buff *skb;
size_t copied;
+ size_t skblen;
int err;
BT_DBG("sock %p sk %p len %zu", sock, sk, len);
@@ -230,6 +231,7 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
return err;
}
+ skblen = skb->len;
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
@@ -248,6 +250,9 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
skb_free_datagram(sk, skb);
+ if (flags & MSG_TRUNC)
+ copied = skblen;
+
return err ? : copied;
}
EXPORT_SYMBOL(bt_sock_recvmsg);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index bf9f8a801a2e..3809617aa98d 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -625,7 +625,7 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src)
list_for_each_entry(d, &hci_dev_list, list) {
if (!test_bit(HCI_UP, &d->flags) ||
hci_dev_test_flag(d, HCI_USER_CHANNEL) ||
- d->dev_type != HCI_BREDR)
+ d->dev_type != HCI_PRIMARY)
continue;
/* Simple routing:
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 45a9fc68c677..ddf8432fe8fb 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -260,14 +260,12 @@ static int hci_init1_req(struct hci_request *req, unsigned long opt)
hci_reset_req(req, 0);
switch (hdev->dev_type) {
- case HCI_BREDR:
+ case HCI_PRIMARY:
bredr_init(req);
break;
-
case HCI_AMP:
amp_init1(req);
break;
-
default:
BT_ERR("Unknown device type %d", hdev->dev_type);
break;
@@ -791,11 +789,11 @@ static int __hci_init(struct hci_dev *hdev)
if (err < 0)
return err;
- /* HCI_BREDR covers both single-mode LE, BR/EDR and dual-mode
+ /* HCI_PRIMARY covers both single-mode LE, BR/EDR and dual-mode
* BR/EDR/LE type controllers. AMP controllers only need the
* first two stages of init.
*/
- if (hdev->dev_type != HCI_BREDR)
+ if (hdev->dev_type != HCI_PRIMARY)
return 0;
err = __hci_req_sync(hdev, hci_init3_req, 0, HCI_INIT_TIMEOUT, NULL);
@@ -1202,7 +1200,7 @@ int hci_inquiry(void __user *arg)
goto done;
}
- if (hdev->dev_type != HCI_BREDR) {
+ if (hdev->dev_type != HCI_PRIMARY) {
err = -EOPNOTSUPP;
goto done;
}
@@ -1307,7 +1305,7 @@ static int hci_dev_do_open(struct hci_dev *hdev)
* since AMP controllers do not have an address.
*/
if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) &&
- hdev->dev_type == HCI_BREDR &&
+ hdev->dev_type == HCI_PRIMARY &&
!bacmp(&hdev->bdaddr, BDADDR_ANY) &&
!bacmp(&hdev->static_addr, BDADDR_ANY)) {
ret = -EADDRNOTAVAIL;
@@ -1402,7 +1400,7 @@ static int hci_dev_do_open(struct hci_dev *hdev)
!hci_dev_test_flag(hdev, HCI_UNCONFIGURED) &&
!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) &&
hci_dev_test_flag(hdev, HCI_MGMT) &&
- hdev->dev_type == HCI_BREDR) {
+ hdev->dev_type == HCI_PRIMARY) {
ret = __hci_req_hci_power_on(hdev);
mgmt_power_on(hdev, ret);
}
@@ -1563,7 +1561,7 @@ int hci_dev_do_close(struct hci_dev *hdev)
auto_off = hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF);
- if (!auto_off && hdev->dev_type == HCI_BREDR &&
+ if (!auto_off && hdev->dev_type == HCI_PRIMARY &&
hci_dev_test_flag(hdev, HCI_MGMT))
__mgmt_power_off(hdev);
@@ -1802,7 +1800,7 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
goto done;
}
- if (hdev->dev_type != HCI_BREDR) {
+ if (hdev->dev_type != HCI_PRIMARY) {
err = -EOPNOTSUPP;
goto done;
}
@@ -2043,7 +2041,7 @@ static void hci_power_on(struct work_struct *work)
*/
if (hci_dev_test_flag(hdev, HCI_RFKILLED) ||
hci_dev_test_flag(hdev, HCI_UNCONFIGURED) ||
- (hdev->dev_type == HCI_BREDR &&
+ (hdev->dev_type == HCI_PRIMARY &&
!bacmp(&hdev->bdaddr, BDADDR_ANY) &&
!bacmp(&hdev->static_addr, BDADDR_ANY))) {
hci_dev_clear_flag(hdev, HCI_AUTO_OFF);
@@ -3030,7 +3028,7 @@ int hci_register_dev(struct hci_dev *hdev)
* so the index can be used as the AMP controller ID.
*/
switch (hdev->dev_type) {
- case HCI_BREDR:
+ case HCI_PRIMARY:
id = ida_simple_get(&hci_index_ida, 0, 0, GFP_KERNEL);
break;
case HCI_AMP:
@@ -3090,7 +3088,7 @@ int hci_register_dev(struct hci_dev *hdev)
hci_dev_set_flag(hdev, HCI_SETUP);
hci_dev_set_flag(hdev, HCI_AUTO_OFF);
- if (hdev->dev_type == HCI_BREDR) {
+ if (hdev->dev_type == HCI_PRIMARY) {
/* Assume BR/EDR support until proven otherwise (such as
* through reading supported features during init.
*/
@@ -3165,6 +3163,8 @@ void hci_unregister_dev(struct hci_dev *hdev)
device_del(&hdev->dev);
debugfs_remove_recursive(hdev->debugfs);
+ kfree_const(hdev->hw_info);
+ kfree_const(hdev->fw_info);
destroy_workqueue(hdev->workqueue);
destroy_workqueue(hdev->req_workqueue);
@@ -3268,6 +3268,28 @@ int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb)
}
EXPORT_SYMBOL(hci_recv_diag);
+void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...)
+{
+ va_list vargs;
+
+ va_start(vargs, fmt);
+ kfree_const(hdev->hw_info);
+ hdev->hw_info = kvasprintf_const(GFP_KERNEL, fmt, vargs);
+ va_end(vargs);
+}
+EXPORT_SYMBOL(hci_set_hw_info);
+
+void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...)
+{
+ va_list vargs;
+
+ va_start(vargs, fmt);
+ kfree_const(hdev->fw_info);
+ hdev->fw_info = kvasprintf_const(GFP_KERNEL, fmt, vargs);
+ va_end(vargs);
+}
+EXPORT_SYMBOL(hci_set_fw_info);
+
/* ---- Interface to upper protocols ---- */
int hci_register_cb(struct hci_cb *cb)
@@ -3415,7 +3437,7 @@ static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue,
hci_skb_pkt_type(skb) = HCI_ACLDATA_PKT;
switch (hdev->dev_type) {
- case HCI_BREDR:
+ case HCI_PRIMARY:
hci_add_acl_hdr(skb, conn->handle, flags);
break;
case HCI_AMP:
@@ -3826,7 +3848,7 @@ static void hci_sched_acl(struct hci_dev *hdev)
BT_DBG("%s", hdev->name);
/* No ACL link over BR/EDR controller */
- if (!hci_conn_num(hdev, ACL_LINK) && hdev->dev_type == HCI_BREDR)
+ if (!hci_conn_num(hdev, ACL_LINK) && hdev->dev_type == HCI_PRIMARY)
return;
/* No AMP link over AMP controller */
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index 7db4220941cc..63df63ebfb24 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -76,6 +76,30 @@ static const struct file_operations __name ## _fops = { \
.llseek = default_llseek, \
} \
+#define DEFINE_INFO_ATTRIBUTE(__name, __field) \
+static int __name ## _show(struct seq_file *f, void *ptr) \
+{ \
+ struct hci_dev *hdev = f->private; \
+ \
+ hci_dev_lock(hdev); \
+ seq_printf(f, "%s\n", hdev->__field ? : ""); \
+ hci_dev_unlock(hdev); \
+ \
+ return 0; \
+} \
+ \
+static int __name ## _open(struct inode *inode, struct file *file) \
+{ \
+ return single_open(file, __name ## _show, inode->i_private); \
+} \
+ \
+static const struct file_operations __name ## _fops = { \
+ .open = __name ## _open, \
+ .read = seq_read, \
+ .llseek = seq_lseek, \
+ .release = single_release, \
+} \
+
static int features_show(struct seq_file *f, void *ptr)
{
struct hci_dev *hdev = f->private;
@@ -349,6 +373,9 @@ static const struct file_operations sc_only_mode_fops = {
.llseek = default_llseek,
};
+DEFINE_INFO_ATTRIBUTE(hardware_info, hw_info);
+DEFINE_INFO_ATTRIBUTE(firmware_info, fw_info);
+
void hci_debugfs_create_common(struct hci_dev *hdev)
{
debugfs_create_file("features", 0444, hdev->debugfs, hdev,
@@ -382,6 +409,14 @@ void hci_debugfs_create_common(struct hci_dev *hdev)
if (lmp_sc_capable(hdev) || lmp_le_capable(hdev))
debugfs_create_file("sc_only_mode", 0444, hdev->debugfs,
hdev, &sc_only_mode_fops);
+
+ if (hdev->hw_info)
+ debugfs_create_file("hardware_info", 0444, hdev->debugfs,
+ hdev, &hardware_info_fops);
+
+ if (hdev->fw_info)
+ debugfs_create_file("firmware_info", 0444, hdev->debugfs,
+ hdev, &firmware_info_fops);
}
static int inquiry_cache_show(struct seq_file *f, void *p)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index d4b3dd5413be..e17aacbc5630 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2332,7 +2332,7 @@ static u8 hci_to_mgmt_reason(u8 err)
static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
{
struct hci_ev_disconn_complete *ev = (void *) skb->data;
- u8 reason = hci_to_mgmt_reason(ev->reason);
+ u8 reason;
struct hci_conn_params *params;
struct hci_conn *conn;
bool mgmt_connected;
@@ -2355,6 +2355,12 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
conn->state = BT_CLOSED;
mgmt_connected = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags);
+
+ if (test_bit(HCI_CONN_AUTH_FAILURE, &conn->flags))
+ reason = MGMT_DEV_DISCONN_AUTH_FAILURE;
+ else
+ reason = hci_to_mgmt_reason(ev->reason);
+
mgmt_device_disconnected(hdev, &conn->dst, conn->type, conn->dst_type,
reason, mgmt_connected);
@@ -2421,6 +2427,8 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
goto unlock;
if (!ev->status) {
+ clear_bit(HCI_CONN_AUTH_FAILURE, &conn->flags);
+
if (!hci_conn_ssp_enabled(conn) &&
test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) {
BT_INFO("re-auth of legacy device is not possible.");
@@ -2429,6 +2437,9 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
conn->sec_level = conn->pending_sec_level;
}
} else {
+ if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING)
+ set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags);
+
mgmt_auth_failed(conn, ev->status);
}
@@ -2613,6 +2624,9 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
if (ev->status && conn->state == BT_CONNECTED) {
+ if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING)
+ set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags);
+
hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE);
hci_conn_drop(conn);
goto unlock;
@@ -3249,7 +3263,7 @@ static struct hci_conn *__hci_conn_lookup_handle(struct hci_dev *hdev,
struct hci_chan *chan;
switch (hdev->dev_type) {
- case HCI_BREDR:
+ case HCI_PRIMARY:
return hci_conn_hash_lookup_handle(hdev, handle);
case HCI_AMP:
chan = hci_chan_lookup_handle(hdev, handle);
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index c045b3c54768..b0e23dfc5c34 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -262,6 +262,8 @@ int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req,
break;
}
+ kfree_skb(hdev->req_skb);
+ hdev->req_skb = NULL;
hdev->req_status = hdev->req_result = 0;
BT_DBG("%s end: err %d", hdev->name, err);
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 1298d723c0e0..96f04b7b9556 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -676,7 +676,7 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED))
return -EOPNOTSUPP;
- if (hdev->dev_type != HCI_BREDR)
+ if (hdev->dev_type != HCI_PRIMARY)
return -EOPNOTSUPP;
switch (cmd) {
@@ -1048,6 +1048,7 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg,
struct sock *sk = sock->sk;
struct sk_buff *skb;
int copied, err;
+ unsigned int skblen;
BT_DBG("sock %p, sk %p", sock, sk);
@@ -1064,6 +1065,7 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg,
if (!skb)
return err;
+ skblen = skb->len;
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
@@ -1089,6 +1091,9 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg,
skb_free_datagram(sk, skb);
+ if (flags & MSG_TRUNC)
+ copied = skblen;
+
return err ? : copied;
}
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index 555982a78a58..ca7a35ebaefb 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -7,50 +7,6 @@
static struct class *bt_class;
-static inline char *link_typetostr(int type)
-{
- switch (type) {
- case ACL_LINK:
- return "ACL";
- case SCO_LINK:
- return "SCO";
- case ESCO_LINK:
- return "eSCO";
- case LE_LINK:
- return "LE";
- default:
- return "UNKNOWN";
- }
-}
-
-static ssize_t show_link_type(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct hci_conn *conn = to_hci_conn(dev);
- return sprintf(buf, "%s\n", link_typetostr(conn->type));
-}
-
-static ssize_t show_link_address(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct hci_conn *conn = to_hci_conn(dev);
- return sprintf(buf, "%pMR\n", &conn->dst);
-}
-
-#define LINK_ATTR(_name, _mode, _show, _store) \
-struct device_attribute link_attr_##_name = __ATTR(_name, _mode, _show, _store)
-
-static LINK_ATTR(type, S_IRUGO, show_link_type, NULL);
-static LINK_ATTR(address, S_IRUGO, show_link_address, NULL);
-
-static struct attribute *bt_link_attrs[] = {
- &link_attr_type.attr,
- &link_attr_address.attr,
- NULL
-};
-
-ATTRIBUTE_GROUPS(bt_link);
-
static void bt_link_release(struct device *dev)
{
struct hci_conn *conn = to_hci_conn(dev);
@@ -59,7 +15,6 @@ static void bt_link_release(struct device *dev)
static struct device_type bt_link = {
.name = "link",
- .groups = bt_link_groups,
.release = bt_link_release,
};
@@ -124,59 +79,6 @@ void hci_conn_del_sysfs(struct hci_conn *conn)
hci_dev_put(hdev);
}
-static inline char *host_typetostr(int type)
-{
- switch (type) {
- case HCI_BREDR:
- return "BR/EDR";
- case HCI_AMP:
- return "AMP";
- default:
- return "UNKNOWN";
- }
-}
-
-static ssize_t show_type(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct hci_dev *hdev = to_hci_dev(dev);
- return sprintf(buf, "%s\n", host_typetostr(hdev->dev_type));
-}
-
-static ssize_t show_name(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct hci_dev *hdev = to_hci_dev(dev);
- char name[HCI_MAX_NAME_LENGTH + 1];
- int i;
-
- for (i = 0; i < HCI_MAX_NAME_LENGTH; i++)
- name[i] = hdev->dev_name[i];
-
- name[HCI_MAX_NAME_LENGTH] = '\0';
- return sprintf(buf, "%s\n", name);
-}
-
-static ssize_t show_address(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct hci_dev *hdev = to_hci_dev(dev);
- return sprintf(buf, "%pMR\n", &hdev->bdaddr);
-}
-
-static DEVICE_ATTR(type, S_IRUGO, show_type, NULL);
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
-static DEVICE_ATTR(address, S_IRUGO, show_address, NULL);
-
-static struct attribute *bt_host_attrs[] = {
- &dev_attr_type.attr,
- &dev_attr_name.attr,
- &dev_attr_address.attr,
- NULL
-};
-
-ATTRIBUTE_GROUPS(bt_host);
-
static void bt_host_release(struct device *dev)
{
struct hci_dev *hdev = to_hci_dev(dev);
@@ -186,7 +88,6 @@ static void bt_host_release(struct device *dev)
static struct device_type bt_host = {
.name = "host",
- .groups = bt_host_groups,
.release = bt_host_release,
};
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index eb4f5f24cbe3..d4cad29b033f 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -32,6 +32,7 @@
#include <linux/debugfs.h>
#include <linux/crc16.h>
+#include <linux/filter.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
@@ -5835,6 +5836,9 @@ static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb,
if (chan->sdu)
break;
+ if (!pskb_may_pull(skb, L2CAP_SDULEN_SIZE))
+ break;
+
chan->sdu_len = get_unaligned_le16(skb->data);
skb_pull(skb, L2CAP_SDULEN_SIZE);
@@ -6610,6 +6614,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
goto drop;
}
+ if ((chan->mode == L2CAP_MODE_ERTM ||
+ chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb))
+ goto drop;
+
if (!control->sframe) {
int err;
@@ -7468,7 +7476,7 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
int len;
/* For AMP controller do not create l2cap conn */
- if (!conn && hcon->hdev->dev_type != HCI_BREDR)
+ if (!conn && hcon->hdev->dev_type != HCI_PRIMARY)
goto drop;
if (!conn)
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 388ee8b59145..a8ba752732c9 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -927,7 +927,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (get_user(opt, (u32 __user *) optval)) {
+ if (get_user(opt, (u16 __user *) optval)) {
err = -EFAULT;
break;
}
@@ -1019,7 +1019,7 @@ static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg,
goto done;
if (pi->rx_busy_skb) {
- if (!sock_queue_rcv_skb(sk, pi->rx_busy_skb))
+ if (!__sock_queue_rcv_skb(sk, pi->rx_busy_skb))
pi->rx_busy_skb = NULL;
else
goto done;
@@ -1270,7 +1270,17 @@ static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
goto done;
}
- err = sock_queue_rcv_skb(sk, skb);
+ if (chan->mode != L2CAP_MODE_ERTM &&
+ chan->mode != L2CAP_MODE_STREAMING) {
+ /* Even if no filter is attached, we could potentially
+ * get errors from security modules, etc.
+ */
+ err = sk_filter(sk, skb);
+ if (err)
+ goto done;
+ }
+
+ err = __sock_queue_rcv_skb(sk, skb);
/* For ERTM, handle one skb that doesn't fit into the recv
* buffer. This is important to do because the data frames
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 9e4b931588cf..7639290b6de3 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -38,7 +38,7 @@
#include "mgmt_util.h"
#define MGMT_VERSION 1
-#define MGMT_REVISION 12
+#define MGMT_REVISION 13
static const u16 mgmt_commands[] = {
MGMT_OP_READ_INDEX_LIST,
@@ -359,7 +359,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data,
count = 0;
list_for_each_entry(d, &hci_dev_list, list) {
- if (d->dev_type == HCI_BREDR &&
+ if (d->dev_type == HCI_PRIMARY &&
!hci_dev_test_flag(d, HCI_UNCONFIGURED))
count++;
}
@@ -384,7 +384,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data,
if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks))
continue;
- if (d->dev_type == HCI_BREDR &&
+ if (d->dev_type == HCI_PRIMARY &&
!hci_dev_test_flag(d, HCI_UNCONFIGURED)) {
rp->index[count++] = cpu_to_le16(d->id);
BT_DBG("Added hci%u", d->id);
@@ -419,7 +419,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev,
count = 0;
list_for_each_entry(d, &hci_dev_list, list) {
- if (d->dev_type == HCI_BREDR &&
+ if (d->dev_type == HCI_PRIMARY &&
hci_dev_test_flag(d, HCI_UNCONFIGURED))
count++;
}
@@ -444,7 +444,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev,
if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks))
continue;
- if (d->dev_type == HCI_BREDR &&
+ if (d->dev_type == HCI_PRIMARY &&
hci_dev_test_flag(d, HCI_UNCONFIGURED)) {
rp->index[count++] = cpu_to_le16(d->id);
BT_DBG("Added hci%u", d->id);
@@ -479,7 +479,7 @@ static int read_ext_index_list(struct sock *sk, struct hci_dev *hdev,
count = 0;
list_for_each_entry(d, &hci_dev_list, list) {
- if (d->dev_type == HCI_BREDR || d->dev_type == HCI_AMP)
+ if (d->dev_type == HCI_PRIMARY || d->dev_type == HCI_AMP)
count++;
}
@@ -503,7 +503,7 @@ static int read_ext_index_list(struct sock *sk, struct hci_dev *hdev,
if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks))
continue;
- if (d->dev_type == HCI_BREDR) {
+ if (d->dev_type == HCI_PRIMARY) {
if (hci_dev_test_flag(d, HCI_UNCONFIGURED))
rp->entry[count].type = 0x01;
else
@@ -6366,7 +6366,7 @@ void mgmt_index_added(struct hci_dev *hdev)
return;
switch (hdev->dev_type) {
- case HCI_BREDR:
+ case HCI_PRIMARY:
if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
mgmt_index_event(MGMT_EV_UNCONF_INDEX_ADDED, hdev,
NULL, 0, HCI_MGMT_UNCONF_INDEX_EVENTS);
@@ -6399,7 +6399,7 @@ void mgmt_index_removed(struct hci_dev *hdev)
return;
switch (hdev->dev_type) {
- case HCI_BREDR:
+ case HCI_PRIMARY:
mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status);
if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 50976a6481f3..4c1a16a96ae5 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -22,9 +22,9 @@
#include <linux/debugfs.h>
#include <linux/scatterlist.h>
+#include <linux/crypto.h>
#include <crypto/b128ops.h>
#include <crypto/hash.h>
-#include <crypto/skcipher.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
@@ -88,7 +88,7 @@ struct smp_dev {
u8 min_key_size;
u8 max_key_size;
- struct crypto_skcipher *tfm_aes;
+ struct crypto_cipher *tfm_aes;
struct crypto_shash *tfm_cmac;
};
@@ -127,7 +127,7 @@ struct smp_chan {
u8 dhkey[32];
u8 mackey[16];
- struct crypto_skcipher *tfm_aes;
+ struct crypto_cipher *tfm_aes;
struct crypto_shash *tfm_cmac;
};
@@ -361,10 +361,8 @@ static int smp_h6(struct crypto_shash *tfm_cmac, const u8 w[16],
* s1 and ah.
*/
-static int smp_e(struct crypto_skcipher *tfm, const u8 *k, u8 *r)
+static int smp_e(struct crypto_cipher *tfm, const u8 *k, u8 *r)
{
- SKCIPHER_REQUEST_ON_STACK(req, tfm);
- struct scatterlist sg;
uint8_t tmp[16], data[16];
int err;
@@ -378,7 +376,7 @@ static int smp_e(struct crypto_skcipher *tfm, const u8 *k, u8 *r)
/* The most significant octet of key corresponds to k[0] */
swap_buf(k, tmp, 16);
- err = crypto_skcipher_setkey(tfm, tmp, 16);
+ err = crypto_cipher_setkey(tfm, tmp, 16);
if (err) {
BT_ERR("cipher setkey failed: %d", err);
return err;
@@ -387,16 +385,7 @@ static int smp_e(struct crypto_skcipher *tfm, const u8 *k, u8 *r)
/* Most significant octet of plaintextData corresponds to data[0] */
swap_buf(r, data, 16);
- sg_init_one(&sg, data, 16);
-
- skcipher_request_set_tfm(req, tfm);
- skcipher_request_set_callback(req, 0, NULL, NULL);
- skcipher_request_set_crypt(req, &sg, &sg, 16, NULL);
-
- err = crypto_skcipher_encrypt(req);
- skcipher_request_zero(req);
- if (err)
- BT_ERR("Encrypt data error %d", err);
+ crypto_cipher_encrypt_one(tfm, data, data);
/* Most significant octet of encryptedData corresponds to data[0] */
swap_buf(data, r, 16);
@@ -406,7 +395,7 @@ static int smp_e(struct crypto_skcipher *tfm, const u8 *k, u8 *r)
return err;
}
-static int smp_c1(struct crypto_skcipher *tfm_aes, const u8 k[16],
+static int smp_c1(struct crypto_cipher *tfm_aes, const u8 k[16],
const u8 r[16], const u8 preq[7], const u8 pres[7], u8 _iat,
const bdaddr_t *ia, u8 _rat, const bdaddr_t *ra, u8 res[16])
{
@@ -455,7 +444,7 @@ static int smp_c1(struct crypto_skcipher *tfm_aes, const u8 k[16],
return err;
}
-static int smp_s1(struct crypto_skcipher *tfm_aes, const u8 k[16],
+static int smp_s1(struct crypto_cipher *tfm_aes, const u8 k[16],
const u8 r1[16], const u8 r2[16], u8 _r[16])
{
int err;
@@ -471,7 +460,7 @@ static int smp_s1(struct crypto_skcipher *tfm_aes, const u8 k[16],
return err;
}
-static int smp_ah(struct crypto_skcipher *tfm, const u8 irk[16],
+static int smp_ah(struct crypto_cipher *tfm, const u8 irk[16],
const u8 r[3], u8 res[3])
{
u8 _res[16];
@@ -759,7 +748,7 @@ static void smp_chan_destroy(struct l2cap_conn *conn)
kzfree(smp->slave_csrk);
kzfree(smp->link_key);
- crypto_free_skcipher(smp->tfm_aes);
+ crypto_free_cipher(smp->tfm_aes);
crypto_free_shash(smp->tfm_cmac);
/* Ensure that we don't leave any debug key around if debug key
@@ -1359,9 +1348,9 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
if (!smp)
return NULL;
- smp->tfm_aes = crypto_alloc_skcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
+ smp->tfm_aes = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(smp->tfm_aes)) {
- BT_ERR("Unable to create ECB crypto context");
+ BT_ERR("Unable to create AES crypto context");
kzfree(smp);
return NULL;
}
@@ -1369,7 +1358,7 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
smp->tfm_cmac = crypto_alloc_shash("cmac(aes)", 0, 0);
if (IS_ERR(smp->tfm_cmac)) {
BT_ERR("Unable to create CMAC crypto context");
- crypto_free_skcipher(smp->tfm_aes);
+ crypto_free_cipher(smp->tfm_aes);
kzfree(smp);
return NULL;
}
@@ -3120,7 +3109,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
{
struct l2cap_chan *chan;
struct smp_dev *smp;
- struct crypto_skcipher *tfm_aes;
+ struct crypto_cipher *tfm_aes;
struct crypto_shash *tfm_cmac;
if (cid == L2CAP_CID_SMP_BREDR) {
@@ -3132,9 +3121,9 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
if (!smp)
return ERR_PTR(-ENOMEM);
- tfm_aes = crypto_alloc_skcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
+ tfm_aes = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(tfm_aes)) {
- BT_ERR("Unable to create ECB crypto context");
+ BT_ERR("Unable to create AES crypto context");
kzfree(smp);
return ERR_CAST(tfm_aes);
}
@@ -3142,7 +3131,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
tfm_cmac = crypto_alloc_shash("cmac(aes)", 0, 0);
if (IS_ERR(tfm_cmac)) {
BT_ERR("Unable to create CMAC crypto context");
- crypto_free_skcipher(tfm_aes);
+ crypto_free_cipher(tfm_aes);
kzfree(smp);
return ERR_CAST(tfm_cmac);
}
@@ -3156,7 +3145,7 @@ create_chan:
chan = l2cap_chan_create();
if (!chan) {
if (smp) {
- crypto_free_skcipher(smp->tfm_aes);
+ crypto_free_cipher(smp->tfm_aes);
crypto_free_shash(smp->tfm_cmac);
kzfree(smp);
}
@@ -3203,7 +3192,7 @@ static void smp_del_chan(struct l2cap_chan *chan)
smp = chan->data;
if (smp) {
chan->data = NULL;
- crypto_free_skcipher(smp->tfm_aes);
+ crypto_free_cipher(smp->tfm_aes);
crypto_free_shash(smp->tfm_cmac);
kzfree(smp);
}
@@ -3440,7 +3429,7 @@ void smp_unregister(struct hci_dev *hdev)
#if IS_ENABLED(CONFIG_BT_SELFTEST_SMP)
-static int __init test_ah(struct crypto_skcipher *tfm_aes)
+static int __init test_ah(struct crypto_cipher *tfm_aes)
{
const u8 irk[16] = {
0x9b, 0x7d, 0x39, 0x0a, 0xa6, 0x10, 0x10, 0x34,
@@ -3460,7 +3449,7 @@ static int __init test_ah(struct crypto_skcipher *tfm_aes)
return 0;
}
-static int __init test_c1(struct crypto_skcipher *tfm_aes)
+static int __init test_c1(struct crypto_cipher *tfm_aes)
{
const u8 k[16] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
@@ -3490,7 +3479,7 @@ static int __init test_c1(struct crypto_skcipher *tfm_aes)
return 0;
}
-static int __init test_s1(struct crypto_skcipher *tfm_aes)
+static int __init test_s1(struct crypto_cipher *tfm_aes)
{
const u8 k[16] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
@@ -3686,7 +3675,7 @@ static const struct file_operations test_smp_fops = {
.llseek = default_llseek,
};
-static int __init run_selftests(struct crypto_skcipher *tfm_aes,
+static int __init run_selftests(struct crypto_cipher *tfm_aes,
struct crypto_shash *tfm_cmac)
{
ktime_t calltime, delta, rettime;
@@ -3764,27 +3753,27 @@ done:
int __init bt_selftest_smp(void)
{
- struct crypto_skcipher *tfm_aes;
+ struct crypto_cipher *tfm_aes;
struct crypto_shash *tfm_cmac;
int err;
- tfm_aes = crypto_alloc_skcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
+ tfm_aes = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(tfm_aes)) {
- BT_ERR("Unable to create ECB crypto context");
+ BT_ERR("Unable to create AES crypto context");
return PTR_ERR(tfm_aes);
}
tfm_cmac = crypto_alloc_shash("cmac(aes)", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(tfm_cmac)) {
BT_ERR("Unable to create CMAC crypto context");
- crypto_free_skcipher(tfm_aes);
+ crypto_free_cipher(tfm_aes);
return PTR_ERR(tfm_cmac);
}
err = run_selftests(tfm_aes, tfm_cmac);
crypto_free_shash(tfm_cmac);
- crypto_free_skcipher(tfm_aes);
+ crypto_free_cipher(tfm_aes);
return err;
}
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 2c8095a5d824..09f26940aba5 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -61,11 +61,11 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid))
goto out;
- if (is_broadcast_ether_addr(dest))
- br_flood_deliver(br, skb, false);
- else if (is_multicast_ether_addr(dest)) {
+ if (is_broadcast_ether_addr(dest)) {
+ br_flood(br, skb, false, false, true);
+ } else if (is_multicast_ether_addr(dest)) {
if (unlikely(netpoll_tx_running(dev))) {
- br_flood_deliver(br, skb, false);
+ br_flood(br, skb, false, false, true);
goto out;
}
if (br_multicast_rcv(br, NULL, skb, vid)) {
@@ -76,14 +76,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
br_multicast_querier_exists(br, eth_hdr(skb)))
- br_multicast_deliver(mdst, skb);
+ br_multicast_flood(mdst, skb, false, true);
else
- br_flood_deliver(br, skb, false);
- } else if ((dst = __br_fdb_get(br, dest, vid)) != NULL)
- br_deliver(dst->dst, skb);
- else
- br_flood_deliver(br, skb, true);
-
+ br_flood(br, skb, false, false, true);
+ } else if ((dst = __br_fdb_get(br, dest, vid)) != NULL) {
+ br_forward(dst->dst, skb, false, true);
+ } else {
+ br_flood(br, skb, true, false, true);
+ }
out:
rcu_read_unlock();
return NETDEV_TX_OK;
@@ -104,8 +104,16 @@ static int br_dev_init(struct net_device *dev)
return -ENOMEM;
err = br_vlan_init(br);
- if (err)
+ if (err) {
free_percpu(br->stats);
+ return err;
+ }
+
+ err = br_multicast_init_stats(br);
+ if (err) {
+ free_percpu(br->stats);
+ br_vlan_flush(br);
+ }
br_set_lockdep_class(dev);
return err;
@@ -341,6 +349,8 @@ static const struct net_device_ops br_netdev_ops = {
.ndo_add_slave = br_add_slave,
.ndo_del_slave = br_del_slave,
.ndo_fix_features = br_fix_features,
+ .ndo_neigh_construct = netdev_default_l2upper_neigh_construct,
+ .ndo_neigh_destroy = netdev_default_l2upper_neigh_destroy,
.ndo_fdb_add = br_fdb_add,
.ndo_fdb_del = br_fdb_delete,
.ndo_fdb_dump = br_fdb_dump,
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index c18080ad4085..cd620fab41b0 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -267,7 +267,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
/* If old entry was unassociated with any port, then delete it. */
f = __br_fdb_get(br, br->dev->dev_addr, 0);
- if (f && f->is_local && !f->dst)
+ if (f && f->is_local && !f->dst && !f->added_by_user)
fdb_delete_local(br, NULL, f);
fdb_insert(br, NULL, newaddr, 0);
@@ -282,7 +282,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
if (!br_vlan_should_use(v))
continue;
f = __br_fdb_get(br, br->dev->dev_addr, v->vid);
- if (f && f->is_local && !f->dst)
+ if (f && f->is_local && !f->dst && !f->added_by_user)
fdb_delete_local(br, NULL, f);
fdb_insert(br, NULL, newaddr, v->vid);
}
@@ -764,20 +764,25 @@ out:
}
/* Update (create or replace) forwarding database entry */
-static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
- __u16 state, __u16 flags, __u16 vid)
+static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
+ const __u8 *addr, __u16 state, __u16 flags, __u16 vid)
{
- struct net_bridge *br = source->br;
struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
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) &&
+ if (source && !(state & NUD_PERMANENT) && !(state & NUD_NOARP) &&
!(source->state == BR_STATE_LEARNING ||
source->state == BR_STATE_FORWARDING))
return -EPERM;
+ if (!source && !(state & NUD_PERMANENT)) {
+ pr_info("bridge: RTM_NEWNEIGH %s without NUD_PERMANENT\n",
+ br->dev->name);
+ return -EINVAL;
+ }
+
fdb = fdb_find(head, addr, vid);
if (fdb == NULL) {
if (!(flags & NLM_F_CREATE))
@@ -832,22 +837,28 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
return 0;
}
-static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
- const unsigned char *addr, u16 nlh_flags, u16 vid)
+static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
+ struct net_bridge_port *p, const unsigned char *addr,
+ u16 nlh_flags, u16 vid)
{
int err = 0;
if (ndm->ndm_flags & NTF_USE) {
+ if (!p) {
+ pr_info("bridge: RTM_NEWNEIGH %s with NTF_USE is not supported\n",
+ br->dev->name);
+ return -EINVAL;
+ }
local_bh_disable();
rcu_read_lock();
- br_fdb_update(p->br, p, addr, vid, true);
+ br_fdb_update(br, p, addr, vid, true);
rcu_read_unlock();
local_bh_enable();
} else {
- spin_lock_bh(&p->br->hash_lock);
- err = fdb_add_entry(p, addr, ndm->ndm_state,
+ spin_lock_bh(&br->hash_lock);
+ err = fdb_add_entry(br, p, addr, ndm->ndm_state,
nlh_flags, vid);
- spin_unlock_bh(&p->br->hash_lock);
+ spin_unlock_bh(&br->hash_lock);
}
return err;
@@ -884,6 +895,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
dev->name);
return -EINVAL;
}
+ br = p->br;
vg = nbp_vlan_group(p);
}
@@ -895,15 +907,9 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
}
/* VID was specified, so use it. */
- if (dev->priv_flags & IFF_EBRIDGE)
- err = br_fdb_insert(br, NULL, addr, vid);
- else
- err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
+ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid);
} else {
- if (dev->priv_flags & IFF_EBRIDGE)
- err = br_fdb_insert(br, NULL, addr, 0);
- else
- err = __br_fdb_add(ndm, p, addr, nlh_flags, 0);
+ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0);
if (err || !vg || !vg->num_vlans)
goto out;
@@ -914,11 +920,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
list_for_each_entry(v, &vg->vlan_list, vlist) {
if (!br_vlan_should_use(v))
continue;
- if (dev->priv_flags & IFF_EBRIDGE)
- err = br_fdb_insert(br, NULL, addr, v->vid);
- else
- err = __br_fdb_add(ndm, p, addr, nlh_flags,
- v->vid);
+ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid);
if (err)
goto out;
}
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index f47759f05b6d..63a83d8d7da3 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -21,11 +21,6 @@
#include <linux/netfilter_bridge.h>
#include "br_private.h"
-static int deliver_clone(const struct net_bridge_port *prev,
- struct sk_buff *skb,
- void (*__packet_hook)(const struct net_bridge_port *p,
- struct sk_buff *skb));
-
/* Don't forward packets to originating port or forwarding disabled */
static inline int should_deliver(const struct net_bridge_port *p,
const struct sk_buff *skb)
@@ -75,105 +70,92 @@ int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(br_forward_finish);
-static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
+static void __br_forward(const struct net_bridge_port *to,
+ struct sk_buff *skb, bool local_orig)
{
struct net_bridge_vlan_group *vg;
+ struct net_device *indev;
+ struct net *net;
+ int br_hook;
vg = nbp_vlan_group_rcu(to);
skb = br_handle_vlan(to->br, vg, skb);
if (!skb)
return;
+ indev = skb->dev;
skb->dev = to->dev;
-
- if (unlikely(netpoll_tx_running(to->br->dev))) {
- if (!is_skb_forwardable(skb->dev, skb))
+ if (!local_orig) {
+ if (skb_warn_if_lro(skb)) {
kfree_skb(skb);
- else {
- skb_push(skb, ETH_HLEN);
- br_netpoll_send_skb(to, skb);
+ return;
}
- return;
+ br_hook = NF_BR_FORWARD;
+ skb_forward_csum(skb);
+ net = dev_net(indev);
+ } else {
+ if (unlikely(netpoll_tx_running(to->br->dev))) {
+ if (!is_skb_forwardable(skb->dev, skb)) {
+ kfree_skb(skb);
+ } else {
+ skb_push(skb, ETH_HLEN);
+ br_netpoll_send_skb(to, skb);
+ }
+ return;
+ }
+ br_hook = NF_BR_LOCAL_OUT;
+ net = dev_net(skb->dev);
+ indev = NULL;
}
- NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT,
- dev_net(skb->dev), NULL, skb,NULL, skb->dev,
+ NF_HOOK(NFPROTO_BRIDGE, br_hook,
+ net, NULL, skb, indev, skb->dev,
br_forward_finish);
}
-static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
+static int deliver_clone(const struct net_bridge_port *prev,
+ struct sk_buff *skb, bool local_orig)
{
- struct net_bridge_vlan_group *vg;
- struct net_device *indev;
-
- if (skb_warn_if_lro(skb)) {
- kfree_skb(skb);
- return;
- }
-
- vg = nbp_vlan_group_rcu(to);
- skb = br_handle_vlan(to->br, vg, skb);
- if (!skb)
- return;
-
- indev = skb->dev;
- skb->dev = to->dev;
- skb_forward_csum(skb);
-
- NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD,
- dev_net(indev), NULL, skb, indev, skb->dev,
- br_forward_finish);
-}
+ struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
-/* called with rcu_read_lock */
-void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
-{
- if (to && should_deliver(to, skb)) {
- __br_deliver(to, skb);
- return;
+ skb = skb_clone(skb, GFP_ATOMIC);
+ if (!skb) {
+ dev->stats.tx_dropped++;
+ return -ENOMEM;
}
- kfree_skb(skb);
+ __br_forward(prev, skb, local_orig);
+ return 0;
}
-EXPORT_SYMBOL_GPL(br_deliver);
-/* called with rcu_read_lock */
-void br_forward(const struct net_bridge_port *to, struct sk_buff *skb, struct sk_buff *skb0)
+/**
+ * br_forward - forward a packet to a specific port
+ * @to: destination port
+ * @skb: packet being forwarded
+ * @local_rcv: packet will be received locally after forwarding
+ * @local_orig: packet is locally originated
+ *
+ * Should be called with rcu_read_lock.
+ */
+void br_forward(const struct net_bridge_port *to,
+ struct sk_buff *skb, bool local_rcv, bool local_orig)
{
if (to && should_deliver(to, skb)) {
- if (skb0)
- deliver_clone(to, skb, __br_forward);
+ if (local_rcv)
+ deliver_clone(to, skb, local_orig);
else
- __br_forward(to, skb);
+ __br_forward(to, skb, local_orig);
return;
}
- if (!skb0)
+ if (!local_rcv)
kfree_skb(skb);
}
-
-static int deliver_clone(const struct net_bridge_port *prev,
- struct sk_buff *skb,
- void (*__packet_hook)(const struct net_bridge_port *p,
- struct sk_buff *skb))
-{
- struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
-
- skb = skb_clone(skb, GFP_ATOMIC);
- if (!skb) {
- dev->stats.tx_dropped++;
- return -ENOMEM;
- }
-
- __packet_hook(prev, skb);
- return 0;
-}
+EXPORT_SYMBOL_GPL(br_forward);
static struct net_bridge_port *maybe_deliver(
struct net_bridge_port *prev, struct net_bridge_port *p,
- struct sk_buff *skb,
- void (*__packet_hook)(const struct net_bridge_port *p,
- struct sk_buff *skb))
+ struct sk_buff *skb, bool local_orig)
{
int err;
@@ -183,7 +165,7 @@ static struct net_bridge_port *maybe_deliver(
if (!prev)
goto out;
- err = deliver_clone(prev, skb, __packet_hook);
+ err = deliver_clone(prev, skb, local_orig);
if (err)
return ERR_PTR(err);
@@ -191,17 +173,13 @@ out:
return p;
}
-/* called under bridge lock */
-static void br_flood(struct net_bridge *br, struct sk_buff *skb,
- struct sk_buff *skb0,
- void (*__packet_hook)(const struct net_bridge_port *p,
- struct sk_buff *skb),
- bool unicast)
+/* called under rcu_read_lock */
+void br_flood(struct net_bridge *br, struct sk_buff *skb,
+ bool unicast, bool local_rcv, bool local_orig)
{
+ u8 igmp_type = br_multicast_igmp_type(skb);
+ struct net_bridge_port *prev = NULL;
struct net_bridge_port *p;
- struct net_bridge_port *prev;
-
- prev = NULL;
list_for_each_entry_rcu(p, &br->port_list, list) {
/* Do not flood unicast traffic to ports that turn it off */
@@ -215,48 +193,36 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb,
BR_INPUT_SKB_CB(skb)->proxyarp_replied)
continue;
- prev = maybe_deliver(prev, p, skb, __packet_hook);
+ prev = maybe_deliver(prev, p, skb, local_orig);
if (IS_ERR(prev))
goto out;
+ if (prev == p)
+ br_multicast_count(p->br, p, skb, igmp_type,
+ BR_MCAST_DIR_TX);
}
if (!prev)
goto out;
- if (skb0)
- deliver_clone(prev, skb, __packet_hook);
+ if (local_rcv)
+ deliver_clone(prev, skb, local_orig);
else
- __packet_hook(prev, skb);
+ __br_forward(prev, skb, local_orig);
return;
out:
- if (!skb0)
+ if (!local_rcv)
kfree_skb(skb);
}
-
-/* called with rcu_read_lock */
-void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast)
-{
- br_flood(br, skb, NULL, __br_deliver, unicast);
-}
-
-/* called under bridge lock */
-void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
- struct sk_buff *skb2, bool unicast)
-{
- br_flood(br, skb, skb2, __br_forward, unicast);
-}
-
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
/* called with rcu_read_lock */
-static void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
- struct sk_buff *skb, struct sk_buff *skb0,
- void (*__packet_hook)(
- const struct net_bridge_port *p,
- struct sk_buff *skb))
+void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
+ struct sk_buff *skb,
+ bool local_rcv, bool local_orig)
{
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
+ u8 igmp_type = br_multicast_igmp_type(skb);
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *prev = NULL;
struct net_bridge_port_group *p;
@@ -274,9 +240,12 @@ static void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
port = (unsigned long)lport > (unsigned long)rport ?
lport : rport;
- prev = maybe_deliver(prev, port, skb, __packet_hook);
+ prev = maybe_deliver(prev, port, skb, local_orig);
if (IS_ERR(prev))
goto out;
+ if (prev == port)
+ br_multicast_count(port->br, port, skb, igmp_type,
+ BR_MCAST_DIR_TX);
if ((unsigned long)lport >= (unsigned long)port)
p = rcu_dereference(p->next);
@@ -287,28 +256,14 @@ static void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
if (!prev)
goto out;
- if (skb0)
- deliver_clone(prev, skb, __packet_hook);
+ if (local_rcv)
+ deliver_clone(prev, skb, local_orig);
else
- __packet_hook(prev, skb);
+ __br_forward(prev, skb, local_orig);
return;
out:
- if (!skb0)
+ if (!local_rcv)
kfree_skb(skb);
}
-
-/* called with rcu_read_lock */
-void br_multicast_deliver(struct net_bridge_mdb_entry *mdst,
- struct sk_buff *skb)
-{
- br_multicast_flood(mdst, skb, NULL, __br_deliver);
-}
-
-/* called with rcu_read_lock */
-void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
- struct sk_buff *skb, struct sk_buff *skb2)
-{
- br_multicast_flood(mdst, skb, skb2, __br_forward);
-}
#endif
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 8217aecf025b..f2fede05d32c 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -345,8 +345,8 @@ static int find_portno(struct net_bridge *br)
static struct net_bridge_port *new_nbp(struct net_bridge *br,
struct net_device *dev)
{
- int index;
struct net_bridge_port *p;
+ int index, err;
index = find_portno(br);
if (index < 0)
@@ -366,7 +366,12 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br,
br_init_port(p);
br_set_state(p, BR_STATE_DISABLED);
br_stp_port_timer_init(p);
- br_multicast_add_port(p);
+ err = br_multicast_add_port(p);
+ if (err) {
+ dev_put(dev);
+ kfree(p);
+ p = ERR_PTR(err);
+ }
return p;
}
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 43d2cd862bc2..abe11f085479 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -60,6 +60,9 @@ static int br_pass_frame_up(struct sk_buff *skb)
skb = br_handle_vlan(br, vg, skb);
if (!skb)
return NET_RX_DROP;
+ /* update the multicast stats if the packet is IGMP/MLD */
+ br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb),
+ BR_MCAST_DIR_TX);
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
dev_net(indev), NULL, skb, indev, NULL,
@@ -77,13 +80,10 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
- if (dev->flags & IFF_NOARP)
+ if ((dev->flags & IFF_NOARP) ||
+ !pskb_may_pull(skb, arp_hdr_len(dev)))
return;
- if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
- dev->stats.tx_dropped++;
- return;
- }
parp = arp_hdr(skb);
if (parp->ar_pro != htons(ETH_P_IP) ||
@@ -128,13 +128,12 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
/* note: already called with rcu_read_lock */
int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- const unsigned char *dest = eth_hdr(skb)->h_dest;
+ bool local_rcv = false, mcast_hit = false, unicast = true;
struct net_bridge_port *p = br_port_get_rcu(skb->dev);
- struct net_bridge *br;
- struct net_bridge_fdb_entry *dst;
+ const unsigned char *dest = eth_hdr(skb)->h_dest;
+ struct net_bridge_fdb_entry *dst = NULL;
struct net_bridge_mdb_entry *mdst;
- struct sk_buff *skb2;
- bool unicast = true;
+ struct net_bridge *br;
u16 vid = 0;
if (!p || p->state == BR_STATE_DISABLED)
@@ -157,53 +156,46 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
BR_INPUT_SKB_CB(skb)->brdev = br->dev;
- /* The packet skb2 goes to the local host (NULL to skip). */
- skb2 = NULL;
-
- if (br->dev->flags & IFF_PROMISC)
- skb2 = skb;
-
- dst = NULL;
+ local_rcv = !!(br->dev->flags & IFF_PROMISC);
if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP))
br_do_proxy_arp(skb, br, vid, p);
if (is_broadcast_ether_addr(dest)) {
- skb2 = skb;
+ local_rcv = true;
unicast = false;
} else if (is_multicast_ether_addr(dest)) {
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
br_multicast_querier_exists(br, eth_hdr(skb))) {
if ((mdst && mdst->mglist) ||
- br_multicast_is_router(br))
- skb2 = skb;
- br_multicast_forward(mdst, skb, skb2);
- skb = NULL;
- if (!skb2)
- goto out;
- } else
- skb2 = skb;
-
+ br_multicast_is_router(br)) {
+ local_rcv = true;
+ br->dev->stats.multicast++;
+ }
+ mcast_hit = true;
+ } else {
+ local_rcv = true;
+ br->dev->stats.multicast++;
+ }
unicast = false;
- br->dev->stats.multicast++;
- } else if ((dst = __br_fdb_get(br, dest, vid)) &&
- dst->is_local) {
- skb2 = skb;
+ } else if ((dst = __br_fdb_get(br, dest, vid)) && dst->is_local) {
/* Do not forward the packet since it's local. */
- skb = NULL;
+ return br_pass_frame_up(skb);
}
- if (skb) {
- if (dst) {
- dst->used = jiffies;
- br_forward(dst->dst, skb, skb2);
- } else
- br_flood_forward(br, skb, skb2, unicast);
+ if (dst) {
+ dst->used = jiffies;
+ br_forward(dst->dst, skb, local_rcv, false);
+ } else {
+ if (!mcast_hit)
+ br_flood(br, skb, unicast, local_rcv, false);
+ else
+ br_multicast_flood(mdst, skb, local_rcv, false);
}
- if (skb2)
- return br_pass_frame_up(skb2);
+ if (local_rcv)
+ return br_pass_frame_up(skb);
out:
return 0;
@@ -288,6 +280,14 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
case 0x01: /* IEEE MAC (Pause) */
goto drop;
+ case 0x0E: /* 802.1AB LLDP */
+ fwd_mask |= p->br->group_fwd_mask;
+ if (fwd_mask & (1u << dest[5]))
+ goto forward;
+ *pskb = skb;
+ __br_handle_local_finish(skb);
+ return RX_HANDLER_PASS;
+
default:
/* Allow selective forwarding for most other protocols */
fwd_mask |= p->br->group_fwd_mask;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 43844144c9c4..c5fea9393946 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -361,7 +361,8 @@ out:
}
static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
- __be32 group)
+ __be32 group,
+ u8 *igmp_type)
{
struct sk_buff *skb;
struct igmphdr *ih;
@@ -411,6 +412,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
skb_set_transport_header(skb, skb->len);
ih = igmp_hdr(skb);
+ *igmp_type = IGMP_HOST_MEMBERSHIP_QUERY;
ih->type = IGMP_HOST_MEMBERSHIP_QUERY;
ih->code = (group ? br->multicast_last_member_interval :
br->multicast_query_response_interval) /
@@ -428,7 +430,8 @@ out:
#if IS_ENABLED(CONFIG_IPV6)
static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
- const struct in6_addr *group)
+ const struct in6_addr *grp,
+ u8 *igmp_type)
{
struct sk_buff *skb;
struct ipv6hdr *ip6h;
@@ -487,16 +490,17 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
skb_set_transport_header(skb, skb->len);
mldq = (struct mld_msg *) icmp6_hdr(skb);
- interval = ipv6_addr_any(group) ?
+ interval = ipv6_addr_any(grp) ?
br->multicast_query_response_interval :
br->multicast_last_member_interval;
+ *igmp_type = ICMPV6_MGM_QUERY;
mldq->mld_type = ICMPV6_MGM_QUERY;
mldq->mld_code = 0;
mldq->mld_cksum = 0;
mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval));
mldq->mld_reserved = 0;
- mldq->mld_mca = *group;
+ mldq->mld_mca = *grp;
/* checksum */
mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
@@ -513,14 +517,16 @@ out:
#endif
static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
- struct br_ip *addr)
+ struct br_ip *addr,
+ u8 *igmp_type)
{
switch (addr->proto) {
case htons(ETH_P_IP):
- return br_ip4_multicast_alloc_query(br, addr->u.ip4);
+ return br_ip4_multicast_alloc_query(br, addr->u.ip4, igmp_type);
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
- return br_ip6_multicast_alloc_query(br, &addr->u.ip6);
+ return br_ip6_multicast_alloc_query(br, &addr->u.ip6,
+ igmp_type);
#endif
}
return NULL;
@@ -829,18 +835,23 @@ static void __br_multicast_send_query(struct net_bridge *br,
struct br_ip *ip)
{
struct sk_buff *skb;
+ u8 igmp_type;
- skb = br_multicast_alloc_query(br, ip);
+ skb = br_multicast_alloc_query(br, ip, &igmp_type);
if (!skb)
return;
if (port) {
skb->dev = port->dev;
+ br_multicast_count(br, port, skb, igmp_type,
+ BR_MCAST_DIR_TX);
NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT,
dev_net(port->dev), NULL, skb, NULL, skb->dev,
br_dev_queue_push_xmit);
} else {
br_multicast_select_own_querier(br, ip, skb);
+ br_multicast_count(br, port, skb, igmp_type,
+ BR_MCAST_DIR_RX);
netif_rx(skb);
}
}
@@ -918,7 +929,7 @@ static void br_ip6_multicast_port_query_expired(unsigned long data)
}
#endif
-void br_multicast_add_port(struct net_bridge_port *port)
+int br_multicast_add_port(struct net_bridge_port *port)
{
port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY;
@@ -930,6 +941,11 @@ void br_multicast_add_port(struct net_bridge_port *port)
setup_timer(&port->ip6_own_query.timer,
br_ip6_multicast_port_query_expired, (unsigned long)port);
#endif
+ port->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats);
+ if (!port->mcast_stats)
+ return -ENOMEM;
+
+ return 0;
}
void br_multicast_del_port(struct net_bridge_port *port)
@@ -944,6 +960,7 @@ void br_multicast_del_port(struct net_bridge_port *port)
br_multicast_del_pg(br, pg);
spin_unlock_bh(&br->multicast_lock);
del_timer_sync(&port->multicast_router_timer);
+ free_percpu(port->mcast_stats);
}
static void br_multicast_enable(struct bridge_mcast_own_query *query)
@@ -1121,7 +1138,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
} else {
err = br_ip6_multicast_add_group(br, port,
&grec->grec_mca, vid);
- if (!err)
+ if (err)
break;
}
}
@@ -1583,6 +1600,39 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
}
#endif
+static void br_multicast_err_count(const struct net_bridge *br,
+ const struct net_bridge_port *p,
+ __be16 proto)
+{
+ struct bridge_mcast_stats __percpu *stats;
+ struct bridge_mcast_stats *pstats;
+
+ if (!br->multicast_stats_enabled)
+ return;
+
+ if (p)
+ stats = p->mcast_stats;
+ else
+ stats = br->mcast_stats;
+ if (WARN_ON(!stats))
+ return;
+
+ pstats = this_cpu_ptr(stats);
+
+ u64_stats_update_begin(&pstats->syncp);
+ switch (proto) {
+ case htons(ETH_P_IP):
+ pstats->mstats.igmp_parse_errors++;
+ break;
+#if IS_ENABLED(CONFIG_IPV6)
+ case htons(ETH_P_IPV6):
+ pstats->mstats.mld_parse_errors++;
+ break;
+#endif
+ }
+ u64_stats_update_end(&pstats->syncp);
+}
+
static int br_multicast_ipv4_rcv(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb,
@@ -1599,11 +1649,12 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
return 0;
} else if (err < 0) {
+ br_multicast_err_count(br, port, skb->protocol);
return err;
}
- BR_INPUT_SKB_CB(skb)->igmp = 1;
ih = igmp_hdr(skb);
+ BR_INPUT_SKB_CB(skb)->igmp = ih->type;
switch (ih->type) {
case IGMP_HOST_MEMBERSHIP_REPORT:
@@ -1625,6 +1676,9 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
if (skb_trimmed && skb_trimmed != skb)
kfree_skb(skb_trimmed);
+ br_multicast_count(br, port, skb, BR_INPUT_SKB_CB(skb)->igmp,
+ BR_MCAST_DIR_RX);
+
return err;
}
@@ -1645,11 +1699,12 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
return 0;
} else if (err < 0) {
+ br_multicast_err_count(br, port, skb->protocol);
return err;
}
- BR_INPUT_SKB_CB(skb)->igmp = 1;
mld = (struct mld_msg *)skb_transport_header(skb);
+ BR_INPUT_SKB_CB(skb)->igmp = mld->mld_type;
switch (mld->mld_type) {
case ICMPV6_MGM_REPORT:
@@ -1670,6 +1725,9 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
if (skb_trimmed && skb_trimmed != skb)
kfree_skb(skb_trimmed);
+ br_multicast_count(br, port, skb, BR_INPUT_SKB_CB(skb)->igmp,
+ BR_MCAST_DIR_RX);
+
return err;
}
#endif
@@ -1677,6 +1735,8 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
struct sk_buff *skb, u16 vid)
{
+ int ret = 0;
+
BR_INPUT_SKB_CB(skb)->igmp = 0;
BR_INPUT_SKB_CB(skb)->mrouters_only = 0;
@@ -1685,14 +1745,16 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
switch (skb->protocol) {
case htons(ETH_P_IP):
- return br_multicast_ipv4_rcv(br, port, skb, vid);
+ ret = br_multicast_ipv4_rcv(br, port, skb, vid);
+ break;
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
- return br_multicast_ipv6_rcv(br, port, skb, vid);
+ ret = br_multicast_ipv6_rcv(br, port, skb, vid);
+ break;
#endif
}
- return 0;
+ return ret;
}
static void br_multicast_query_expired(struct net_bridge *br,
@@ -1831,6 +1893,8 @@ void br_multicast_dev_del(struct net_bridge *br)
out:
spin_unlock_bh(&br->multicast_lock);
+
+ free_percpu(br->mcast_stats);
}
int br_multicast_set_router(struct net_bridge *br, unsigned long val)
@@ -2185,3 +2249,154 @@ unlock:
return ret;
}
EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent);
+
+static void br_mcast_stats_add(struct bridge_mcast_stats __percpu *stats,
+ const struct sk_buff *skb, u8 type, u8 dir)
+{
+ struct bridge_mcast_stats *pstats = this_cpu_ptr(stats);
+ __be16 proto = skb->protocol;
+ unsigned int t_len;
+
+ u64_stats_update_begin(&pstats->syncp);
+ switch (proto) {
+ case htons(ETH_P_IP):
+ t_len = ntohs(ip_hdr(skb)->tot_len) - ip_hdrlen(skb);
+ switch (type) {
+ case IGMP_HOST_MEMBERSHIP_REPORT:
+ pstats->mstats.igmp_v1reports[dir]++;
+ break;
+ case IGMPV2_HOST_MEMBERSHIP_REPORT:
+ pstats->mstats.igmp_v2reports[dir]++;
+ break;
+ case IGMPV3_HOST_MEMBERSHIP_REPORT:
+ pstats->mstats.igmp_v3reports[dir]++;
+ break;
+ case IGMP_HOST_MEMBERSHIP_QUERY:
+ if (t_len != sizeof(struct igmphdr)) {
+ pstats->mstats.igmp_v3queries[dir]++;
+ } else {
+ unsigned int offset = skb_transport_offset(skb);
+ struct igmphdr *ih, _ihdr;
+
+ ih = skb_header_pointer(skb, offset,
+ sizeof(_ihdr), &_ihdr);
+ if (!ih)
+ break;
+ if (!ih->code)
+ pstats->mstats.igmp_v1queries[dir]++;
+ else
+ pstats->mstats.igmp_v2queries[dir]++;
+ }
+ break;
+ case IGMP_HOST_LEAVE_MESSAGE:
+ pstats->mstats.igmp_leaves[dir]++;
+ break;
+ }
+ break;
+#if IS_ENABLED(CONFIG_IPV6)
+ case htons(ETH_P_IPV6):
+ t_len = ntohs(ipv6_hdr(skb)->payload_len) +
+ sizeof(struct ipv6hdr);
+ t_len -= skb_network_header_len(skb);
+ switch (type) {
+ case ICMPV6_MGM_REPORT:
+ pstats->mstats.mld_v1reports[dir]++;
+ break;
+ case ICMPV6_MLD2_REPORT:
+ pstats->mstats.mld_v2reports[dir]++;
+ break;
+ case ICMPV6_MGM_QUERY:
+ if (t_len != sizeof(struct mld_msg))
+ pstats->mstats.mld_v2queries[dir]++;
+ else
+ pstats->mstats.mld_v1queries[dir]++;
+ break;
+ case ICMPV6_MGM_REDUCTION:
+ pstats->mstats.mld_leaves[dir]++;
+ break;
+ }
+ break;
+#endif /* CONFIG_IPV6 */
+ }
+ u64_stats_update_end(&pstats->syncp);
+}
+
+void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p,
+ const struct sk_buff *skb, u8 type, u8 dir)
+{
+ struct bridge_mcast_stats __percpu *stats;
+
+ /* if multicast_disabled is true then igmp type can't be set */
+ if (!type || !br->multicast_stats_enabled)
+ return;
+
+ if (p)
+ stats = p->mcast_stats;
+ else
+ stats = br->mcast_stats;
+ if (WARN_ON(!stats))
+ return;
+
+ br_mcast_stats_add(stats, skb, type, dir);
+}
+
+int br_multicast_init_stats(struct net_bridge *br)
+{
+ br->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats);
+ if (!br->mcast_stats)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void mcast_stats_add_dir(u64 *dst, u64 *src)
+{
+ dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX];
+ dst[BR_MCAST_DIR_TX] += src[BR_MCAST_DIR_TX];
+}
+
+void br_multicast_get_stats(const struct net_bridge *br,
+ const struct net_bridge_port *p,
+ struct br_mcast_stats *dest)
+{
+ struct bridge_mcast_stats __percpu *stats;
+ struct br_mcast_stats tdst;
+ int i;
+
+ memset(dest, 0, sizeof(*dest));
+ if (p)
+ stats = p->mcast_stats;
+ else
+ stats = br->mcast_stats;
+ if (WARN_ON(!stats))
+ return;
+
+ memset(&tdst, 0, sizeof(tdst));
+ for_each_possible_cpu(i) {
+ struct bridge_mcast_stats *cpu_stats = per_cpu_ptr(stats, i);
+ struct br_mcast_stats temp;
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
+ memcpy(&temp, &cpu_stats->mstats, sizeof(temp));
+ } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
+
+ mcast_stats_add_dir(tdst.igmp_v1queries, temp.igmp_v1queries);
+ mcast_stats_add_dir(tdst.igmp_v2queries, temp.igmp_v2queries);
+ mcast_stats_add_dir(tdst.igmp_v3queries, temp.igmp_v3queries);
+ mcast_stats_add_dir(tdst.igmp_leaves, temp.igmp_leaves);
+ mcast_stats_add_dir(tdst.igmp_v1reports, temp.igmp_v1reports);
+ mcast_stats_add_dir(tdst.igmp_v2reports, temp.igmp_v2reports);
+ mcast_stats_add_dir(tdst.igmp_v3reports, temp.igmp_v3reports);
+ tdst.igmp_parse_errors += temp.igmp_parse_errors;
+
+ mcast_stats_add_dir(tdst.mld_v1queries, temp.mld_v1queries);
+ mcast_stats_add_dir(tdst.mld_v2queries, temp.mld_v2queries);
+ mcast_stats_add_dir(tdst.mld_leaves, temp.mld_leaves);
+ mcast_stats_add_dir(tdst.mld_v1reports, temp.mld_v1reports);
+ mcast_stats_add_dir(tdst.mld_v2reports, temp.mld_v2reports);
+ tdst.mld_parse_errors += temp.mld_parse_errors;
+ }
+ memcpy(dest, &tdst, sizeof(*dest));
+}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 85e89f693589..f2a29e467e78 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -851,6 +851,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
[IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 },
[IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 },
[IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 },
+ [IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 },
};
static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
@@ -1055,6 +1056,13 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
br->multicast_startup_query_interval = clock_t_to_jiffies(val);
}
+
+ if (data[IFLA_BR_MCAST_STATS_ENABLED]) {
+ __u8 mcast_stats;
+
+ mcast_stats = nla_get_u8(data[IFLA_BR_MCAST_STATS_ENABLED]);
+ br->multicast_stats_enabled = !!mcast_stats;
+ }
#endif
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
if (data[IFLA_BR_NF_CALL_IPTABLES]) {
@@ -1110,6 +1118,7 @@ static size_t br_get_size(const struct net_device *brdev)
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */
+ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_STATS_ENABLED */
nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */
nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */
nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */
@@ -1187,6 +1196,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR,
br->multicast_query_use_ifaddr) ||
nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier) ||
+ nla_put_u8(skb, IFLA_BR_MCAST_STATS_ENABLED,
+ br->multicast_stats_enabled) ||
nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY,
br->hash_elasticity) ||
nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) ||
@@ -1234,7 +1245,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
return 0;
}
-static size_t br_get_linkxstats_size(const struct net_device *dev)
+static size_t bridge_get_linkxstats_size(const struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_vlan_group *vg;
@@ -1242,53 +1253,88 @@ static size_t br_get_linkxstats_size(const struct net_device *dev)
int numvls = 0;
vg = br_vlan_group(br);
- if (!vg)
- return 0;
-
- /* we need to count all, even placeholder entries */
- list_for_each_entry(v, &vg->vlan_list, vlist)
- numvls++;
+ if (vg) {
+ /* we need to count all, even placeholder entries */
+ list_for_each_entry(v, &vg->vlan_list, vlist)
+ numvls++;
+ }
- /* account for the vlans and the link xstats type nest attribute */
return numvls * nla_total_size(sizeof(struct bridge_vlan_xstats)) +
+ nla_total_size(sizeof(struct br_mcast_stats)) +
nla_total_size(0);
}
-static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev,
- int *prividx)
+static size_t brport_get_linkxstats_size(const struct net_device *dev)
+{
+ return nla_total_size(sizeof(struct br_mcast_stats)) +
+ nla_total_size(0);
+}
+
+static size_t br_get_linkxstats_size(const struct net_device *dev, int attr)
+{
+ size_t retsize = 0;
+
+ switch (attr) {
+ case IFLA_STATS_LINK_XSTATS:
+ retsize = bridge_get_linkxstats_size(dev);
+ break;
+ case IFLA_STATS_LINK_XSTATS_SLAVE:
+ retsize = brport_get_linkxstats_size(dev);
+ break;
+ }
+
+ return retsize;
+}
+
+static int bridge_fill_linkxstats(struct sk_buff *skb,
+ const struct net_device *dev,
+ int *prividx)
{
struct net_bridge *br = netdev_priv(dev);
+ struct nlattr *nla __maybe_unused;
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *v;
struct nlattr *nest;
int vl_idx = 0;
- vg = br_vlan_group(br);
- if (!vg)
- goto out;
nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE);
if (!nest)
return -EMSGSIZE;
- list_for_each_entry(v, &vg->vlan_list, vlist) {
- struct bridge_vlan_xstats vxi;
- struct br_vlan_stats stats;
- if (++vl_idx < *prividx)
- continue;
- memset(&vxi, 0, sizeof(vxi));
- vxi.vid = v->vid;
- br_vlan_get_stats(v, &stats);
- vxi.rx_bytes = stats.rx_bytes;
- vxi.rx_packets = stats.rx_packets;
- vxi.tx_bytes = stats.tx_bytes;
- vxi.tx_packets = stats.tx_packets;
-
- if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi))
+ vg = br_vlan_group(br);
+ if (vg) {
+ list_for_each_entry(v, &vg->vlan_list, vlist) {
+ struct bridge_vlan_xstats vxi;
+ struct br_vlan_stats stats;
+
+ if (++vl_idx < *prividx)
+ continue;
+ memset(&vxi, 0, sizeof(vxi));
+ vxi.vid = v->vid;
+ br_vlan_get_stats(v, &stats);
+ vxi.rx_bytes = stats.rx_bytes;
+ vxi.rx_packets = stats.rx_packets;
+ vxi.tx_bytes = stats.tx_bytes;
+ vxi.tx_packets = stats.tx_packets;
+
+ if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi))
+ goto nla_put_failure;
+ }
+ }
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ if (++vl_idx >= *prividx) {
+ nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST,
+ sizeof(struct br_mcast_stats),
+ BRIDGE_XSTATS_PAD);
+ if (!nla)
goto nla_put_failure;
+ br_multicast_get_stats(br, NULL, nla_data(nla));
}
+#endif
nla_nest_end(skb, nest);
*prividx = 0;
-out:
+
return 0;
nla_put_failure:
@@ -1298,6 +1344,52 @@ nla_put_failure:
return -EMSGSIZE;
}
+static int brport_fill_linkxstats(struct sk_buff *skb,
+ const struct net_device *dev,
+ int *prividx)
+{
+ struct net_bridge_port *p = br_port_get_rtnl(dev);
+ struct nlattr *nla __maybe_unused;
+ struct nlattr *nest;
+
+ if (!p)
+ return 0;
+
+ nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE);
+ if (!nest)
+ return -EMSGSIZE;
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST,
+ sizeof(struct br_mcast_stats),
+ BRIDGE_XSTATS_PAD);
+ if (!nla) {
+ nla_nest_end(skb, nest);
+ return -EMSGSIZE;
+ }
+ br_multicast_get_stats(p->br, p, nla_data(nla));
+#endif
+ nla_nest_end(skb, nest);
+
+ return 0;
+}
+
+static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev,
+ int *prividx, int attr)
+{
+ int ret = -EINVAL;
+
+ switch (attr) {
+ case IFLA_STATS_LINK_XSTATS:
+ ret = bridge_fill_linkxstats(skb, dev, prividx);
+ break;
+ case IFLA_STATS_LINK_XSTATS_SLAVE:
+ ret = brport_fill_linkxstats(skb, dev, prividx);
+ break;
+ }
+
+ return ret;
+}
+
static struct rtnl_af_ops br_af_ops __read_mostly = {
.family = AF_BRIDGE,
.get_link_af_size = br_get_link_af_size_filtered,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 52edecf3c294..aac2a6e6b008 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -75,6 +75,12 @@ struct bridge_mcast_querier {
struct br_ip addr;
struct net_bridge_port __rcu *port;
};
+
+/* IGMP/MLD statistics */
+struct bridge_mcast_stats {
+ struct br_mcast_stats mstats;
+ struct u64_stats_sync syncp;
+};
#endif
struct br_vlan_stats {
@@ -229,6 +235,7 @@ struct net_bridge_port
struct bridge_mcast_own_query ip6_own_query;
#endif /* IS_ENABLED(CONFIG_IPV6) */
unsigned char multicast_router;
+ struct bridge_mcast_stats __percpu *mcast_stats;
struct timer_list multicast_router_timer;
struct hlist_head mglist;
struct hlist_node rlist;
@@ -315,6 +322,7 @@ struct net_bridge
u8 multicast_querier:1;
u8 multicast_query_use_ifaddr:1;
u8 has_ipv6_addr:1;
+ u8 multicast_stats_enabled:1;
u32 hash_elasticity;
u32 hash_max;
@@ -337,6 +345,7 @@ struct net_bridge
struct bridge_mcast_other_query ip4_other_query;
struct bridge_mcast_own_query ip4_own_query;
struct bridge_mcast_querier ip4_querier;
+ struct bridge_mcast_stats __percpu *mcast_stats;
#if IS_ENABLED(CONFIG_IPV6)
struct bridge_mcast_other_query ip6_other_query;
struct bridge_mcast_own_query ip6_own_query;
@@ -496,14 +505,12 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
const unsigned char *addr, u16 vid);
/* br_forward.c */
-void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb);
int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb);
-void br_forward(const struct net_bridge_port *to,
- struct sk_buff *skb, struct sk_buff *skb0);
+void br_forward(const struct net_bridge_port *to, struct sk_buff *skb,
+ bool local_rcv, bool local_orig);
int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
-void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast);
-void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
- struct sk_buff *skb2, bool unicast);
+void br_flood(struct net_bridge *br, struct sk_buff *skb,
+ bool unicast, bool local_rcv, bool local_orig);
/* br_if.c */
void br_port_carrier_check(struct net_bridge_port *p);
@@ -543,7 +550,7 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
struct sk_buff *skb, u16 vid);
struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
struct sk_buff *skb, u16 vid);
-void br_multicast_add_port(struct net_bridge_port *port);
+int br_multicast_add_port(struct net_bridge_port *port);
void br_multicast_del_port(struct net_bridge_port *port);
void br_multicast_enable_port(struct net_bridge_port *port);
void br_multicast_disable_port(struct net_bridge_port *port);
@@ -551,10 +558,8 @@ void br_multicast_init(struct net_bridge *br);
void br_multicast_open(struct net_bridge *br);
void br_multicast_stop(struct net_bridge *br);
void br_multicast_dev_del(struct net_bridge *br);
-void br_multicast_deliver(struct net_bridge_mdb_entry *mdst,
- struct sk_buff *skb);
-void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
- struct sk_buff *skb, struct sk_buff *skb2);
+void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
+ struct sk_buff *skb, bool local_rcv, bool local_orig);
int br_multicast_set_router(struct net_bridge *br, unsigned long val);
int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val);
int br_multicast_toggle(struct net_bridge *br, unsigned long val);
@@ -576,6 +581,12 @@ void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
struct br_ip *group, int type, u8 flags);
void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port,
int type);
+void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p,
+ const struct sk_buff *skb, u8 type, u8 dir);
+int br_multicast_init_stats(struct net_bridge *br);
+void br_multicast_get_stats(const struct net_bridge *br,
+ const struct net_bridge_port *p,
+ struct br_mcast_stats *dest);
#define mlock_dereference(X, br) \
rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
@@ -623,6 +634,11 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
return false;
}
}
+
+static inline int br_multicast_igmp_type(const struct sk_buff *skb)
+{
+ return BR_INPUT_SKB_CB(skb)->igmp;
+}
#else
static inline int br_multicast_rcv(struct net_bridge *br,
struct net_bridge_port *port,
@@ -638,8 +654,9 @@ static inline struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
return NULL;
}
-static inline void br_multicast_add_port(struct net_bridge_port *port)
+static inline int br_multicast_add_port(struct net_bridge_port *port)
{
+ return 0;
}
static inline void br_multicast_del_port(struct net_bridge_port *port)
@@ -670,31 +687,47 @@ static inline void br_multicast_dev_del(struct net_bridge *br)
{
}
-static inline void br_multicast_deliver(struct net_bridge_mdb_entry *mdst,
- struct sk_buff *skb)
+static inline void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
+ struct sk_buff *skb,
+ bool local_rcv, bool local_orig)
{
}
-static inline void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
- struct sk_buff *skb,
- struct sk_buff *skb2)
-{
-}
static inline bool br_multicast_is_router(struct net_bridge *br)
{
return 0;
}
+
static inline bool br_multicast_querier_exists(struct net_bridge *br,
struct ethhdr *eth)
{
return false;
}
+
static inline void br_mdb_init(void)
{
}
+
static inline void br_mdb_uninit(void)
{
}
+
+static inline void br_multicast_count(struct net_bridge *br,
+ const struct net_bridge_port *p,
+ const struct sk_buff *skb,
+ u8 type, u8 dir)
+{
+}
+
+static inline int br_multicast_init_stats(struct net_bridge *br)
+{
+ return 0;
+}
+
+static inline int br_multicast_igmp_type(const struct sk_buff *skb)
+{
+ return 0;
+}
#endif
/* br_vlan.c */
@@ -942,7 +975,7 @@ void __br_set_forward_delay(struct net_bridge *br, unsigned long t);
int br_set_forward_delay(struct net_bridge *br, unsigned long x);
int br_set_hello_time(struct net_bridge *br, unsigned long x);
int br_set_max_age(struct net_bridge *br, unsigned long x);
-int br_set_ageing_time(struct net_bridge *br, u32 ageing_time);
+int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time);
/* br_stp_if.c */
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 9cb7044d0801..9258b8ef14ff 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -570,7 +570,7 @@ int br_set_max_age(struct net_bridge *br, unsigned long val)
*
* Offloaded switch entries maybe more restrictive
*/
-int br_set_ageing_time(struct net_bridge *br, u32 ageing_time)
+int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time)
{
struct switchdev_attr attr = {
.orig_dev = br->dev,
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 984d46263007..341caa0ca63a 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -55,7 +55,7 @@ void br_init_port(struct net_bridge_port *p)
netdev_err(p->dev, "failed to set HW ageing time\n");
}
-/* called under bridge lock */
+/* NO locks held */
void br_stp_enable_bridge(struct net_bridge *br)
{
struct net_bridge_port *p;
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index beb47071e38d..e120307c6e36 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -618,6 +618,30 @@ static ssize_t multicast_startup_query_interval_store(
return store_bridge_parm(d, buf, len, set_startup_query_interval);
}
static DEVICE_ATTR_RW(multicast_startup_query_interval);
+
+static ssize_t multicast_stats_enabled_show(struct device *d,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct net_bridge *br = to_bridge(d);
+
+ return sprintf(buf, "%u\n", br->multicast_stats_enabled);
+}
+
+static int set_stats_enabled(struct net_bridge *br, unsigned long val)
+{
+ br->multicast_stats_enabled = !!val;
+ return 0;
+}
+
+static ssize_t multicast_stats_enabled_store(struct device *d,
+ struct device_attribute *attr,
+ const char *buf,
+ size_t len)
+{
+ return store_bridge_parm(d, buf, len, set_stats_enabled);
+}
+static DEVICE_ATTR_RW(multicast_stats_enabled);
#endif
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
static ssize_t nf_call_iptables_show(
@@ -784,6 +808,7 @@ static struct attribute *bridge_attrs[] = {
&dev_attr_multicast_query_interval.attr,
&dev_attr_multicast_query_response_interval.attr,
&dev_attr_multicast_startup_query_interval.attr,
+ &dev_attr_multicast_stats_enabled.attr,
#endif
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
&dev_attr_nf_call_iptables.attr,
diff --git a/net/bridge/netfilter/ebt_802_3.c b/net/bridge/netfilter/ebt_802_3.c
index 2a449b7ab8fa..5fc4affd9fdb 100644
--- a/net/bridge/netfilter/ebt_802_3.c
+++ b/net/bridge/netfilter/ebt_802_3.c
@@ -20,16 +20,16 @@ ebt_802_3_mt(const struct sk_buff *skb, struct xt_action_param *par)
__be16 type = hdr->llc.ui.ctrl & IS_UI ? hdr->llc.ui.type : hdr->llc.ni.type;
if (info->bitmask & EBT_802_3_SAP) {
- if (FWINV(info->sap != hdr->llc.ui.ssap, EBT_802_3_SAP))
+ if (NF_INVF(info, EBT_802_3_SAP, info->sap != hdr->llc.ui.ssap))
return false;
- if (FWINV(info->sap != hdr->llc.ui.dsap, EBT_802_3_SAP))
+ if (NF_INVF(info, EBT_802_3_SAP, info->sap != hdr->llc.ui.dsap))
return false;
}
if (info->bitmask & EBT_802_3_TYPE) {
if (!(hdr->llc.ui.dsap == CHECK_TYPE && hdr->llc.ui.ssap == CHECK_TYPE))
return false;
- if (FWINV(info->type != type, EBT_802_3_TYPE))
+ if (NF_INVF(info, EBT_802_3_TYPE, info->type != type))
return false;
}
diff --git a/net/bridge/netfilter/ebt_arp.c b/net/bridge/netfilter/ebt_arp.c
index cd457b891b27..227142282b45 100644
--- a/net/bridge/netfilter/ebt_arp.c
+++ b/net/bridge/netfilter/ebt_arp.c
@@ -25,14 +25,14 @@ ebt_arp_mt(const struct sk_buff *skb, struct xt_action_param *par)
ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
if (ah == NULL)
return false;
- if (info->bitmask & EBT_ARP_OPCODE && FWINV(info->opcode !=
- ah->ar_op, EBT_ARP_OPCODE))
+ if ((info->bitmask & EBT_ARP_OPCODE) &&
+ NF_INVF(info, EBT_ARP_OPCODE, info->opcode != ah->ar_op))
return false;
- if (info->bitmask & EBT_ARP_HTYPE && FWINV(info->htype !=
- ah->ar_hrd, EBT_ARP_HTYPE))
+ if ((info->bitmask & EBT_ARP_HTYPE) &&
+ NF_INVF(info, EBT_ARP_HTYPE, info->htype != ah->ar_hrd))
return false;
- if (info->bitmask & EBT_ARP_PTYPE && FWINV(info->ptype !=
- ah->ar_pro, EBT_ARP_PTYPE))
+ if ((info->bitmask & EBT_ARP_PTYPE) &&
+ NF_INVF(info, EBT_ARP_PTYPE, info->ptype != ah->ar_pro))
return false;
if (info->bitmask & (EBT_ARP_SRC_IP | EBT_ARP_DST_IP | EBT_ARP_GRAT)) {
@@ -51,21 +51,22 @@ ebt_arp_mt(const struct sk_buff *skb, struct xt_action_param *par)
sizeof(daddr), &daddr);
if (dap == NULL)
return false;
- if (info->bitmask & EBT_ARP_SRC_IP &&
- FWINV(info->saddr != (*sap & info->smsk), EBT_ARP_SRC_IP))
+ if ((info->bitmask & EBT_ARP_SRC_IP) &&
+ NF_INVF(info, EBT_ARP_SRC_IP,
+ info->saddr != (*sap & info->smsk)))
return false;
- if (info->bitmask & EBT_ARP_DST_IP &&
- FWINV(info->daddr != (*dap & info->dmsk), EBT_ARP_DST_IP))
+ if ((info->bitmask & EBT_ARP_DST_IP) &&
+ NF_INVF(info, EBT_ARP_DST_IP,
+ info->daddr != (*dap & info->dmsk)))
return false;
- if (info->bitmask & EBT_ARP_GRAT &&
- FWINV(*dap != *sap, EBT_ARP_GRAT))
+ if ((info->bitmask & EBT_ARP_GRAT) &&
+ NF_INVF(info, EBT_ARP_GRAT, *dap != *sap))
return false;
}
if (info->bitmask & (EBT_ARP_SRC_MAC | EBT_ARP_DST_MAC)) {
const unsigned char *mp;
unsigned char _mac[ETH_ALEN];
- uint8_t verdict, i;
if (ah->ar_hln != ETH_ALEN || ah->ar_hrd != htons(ARPHRD_ETHER))
return false;
@@ -74,11 +75,9 @@ ebt_arp_mt(const struct sk_buff *skb, struct xt_action_param *par)
sizeof(_mac), &_mac);
if (mp == NULL)
return false;
- verdict = 0;
- for (i = 0; i < 6; i++)
- verdict |= (mp[i] ^ info->smaddr[i]) &
- info->smmsk[i];
- if (FWINV(verdict != 0, EBT_ARP_SRC_MAC))
+ if (NF_INVF(info, EBT_ARP_SRC_MAC,
+ !ether_addr_equal_masked(mp, info->smaddr,
+ info->smmsk)))
return false;
}
@@ -88,11 +87,9 @@ ebt_arp_mt(const struct sk_buff *skb, struct xt_action_param *par)
sizeof(_mac), &_mac);
if (mp == NULL)
return false;
- verdict = 0;
- for (i = 0; i < 6; i++)
- verdict |= (mp[i] ^ info->dmaddr[i]) &
- info->dmmsk[i];
- if (FWINV(verdict != 0, EBT_ARP_DST_MAC))
+ if (NF_INVF(info, EBT_ARP_DST_MAC,
+ !ether_addr_equal_masked(mp, info->dmaddr,
+ info->dmmsk)))
return false;
}
}
diff --git a/net/bridge/netfilter/ebt_ip.c b/net/bridge/netfilter/ebt_ip.c
index 23bca62d58d2..d06968bdf5ec 100644
--- a/net/bridge/netfilter/ebt_ip.c
+++ b/net/bridge/netfilter/ebt_ip.c
@@ -36,19 +36,19 @@ ebt_ip_mt(const struct sk_buff *skb, struct xt_action_param *par)
ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
if (ih == NULL)
return false;
- if (info->bitmask & EBT_IP_TOS &&
- FWINV(info->tos != ih->tos, EBT_IP_TOS))
+ if ((info->bitmask & EBT_IP_TOS) &&
+ NF_INVF(info, EBT_IP_TOS, info->tos != ih->tos))
return false;
- if (info->bitmask & EBT_IP_SOURCE &&
- FWINV((ih->saddr & info->smsk) !=
- info->saddr, EBT_IP_SOURCE))
+ if ((info->bitmask & EBT_IP_SOURCE) &&
+ NF_INVF(info, EBT_IP_SOURCE,
+ (ih->saddr & info->smsk) != info->saddr))
return false;
if ((info->bitmask & EBT_IP_DEST) &&
- FWINV((ih->daddr & info->dmsk) !=
- info->daddr, EBT_IP_DEST))
+ NF_INVF(info, EBT_IP_DEST,
+ (ih->daddr & info->dmsk) != info->daddr))
return false;
if (info->bitmask & EBT_IP_PROTO) {
- if (FWINV(info->protocol != ih->protocol, EBT_IP_PROTO))
+ if (NF_INVF(info, EBT_IP_PROTO, info->protocol != ih->protocol))
return false;
if (!(info->bitmask & EBT_IP_DPORT) &&
!(info->bitmask & EBT_IP_SPORT))
@@ -61,16 +61,16 @@ ebt_ip_mt(const struct sk_buff *skb, struct xt_action_param *par)
return false;
if (info->bitmask & EBT_IP_DPORT) {
u32 dst = ntohs(pptr->dst);
- if (FWINV(dst < info->dport[0] ||
- dst > info->dport[1],
- EBT_IP_DPORT))
+ if (NF_INVF(info, EBT_IP_DPORT,
+ dst < info->dport[0] ||
+ dst > info->dport[1]))
return false;
}
if (info->bitmask & EBT_IP_SPORT) {
u32 src = ntohs(pptr->src);
- if (FWINV(src < info->sport[0] ||
- src > info->sport[1],
- EBT_IP_SPORT))
+ if (NF_INVF(info, EBT_IP_SPORT,
+ src < info->sport[0] ||
+ src > info->sport[1]))
return false;
}
}
diff --git a/net/bridge/netfilter/ebt_ip6.c b/net/bridge/netfilter/ebt_ip6.c
index 98de6e7fd86d..4617491be41e 100644
--- a/net/bridge/netfilter/ebt_ip6.c
+++ b/net/bridge/netfilter/ebt_ip6.c
@@ -45,15 +45,18 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
if (ih6 == NULL)
return false;
- if (info->bitmask & EBT_IP6_TCLASS &&
- FWINV(info->tclass != ipv6_get_dsfield(ih6), EBT_IP6_TCLASS))
+ if ((info->bitmask & EBT_IP6_TCLASS) &&
+ NF_INVF(info, EBT_IP6_TCLASS,
+ info->tclass != ipv6_get_dsfield(ih6)))
return false;
- if ((info->bitmask & EBT_IP6_SOURCE &&
- FWINV(ipv6_masked_addr_cmp(&ih6->saddr, &info->smsk,
- &info->saddr), EBT_IP6_SOURCE)) ||
- (info->bitmask & EBT_IP6_DEST &&
- FWINV(ipv6_masked_addr_cmp(&ih6->daddr, &info->dmsk,
- &info->daddr), EBT_IP6_DEST)))
+ if (((info->bitmask & EBT_IP6_SOURCE) &&
+ NF_INVF(info, EBT_IP6_SOURCE,
+ ipv6_masked_addr_cmp(&ih6->saddr, &info->smsk,
+ &info->saddr))) ||
+ ((info->bitmask & EBT_IP6_DEST) &&
+ NF_INVF(info, EBT_IP6_DEST,
+ ipv6_masked_addr_cmp(&ih6->daddr, &info->dmsk,
+ &info->daddr))))
return false;
if (info->bitmask & EBT_IP6_PROTO) {
uint8_t nexthdr = ih6->nexthdr;
@@ -63,7 +66,7 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr, &frag_off);
if (offset_ph == -1)
return false;
- if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
+ if (NF_INVF(info, EBT_IP6_PROTO, info->protocol != nexthdr))
return false;
if (!(info->bitmask & (EBT_IP6_DPORT |
EBT_IP6_SPORT | EBT_IP6_ICMP6)))
@@ -76,22 +79,24 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
return false;
if (info->bitmask & EBT_IP6_DPORT) {
u16 dst = ntohs(pptr->tcpudphdr.dst);
- if (FWINV(dst < info->dport[0] ||
- dst > info->dport[1], EBT_IP6_DPORT))
+ if (NF_INVF(info, EBT_IP6_DPORT,
+ dst < info->dport[0] ||
+ dst > info->dport[1]))
return false;
}
if (info->bitmask & EBT_IP6_SPORT) {
u16 src = ntohs(pptr->tcpudphdr.src);
- if (FWINV(src < info->sport[0] ||
- src > info->sport[1], EBT_IP6_SPORT))
+ if (NF_INVF(info, EBT_IP6_SPORT,
+ src < info->sport[0] ||
+ src > info->sport[1]))
return false;
}
if ((info->bitmask & EBT_IP6_ICMP6) &&
- FWINV(pptr->icmphdr.type < info->icmpv6_type[0] ||
- pptr->icmphdr.type > info->icmpv6_type[1] ||
- pptr->icmphdr.code < info->icmpv6_code[0] ||
- pptr->icmphdr.code > info->icmpv6_code[1],
- EBT_IP6_ICMP6))
+ NF_INVF(info, EBT_IP6_ICMP6,
+ pptr->icmphdr.type < info->icmpv6_type[0] ||
+ pptr->icmphdr.type > info->icmpv6_type[1] ||
+ pptr->icmphdr.code < info->icmpv6_code[0] ||
+ pptr->icmphdr.code > info->icmpv6_code[1]))
return false;
}
return true;
diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c
index 6b731e12ecfa..3140eb912d7e 100644
--- a/net/bridge/netfilter/ebt_stp.c
+++ b/net/bridge/netfilter/ebt_stp.c
@@ -17,24 +17,24 @@
#define BPDU_TYPE_TCN 0x80
struct stp_header {
- uint8_t dsap;
- uint8_t ssap;
- uint8_t ctrl;
- uint8_t pid;
- uint8_t vers;
- uint8_t type;
+ u8 dsap;
+ u8 ssap;
+ u8 ctrl;
+ u8 pid;
+ u8 vers;
+ u8 type;
};
struct stp_config_pdu {
- uint8_t flags;
- uint8_t root[8];
- uint8_t root_cost[4];
- uint8_t sender[8];
- uint8_t port[2];
- uint8_t msg_age[2];
- uint8_t max_age[2];
- uint8_t hello_time[2];
- uint8_t forward_delay[2];
+ u8 flags;
+ u8 root[8];
+ u8 root_cost[4];
+ u8 sender[8];
+ u8 port[2];
+ u8 msg_age[2];
+ u8 max_age[2];
+ u8 hello_time[2];
+ u8 forward_delay[2];
};
#define NR16(p) (p[0] << 8 | p[1])
@@ -44,76 +44,73 @@ static bool ebt_filter_config(const struct ebt_stp_info *info,
const struct stp_config_pdu *stpc)
{
const struct ebt_stp_config_info *c;
- uint16_t v16;
- uint32_t v32;
- int verdict, i;
+ u16 v16;
+ u32 v32;
c = &info->config;
if ((info->bitmask & EBT_STP_FLAGS) &&
- FWINV(c->flags != stpc->flags, EBT_STP_FLAGS))
+ NF_INVF(info, EBT_STP_FLAGS, c->flags != stpc->flags))
return false;
if (info->bitmask & EBT_STP_ROOTPRIO) {
v16 = NR16(stpc->root);
- if (FWINV(v16 < c->root_priol ||
- v16 > c->root_priou, EBT_STP_ROOTPRIO))
+ if (NF_INVF(info, EBT_STP_ROOTPRIO,
+ v16 < c->root_priol || v16 > c->root_priou))
return false;
}
if (info->bitmask & EBT_STP_ROOTADDR) {
- verdict = 0;
- for (i = 0; i < 6; i++)
- verdict |= (stpc->root[2+i] ^ c->root_addr[i]) &
- c->root_addrmsk[i];
- if (FWINV(verdict != 0, EBT_STP_ROOTADDR))
+ if (NF_INVF(info, EBT_STP_ROOTADDR,
+ !ether_addr_equal_masked(&stpc->root[2],
+ c->root_addr,
+ c->root_addrmsk)))
return false;
}
if (info->bitmask & EBT_STP_ROOTCOST) {
v32 = NR32(stpc->root_cost);
- if (FWINV(v32 < c->root_costl ||
- v32 > c->root_costu, EBT_STP_ROOTCOST))
+ if (NF_INVF(info, EBT_STP_ROOTCOST,
+ v32 < c->root_costl || v32 > c->root_costu))
return false;
}
if (info->bitmask & EBT_STP_SENDERPRIO) {
v16 = NR16(stpc->sender);
- if (FWINV(v16 < c->sender_priol ||
- v16 > c->sender_priou, EBT_STP_SENDERPRIO))
+ if (NF_INVF(info, EBT_STP_SENDERPRIO,
+ v16 < c->sender_priol || v16 > c->sender_priou))
return false;
}
if (info->bitmask & EBT_STP_SENDERADDR) {
- verdict = 0;
- for (i = 0; i < 6; i++)
- verdict |= (stpc->sender[2+i] ^ c->sender_addr[i]) &
- c->sender_addrmsk[i];
- if (FWINV(verdict != 0, EBT_STP_SENDERADDR))
+ if (NF_INVF(info, EBT_STP_SENDERADDR,
+ !ether_addr_equal_masked(&stpc->sender[2],
+ c->sender_addr,
+ c->sender_addrmsk)))
return false;
}
if (info->bitmask & EBT_STP_PORT) {
v16 = NR16(stpc->port);
- if (FWINV(v16 < c->portl ||
- v16 > c->portu, EBT_STP_PORT))
+ if (NF_INVF(info, EBT_STP_PORT,
+ v16 < c->portl || v16 > c->portu))
return false;
}
if (info->bitmask & EBT_STP_MSGAGE) {
v16 = NR16(stpc->msg_age);
- if (FWINV(v16 < c->msg_agel ||
- v16 > c->msg_ageu, EBT_STP_MSGAGE))
+ if (NF_INVF(info, EBT_STP_MSGAGE,
+ v16 < c->msg_agel || v16 > c->msg_ageu))
return false;
}
if (info->bitmask & EBT_STP_MAXAGE) {
v16 = NR16(stpc->max_age);
- if (FWINV(v16 < c->max_agel ||
- v16 > c->max_ageu, EBT_STP_MAXAGE))
+ if (NF_INVF(info, EBT_STP_MAXAGE,
+ v16 < c->max_agel || v16 > c->max_ageu))
return false;
}
if (info->bitmask & EBT_STP_HELLOTIME) {
v16 = NR16(stpc->hello_time);
- if (FWINV(v16 < c->hello_timel ||
- v16 > c->hello_timeu, EBT_STP_HELLOTIME))
+ if (NF_INVF(info, EBT_STP_HELLOTIME,
+ v16 < c->hello_timel || v16 > c->hello_timeu))
return false;
}
if (info->bitmask & EBT_STP_FWDD) {
v16 = NR16(stpc->forward_delay);
- if (FWINV(v16 < c->forward_delayl ||
- v16 > c->forward_delayu, EBT_STP_FWDD))
+ if (NF_INVF(info, EBT_STP_FWDD,
+ v16 < c->forward_delayl || v16 > c->forward_delayu))
return false;
}
return true;
@@ -125,7 +122,7 @@ ebt_stp_mt(const struct sk_buff *skb, struct xt_action_param *par)
const struct ebt_stp_info *info = par->matchinfo;
const struct stp_header *sp;
struct stp_header _stph;
- const uint8_t header[6] = {0x42, 0x42, 0x03, 0x00, 0x00, 0x00};
+ const u8 header[6] = {0x42, 0x42, 0x03, 0x00, 0x00, 0x00};
sp = skb_header_pointer(skb, 0, sizeof(_stph), &_stph);
if (sp == NULL)
@@ -135,8 +132,8 @@ ebt_stp_mt(const struct sk_buff *skb, struct xt_action_param *par)
if (memcmp(sp, header, sizeof(header)))
return false;
- if (info->bitmask & EBT_STP_TYPE &&
- FWINV(info->type != sp->type, EBT_STP_TYPE))
+ if ((info->bitmask & EBT_STP_TYPE) &&
+ NF_INVF(info, EBT_STP_TYPE, info->type != sp->type))
return false;
if (sp->type == BPDU_TYPE_CONFIG &&
@@ -156,8 +153,8 @@ ebt_stp_mt(const struct sk_buff *skb, struct xt_action_param *par)
static int ebt_stp_mt_check(const struct xt_mtchk_param *par)
{
const struct ebt_stp_info *info = par->matchinfo;
- const uint8_t bridge_ula[6] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00};
- const uint8_t msk[6] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+ const u8 bridge_ula[6] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00};
+ const u8 msk[6] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
const struct ebt_entry *e = par->entryinfo;
if (info->bitmask & ~EBT_STP_MASK || info->invflags & ~EBT_STP_MASK ||
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 5a61f35412a0..0833c251aef7 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -121,7 +121,6 @@ ebt_dev_check(const char *entry, const struct net_device *device)
return devname[i] != entry[i] && entry[i] != 1;
}
-#define FWINV2(bool, invflg) ((bool) ^ !!(e->invflags & invflg))
/* process standard matches */
static inline int
ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb,
@@ -130,7 +129,6 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb,
const struct ethhdr *h = eth_hdr(skb);
const struct net_bridge_port *p;
__be16 ethproto;
- int verdict, i;
if (skb_vlan_tag_present(skb))
ethproto = htons(ETH_P_8021Q);
@@ -138,38 +136,36 @@ 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(eth_proto_is_802_3(ethproto), EBT_IPROTO))
+ if (NF_INVF(e, EBT_IPROTO, eth_proto_is_802_3(ethproto)))
return 1;
} else if (!(e->bitmask & EBT_NOPROTO) &&
- FWINV2(e->ethproto != ethproto, EBT_IPROTO))
+ NF_INVF(e, EBT_IPROTO, e->ethproto != ethproto))
return 1;
- if (FWINV2(ebt_dev_check(e->in, in), EBT_IIN))
+ if (NF_INVF(e, EBT_IIN, ebt_dev_check(e->in, in)))
return 1;
- if (FWINV2(ebt_dev_check(e->out, out), EBT_IOUT))
+ if (NF_INVF(e, EBT_IOUT, ebt_dev_check(e->out, out)))
return 1;
/* rcu_read_lock()ed by nf_hook_slow */
if (in && (p = br_port_get_rcu(in)) != NULL &&
- FWINV2(ebt_dev_check(e->logical_in, p->br->dev), EBT_ILOGICALIN))
+ NF_INVF(e, EBT_ILOGICALIN,
+ ebt_dev_check(e->logical_in, p->br->dev)))
return 1;
if (out && (p = br_port_get_rcu(out)) != NULL &&
- FWINV2(ebt_dev_check(e->logical_out, p->br->dev), EBT_ILOGICALOUT))
+ NF_INVF(e, EBT_ILOGICALOUT,
+ ebt_dev_check(e->logical_out, p->br->dev)))
return 1;
if (e->bitmask & EBT_SOURCEMAC) {
- verdict = 0;
- for (i = 0; i < 6; i++)
- verdict |= (h->h_source[i] ^ e->sourcemac[i]) &
- e->sourcemsk[i];
- if (FWINV2(verdict != 0, EBT_ISOURCE))
+ if (NF_INVF(e, EBT_ISOURCE,
+ !ether_addr_equal_masked(h->h_source, e->sourcemac,
+ e->sourcemsk)))
return 1;
}
if (e->bitmask & EBT_DESTMAC) {
- verdict = 0;
- for (i = 0; i < 6; i++)
- verdict |= (h->h_dest[i] ^ e->destmac[i]) &
- e->destmsk[i];
- if (FWINV2(verdict != 0, EBT_IDEST))
+ if (NF_INVF(e, EBT_IDEST,
+ !ether_addr_equal_masked(h->h_dest, e->destmac,
+ e->destmsk)))
return 1;
}
return 0;
@@ -372,6 +368,8 @@ ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par,
match = xt_find_match(NFPROTO_BRIDGE, m->u.name, 0);
if (IS_ERR(match) || match->family != NFPROTO_BRIDGE) {
+ if (!IS_ERR(match))
+ module_put(match->me);
request_module("ebt_%s", m->u.name);
match = xt_find_match(NFPROTO_BRIDGE, m->u.name, 0);
}
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
index 4b901d9f2e7c..ad47a921b701 100644
--- a/net/bridge/netfilter/nft_meta_bridge.c
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -86,6 +86,7 @@ static const struct nft_expr_ops nft_meta_bridge_set_ops = {
.init = nft_meta_set_init,
.destroy = nft_meta_set_destroy,
.dump = nft_meta_set_dump,
+ .validate = nft_meta_set_validate,
};
static const struct nft_expr_ops *
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 77f7e7a9ebe1..0b77ffbc27d6 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -72,7 +72,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
nft_reject_br_push_etherhdr(oldskb, nskb);
- br_deliver(br_port_get_rcu(dev), nskb);
+ br_forward(br_port_get_rcu(dev), nskb, false, true);
}
static void nft_reject_br_send_v4_unreach(struct net *net,
@@ -140,7 +140,7 @@ static void nft_reject_br_send_v4_unreach(struct net *net,
nft_reject_br_push_etherhdr(oldskb, nskb);
- br_deliver(br_port_get_rcu(dev), nskb);
+ br_forward(br_port_get_rcu(dev), nskb, false, true);
}
static void nft_reject_br_send_v6_tcp_reset(struct net *net,
@@ -174,7 +174,7 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net,
nft_reject_br_push_etherhdr(oldskb, nskb);
- br_deliver(br_port_get_rcu(dev), nskb);
+ br_forward(br_port_get_rcu(dev), nskb, false, true);
}
static bool reject6_br_csum_ok(struct sk_buff *skb, int hook)
@@ -255,7 +255,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
nft_reject_br_push_etherhdr(oldskb, nskb);
- br_deliver(br_port_get_rcu(dev), nskb);
+ br_forward(br_port_get_rcu(dev), nskb, false, true);
}
static void nft_reject_bridge_eval(const struct nft_expr *expr,
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 67a4a36febd1..3408ed51b611 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -13,7 +13,6 @@
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/if_ether.h>
-#include <linux/moduleparam.h>
#include <linux/ip.h>
#include <linux/sched.h>
#include <linux/sockios.h>
diff --git a/net/can/Makefile b/net/can/Makefile
index cef49eb1f5c7..10936754e3f2 100644
--- a/net/can/Makefile
+++ b/net/can/Makefile
@@ -3,7 +3,8 @@
#
obj-$(CONFIG_CAN) += can.o
-can-y := af_can.o proc.o
+can-y := af_can.o
+can-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_CAN_RAW) += can-raw.o
can-raw-y := raw.o
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 166d436196c1..1108079d934f 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -911,14 +911,14 @@ static __init int can_init(void)
if (!rcv_cache)
return -ENOMEM;
- if (stats_timer) {
+ if (IS_ENABLED(CONFIG_PROC_FS)) {
+ if (stats_timer) {
/* the statistics are updated every second (timer triggered) */
- setup_timer(&can_stattimer, can_stat_update, 0);
- mod_timer(&can_stattimer, round_jiffies(jiffies + HZ));
- } else
- can_stattimer.function = NULL;
-
- can_init_proc();
+ setup_timer(&can_stattimer, can_stat_update, 0);
+ mod_timer(&can_stattimer, round_jiffies(jiffies + HZ));
+ }
+ can_init_proc();
+ }
/* protocol register */
sock_register(&can_family_ops);
@@ -933,10 +933,12 @@ static __exit void can_exit(void)
{
struct net_device *dev;
- if (stats_timer)
- del_timer_sync(&can_stattimer);
+ if (IS_ENABLED(CONFIG_PROC_FS)) {
+ if (stats_timer)
+ del_timer_sync(&can_stattimer);
- can_remove_proc();
+ can_remove_proc();
+ }
/* protocol unregister */
dev_remove_pack(&canfd_packet);
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 6863310d6973..8e999ffdf28b 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1,7 +1,7 @@
/*
* bcm.c - Broadcast Manager to filter/send (cyclic) CAN content
*
- * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
+ * Copyright (c) 2002-2016 Volkswagen Group Electronic Research
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -67,27 +67,31 @@
*/
#define MAX_NFRAMES 256
-/* use of last_frames[index].can_dlc */
+/* use of last_frames[index].flags */
#define RX_RECV 0x40 /* received data for this element */
#define RX_THR 0x80 /* element not been sent due to throttle feature */
-#define BCM_CAN_DLC_MASK 0x0F /* clean private flags in can_dlc by masking */
+#define BCM_CAN_FLAGS_MASK 0x3F /* to clean private flags after usage */
/* get best masking value for can_rx_register() for a given single can_id */
#define REGMASK(id) ((id & CAN_EFF_FLAG) ? \
(CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
(CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
-#define CAN_BCM_VERSION CAN_VERSION
+#define CAN_BCM_VERSION "20160617"
MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
MODULE_ALIAS("can-proto-2");
-/* easy access to can_frame payload */
-static inline u64 GET_U64(const struct can_frame *cp)
+/*
+ * easy access to the first 64 bit of can(fd)_frame payload. cp->data is
+ * 64 bit aligned so the offset has to be multiples of 8 which is ensured
+ * by the only callers in bcm_rx_cmp_to_index() bcm_rx_handler().
+ */
+static inline u64 get_u64(const struct canfd_frame *cp, int offset)
{
- return *(u64 *)cp->data;
+ return *(u64 *)(cp->data + offset);
}
struct bcm_op {
@@ -101,13 +105,14 @@ struct bcm_op {
struct tasklet_struct tsklet, thrtsklet;
ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg;
int rx_ifindex;
+ int cfsiz;
u32 count;
u32 nframes;
u32 currframe;
- struct can_frame *frames;
- struct can_frame *last_frames;
- struct can_frame sframe;
- struct can_frame last_sframe;
+ struct canfd_frame *frames;
+ struct canfd_frame *last_frames;
+ struct canfd_frame sframe;
+ struct canfd_frame last_sframe;
struct sock *sk;
struct net_device *rx_reg_dev;
};
@@ -136,7 +141,7 @@ static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv)
return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC);
}
-#define CFSIZ sizeof(struct can_frame)
+#define CFSIZ(flags) ((flags & CAN_FD_FRAME) ? CANFD_MTU : CAN_MTU)
#define OPSIZ sizeof(struct bcm_op)
#define MHSIZ sizeof(struct bcm_msg_head)
@@ -183,43 +188,50 @@ static int bcm_proc_show(struct seq_file *m, void *v)
if (!op->frames_abs)
continue;
- seq_printf(m, "rx_op: %03X %-5s ",
- op->can_id, bcm_proc_getifname(ifname, op->ifindex));
- seq_printf(m, "[%u]%c ", op->nframes,
- (op->flags & RX_CHECK_DLC)?'d':' ');
+ seq_printf(m, "rx_op: %03X %-5s ", op->can_id,
+ bcm_proc_getifname(ifname, op->ifindex));
+
+ if (op->flags & CAN_FD_FRAME)
+ seq_printf(m, "(%u)", op->nframes);
+ else
+ seq_printf(m, "[%u]", op->nframes);
+
+ seq_printf(m, "%c ", (op->flags & RX_CHECK_DLC) ? 'd' : ' ');
+
if (op->kt_ival1.tv64)
seq_printf(m, "timeo=%lld ",
- (long long)
- ktime_to_us(op->kt_ival1));
+ (long long)ktime_to_us(op->kt_ival1));
if (op->kt_ival2.tv64)
seq_printf(m, "thr=%lld ",
- (long long)
- ktime_to_us(op->kt_ival2));
+ (long long)ktime_to_us(op->kt_ival2));
seq_printf(m, "# recv %ld (%ld) => reduction: ",
- op->frames_filtered, op->frames_abs);
+ op->frames_filtered, op->frames_abs);
reduction = 100 - (op->frames_filtered * 100) / op->frames_abs;
seq_printf(m, "%s%ld%%\n",
- (reduction == 100)?"near ":"", reduction);
+ (reduction == 100) ? "near " : "", reduction);
}
list_for_each_entry(op, &bo->tx_ops, list) {
- seq_printf(m, "tx_op: %03X %s [%u] ",
- op->can_id,
- bcm_proc_getifname(ifname, op->ifindex),
- op->nframes);
+ seq_printf(m, "tx_op: %03X %s ", op->can_id,
+ bcm_proc_getifname(ifname, op->ifindex));
+
+ if (op->flags & CAN_FD_FRAME)
+ seq_printf(m, "(%u) ", op->nframes);
+ else
+ seq_printf(m, "[%u] ", op->nframes);
if (op->kt_ival1.tv64)
seq_printf(m, "t1=%lld ",
- (long long) ktime_to_us(op->kt_ival1));
+ (long long)ktime_to_us(op->kt_ival1));
if (op->kt_ival2.tv64)
seq_printf(m, "t2=%lld ",
- (long long) ktime_to_us(op->kt_ival2));
+ (long long)ktime_to_us(op->kt_ival2));
seq_printf(m, "# sent %ld\n", op->frames_abs);
}
@@ -248,7 +260,7 @@ static void bcm_can_tx(struct bcm_op *op)
{
struct sk_buff *skb;
struct net_device *dev;
- struct can_frame *cf = &op->frames[op->currframe];
+ struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe;
/* no target device? => exit */
if (!op->ifindex)
@@ -260,7 +272,7 @@ static void bcm_can_tx(struct bcm_op *op)
return;
}
- skb = alloc_skb(CFSIZ + sizeof(struct can_skb_priv), gfp_any());
+ skb = alloc_skb(op->cfsiz + sizeof(struct can_skb_priv), gfp_any());
if (!skb)
goto out;
@@ -268,7 +280,7 @@ static void bcm_can_tx(struct bcm_op *op)
can_skb_prv(skb)->ifindex = dev->ifindex;
can_skb_prv(skb)->skbcnt = 0;
- memcpy(skb_put(skb, CFSIZ), cf, CFSIZ);
+ memcpy(skb_put(skb, op->cfsiz), cf, op->cfsiz);
/* send with loopback */
skb->dev = dev;
@@ -282,7 +294,7 @@ static void bcm_can_tx(struct bcm_op *op)
/* reached last frame? */
if (op->currframe >= op->nframes)
op->currframe = 0;
- out:
+out:
dev_put(dev);
}
@@ -291,13 +303,13 @@ static void bcm_can_tx(struct bcm_op *op)
* (consisting of bcm_msg_head + x CAN frames)
*/
static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
- struct can_frame *frames, int has_timestamp)
+ struct canfd_frame *frames, int has_timestamp)
{
struct sk_buff *skb;
- struct can_frame *firstframe;
+ struct canfd_frame *firstframe;
struct sockaddr_can *addr;
struct sock *sk = op->sk;
- unsigned int datalen = head->nframes * CFSIZ;
+ unsigned int datalen = head->nframes * op->cfsiz;
int err;
skb = alloc_skb(sizeof(*head) + datalen, gfp_any());
@@ -307,19 +319,19 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
memcpy(skb_put(skb, sizeof(*head)), head, sizeof(*head));
if (head->nframes) {
- /* can_frames starting here */
- firstframe = (struct can_frame *)skb_tail_pointer(skb);
+ /* CAN frames starting here */
+ firstframe = (struct canfd_frame *)skb_tail_pointer(skb);
memcpy(skb_put(skb, datalen), frames, datalen);
/*
- * the BCM uses the can_dlc-element of the can_frame
+ * the BCM uses the flags-element of the canfd_frame
* structure for internal purposes. This is only
* relevant for updates that are generated by the
* BCM, where nframes is 1
*/
if (head->nframes == 1)
- firstframe->can_dlc &= BCM_CAN_DLC_MASK;
+ firstframe->flags &= BCM_CAN_FLAGS_MASK;
}
if (has_timestamp) {
@@ -406,7 +418,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
/*
* bcm_rx_changed - create a RX_CHANGED notification due to changed content
*/
-static void bcm_rx_changed(struct bcm_op *op, struct can_frame *data)
+static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data)
{
struct bcm_msg_head head;
@@ -418,7 +430,7 @@ static void bcm_rx_changed(struct bcm_op *op, struct can_frame *data)
op->frames_filtered = op->frames_abs = 0;
/* this element is not throttled anymore */
- data->can_dlc &= (BCM_CAN_DLC_MASK|RX_RECV);
+ data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV);
head.opcode = RX_CHANGED;
head.flags = op->flags;
@@ -437,13 +449,13 @@ static void bcm_rx_changed(struct bcm_op *op, struct can_frame *data)
* 2. send a notification to the user (if possible)
*/
static void bcm_rx_update_and_send(struct bcm_op *op,
- struct can_frame *lastdata,
- const struct can_frame *rxdata)
+ struct canfd_frame *lastdata,
+ const struct canfd_frame *rxdata)
{
- memcpy(lastdata, rxdata, CFSIZ);
+ memcpy(lastdata, rxdata, op->cfsiz);
/* mark as used and throttled by default */
- lastdata->can_dlc |= (RX_RECV|RX_THR);
+ lastdata->flags |= (RX_RECV|RX_THR);
/* throttling mode inactive ? */
if (!op->kt_ival2.tv64) {
@@ -481,33 +493,36 @@ rx_changed_settime:
* received data stored in op->last_frames[]
*/
static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index,
- const struct can_frame *rxdata)
+ const struct canfd_frame *rxdata)
{
+ struct canfd_frame *cf = op->frames + op->cfsiz * index;
+ struct canfd_frame *lcf = op->last_frames + op->cfsiz * index;
+ int i;
+
/*
- * no one uses the MSBs of can_dlc for comparison,
+ * no one uses the MSBs of flags for comparison,
* so we use it here to detect the first time of reception
*/
- if (!(op->last_frames[index].can_dlc & RX_RECV)) {
+ if (!(lcf->flags & RX_RECV)) {
/* received data for the first time => send update to user */
- bcm_rx_update_and_send(op, &op->last_frames[index], rxdata);
+ bcm_rx_update_and_send(op, lcf, rxdata);
return;
}
- /* do a real check in can_frame data section */
-
- if ((GET_U64(&op->frames[index]) & GET_U64(rxdata)) !=
- (GET_U64(&op->frames[index]) & GET_U64(&op->last_frames[index]))) {
- bcm_rx_update_and_send(op, &op->last_frames[index], rxdata);
- return;
+ /* do a real check in CAN frame data section */
+ for (i = 0; i < rxdata->len; i += 8) {
+ if ((get_u64(cf, i) & get_u64(rxdata, i)) !=
+ (get_u64(cf, i) & get_u64(lcf, i))) {
+ bcm_rx_update_and_send(op, lcf, rxdata);
+ return;
+ }
}
if (op->flags & RX_CHECK_DLC) {
- /* do a real check in can_frame dlc */
- if (rxdata->can_dlc != (op->last_frames[index].can_dlc &
- BCM_CAN_DLC_MASK)) {
- bcm_rx_update_and_send(op, &op->last_frames[index],
- rxdata);
+ /* do a real check in CAN frame length */
+ if (rxdata->len != lcf->len) {
+ bcm_rx_update_and_send(op, lcf, rxdata);
return;
}
}
@@ -556,8 +571,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
/* if user wants to be informed, when cyclic CAN-Messages come back */
if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) {
- /* clear received can_frames to indicate 'nothing received' */
- memset(op->last_frames, 0, op->nframes * CFSIZ);
+ /* clear received CAN frames to indicate 'nothing received' */
+ memset(op->last_frames, 0, op->nframes * op->cfsiz);
}
return HRTIMER_NORESTART;
@@ -569,9 +584,11 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
static inline int bcm_rx_do_flush(struct bcm_op *op, int update,
unsigned int index)
{
- if ((op->last_frames) && (op->last_frames[index].can_dlc & RX_THR)) {
+ struct canfd_frame *lcf = op->last_frames + op->cfsiz * index;
+
+ if ((op->last_frames) && (lcf->flags & RX_THR)) {
if (update)
- bcm_rx_changed(op, &op->last_frames[index]);
+ bcm_rx_changed(op, lcf);
return 1;
}
return 0;
@@ -636,15 +653,19 @@ static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer)
static void bcm_rx_handler(struct sk_buff *skb, void *data)
{
struct bcm_op *op = (struct bcm_op *)data;
- const struct can_frame *rxframe = (struct can_frame *)skb->data;
+ const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data;
unsigned int i;
- /* disable timeout */
- hrtimer_cancel(&op->timer);
-
if (op->can_id != rxframe->can_id)
return;
+ /* make sure to handle the correct frame type (CAN / CAN FD) */
+ if (skb->len != op->cfsiz)
+ return;
+
+ /* disable timeout */
+ hrtimer_cancel(&op->timer);
+
/* save rx timestamp */
op->rx_stamp = skb->tstamp;
/* save originator for recvfrom() */
@@ -675,13 +696,14 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
* multiplex compare
*
* find the first multiplex mask that fits.
- * Remark: The MUX-mask is stored in index 0
+ * Remark: The MUX-mask is stored in index 0 - but only the
+ * first 64 bits of the frame data[] are relevant (CAN FD)
*/
for (i = 1; i < op->nframes; i++) {
- if ((GET_U64(&op->frames[0]) & GET_U64(rxframe)) ==
- (GET_U64(&op->frames[0]) &
- GET_U64(&op->frames[i]))) {
+ if ((get_u64(op->frames, 0) & get_u64(rxframe, 0)) ==
+ (get_u64(op->frames, 0) &
+ get_u64(op->frames + op->cfsiz * i, 0))) {
bcm_rx_cmp_to_index(op, i, rxframe);
break;
}
@@ -695,13 +717,14 @@ rx_starttimer:
/*
* helpers for bcm_op handling: find & delete bcm [rx|tx] op elements
*/
-static struct bcm_op *bcm_find_op(struct list_head *ops, canid_t can_id,
- int ifindex)
+static struct bcm_op *bcm_find_op(struct list_head *ops,
+ struct bcm_msg_head *mh, int ifindex)
{
struct bcm_op *op;
list_for_each_entry(op, ops, list) {
- if ((op->can_id == can_id) && (op->ifindex == ifindex))
+ if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
+ (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME))
return op;
}
@@ -744,12 +767,14 @@ static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
/*
* bcm_delete_rx_op - find and remove a rx op (returns number of removed ops)
*/
-static int bcm_delete_rx_op(struct list_head *ops, canid_t can_id, int ifindex)
+static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
+ int ifindex)
{
struct bcm_op *op, *n;
list_for_each_entry_safe(op, n, ops, list) {
- if ((op->can_id == can_id) && (op->ifindex == ifindex)) {
+ if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
+ (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
/*
* Don't care if we're bound or not (due to netdev
@@ -789,12 +814,14 @@ static int bcm_delete_rx_op(struct list_head *ops, canid_t can_id, int ifindex)
/*
* bcm_delete_tx_op - find and remove a tx op (returns number of removed ops)
*/
-static int bcm_delete_tx_op(struct list_head *ops, canid_t can_id, int ifindex)
+static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh,
+ int ifindex)
{
struct bcm_op *op, *n;
list_for_each_entry_safe(op, n, ops, list) {
- if ((op->can_id == can_id) && (op->ifindex == ifindex)) {
+ if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
+ (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
list_del(&op->list);
bcm_remove_op(op);
return 1; /* done */
@@ -810,7 +837,7 @@ static int bcm_delete_tx_op(struct list_head *ops, canid_t can_id, int ifindex)
static int bcm_read_op(struct list_head *ops, struct bcm_msg_head *msg_head,
int ifindex)
{
- struct bcm_op *op = bcm_find_op(ops, msg_head->can_id, ifindex);
+ struct bcm_op *op = bcm_find_op(ops, msg_head, ifindex);
if (!op)
return -EINVAL;
@@ -835,6 +862,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
{
struct bcm_sock *bo = bcm_sk(sk);
struct bcm_op *op;
+ struct canfd_frame *cf;
unsigned int i;
int err;
@@ -842,39 +870,46 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
if (!ifindex)
return -ENODEV;
- /* check nframes boundaries - we need at least one can_frame */
+ /* check nframes boundaries - we need at least one CAN frame */
if (msg_head->nframes < 1 || msg_head->nframes > MAX_NFRAMES)
return -EINVAL;
/* check the given can_id */
- op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex);
-
+ op = bcm_find_op(&bo->tx_ops, msg_head, ifindex);
if (op) {
/* update existing BCM operation */
/*
- * Do we need more space for the can_frames than currently
+ * Do we need more space for the CAN frames than currently
* allocated? -> This is a _really_ unusual use-case and
* therefore (complexity / locking) it is not supported.
*/
if (msg_head->nframes > op->nframes)
return -E2BIG;
- /* update can_frames content */
+ /* update CAN frames content */
for (i = 0; i < msg_head->nframes; i++) {
- err = memcpy_from_msg((u8 *)&op->frames[i], msg, CFSIZ);
- if (op->frames[i].can_dlc > 8)
- err = -EINVAL;
+ cf = op->frames + op->cfsiz * i;
+ err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz);
+
+ if (op->flags & CAN_FD_FRAME) {
+ if (cf->len > 64)
+ err = -EINVAL;
+ } else {
+ if (cf->len > 8)
+ err = -EINVAL;
+ }
if (err < 0)
return err;
if (msg_head->flags & TX_CP_CAN_ID) {
/* copy can_id into frame */
- op->frames[i].can_id = msg_head->can_id;
+ cf->can_id = msg_head->can_id;
}
}
+ op->flags = msg_head->flags;
} else {
/* insert new BCM operation for the given can_id */
@@ -883,11 +918,13 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
if (!op)
return -ENOMEM;
- op->can_id = msg_head->can_id;
+ op->can_id = msg_head->can_id;
+ op->cfsiz = CFSIZ(msg_head->flags);
+ op->flags = msg_head->flags;
- /* create array for can_frames and copy the data */
+ /* create array for CAN frames and copy the data */
if (msg_head->nframes > 1) {
- op->frames = kmalloc(msg_head->nframes * CFSIZ,
+ op->frames = kmalloc(msg_head->nframes * op->cfsiz,
GFP_KERNEL);
if (!op->frames) {
kfree(op);
@@ -897,10 +934,17 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
op->frames = &op->sframe;
for (i = 0; i < msg_head->nframes; i++) {
- err = memcpy_from_msg((u8 *)&op->frames[i], msg, CFSIZ);
- if (op->frames[i].can_dlc > 8)
- err = -EINVAL;
+ cf = op->frames + op->cfsiz * i;
+ err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz);
+
+ if (op->flags & CAN_FD_FRAME) {
+ if (cf->len > 64)
+ err = -EINVAL;
+ } else {
+ if (cf->len > 8)
+ err = -EINVAL;
+ }
if (err < 0) {
if (op->frames != &op->sframe)
@@ -911,7 +955,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
if (msg_head->flags & TX_CP_CAN_ID) {
/* copy can_id into frame */
- op->frames[i].can_id = msg_head->can_id;
+ cf->can_id = msg_head->can_id;
}
}
@@ -946,8 +990,6 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
/* check flags */
- op->flags = msg_head->flags;
-
if (op->flags & TX_RESET_MULTI_IDX) {
/* start multiple frame transmission with index 0 */
op->currframe = 0;
@@ -968,7 +1010,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
if (op->flags & STARTTIMER) {
hrtimer_cancel(&op->timer);
- /* spec: send can_frame when starting timer */
+ /* spec: send CAN frame when starting timer */
op->flags |= TX_ANNOUNCE;
}
@@ -981,7 +1023,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
if (op->flags & STARTTIMER)
bcm_tx_start_timer(op);
- return msg_head->nframes * CFSIZ + MHSIZ;
+ return msg_head->nframes * op->cfsiz + MHSIZ;
}
/*
@@ -1012,12 +1054,12 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
return -EINVAL;
/* check the given can_id */
- op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex);
+ op = bcm_find_op(&bo->rx_ops, msg_head, ifindex);
if (op) {
/* update existing BCM operation */
/*
- * Do we need more space for the can_frames than currently
+ * Do we need more space for the CAN frames than currently
* allocated? -> This is a _really_ unusual use-case and
* therefore (complexity / locking) it is not supported.
*/
@@ -1025,17 +1067,18 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
return -E2BIG;
if (msg_head->nframes) {
- /* update can_frames content */
+ /* update CAN frames content */
err = memcpy_from_msg((u8 *)op->frames, msg,
- msg_head->nframes * CFSIZ);
+ msg_head->nframes * op->cfsiz);
if (err < 0)
return err;
/* clear last_frames to indicate 'nothing received' */
- memset(op->last_frames, 0, msg_head->nframes * CFSIZ);
+ memset(op->last_frames, 0, msg_head->nframes * op->cfsiz);
}
op->nframes = msg_head->nframes;
+ op->flags = msg_head->flags;
/* Only an update -> do not call can_rx_register() */
do_rx_register = 0;
@@ -1046,20 +1089,22 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
if (!op)
return -ENOMEM;
- op->can_id = msg_head->can_id;
- op->nframes = msg_head->nframes;
+ op->can_id = msg_head->can_id;
+ op->nframes = msg_head->nframes;
+ op->cfsiz = CFSIZ(msg_head->flags);
+ op->flags = msg_head->flags;
if (msg_head->nframes > 1) {
- /* create array for can_frames and copy the data */
- op->frames = kmalloc(msg_head->nframes * CFSIZ,
+ /* create array for CAN frames and copy the data */
+ op->frames = kmalloc(msg_head->nframes * op->cfsiz,
GFP_KERNEL);
if (!op->frames) {
kfree(op);
return -ENOMEM;
}
- /* create and init array for received can_frames */
- op->last_frames = kzalloc(msg_head->nframes * CFSIZ,
+ /* create and init array for received CAN frames */
+ op->last_frames = kzalloc(msg_head->nframes * op->cfsiz,
GFP_KERNEL);
if (!op->last_frames) {
kfree(op->frames);
@@ -1074,7 +1119,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
if (msg_head->nframes) {
err = memcpy_from_msg((u8 *)op->frames, msg,
- msg_head->nframes * CFSIZ);
+ msg_head->nframes * op->cfsiz);
if (err < 0) {
if (op->frames != &op->sframe)
kfree(op->frames);
@@ -1116,7 +1161,6 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
} /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */
/* check flags */
- op->flags = msg_head->flags;
if (op->flags & RX_RTR_FRAME) {
@@ -1188,13 +1232,14 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
}
}
- return msg_head->nframes * CFSIZ + MHSIZ;
+ return msg_head->nframes * op->cfsiz + MHSIZ;
}
/*
* bcm_tx_send - send a single CAN frame to the CAN interface (for bcm_sendmsg)
*/
-static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
+static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk,
+ int cfsiz)
{
struct sk_buff *skb;
struct net_device *dev;
@@ -1204,13 +1249,13 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
if (!ifindex)
return -ENODEV;
- skb = alloc_skb(CFSIZ + sizeof(struct can_skb_priv), GFP_KERNEL);
+ skb = alloc_skb(cfsiz + sizeof(struct can_skb_priv), GFP_KERNEL);
if (!skb)
return -ENOMEM;
can_skb_reserve(skb);
- err = memcpy_from_msg(skb_put(skb, CFSIZ), msg, CFSIZ);
+ err = memcpy_from_msg(skb_put(skb, cfsiz), msg, cfsiz);
if (err < 0) {
kfree_skb(skb);
return err;
@@ -1232,7 +1277,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
if (err)
return err;
- return CFSIZ + MHSIZ;
+ return cfsiz + MHSIZ;
}
/*
@@ -1244,13 +1289,23 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
struct bcm_sock *bo = bcm_sk(sk);
int ifindex = bo->ifindex; /* default ifindex for this bcm_op */
struct bcm_msg_head msg_head;
+ int cfsiz;
int ret; /* read bytes or error codes as return value */
if (!bo->bound)
return -ENOTCONN;
/* check for valid message length from userspace */
- if (size < MHSIZ || (size - MHSIZ) % CFSIZ)
+ if (size < MHSIZ)
+ return -EINVAL;
+
+ /* read message head information */
+ ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ);
+ if (ret < 0)
+ return ret;
+
+ cfsiz = CFSIZ(msg_head.flags);
+ if ((size - MHSIZ) % cfsiz)
return -EINVAL;
/* check for alternative ifindex for this bcm_op */
@@ -1284,12 +1339,6 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
}
}
- /* read message head information */
-
- ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ);
- if (ret < 0)
- return ret;
-
lock_sock(sk);
switch (msg_head.opcode) {
@@ -1303,14 +1352,14 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
break;
case TX_DELETE:
- if (bcm_delete_tx_op(&bo->tx_ops, msg_head.can_id, ifindex))
+ if (bcm_delete_tx_op(&bo->tx_ops, &msg_head, ifindex))
ret = MHSIZ;
else
ret = -EINVAL;
break;
case RX_DELETE:
- if (bcm_delete_rx_op(&bo->rx_ops, msg_head.can_id, ifindex))
+ if (bcm_delete_rx_op(&bo->rx_ops, &msg_head, ifindex))
ret = MHSIZ;
else
ret = -EINVAL;
@@ -1329,11 +1378,11 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
break;
case TX_SEND:
- /* we need exactly one can_frame behind the msg head */
- if ((msg_head.nframes != 1) || (size != CFSIZ + MHSIZ))
+ /* we need exactly one CAN frame behind the msg head */
+ if ((msg_head.nframes != 1) || (size != cfsiz + MHSIZ))
ret = -EINVAL;
else
- ret = bcm_tx_send(msg, ifindex, sk);
+ ret = bcm_tx_send(msg, ifindex, sk, cfsiz);
break;
default:
diff --git a/net/can/proc.c b/net/can/proc.c
index 1a19b985a868..85ef7bb0f176 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -517,8 +517,7 @@ void can_init_proc(void)
can_dir = proc_mkdir("can", init_net.proc_net);
if (!can_dir) {
- printk(KERN_INFO "can: failed to create /proc/net/can . "
- "CONFIG_PROC_FS missing?\n");
+ pr_info("can: failed to create /proc/net/can.\n");
return;
}
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
index 958d9856912c..84cbed630c4b 100644
--- a/net/ceph/Makefile
+++ b/net/ceph/Makefile
@@ -11,5 +11,5 @@ libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
crypto.o armor.o \
auth_x.o \
ceph_fs.o ceph_strings.o ceph_hash.o \
- pagevec.o snapshot.o
+ pagevec.o snapshot.o string_table.o
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 55d2bfee16d7..bddfcf6f09c2 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -747,6 +747,8 @@ out:
static void __exit exit_ceph_lib(void)
{
dout("exit_ceph_lib\n");
+ WARN_ON(!ceph_strings_empty());
+
ceph_osdc_cleanup();
ceph_msgr_exit();
ceph_crypto_shutdown();
diff --git a/net/ceph/ceph_fs.c b/net/ceph/ceph_fs.c
index 41466ccb972a..7d54e944de5e 100644
--- a/net/ceph/ceph_fs.c
+++ b/net/ceph/ceph_fs.c
@@ -9,9 +9,9 @@
*/
int ceph_file_layout_is_valid(const struct ceph_file_layout *layout)
{
- __u32 su = le32_to_cpu(layout->fl_stripe_unit);
- __u32 sc = le32_to_cpu(layout->fl_stripe_count);
- __u32 os = le32_to_cpu(layout->fl_object_size);
+ __u32 su = layout->stripe_unit;
+ __u32 sc = layout->stripe_count;
+ __u32 os = layout->object_size;
/* stripe unit, object size must be non-zero, 64k increment */
if (!su || (su & (CEPH_MIN_STRIPE_UNIT-1)))
@@ -27,6 +27,30 @@ int ceph_file_layout_is_valid(const struct ceph_file_layout *layout)
return 1;
}
+void ceph_file_layout_from_legacy(struct ceph_file_layout *fl,
+ struct ceph_file_layout_legacy *legacy)
+{
+ fl->stripe_unit = le32_to_cpu(legacy->fl_stripe_unit);
+ fl->stripe_count = le32_to_cpu(legacy->fl_stripe_count);
+ fl->object_size = le32_to_cpu(legacy->fl_object_size);
+ fl->pool_id = le32_to_cpu(legacy->fl_pg_pool);
+ if (fl->pool_id == 0)
+ fl->pool_id = -1;
+}
+EXPORT_SYMBOL(ceph_file_layout_from_legacy);
+
+void ceph_file_layout_to_legacy(struct ceph_file_layout *fl,
+ struct ceph_file_layout_legacy *legacy)
+{
+ legacy->fl_stripe_unit = cpu_to_le32(fl->stripe_unit);
+ legacy->fl_stripe_count = cpu_to_le32(fl->stripe_count);
+ legacy->fl_object_size = cpu_to_le32(fl->object_size);
+ if (fl->pool_id >= 0)
+ legacy->fl_pg_pool = cpu_to_le32(fl->pool_id);
+ else
+ legacy->fl_pg_pool = 0;
+}
+EXPORT_SYMBOL(ceph_file_layout_to_legacy);
int ceph_flags_to_mode(int flags)
{
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index e77b04ca7802..c62b2b029a6e 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -156,8 +156,16 @@ static void dump_target(struct seq_file *s, struct ceph_osd_request_target *t)
seq_printf(s, "]/%d\t[", t->up.primary);
for (i = 0; i < t->acting.size; i++)
seq_printf(s, "%s%d", (!i ? "" : ","), t->acting.osds[i]);
- seq_printf(s, "]/%d\t%*pE\t0x%x", t->acting.primary,
- t->target_oid.name_len, t->target_oid.name, t->flags);
+ seq_printf(s, "]/%d\t", t->acting.primary);
+ if (t->target_oloc.pool_ns) {
+ seq_printf(s, "%*pE/%*pE\t0x%x",
+ (int)t->target_oloc.pool_ns->len,
+ t->target_oloc.pool_ns->str,
+ t->target_oid.name_len, t->target_oid.name, t->flags);
+ } else {
+ seq_printf(s, "%*pE\t0x%x", t->target_oid.name_len,
+ t->target_oid.name, t->flags);
+ }
if (t->paused)
seq_puts(s, "\tP");
}
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 37c38a7fb5c5..ef34a02719d7 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -227,9 +227,10 @@ static void __schedule_delayed(struct ceph_mon_client *monc)
}
const char *ceph_sub_str[] = {
- [CEPH_SUB_MDSMAP] = "mdsmap",
[CEPH_SUB_MONMAP] = "monmap",
[CEPH_SUB_OSDMAP] = "osdmap",
+ [CEPH_SUB_FSMAP] = "fsmap.user",
+ [CEPH_SUB_MDSMAP] = "mdsmap",
};
/*
@@ -573,7 +574,7 @@ static void complete_generic_request(struct ceph_mon_generic_request *req)
put_generic_request(req);
}
-void cancel_generic_request(struct ceph_mon_generic_request *req)
+static void cancel_generic_request(struct ceph_mon_generic_request *req)
{
struct ceph_mon_client *monc = req->monc;
struct ceph_mon_generic_request *lookup_req;
@@ -1193,6 +1194,7 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
case CEPH_MSG_MON_MAP:
case CEPH_MSG_MDS_MAP:
case CEPH_MSG_OSD_MAP:
+ case CEPH_MSG_FS_MAP_USER:
m = ceph_msg_new(type, front_len, GFP_NOFS, false);
if (!m)
return NULL; /* ENOMEM--return skip == 0 */
diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c
index ddec1c10ac80..aaed59a47b1d 100644
--- a/net/ceph/msgpool.c
+++ b/net/ceph/msgpool.c
@@ -5,6 +5,7 @@
#include <linux/types.h>
#include <linux/vmalloc.h>
+#include <linux/ceph/messenger.h>
#include <linux/ceph/msgpool.h>
static void *msgpool_alloc(gfp_t gfp_mask, void *arg)
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 89469592076c..a97e7b506612 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -387,7 +387,9 @@ static void target_copy(struct ceph_osd_request_target *dest,
static void target_destroy(struct ceph_osd_request_target *t)
{
ceph_oid_destroy(&t->base_oid);
+ ceph_oloc_destroy(&t->base_oloc);
ceph_oid_destroy(&t->target_oid);
+ ceph_oloc_destroy(&t->target_oloc);
}
/*
@@ -533,6 +535,11 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
}
EXPORT_SYMBOL(ceph_osdc_alloc_request);
+static int ceph_oloc_encoding_size(struct ceph_object_locator *oloc)
+{
+ return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0);
+}
+
int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
{
struct ceph_osd_client *osdc = req->r_osdc;
@@ -540,11 +547,13 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
int msg_size;
WARN_ON(ceph_oid_empty(&req->r_base_oid));
+ WARN_ON(ceph_oloc_empty(&req->r_base_oloc));
/* create request message */
msg_size = 4 + 4 + 4; /* client_inc, osdmap_epoch, flags */
msg_size += 4 + 4 + 4 + 8; /* mtime, reassert_version */
- msg_size += 2 + 4 + 8 + 4 + 4; /* oloc */
+ msg_size += CEPH_ENCODING_START_BLK_LEN +
+ ceph_oloc_encoding_size(&req->r_base_oloc); /* oloc */
msg_size += 1 + 8 + 4 + 4; /* pgid */
msg_size += 4 + req->r_base_oid.name_len; /* oid */
msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op);
@@ -932,7 +941,7 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
osd_req_op_init(req, which, opcode, 0);
} else {
- u32 object_size = le32_to_cpu(layout->fl_object_size);
+ u32 object_size = layout->object_size;
u32 object_base = off - objoff;
if (!(truncate_seq == 1 && truncate_size == -1ULL)) {
if (truncate_size <= object_base) {
@@ -948,7 +957,8 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
}
req->r_flags = flags;
- req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout);
+ req->r_base_oloc.pool = layout->pool_id;
+ req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns);
ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum);
req->r_snapid = vino.snap;
@@ -1489,12 +1499,16 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg)
p += sizeof(req->r_replay_version);
/* oloc */
- ceph_encode_8(&p, 4);
- ceph_encode_8(&p, 4);
- ceph_encode_32(&p, 8 + 4 + 4);
+ ceph_start_encoding(&p, 5, 4,
+ ceph_oloc_encoding_size(&req->r_t.target_oloc));
ceph_encode_64(&p, req->r_t.target_oloc.pool);
ceph_encode_32(&p, -1); /* preferred */
ceph_encode_32(&p, 0); /* key len */
+ if (req->r_t.target_oloc.pool_ns)
+ ceph_encode_string(&p, end, req->r_t.target_oloc.pool_ns->str,
+ req->r_t.target_oloc.pool_ns->len);
+ else
+ ceph_encode_32(&p, 0);
/* pgid */
ceph_encode_8(&p, 1);
@@ -2594,9 +2608,22 @@ static int ceph_oloc_decode(void **p, void *end,
}
if (struct_v >= 5) {
+ bool changed = false;
+
len = ceph_decode_32(p);
if (len > 0) {
- pr_warn("ceph_object_locator::nspace is set\n");
+ ceph_decode_need(p, end, len, e_inval);
+ if (!oloc->pool_ns ||
+ ceph_compare_string(oloc->pool_ns, *p, len))
+ changed = true;
+ *p += len;
+ } else {
+ if (oloc->pool_ns)
+ changed = true;
+ }
+ if (changed) {
+ /* redirect changes namespace */
+ pr_warn("ceph_object_locator::nspace is changed\n");
goto e_inval;
}
}
@@ -2806,7 +2833,9 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
goto out_unlock_session;
}
+ m.redirect.oloc.pool_ns = req->r_t.target_oloc.pool_ns;
ret = decode_MOSDOpReply(msg, &m);
+ m.redirect.oloc.pool_ns = NULL;
if (ret) {
pr_err("failed to decode MOSDOpReply for tid %llu: %d\n",
req->r_tid, ret);
@@ -2835,7 +2864,11 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
unlink_request(osd, req);
mutex_unlock(&osd->lock);
- ceph_oloc_copy(&req->r_t.target_oloc, &m.redirect.oloc);
+ /*
+ * Not ceph_oloc_copy() - changing pool_ns is not
+ * supported.
+ */
+ req->r_t.target_oloc.pool = m.redirect.oloc.pool;
req->r_flags |= CEPH_OSD_FLAG_REDIRECTED;
req->r_tid = 0;
__submit_request(req, false);
@@ -4187,7 +4220,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
pages = ceph_alloc_page_vector(calc_pages_for(0, data_len),
GFP_NOIO);
- if (!pages) {
+ if (IS_ERR(pages)) {
ceph_msg_put(m);
return NULL;
}
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 03062bb763b3..d2436880b305 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1261,6 +1261,115 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
}
/*
+ * Encoding order is (new_up_client, new_state, new_weight). Need to
+ * apply in the (new_weight, new_state, new_up_client) order, because
+ * an incremental map may look like e.g.
+ *
+ * new_up_client: { osd=6, addr=... } # set osd_state and addr
+ * new_state: { osd=6, xorstate=EXISTS } # clear osd_state
+ */
+static int decode_new_up_state_weight(void **p, void *end,
+ struct ceph_osdmap *map)
+{
+ void *new_up_client;
+ void *new_state;
+ void *new_weight_end;
+ u32 len;
+
+ new_up_client = *p;
+ ceph_decode_32_safe(p, end, len, e_inval);
+ len *= sizeof(u32) + sizeof(struct ceph_entity_addr);
+ ceph_decode_need(p, end, len, e_inval);
+ *p += len;
+
+ new_state = *p;
+ ceph_decode_32_safe(p, end, len, e_inval);
+ len *= sizeof(u32) + sizeof(u8);
+ ceph_decode_need(p, end, len, e_inval);
+ *p += len;
+
+ /* new_weight */
+ ceph_decode_32_safe(p, end, len, e_inval);
+ while (len--) {
+ s32 osd;
+ u32 w;
+
+ ceph_decode_need(p, end, 2*sizeof(u32), e_inval);
+ osd = ceph_decode_32(p);
+ w = ceph_decode_32(p);
+ BUG_ON(osd >= map->max_osd);
+ pr_info("osd%d weight 0x%x %s\n", osd, w,
+ w == CEPH_OSD_IN ? "(in)" :
+ (w == CEPH_OSD_OUT ? "(out)" : ""));
+ map->osd_weight[osd] = w;
+
+ /*
+ * If we are marking in, set the EXISTS, and clear the
+ * AUTOOUT and NEW bits.
+ */
+ if (w) {
+ map->osd_state[osd] |= CEPH_OSD_EXISTS;
+ map->osd_state[osd] &= ~(CEPH_OSD_AUTOOUT |
+ CEPH_OSD_NEW);
+ }
+ }
+ new_weight_end = *p;
+
+ /* new_state (up/down) */
+ *p = new_state;
+ len = ceph_decode_32(p);
+ while (len--) {
+ s32 osd;
+ u8 xorstate;
+ int ret;
+
+ osd = ceph_decode_32(p);
+ xorstate = ceph_decode_8(p);
+ if (xorstate == 0)
+ xorstate = CEPH_OSD_UP;
+ BUG_ON(osd >= map->max_osd);
+ if ((map->osd_state[osd] & CEPH_OSD_UP) &&
+ (xorstate & CEPH_OSD_UP))
+ pr_info("osd%d down\n", osd);
+ if ((map->osd_state[osd] & CEPH_OSD_EXISTS) &&
+ (xorstate & CEPH_OSD_EXISTS)) {
+ pr_info("osd%d does not exist\n", osd);
+ map->osd_weight[osd] = CEPH_OSD_IN;
+ ret = set_primary_affinity(map, osd,
+ CEPH_OSD_DEFAULT_PRIMARY_AFFINITY);
+ if (ret)
+ return ret;
+ memset(map->osd_addr + osd, 0, sizeof(*map->osd_addr));
+ map->osd_state[osd] = 0;
+ } else {
+ map->osd_state[osd] ^= xorstate;
+ }
+ }
+
+ /* new_up_client */
+ *p = new_up_client;
+ len = ceph_decode_32(p);
+ while (len--) {
+ s32 osd;
+ struct ceph_entity_addr addr;
+
+ osd = ceph_decode_32(p);
+ ceph_decode_copy(p, &addr, sizeof(addr));
+ ceph_decode_addr(&addr);
+ BUG_ON(osd >= map->max_osd);
+ pr_info("osd%d up\n", osd);
+ map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP;
+ map->osd_addr[osd] = addr;
+ }
+
+ *p = new_weight_end;
+ return 0;
+
+e_inval:
+ return -EINVAL;
+}
+
+/*
* decode and apply an incremental map update.
*/
struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
@@ -1358,49 +1467,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
__remove_pg_pool(&map->pg_pools, pi);
}
- /* new_up */
- ceph_decode_32_safe(p, end, len, e_inval);
- while (len--) {
- u32 osd;
- struct ceph_entity_addr addr;
- ceph_decode_32_safe(p, end, osd, e_inval);
- ceph_decode_copy_safe(p, end, &addr, sizeof(addr), e_inval);
- ceph_decode_addr(&addr);
- pr_info("osd%d up\n", osd);
- BUG_ON(osd >= map->max_osd);
- map->osd_state[osd] |= CEPH_OSD_UP | CEPH_OSD_EXISTS;
- map->osd_addr[osd] = addr;
- }
-
- /* new_state */
- ceph_decode_32_safe(p, end, len, e_inval);
- while (len--) {
- u32 osd;
- u8 xorstate;
- ceph_decode_32_safe(p, end, osd, e_inval);
- xorstate = **(u8 **)p;
- (*p)++; /* clean flag */
- if (xorstate == 0)
- xorstate = CEPH_OSD_UP;
- if (xorstate & CEPH_OSD_UP)
- pr_info("osd%d down\n", osd);
- if (osd < map->max_osd)
- map->osd_state[osd] ^= xorstate;
- }
-
- /* new_weight */
- ceph_decode_32_safe(p, end, len, e_inval);
- while (len--) {
- u32 osd, off;
- ceph_decode_need(p, end, sizeof(u32)*2, e_inval);
- osd = ceph_decode_32(p);
- off = ceph_decode_32(p);
- pr_info("osd%d weight 0x%x %s\n", osd, off,
- off == CEPH_OSD_IN ? "(in)" :
- (off == CEPH_OSD_OUT ? "(out)" : ""));
- if (osd < map->max_osd)
- map->osd_weight[osd] = off;
- }
+ /* new_up_client, new_state, new_weight */
+ err = decode_new_up_state_weight(p, end, map);
+ if (err)
+ goto bad;
/* new_pg_temp */
err = decode_new_pg_temp(p, end, map);
@@ -1440,6 +1510,24 @@ bad:
return ERR_PTR(err);
}
+void ceph_oloc_copy(struct ceph_object_locator *dest,
+ const struct ceph_object_locator *src)
+{
+ WARN_ON(!ceph_oloc_empty(dest));
+ WARN_ON(dest->pool_ns); /* empty() only covers ->pool */
+
+ dest->pool = src->pool;
+ if (src->pool_ns)
+ dest->pool_ns = ceph_get_string(src->pool_ns);
+}
+EXPORT_SYMBOL(ceph_oloc_copy);
+
+void ceph_oloc_destroy(struct ceph_object_locator *oloc)
+{
+ ceph_put_string(oloc->pool_ns);
+}
+EXPORT_SYMBOL(ceph_oloc_destroy);
+
void ceph_oid_copy(struct ceph_object_id *dest,
const struct ceph_object_id *src)
{
@@ -1700,9 +1788,9 @@ int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
u64 *ono,
u64 *oxoff, u64 *oxlen)
{
- u32 osize = le32_to_cpu(layout->fl_object_size);
- u32 su = le32_to_cpu(layout->fl_stripe_unit);
- u32 sc = le32_to_cpu(layout->fl_stripe_count);
+ u32 osize = layout->object_size;
+ u32 su = layout->stripe_unit;
+ u32 sc = layout->stripe_count;
u32 bl, stripeno, stripepos, objsetno;
u32 su_per_object;
u64 t, su_offset;
@@ -1774,12 +1862,34 @@ int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
if (!pi)
return -ENOENT;
- raw_pgid->pool = oloc->pool;
- raw_pgid->seed = ceph_str_hash(pi->object_hash, oid->name,
- oid->name_len);
-
- dout("%s %s -> raw_pgid %llu.%x\n", __func__, oid->name,
- raw_pgid->pool, raw_pgid->seed);
+ if (!oloc->pool_ns) {
+ raw_pgid->pool = oloc->pool;
+ raw_pgid->seed = ceph_str_hash(pi->object_hash, oid->name,
+ oid->name_len);
+ dout("%s %s -> raw_pgid %llu.%x\n", __func__, oid->name,
+ raw_pgid->pool, raw_pgid->seed);
+ } else {
+ char stack_buf[256];
+ char *buf = stack_buf;
+ int nsl = oloc->pool_ns->len;
+ size_t total = nsl + 1 + oid->name_len;
+
+ if (total > sizeof(stack_buf)) {
+ buf = kmalloc(total, GFP_NOIO);
+ if (!buf)
+ return -ENOMEM;
+ }
+ memcpy(buf, oloc->pool_ns->str, nsl);
+ buf[nsl] = '\037';
+ memcpy(buf + nsl + 1, oid->name, oid->name_len);
+ raw_pgid->pool = oloc->pool;
+ raw_pgid->seed = ceph_str_hash(pi->object_hash, buf, total);
+ if (buf != stack_buf)
+ kfree(buf);
+ dout("%s %s ns %.*s -> raw_pgid %llu.%x\n", __func__,
+ oid->name, nsl, oloc->pool_ns->str,
+ raw_pgid->pool, raw_pgid->seed);
+ }
return 0;
}
EXPORT_SYMBOL(ceph_object_locator_to_pg);
diff --git a/net/ceph/string_table.c b/net/ceph/string_table.c
new file mode 100644
index 000000000000..22fb96efcf34
--- /dev/null
+++ b/net/ceph/string_table.c
@@ -0,0 +1,105 @@
+#include <linux/slab.h>
+#include <linux/gfp.h>
+#include <linux/string.h>
+#include <linux/spinlock.h>
+#include <linux/ceph/string_table.h>
+
+static DEFINE_SPINLOCK(string_tree_lock);
+static struct rb_root string_tree = RB_ROOT;
+
+struct ceph_string *ceph_find_or_create_string(const char* str, size_t len)
+{
+ struct ceph_string *cs, *exist;
+ struct rb_node **p, *parent;
+ int ret;
+
+ exist = NULL;
+ spin_lock(&string_tree_lock);
+ p = &string_tree.rb_node;
+ while (*p) {
+ exist = rb_entry(*p, struct ceph_string, node);
+ ret = ceph_compare_string(exist, str, len);
+ if (ret > 0)
+ p = &(*p)->rb_left;
+ else if (ret < 0)
+ p = &(*p)->rb_right;
+ else
+ break;
+ exist = NULL;
+ }
+ if (exist && !kref_get_unless_zero(&exist->kref)) {
+ rb_erase(&exist->node, &string_tree);
+ RB_CLEAR_NODE(&exist->node);
+ exist = NULL;
+ }
+ spin_unlock(&string_tree_lock);
+ if (exist)
+ return exist;
+
+ cs = kmalloc(sizeof(*cs) + len + 1, GFP_NOFS);
+ if (!cs)
+ return NULL;
+
+ kref_init(&cs->kref);
+ cs->len = len;
+ memcpy(cs->str, str, len);
+ cs->str[len] = 0;
+
+retry:
+ exist = NULL;
+ parent = NULL;
+ p = &string_tree.rb_node;
+ spin_lock(&string_tree_lock);
+ while (*p) {
+ parent = *p;
+ exist = rb_entry(*p, struct ceph_string, node);
+ ret = ceph_compare_string(exist, str, len);
+ if (ret > 0)
+ p = &(*p)->rb_left;
+ else if (ret < 0)
+ p = &(*p)->rb_right;
+ else
+ break;
+ exist = NULL;
+ }
+ ret = 0;
+ if (!exist) {
+ rb_link_node(&cs->node, parent, p);
+ rb_insert_color(&cs->node, &string_tree);
+ } else if (!kref_get_unless_zero(&exist->kref)) {
+ rb_erase(&exist->node, &string_tree);
+ RB_CLEAR_NODE(&exist->node);
+ ret = -EAGAIN;
+ }
+ spin_unlock(&string_tree_lock);
+ if (ret == -EAGAIN)
+ goto retry;
+
+ if (exist) {
+ kfree(cs);
+ cs = exist;
+ }
+
+ return cs;
+}
+EXPORT_SYMBOL(ceph_find_or_create_string);
+
+void ceph_release_string(struct kref *ref)
+{
+ struct ceph_string *cs = container_of(ref, struct ceph_string, kref);
+
+ spin_lock(&string_tree_lock);
+ if (!RB_EMPTY_NODE(&cs->node)) {
+ rb_erase(&cs->node, &string_tree);
+ RB_CLEAR_NODE(&cs->node);
+ }
+ spin_unlock(&string_tree_lock);
+
+ kfree_rcu(cs, rcu);
+}
+EXPORT_SYMBOL(ceph_release_string);
+
+bool ceph_strings_empty(void)
+{
+ return RB_EMPTY_ROOT(&string_tree);
+}
diff --git a/net/core/dev.c b/net/core/dev.c
index 904ff431d570..ea6312057a71 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -94,6 +94,7 @@
#include <linux/ethtool.h>
#include <linux/notifier.h>
#include <linux/skbuff.h>
+#include <linux/bpf.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/busy_poll.h>
@@ -139,6 +140,7 @@
#include <linux/hrtimer.h>
#include <linux/netfilter_ingress.h>
#include <linux/sctp.h>
+#include <linux/crash_dump.h>
#include "net-sysfs.h"
@@ -196,7 +198,7 @@ static inline void dev_base_seq_inc(struct net *net)
static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
- unsigned int hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
+ unsigned int hash = full_name_hash(net, name, strnlen(name, IFNAMSIZ));
return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)];
}
@@ -2249,11 +2251,12 @@ EXPORT_SYMBOL(netif_set_real_num_rx_queues);
*/
int netif_get_num_default_rss_queues(void)
{
- return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
+ return is_kdump_kernel() ?
+ 1 : min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
}
EXPORT_SYMBOL(netif_get_num_default_rss_queues);
-static inline void __netif_reschedule(struct Qdisc *q)
+static void __netif_reschedule(struct Qdisc *q)
{
struct softnet_data *sd;
unsigned long flags;
@@ -2420,7 +2423,7 @@ EXPORT_SYMBOL(__skb_tx_hash);
static void skb_warn_bad_offload(const struct sk_buff *skb)
{
- static const netdev_features_t null_features = 0;
+ static const netdev_features_t null_features;
struct net_device *dev = skb->dev;
const char *name = "";
@@ -3068,6 +3071,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
struct netdev_queue *txq)
{
spinlock_t *root_lock = qdisc_lock(q);
+ struct sk_buff *to_free = NULL;
bool contended;
int rc;
@@ -3075,7 +3079,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
/*
* Heuristic to force contended enqueues to serialize on a
* separate lock before trying to get qdisc main lock.
- * This permits __QDISC___STATE_RUNNING owner to get the lock more
+ * This permits qdisc->running owner to get the lock more
* often and dequeue packets faster.
*/
contended = qdisc_is_running(q);
@@ -3084,7 +3088,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
spin_lock(root_lock);
if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
- kfree_skb(skb);
+ __qdisc_drop(skb, &to_free);
rc = NET_XMIT_DROP;
} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
qdisc_run_begin(q)) {
@@ -3107,7 +3111,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
rc = NET_XMIT_SUCCESS;
} else {
- rc = q->enqueue(skb, q) & NET_XMIT_MASK;
+ rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
if (qdisc_run_begin(q)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
@@ -3117,6 +3121,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
}
}
spin_unlock(root_lock);
+ if (unlikely(to_free))
+ kfree_skb_list(to_free);
if (unlikely(contended))
spin_unlock(&q->busylock);
return rc;
@@ -3142,8 +3148,6 @@ static void skb_update_prio(struct sk_buff *skb)
DEFINE_PER_CPU(int, xmit_recursion);
EXPORT_SYMBOL(xmit_recursion);
-#define RECURSION_LIMIT 10
-
/**
* dev_loopback_xmit - loop back @skb
* @net: network namespace this loopback is happening in
@@ -3386,8 +3390,8 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
int cpu = smp_processor_id(); /* ok because BHs are off */
if (txq->xmit_lock_owner != cpu) {
-
- if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
+ if (unlikely(__this_cpu_read(xmit_recursion) >
+ XMIT_RECURSION_LIMIT))
goto recursion_alert;
skb = validate_xmit_skb(skb, dev);
@@ -3898,22 +3902,14 @@ static void net_tx_action(struct softirq_action *h)
head = head->next_sched;
root_lock = qdisc_lock(q);
- if (spin_trylock(root_lock)) {
- smp_mb__before_atomic();
- clear_bit(__QDISC_STATE_SCHED,
- &q->state);
- qdisc_run(q);
- spin_unlock(root_lock);
- } else {
- if (!test_bit(__QDISC_STATE_DEACTIVATED,
- &q->state)) {
- __netif_reschedule(q);
- } else {
- smp_mb__before_atomic();
- clear_bit(__QDISC_STATE_SCHED,
- &q->state);
- }
- }
+ spin_lock(root_lock);
+ /* We need to make sure head->next_sched is read
+ * before clearing __QDISC_STATE_SCHED
+ */
+ smp_mb__before_atomic();
+ clear_bit(__QDISC_STATE_SCHED, &q->state);
+ qdisc_run(q);
+ spin_unlock(root_lock);
}
}
}
@@ -3979,6 +3975,22 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
}
/**
+ * netdev_is_rx_handler_busy - check if receive handler is registered
+ * @dev: device to check
+ *
+ * Check if a receive handler is already registered for a given device.
+ * Return true if there one.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+bool netdev_is_rx_handler_busy(struct net_device *dev)
+{
+ ASSERT_RTNL();
+ return dev && rtnl_dereference(dev->rx_handler);
+}
+EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy);
+
+/**
* netdev_rx_handler_register - register receive handler
* @dev: device to register a handler for
* @rx_handler: receive handler to register
@@ -4977,7 +4989,7 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
rc = napi->poll(napi, BUSY_POLL_BUDGET);
- trace_napi_poll(napi);
+ trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
if (rc == BUSY_POLL_BUDGET) {
napi_complete_done(napi, rc);
napi_schedule(napi);
@@ -5133,7 +5145,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
work = 0;
if (test_bit(NAPI_STATE_SCHED, &n->state)) {
work = n->poll(n, weight);
- trace_napi_poll(n);
+ trace_napi_poll(n, work, weight);
}
WARN_ON_ONCE(work > weight);
@@ -5450,6 +5462,52 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
EXPORT_SYMBOL(netdev_lower_get_next);
/**
+ * netdev_all_lower_get_next - Get the next device from all lower neighbour list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's all lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour all lower
+ * list will remain unchanged.
+ */
+struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_entry(*iter, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->all_adj_list.lower)
+ return NULL;
+
+ *iter = lower->list.next;
+
+ return lower->dev;
+}
+EXPORT_SYMBOL(netdev_all_lower_get_next);
+
+/**
+ * netdev_all_lower_get_next_rcu - Get the next device from all
+ * lower neighbour list, RCU variant
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's all lower neighbour
+ * list, starting from iter position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_first_or_null_rcu(&dev->all_adj_list.lower,
+ struct netdev_adjacent, list);
+
+ return lower ? lower->dev : NULL;
+}
+EXPORT_SYMBOL(netdev_all_lower_get_next_rcu);
+
+/**
* netdev_lower_get_first_private_rcu - Get the first ->private from the
* lower neighbour list, RCU
* variant
@@ -5919,7 +5977,7 @@ static void netdev_adjacent_add_links(struct net_device *dev)
struct net *net = dev_net(dev);
list_for_each_entry(iter, &dev->adj_list.upper, list) {
- if (!net_eq(net,dev_net(iter->dev)))
+ if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_add(iter->dev, dev,
&iter->dev->adj_list.lower);
@@ -5928,7 +5986,7 @@ static void netdev_adjacent_add_links(struct net_device *dev)
}
list_for_each_entry(iter, &dev->adj_list.lower, list) {
- if (!net_eq(net,dev_net(iter->dev)))
+ if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_add(iter->dev, dev,
&iter->dev->adj_list.upper);
@@ -5944,7 +6002,7 @@ static void netdev_adjacent_del_links(struct net_device *dev)
struct net *net = dev_net(dev);
list_for_each_entry(iter, &dev->adj_list.upper, list) {
- if (!net_eq(net,dev_net(iter->dev)))
+ if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_del(iter->dev, dev->name,
&iter->dev->adj_list.lower);
@@ -5953,7 +6011,7 @@ static void netdev_adjacent_del_links(struct net_device *dev)
}
list_for_each_entry(iter, &dev->adj_list.lower, list) {
- if (!net_eq(net,dev_net(iter->dev)))
+ if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_del(iter->dev, dev->name,
&iter->dev->adj_list.upper);
@@ -5969,7 +6027,7 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
struct net *net = dev_net(dev);
list_for_each_entry(iter, &dev->adj_list.upper, list) {
- if (!net_eq(net,dev_net(iter->dev)))
+ if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_del(iter->dev, oldname,
&iter->dev->adj_list.lower);
@@ -5978,7 +6036,7 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
}
list_for_each_entry(iter, &dev->adj_list.lower, list) {
- if (!net_eq(net,dev_net(iter->dev)))
+ if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_del(iter->dev, oldname,
&iter->dev->adj_list.upper);
@@ -6003,8 +6061,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
EXPORT_SYMBOL(netdev_lower_dev_get_private);
-int dev_get_nest_level(struct net_device *dev,
- bool (*type_check)(const struct net_device *dev))
+int dev_get_nest_level(struct net_device *dev)
{
struct net_device *lower = NULL;
struct list_head *iter;
@@ -6014,15 +6071,12 @@ int dev_get_nest_level(struct net_device *dev,
ASSERT_RTNL();
netdev_for_each_lower_dev(dev, lower, iter) {
- nest = dev_get_nest_level(lower, type_check);
+ nest = dev_get_nest_level(lower);
if (max_nest < nest)
max_nest = nest;
}
- if (type_check(dev))
- max_nest++;
-
- return max_nest;
+ return max_nest + 1;
}
EXPORT_SYMBOL(dev_get_nest_level);
@@ -6046,6 +6100,50 @@ void netdev_lower_state_changed(struct net_device *lower_dev,
}
EXPORT_SYMBOL(netdev_lower_state_changed);
+int netdev_default_l2upper_neigh_construct(struct net_device *dev,
+ struct neighbour *n)
+{
+ struct net_device *lower_dev, *stop_dev;
+ struct list_head *iter;
+ int err;
+
+ netdev_for_each_lower_dev(dev, lower_dev, iter) {
+ if (!lower_dev->netdev_ops->ndo_neigh_construct)
+ continue;
+ err = lower_dev->netdev_ops->ndo_neigh_construct(lower_dev, n);
+ if (err) {
+ stop_dev = lower_dev;
+ goto rollback;
+ }
+ }
+ return 0;
+
+rollback:
+ netdev_for_each_lower_dev(dev, lower_dev, iter) {
+ if (lower_dev == stop_dev)
+ break;
+ if (!lower_dev->netdev_ops->ndo_neigh_destroy)
+ continue;
+ lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n);
+ }
+ return err;
+}
+EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_construct);
+
+void netdev_default_l2upper_neigh_destroy(struct net_device *dev,
+ struct neighbour *n)
+{
+ struct net_device *lower_dev;
+ struct list_head *iter;
+
+ netdev_for_each_lower_dev(dev, lower_dev, iter) {
+ if (!lower_dev->netdev_ops->ndo_neigh_destroy)
+ continue;
+ lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n);
+ }
+}
+EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_destroy);
+
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
const struct net_device_ops *ops = dev->netdev_ops;
@@ -6530,6 +6628,38 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
EXPORT_SYMBOL(dev_change_proto_down);
/**
+ * dev_change_xdp_fd - set or clear a bpf program for a device rx path
+ * @dev: device
+ * @fd: new program fd or negative value to clear
+ *
+ * Set or clear a bpf program for a device
+ */
+int dev_change_xdp_fd(struct net_device *dev, int fd)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ struct bpf_prog *prog = NULL;
+ struct netdev_xdp xdp = {};
+ int err;
+
+ if (!ops->ndo_xdp)
+ return -EOPNOTSUPP;
+ if (fd >= 0) {
+ prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+ }
+
+ xdp.command = XDP_SETUP_PROG;
+ xdp.prog = prog;
+ err = ops->ndo_xdp(dev, &xdp);
+ if (err < 0 && prog)
+ bpf_prog_put(prog);
+
+ return err;
+}
+EXPORT_SYMBOL(dev_change_xdp_fd);
+
+/**
* dev_new_index - allocate an ifindex
* @net: the applicable net namespace
*
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 933e8d4d3968..1b5063088f1a 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -26,6 +26,10 @@
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/devlink.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/devlink.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
static LIST_HEAD(devlink_list);
@@ -1394,6 +1398,78 @@ static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb,
return -EOPNOTSUPP;
}
+static int devlink_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
+ enum devlink_command cmd, u32 portid,
+ u32 seq, int flags, u16 mode)
+{
+ void *hdr;
+
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (devlink_nl_put_handle(msg, devlink))
+ goto nla_put_failure;
+
+ if (nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode))
+ goto nla_put_failure;
+
+ genlmsg_end(msg, hdr);
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ const struct devlink_ops *ops = devlink->ops;
+ struct sk_buff *msg;
+ u16 mode;
+ int err;
+
+ if (!ops || !ops->eswitch_mode_get)
+ return -EOPNOTSUPP;
+
+ err = ops->eswitch_mode_get(devlink, &mode);
+ if (err)
+ return err;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_MODE_GET,
+ info->snd_portid, info->snd_seq, 0, mode);
+
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_eswitch_mode_set_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ const struct devlink_ops *ops = devlink->ops;
+ u16 mode;
+
+ if (!info->attrs[DEVLINK_ATTR_ESWITCH_MODE])
+ return -EINVAL;
+
+ mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
+
+ if (ops && ops->eswitch_mode_set)
+ return ops->eswitch_mode_set(devlink, mode);
+ return -EOPNOTSUPP;
+}
+
static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -1407,6 +1483,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 },
[DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 },
[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
+ [DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
};
static const struct genl_ops devlink_nl_ops[] = {
@@ -1525,6 +1602,20 @@ static const struct genl_ops devlink_nl_ops[] = {
DEVLINK_NL_FLAG_NEED_SB |
DEVLINK_NL_FLAG_LOCK_PORTS,
},
+ {
+ .cmd = DEVLINK_CMD_ESWITCH_MODE_GET,
+ .doit = devlink_nl_cmd_eswitch_mode_get_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_ESWITCH_MODE_SET,
+ .doit = devlink_nl_cmd_eswitch_mode_set_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
};
/**
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 252e155c837b..d6b3b579560d 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -187,7 +187,8 @@ static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *locatio
trace_drop_common(skb, location);
}
-static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi)
+static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi,
+ int work, int budget)
{
struct dm_hw_stat_delta *new_stat;
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index f4034817d255..977489820eb9 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -89,6 +89,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation",
[NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation",
[NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial",
+ [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation",
[NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
[NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp",
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 840acebbb80c..be4629c344a6 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -173,7 +173,8 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
EXPORT_SYMBOL_GPL(fib_rules_unregister);
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
- struct flowi *fl, int flags)
+ struct flowi *fl, int flags,
+ struct fib_lookup_arg *arg)
{
int ret = 0;
@@ -189,6 +190,9 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id))
goto out;
+ if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg))
+ goto out;
+
ret = ops->match(rule, fl, flags);
out:
return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -204,7 +208,7 @@ int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl,
list_for_each_entry_rcu(rule, &ops->rules_list, list) {
jumped:
- if (!fib_rule_match(rule, ops, fl, flags))
+ if (!fib_rule_match(rule, ops, fl, flags, arg))
continue;
if (rule->action == FR_ACT_GOTO) {
@@ -265,7 +269,50 @@ errout:
return err;
}
-static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
+static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
+ struct nlattr **tb, struct fib_rule *rule)
+{
+ struct fib_rule *r;
+
+ list_for_each_entry(r, &ops->rules_list, list) {
+ if (r->action != rule->action)
+ continue;
+
+ if (r->table != rule->table)
+ continue;
+
+ if (r->pref != rule->pref)
+ continue;
+
+ if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
+ continue;
+
+ if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
+ continue;
+
+ if (r->mark != rule->mark)
+ continue;
+
+ if (r->mark_mask != rule->mark_mask)
+ continue;
+
+ if (r->tun_id != rule->tun_id)
+ continue;
+
+ if (r->fr_net != rule->fr_net)
+ continue;
+
+ if (r->l3mdev != rule->l3mdev)
+ continue;
+
+ if (!ops->compare(r, frh, tb))
+ continue;
+ return 1;
+ }
+ return 0;
+}
+
+int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -336,6 +383,14 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
if (tb[FRA_TUN_ID])
rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
+ if (tb[FRA_L3MDEV]) {
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ rule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]);
+ if (rule->l3mdev != 1)
+#endif
+ goto errout_free;
+ }
+
rule->action = frh->action;
rule->flags = frh->flags;
rule->table = frh_get_table(frh, tb);
@@ -371,6 +426,15 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
} else if (rule->action == FR_ACT_GOTO)
goto errout_free;
+ if (rule->l3mdev && rule->table)
+ goto errout_free;
+
+ if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
+ rule_exists(ops, frh, tb, rule)) {
+ err = -EEXIST;
+ goto errout_free;
+ }
+
err = ops->configure(rule, skb, frh, tb);
if (err < 0)
goto errout_free;
@@ -424,8 +488,9 @@ errout:
rules_ops_put(ops);
return err;
}
+EXPORT_SYMBOL_GPL(fib_nl_newrule);
-static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
+int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -483,6 +548,10 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
(rule->tun_id != nla_get_be64(tb[FRA_TUN_ID])))
continue;
+ if (tb[FRA_L3MDEV] &&
+ (rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV])))
+ continue;
+
if (!ops->compare(rule, frh, tb))
continue;
@@ -536,6 +605,7 @@ errout:
rules_ops_put(ops);
return err;
}
+EXPORT_SYMBOL_GPL(fib_nl_delrule);
static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
struct fib_rule *rule)
@@ -607,7 +677,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
(rule->target &&
nla_put_u32(skb, FRA_GOTO, rule->target)) ||
(rule->tun_id &&
- nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)))
+ nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) ||
+ (rule->l3mdev &&
+ nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)))
goto nla_put_failure;
if (rule->suppress_ifgroup != -1) {
diff --git a/net/core/filter.c b/net/core/filter.c
index e759d90e8cef..cb06aceb512a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -150,6 +150,12 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
return raw_smp_processor_id();
}
+static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
+ .func = __get_raw_cpu_id,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+};
+
static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
struct bpf_insn *insn_buf)
{
@@ -748,6 +754,17 @@ static bool chk_code_allowed(u16 code_to_probe)
return codes[code_to_probe];
}
+static bool bpf_check_basics_ok(const struct sock_filter *filter,
+ unsigned int flen)
+{
+ if (filter == NULL)
+ return false;
+ if (flen == 0 || flen > BPF_MAXINSNS)
+ return false;
+
+ return true;
+}
+
/**
* bpf_check_classic - verify socket filter code
* @filter: filter to verify
@@ -768,9 +785,6 @@ static int bpf_check_classic(const struct sock_filter *filter,
bool anc_found;
int pc;
- if (flen == 0 || flen > BPF_MAXINSNS)
- return -EINVAL;
-
/* Check the filter code now */
for (pc = 0; pc < flen; pc++) {
const struct sock_filter *ftest = &filter[pc];
@@ -1065,7 +1079,7 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
struct bpf_prog *fp;
/* Make sure new filter is there and in the right amounts. */
- if (fprog->filter == NULL)
+ if (!bpf_check_basics_ok(fprog->filter, fprog->len))
return -EINVAL;
fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
@@ -1112,7 +1126,7 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
int err;
/* Make sure new filter is there and in the right amounts. */
- if (fprog->filter == NULL)
+ if (!bpf_check_basics_ok(fprog->filter, fprog->len))
return -EINVAL;
fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
@@ -1207,7 +1221,6 @@ static
struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk)
{
unsigned int fsize = bpf_classic_proglen(fprog);
- unsigned int bpf_fsize = bpf_prog_size(fprog->len);
struct bpf_prog *prog;
int err;
@@ -1215,10 +1228,10 @@ struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk)
return ERR_PTR(-EPERM);
/* Make sure new filter is there and in the right amounts. */
- if (fprog->filter == NULL)
+ if (!bpf_check_basics_ok(fprog->filter, fprog->len))
return ERR_PTR(-EINVAL);
- prog = bpf_prog_alloc(bpf_fsize, 0);
+ prog = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
if (!prog)
return ERR_PTR(-ENOMEM);
@@ -1288,21 +1301,10 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk)
{
- struct bpf_prog *prog;
-
if (sock_flag(sk, SOCK_FILTER_LOCKED))
return ERR_PTR(-EPERM);
- prog = bpf_prog_get(ufd);
- if (IS_ERR(prog))
- return prog;
-
- if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) {
- bpf_prog_put(prog);
- return ERR_PTR(-EINVAL);
- }
-
- return prog;
+ return bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER);
}
int sk_attach_bpf(u32 ufd, struct sock *sk)
@@ -1353,56 +1355,47 @@ static inline int bpf_try_make_writable(struct sk_buff *skb,
{
int err;
- if (!skb_cloned(skb))
- return 0;
- if (skb_clone_writable(skb, write_len))
- return 0;
- err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (!err)
- bpf_compute_data_end(skb);
+ err = skb_ensure_writable(skb, write_len);
+ bpf_compute_data_end(skb);
+
return err;
}
+static inline void bpf_push_mac_rcsum(struct sk_buff *skb)
+{
+ if (skb_at_tc_ingress(skb))
+ skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len);
+}
+
+static inline void bpf_pull_mac_rcsum(struct sk_buff *skb)
+{
+ if (skb_at_tc_ingress(skb))
+ skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len);
+}
+
static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
{
- struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp);
struct sk_buff *skb = (struct sk_buff *) (long) r1;
- int offset = (int) r2;
+ unsigned int offset = (unsigned int) r2;
void *from = (void *) (long) r3;
unsigned int len = (unsigned int) r4;
void *ptr;
if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH)))
return -EINVAL;
-
- /* bpf verifier guarantees that:
- * 'from' pointer points to bpf program stack
- * 'len' bytes of it were initialized
- * 'len' > 0
- * 'skb' is a valid pointer to 'struct sk_buff'
- *
- * so check for invalid 'offset' and too large 'len'
- */
- if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff)))
+ if (unlikely(offset > 0xffff))
return -EFAULT;
if (unlikely(bpf_try_make_writable(skb, offset + len)))
return -EFAULT;
- ptr = skb_header_pointer(skb, offset, len, sp->buff);
- if (unlikely(!ptr))
- return -EFAULT;
-
+ ptr = skb->data + offset;
if (flags & BPF_F_RECOMPUTE_CSUM)
- skb_postpull_rcsum(skb, ptr, len);
+ __skb_postpull_rcsum(skb, ptr, len, offset);
memcpy(ptr, from, len);
- if (ptr == sp->buff)
- /* skb_store_bits cannot return -EFAULT here */
- skb_store_bits(skb, offset, ptr, len);
-
if (flags & BPF_F_RECOMPUTE_CSUM)
- skb_postpush_rcsum(skb, ptr, len);
+ __skb_postpush_rcsum(skb, ptr, len, offset);
if (flags & BPF_F_INVALIDATE_HASH)
skb_clear_hash(skb);
@@ -1423,12 +1416,12 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = {
static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1;
- int offset = (int) r2;
+ unsigned int offset = (unsigned int) r2;
void *to = (void *)(unsigned long) r3;
unsigned int len = (unsigned int) r4;
void *ptr;
- if (unlikely((u32) offset > 0xffff))
+ if (unlikely(offset > 0xffff))
goto err_clear;
ptr = skb_header_pointer(skb, offset, len, to);
@@ -1456,20 +1449,17 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
{
struct sk_buff *skb = (struct sk_buff *) (long) r1;
- int offset = (int) r2;
- __sum16 sum, *ptr;
+ unsigned int offset = (unsigned int) r2;
+ __sum16 *ptr;
if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK)))
return -EINVAL;
- if (unlikely((u32) offset > 0xffff))
+ if (unlikely(offset > 0xffff || offset & 1))
return -EFAULT;
- if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum))))
- return -EFAULT;
-
- ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
- if (unlikely(!ptr))
+ if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
return -EFAULT;
+ ptr = (__sum16 *)(skb->data + offset);
switch (flags & BPF_F_HDR_FIELD_MASK) {
case 0:
if (unlikely(from != 0))
@@ -1487,10 +1477,6 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
return -EINVAL;
}
- if (ptr == &sum)
- /* skb_store_bits guaranteed to not return -EFAULT here */
- skb_store_bits(skb, offset, ptr, sizeof(sum));
-
return 0;
}
@@ -1510,20 +1496,18 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
struct sk_buff *skb = (struct sk_buff *) (long) r1;
bool is_pseudo = flags & BPF_F_PSEUDO_HDR;
bool is_mmzero = flags & BPF_F_MARK_MANGLED_0;
- int offset = (int) r2;
- __sum16 sum, *ptr;
+ unsigned int offset = (unsigned int) r2;
+ __sum16 *ptr;
if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR |
BPF_F_HDR_FIELD_MASK)))
return -EINVAL;
- if (unlikely((u32) offset > 0xffff))
+ if (unlikely(offset > 0xffff || offset & 1))
return -EFAULT;
- if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum))))
+ if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
return -EFAULT;
- ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
- if (unlikely(!ptr))
- return -EFAULT;
+ ptr = (__sum16 *)(skb->data + offset);
if (is_mmzero && !*ptr)
return 0;
@@ -1546,10 +1530,6 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
if (is_mmzero && !*ptr)
*ptr = CSUM_MANGLED_0;
- if (ptr == &sum)
- /* skb_store_bits guaranteed to not return -EFAULT here */
- skb_store_bits(skb, offset, ptr, sizeof(sum));
-
return 0;
}
@@ -1603,9 +1583,33 @@ static const struct bpf_func_proto bpf_csum_diff_proto = {
.arg5_type = ARG_ANYTHING,
};
+static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
+{
+ return dev_forward_skb(dev, skb);
+}
+
+static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
+{
+ int ret;
+
+ if (unlikely(__this_cpu_read(xmit_recursion) > XMIT_RECURSION_LIMIT)) {
+ net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+ kfree_skb(skb);
+ return -ENETDOWN;
+ }
+
+ skb->dev = dev;
+
+ __this_cpu_inc(xmit_recursion);
+ ret = dev_queue_xmit(skb);
+ __this_cpu_dec(xmit_recursion);
+
+ return ret;
+}
+
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 sk_buff *skb = (struct sk_buff *) (long) r1;
struct net_device *dev;
if (unlikely(flags & ~(BPF_F_INGRESS)))
@@ -1615,19 +1619,14 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
if (unlikely(!dev))
return -EINVAL;
- skb2 = skb_clone(skb, GFP_ATOMIC);
- if (unlikely(!skb2))
+ skb = skb_clone(skb, GFP_ATOMIC);
+ if (unlikely(!skb))
return -ENOMEM;
- if (flags & BPF_F_INGRESS) {
- if (skb_at_tc_ingress(skb2))
- skb_postpush_rcsum(skb2, skb_mac_header(skb2),
- skb2->mac_len);
- return dev_forward_skb(dev, skb2);
- }
+ bpf_push_mac_rcsum(skb);
- skb2->dev = dev;
- return dev_queue_xmit(skb2);
+ return flags & BPF_F_INGRESS ?
+ __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
}
static const struct bpf_func_proto bpf_clone_redirect_proto = {
@@ -1671,15 +1670,10 @@ int skb_do_redirect(struct sk_buff *skb)
return -EINVAL;
}
- if (ri->flags & BPF_F_INGRESS) {
- if (skb_at_tc_ingress(skb))
- skb_postpush_rcsum(skb, skb_mac_header(skb),
- skb->mac_len);
- return dev_forward_skb(dev, skb);
- }
+ bpf_push_mac_rcsum(skb);
- skb->dev = dev;
- return dev_queue_xmit(skb);
+ return ri->flags & BPF_F_INGRESS ?
+ __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
}
static const struct bpf_func_proto bpf_redirect_proto = {
@@ -1714,6 +1708,23 @@ static const struct bpf_func_proto bpf_get_route_realm_proto = {
.arg1_type = ARG_PTR_TO_CTX,
};
+static u64 bpf_get_hash_recalc(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ /* If skb_clear_hash() was called due to mangling, we can
+ * trigger SW recalculation here. Later access to hash
+ * can then use the inline skb->hash via context directly
+ * instead of calling this helper again.
+ */
+ return skb_get_hash((struct sk_buff *) (unsigned long) r1);
+}
+
+static const struct bpf_func_proto bpf_get_hash_recalc_proto = {
+ .func = bpf_get_hash_recalc,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5)
{
struct sk_buff *skb = (struct sk_buff *) (long) r1;
@@ -1724,7 +1735,10 @@ static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5)
vlan_proto != htons(ETH_P_8021AD)))
vlan_proto = htons(ETH_P_8021Q);
+ bpf_push_mac_rcsum(skb);
ret = skb_vlan_push(skb, vlan_proto, vlan_tci);
+ bpf_pull_mac_rcsum(skb);
+
bpf_compute_data_end(skb);
return ret;
}
@@ -1744,7 +1758,10 @@ static u64 bpf_skb_vlan_pop(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
struct sk_buff *skb = (struct sk_buff *) (long) r1;
int ret;
+ bpf_push_mac_rcsum(skb);
ret = skb_vlan_pop(skb);
+ bpf_pull_mac_rcsum(skb);
+
bpf_compute_data_end(skb);
return ret;
}
@@ -1757,6 +1774,224 @@ const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
};
EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto);
+static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
+{
+ /* Caller already did skb_cow() with len as headroom,
+ * so no need to do it here.
+ */
+ skb_push(skb, len);
+ memmove(skb->data, skb->data + len, off);
+ memset(skb->data + off, 0, len);
+
+ /* No skb_postpush_rcsum(skb, skb->data + off, len)
+ * needed here as it does not change the skb->csum
+ * result for checksum complete when summing over
+ * zeroed blocks.
+ */
+ return 0;
+}
+
+static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len)
+{
+ /* skb_ensure_writable() is not needed here, as we're
+ * already working on an uncloned skb.
+ */
+ if (unlikely(!pskb_may_pull(skb, off + len)))
+ return -ENOMEM;
+
+ skb_postpull_rcsum(skb, skb->data + off, len);
+ memmove(skb->data + len, skb->data, off);
+ __skb_pull(skb, len);
+
+ return 0;
+}
+
+static int bpf_skb_net_hdr_push(struct sk_buff *skb, u32 off, u32 len)
+{
+ bool trans_same = skb->transport_header == skb->network_header;
+ int ret;
+
+ /* There's no need for __skb_push()/__skb_pull() pair to
+ * get to the start of the mac header as we're guaranteed
+ * to always start from here under eBPF.
+ */
+ ret = bpf_skb_generic_push(skb, off, len);
+ if (likely(!ret)) {
+ skb->mac_header -= len;
+ skb->network_header -= len;
+ if (trans_same)
+ skb->transport_header = skb->network_header;
+ }
+
+ return ret;
+}
+
+static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len)
+{
+ bool trans_same = skb->transport_header == skb->network_header;
+ int ret;
+
+ /* Same here, __skb_push()/__skb_pull() pair not needed. */
+ ret = bpf_skb_generic_pop(skb, off, len);
+ if (likely(!ret)) {
+ skb->mac_header += len;
+ skb->network_header += len;
+ if (trans_same)
+ skb->transport_header = skb->network_header;
+ }
+
+ return ret;
+}
+
+static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
+{
+ const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr);
+ u32 off = skb->network_header - skb->mac_header;
+ int ret;
+
+ ret = skb_cow(skb, len_diff);
+ if (unlikely(ret < 0))
+ return ret;
+
+ ret = bpf_skb_net_hdr_push(skb, off, len_diff);
+ if (unlikely(ret < 0))
+ return ret;
+
+ if (skb_is_gso(skb)) {
+ /* SKB_GSO_UDP stays as is. SKB_GSO_TCPV4 needs to
+ * be changed into SKB_GSO_TCPV6.
+ */
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
+ skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV4;
+ skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6;
+ }
+
+ /* Due to IPv6 header, MSS needs to be downgraded. */
+ skb_shinfo(skb)->gso_size -= len_diff;
+ /* Header must be checked, and gso_segs recomputed. */
+ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+ skb_shinfo(skb)->gso_segs = 0;
+ }
+
+ skb->protocol = htons(ETH_P_IPV6);
+ skb_clear_hash(skb);
+
+ return 0;
+}
+
+static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
+{
+ const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr);
+ u32 off = skb->network_header - skb->mac_header;
+ int ret;
+
+ ret = skb_unclone(skb, GFP_ATOMIC);
+ if (unlikely(ret < 0))
+ return ret;
+
+ ret = bpf_skb_net_hdr_pop(skb, off, len_diff);
+ if (unlikely(ret < 0))
+ return ret;
+
+ if (skb_is_gso(skb)) {
+ /* SKB_GSO_UDP stays as is. SKB_GSO_TCPV6 needs to
+ * be changed into SKB_GSO_TCPV4.
+ */
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) {
+ skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV6;
+ skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
+ }
+
+ /* Due to IPv4 header, MSS can be upgraded. */
+ skb_shinfo(skb)->gso_size += len_diff;
+ /* Header must be checked, and gso_segs recomputed. */
+ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+ skb_shinfo(skb)->gso_segs = 0;
+ }
+
+ skb->protocol = htons(ETH_P_IP);
+ skb_clear_hash(skb);
+
+ return 0;
+}
+
+static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto)
+{
+ __be16 from_proto = skb->protocol;
+
+ if (from_proto == htons(ETH_P_IP) &&
+ to_proto == htons(ETH_P_IPV6))
+ return bpf_skb_proto_4_to_6(skb);
+
+ if (from_proto == htons(ETH_P_IPV6) &&
+ to_proto == htons(ETH_P_IP))
+ return bpf_skb_proto_6_to_4(skb);
+
+ return -ENOTSUPP;
+}
+
+static u64 bpf_skb_change_proto(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *) (long) r1;
+ __be16 proto = (__force __be16) r2;
+ int ret;
+
+ if (unlikely(flags))
+ return -EINVAL;
+
+ /* General idea is that this helper does the basic groundwork
+ * needed for changing the protocol, and eBPF program fills the
+ * rest through bpf_skb_store_bytes(), bpf_lX_csum_replace()
+ * and other helpers, rather than passing a raw buffer here.
+ *
+ * The rationale is to keep this minimal and without a need to
+ * deal with raw packet data. F.e. even if we would pass buffers
+ * here, the program still needs to call the bpf_lX_csum_replace()
+ * helpers anyway. Plus, this way we keep also separation of
+ * concerns, since f.e. bpf_skb_store_bytes() should only take
+ * care of stores.
+ *
+ * Currently, additional options and extension header space are
+ * not supported, but flags register is reserved so we can adapt
+ * that. For offloads, we mark packet as dodgy, so that headers
+ * need to be verified first.
+ */
+ ret = bpf_skb_proto_xlat(skb, proto);
+ bpf_compute_data_end(skb);
+ return ret;
+}
+
+static const struct bpf_func_proto bpf_skb_change_proto_proto = {
+ .func = bpf_skb_change_proto,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static u64 bpf_skb_change_type(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *) (long) r1;
+ u32 pkt_type = r2;
+
+ /* We only allow a restricted subset to be changed for now. */
+ if (unlikely(skb->pkt_type > PACKET_OTHERHOST ||
+ pkt_type > PACKET_OTHERHOST))
+ return -EINVAL;
+
+ skb->pkt_type = pkt_type;
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_skb_change_type_proto = {
+ .func =