aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c1
-rw-r--r--net/8021q/vlan_dev.c33
-rw-r--r--net/Kconfig26
-rw-r--r--net/atm/clip.c6
-rw-r--r--net/atm/common.c2
-rw-r--r--net/atm/signaling.c2
-rw-r--r--net/atm/svc.c2
-rw-r--r--net/ax25/af_ax25.c2
-rw-r--r--net/ax25/ax25_in.c2
-rw-r--r--net/batman-adv/bat_iv_ogm.c61
-rw-r--r--net/batman-adv/bat_v.c1
-rw-r--r--net/batman-adv/bat_v_ogm.c75
-rw-r--r--net/batman-adv/hard-interface.c2
-rw-r--r--net/batman-adv/main.h2
-rw-r--r--net/batman-adv/multicast.c2
-rw-r--r--net/batman-adv/soft-interface.c37
-rw-r--r--net/batman-adv/types.h10
-rw-r--r--net/bluetooth/6lowpan.c8
-rw-r--r--net/bluetooth/Kconfig2
-rw-r--r--net/bluetooth/af_bluetooth.c8
-rw-r--r--net/bluetooth/hci_conn.c12
-rw-r--r--net/bluetooth/hci_core.c39
-rw-r--r--net/bluetooth/hci_request.c19
-rw-r--r--net/bluetooth/l2cap_core.c4
-rw-r--r--net/bluetooth/smp.c6
-rw-r--r--net/bpf/test_run.c52
-rw-r--r--net/bridge/br_device.c44
-rw-r--r--net/bridge/br_fdb.c157
-rw-r--r--net/bridge/br_input.c7
-rw-r--r--net/bridge/br_private.h24
-rw-r--r--net/bridge/br_switchdev.c12
-rw-r--r--net/bridge/netfilter/ebt_dnat.c19
-rw-r--r--net/bridge/netfilter/nf_conntrack_bridge.c2
-rw-r--r--net/caif/Kconfig10
-rw-r--r--net/caif/caif_socket.c2
-rw-r--r--net/can/af_can.c3
-rw-r--r--net/can/j1939/main.c9
-rw-r--r--net/can/j1939/socket.c103
-rw-r--r--net/can/j1939/transport.c56
-rw-r--r--net/core/bpf_sk_storage.c2
-rw-r--r--net/core/datagram.c8
-rw-r--r--net/core/dev.c1036
-rw-r--r--net/core/dev_addr_lists.c12
-rw-r--r--net/core/devlink.c356
-rw-r--r--net/core/ethtool.c4
-rw-r--r--net/core/fib_notifier.c95
-rw-r--r--net/core/fib_rules.c23
-rw-r--r--net/core/filter.c33
-rw-r--r--net/core/flow_dissector.c191
-rw-r--r--net/core/gen_estimator.c4
-rw-r--r--net/core/gen_stats.c12
-rw-r--r--net/core/lwt_bpf.c7
-rw-r--r--net/core/neighbour.c8
-rw-r--r--net/core/net-procfs.c4
-rw-r--r--net/core/net-sysfs.c25
-rw-r--r--net/core/net_namespace.c18
-rw-r--r--net/core/netprio_cgroup.c8
-rw-r--r--net/core/page_pool.c189
-rw-r--r--net/core/pktgen.c1
-rw-r--r--net/core/rtnetlink.c246
-rw-r--r--net/core/skmsg.c33
-rw-r--r--net/core/sock.c22
-rw-r--r--net/core/xdp.c128
-rw-r--r--net/dccp/ipv4.c4
-rw-r--r--net/dccp/proto.c2
-rw-r--r--net/decnet/af_decnet.c4
-rw-r--r--net/decnet/dn_nsp_in.c2
-rw-r--r--net/dsa/Kconfig9
-rw-r--r--net/dsa/Makefile1
-rw-r--r--net/dsa/dsa.c93
-rw-r--r--net/dsa/dsa2.c384
-rw-r--r--net/dsa/dsa_priv.h27
-rw-r--r--net/dsa/master.c5
-rw-r--r--net/dsa/port.c32
-rw-r--r--net/dsa/slave.c37
-rw-r--r--net/dsa/switch.c4
-rw-r--r--net/dsa/tag_8021q.c22
-rw-r--r--net/dsa/tag_ocelot.c241
-rw-r--r--net/ethernet/eth.c7
-rw-r--r--net/ieee802154/6lowpan/core.c8
-rw-r--r--net/ieee802154/nl802154.c39
-rw-r--r--net/ipv4/Kconfig218
-rw-r--r--net/ipv4/af_inet.c2
-rw-r--r--net/ipv4/datagram.c2
-rw-r--r--net/ipv4/fib_frontend.c12
-rw-r--r--net/ipv4/fib_notifier.c13
-rw-r--r--net/ipv4/fib_rules.c5
-rw-r--r--net/ipv4/fib_semantics.c2
-rw-r--r--net/ipv4/fib_trie.c44
-rw-r--r--net/ipv4/icmp.c14
-rw-r--r--net/ipv4/igmp.c2
-rw-r--r--net/ipv4/inet_connection_sock.c2
-rw-r--r--net/ipv4/inet_diag.c15
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/inetpeer.c12
-rw-r--r--net/ipv4/ip_gre.c10
-rw-r--r--net/ipv4/ip_input.c38
-rw-r--r--net/ipv4/ip_output.c15
-rw-r--r--net/ipv4/ip_tunnel_core.c440
-rw-r--r--net/ipv4/ipconfig.c13
-rw-r--r--net/ipv4/ipmr.c16
-rw-r--r--net/ipv4/ipmr_base.c30
-rw-r--r--net/ipv4/netfilter/nf_flow_table_ipv4.c2
-rw-r--r--net/ipv4/netfilter/nf_socket_ipv4.c10
-rw-r--r--net/ipv4/nexthop.c1
-rw-r--r--net/ipv4/route.c47
-rw-r--r--net/ipv4/syncookies.c4
-rw-r--r--net/ipv4/sysctl_net_ipv4.c6
-rw-r--r--net/ipv4/tcp.c36
-rw-r--r--net/ipv4/tcp_cong.c6
-rw-r--r--net/ipv4/tcp_diag.c4
-rw-r--r--net/ipv4/tcp_fastopen.c5
-rw-r--r--net/ipv4/tcp_input.c4
-rw-r--r--net/ipv4/tcp_ipv4.c14
-rw-r--r--net/ipv4/tcp_output.c2
-rw-r--r--net/ipv4/tcp_ulp.c3
-rw-r--r--net/ipv4/udp.c58
-rw-r--r--net/ipv4/xfrm4_output.c2
-rw-r--r--net/ipv6/addrconf.c7
-rw-r--r--net/ipv6/addrconf_core.c1
-rw-r--r--net/ipv6/fib6_notifier.c11
-rw-r--r--net/ipv6/fib6_rules.c5
-rw-r--r--net/ipv6/icmp.c22
-rw-r--r--net/ipv6/inet6_hashtables.c2
-rw-r--r--net/ipv6/ip6_fib.c54
-rw-r--r--net/ipv6/ip6_gre.c4
-rw-r--r--net/ipv6/ip6_input.c29
-rw-r--r--net/ipv6/ip6_output.c4
-rw-r--r--net/ipv6/ip6mr.c13
-rw-r--r--net/ipv6/ipv6_sockglue.c4
-rw-r--r--net/ipv6/netfilter/Kconfig28
-rw-r--r--net/ipv6/netfilter/nf_flow_table_ipv6.c2
-rw-r--r--net/ipv6/netfilter/nf_tproxy_ipv6.c2
-rw-r--r--net/ipv6/route.c27
-rw-r--r--net/ipv6/seg6_local.c33
-rw-r--r--net/ipv6/tcp_ipv6.c2
-rw-r--r--net/ipv6/udp.c2
-rw-r--r--net/ipv6/xfrm6_output.c2
-rw-r--r--net/l2tp/l2tp_eth.c1
-rw-r--r--net/llc/af_llc.c4
-rw-r--r--net/mac80211/Makefile3
-rw-r--r--net/mac80211/agg-tx.c9
-rw-r--r--net/mac80211/airtime.c597
-rw-r--r--net/mac80211/cfg.c2
-rw-r--r--net/mac80211/debugfs.c88
-rw-r--r--net/mac80211/debugfs_sta.c43
-rw-r--r--net/mac80211/ibss.c9
-rw-r--r--net/mac80211/ieee80211_i.h8
-rw-r--r--net/mac80211/main.c12
-rw-r--r--net/mac80211/mlme.c103
-rw-r--r--net/mac80211/rc80211_minstrel.c48
-rw-r--r--net/mac80211/rc80211_minstrel.h57
-rw-r--r--net/mac80211/rc80211_minstrel_debugfs.c8
-rw-r--r--net/mac80211/rc80211_minstrel_ht.c73
-rw-r--r--net/mac80211/rc80211_minstrel_ht.h2
-rw-r--r--net/mac80211/rc80211_minstrel_ht_debugfs.c8
-rw-r--r--net/mac80211/sta_info.c55
-rw-r--r--net/mac80211/sta_info.h12
-rw-r--r--net/mac80211/status.c39
-rw-r--r--net/mac80211/tx.c136
-rw-r--r--net/netfilter/Makefile3
-rw-r--r--net/netfilter/core.c20
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_gen.h2
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_ip.c26
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_ipmac.c18
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_port.c41
-rw-r--r--net/netfilter/ipset/ip_set_core.c261
-rw-r--r--net/netfilter/ipset/ip_set_getport.c28
-rw-r--r--net/netfilter/ipset/ip_set_hash_gen.h4
-rw-r--r--net/netfilter/ipset/ip_set_hash_ip.c10
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipmac.c10
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipmark.c8
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipport.c8
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportip.c8
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportnet.c24
-rw-r--r--net/netfilter/ipset/ip_set_hash_mac.c6
-rw-r--r--net/netfilter/ipset/ip_set_hash_net.c25
-rw-r--r--net/netfilter/ipset/ip_set_hash_netiface.c47
-rw-r--r--net/netfilter/ipset/ip_set_hash_netnet.c29
-rw-r--r--net/netfilter/ipset/ip_set_hash_netport.c24
-rw-r--r--net/netfilter/ipset/ip_set_hash_netportnet.c28
-rw-r--r--net/netfilter/ipset/ip_set_list_set.c4
-rw-r--r--net/netfilter/ipvs/ip_vs_app.c12
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c47
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c41
-rw-r--r--net/netfilter/ipvs/ip_vs_ovf.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_pe.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_sched.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c13
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c18
-rw-r--r--net/netfilter/nf_conntrack_core.c2
-rw-r--r--net/netfilter/nf_conntrack_ecache.c23
-rw-r--r--net/netfilter/nf_conntrack_extend.c21
-rw-r--r--net/netfilter/nf_conntrack_netlink.c76
-rw-r--r--net/netfilter/nf_conntrack_proto_icmp.c6
-rw-r--r--net/netfilter/nf_flow_table_core.c180
-rw-r--r--net/netfilter/nf_flow_table_inet.c25
-rw-r--r--net/netfilter/nf_flow_table_offload.c851
-rw-r--r--net/netfilter/nf_tables_api.c621
-rw-r--r--net/netfilter/nf_tables_offload.c280
-rw-r--r--net/netfilter/nft_bitwise.c5
-rw-r--r--net/netfilter/nft_chain_filter.c45
-rw-r--r--net/netfilter/nft_cmp.c8
-rw-r--r--net/netfilter/nft_flow_offload.c5
-rw-r--r--net/netfilter/nft_meta.c18
-rw-r--r--net/netfilter/nft_payload.c132
-rw-r--r--net/netfilter/xt_HMARK.c6
-rw-r--r--net/netfilter/xt_time.c19
-rw-r--r--net/netlink/genetlink.c303
-rw-r--r--net/netrom/af_netrom.c23
-rw-r--r--net/nfc/hci/Kconfig14
-rw-r--r--net/nfc/llcp_sock.c4
-rw-r--r--net/nfc/netlink.c19
-rw-r--r--net/openvswitch/actions.c2
-rw-r--r--net/openvswitch/conntrack.c21
-rw-r--r--net/openvswitch/datapath.c133
-rw-r--r--net/openvswitch/datapath.h12
-rw-r--r--net/openvswitch/flow.c20
-rw-r--r--net/openvswitch/flow.h10
-rw-r--r--net/openvswitch/flow_netlink.c87
-rw-r--r--net/openvswitch/flow_table.c381
-rw-r--r--net/openvswitch/flow_table.h19
-rw-r--r--net/openvswitch/vport-internal_dev.c11
-rw-r--r--net/openvswitch/vport.c5
-rw-r--r--net/packet/af_packet.c12
-rw-r--r--net/phonet/socket.c4
-rw-r--r--net/qrtr/tun.c6
-rw-r--r--net/rds/ib.c10
-rw-r--r--net/rds/ib.h15
-rw-r--r--net/rds/ib_cm.c190
-rw-r--r--net/rds/ib_recv.c13
-rw-r--r--net/rds/ib_send.c19
-rw-r--r--net/rose/af_rose.c27
-rw-r--r--net/rxrpc/Kconfig2
-rw-r--r--net/rxrpc/ar-internal.h1
-rw-r--r--net/rxrpc/peer_object.c2
-rw-r--r--net/rxrpc/recvmsg.c18
-rw-r--r--net/sched/act_api.c58
-rw-r--r--net/sched/act_bpf.c5
-rw-r--r--net/sched/act_connmark.c4
-rw-r--r--net/sched/act_csum.c10
-rw-r--r--net/sched/act_ct.c17
-rw-r--r--net/sched/act_ctinfo.c4
-rw-r--r--net/sched/act_gact.c21
-rw-r--r--net/sched/act_ife.c5
-rw-r--r--net/sched/act_ipt.c12
-rw-r--r--net/sched/act_mirred.c19
-rw-r--r--net/sched/act_mpls.c6
-rw-r--r--net/sched/act_nat.c8
-rw-r--r--net/sched/act_pedit.c17
-rw-r--r--net/sched/act_police.c14
-rw-r--r--net/sched/act_sample.c4
-rw-r--r--net/sched/act_simple.c7
-rw-r--r--net/sched/act_skbedit.c4
-rw-r--r--net/sched/act_skbmod.c4
-rw-r--r--net/sched/act_tunnel_key.c216
-rw-r--r--net/sched/act_vlan.c16
-rw-r--r--net/sched/cls_api.c83
-rw-r--r--net/sched/cls_bpf.c8
-rw-r--r--net/sched/cls_flower.c254
-rw-r--r--net/sched/em_meta.c4
-rw-r--r--net/sched/sch_fq.c3
-rw-r--r--net/sched/sch_fq_codel.c1
-rw-r--r--net/sched/sch_generic.c37
-rw-r--r--net/sched/sch_hhf.c8
-rw-r--r--net/sched/sch_pie.c120
-rw-r--r--net/sched/sch_sfb.c13
-rw-r--r--net/sched/sch_sfq.c14
-rw-r--r--net/sched/sch_taprio.c35
-rw-r--r--net/sctp/associola.c61
-rw-r--r--net/sctp/chunk.c40
-rw-r--r--net/sctp/diag.c4
-rw-r--r--net/sctp/endpointola.c3
-rw-r--r--net/sctp/input.c4
-rw-r--r--net/sctp/protocol.c6
-rw-r--r--net/sctp/sm_sideeffect.c5
-rw-r--r--net/sctp/sm_statefuns.c4
-rw-r--r--net/sctp/socket.c159
-rw-r--r--net/sctp/sysctl.c22
-rw-r--r--net/sctp/ulpevent.c57
-rw-r--r--net/smc/af_smc.c40
-rw-r--r--net/smc/smc.h1
-rw-r--r--net/smc/smc_cdc.c7
-rw-r--r--net/smc/smc_clc.c2
-rw-r--r--net/smc/smc_close.c97
-rw-r--r--net/smc/smc_close.h2
-rw-r--r--net/smc/smc_core.c446
-rw-r--r--net/smc/smc_core.h16
-rw-r--r--net/smc/smc_ib.c24
-rw-r--r--net/smc/smc_ib.h4
-rw-r--r--net/smc/smc_ism.c27
-rw-r--r--net/smc/smc_llc.c11
-rw-r--r--net/smc/smc_pnet.c9
-rw-r--r--net/smc/smc_rx.c10
-rw-r--r--net/smc/smc_tx.c28
-rw-r--r--net/smc/smc_wr.c45
-rw-r--r--net/smc/smc_wr.h10
-rw-r--r--net/socket.c66
-rw-r--r--net/sunrpc/backchannel_rqst.c7
-rw-r--r--net/sunrpc/xprt.c5
-rw-r--r--net/sunrpc/xprtrdma/backchannel.c2
-rw-r--r--net/tipc/Kconfig15
-rw-r--r--net/tipc/Makefile1
-rw-r--r--net/tipc/bcast.c6
-rw-r--r--net/tipc/bcast.h2
-rw-r--r--net/tipc/bearer.c49
-rw-r--r--net/tipc/bearer.h6
-rw-r--r--net/tipc/core.c32
-rw-r--r--net/tipc/core.h20
-rw-r--r--net/tipc/crypto.c1986
-rw-r--r--net/tipc/crypto.h167
-rw-r--r--net/tipc/discover.c4
-rw-r--r--net/tipc/link.c109
-rw-r--r--net/tipc/link.h1
-rw-r--r--net/tipc/monitor.c15
-rw-r--r--net/tipc/monitor.h1
-rw-r--r--net/tipc/msg.c221
-rw-r--r--net/tipc/msg.h77
-rw-r--r--net/tipc/name_distr.c2
-rw-r--r--net/tipc/name_table.c51
-rw-r--r--net/tipc/name_table.h4
-rw-r--r--net/tipc/net.c2
-rw-r--r--net/tipc/netlink.c39
-rw-r--r--net/tipc/netlink.h1
-rw-r--r--net/tipc/netlink_compat.c28
-rw-r--r--net/tipc/node.c496
-rw-r--r--net/tipc/node.h25
-rw-r--r--net/tipc/socket.c135
-rw-r--r--net/tipc/sysctl.c11
-rw-r--r--net/tipc/udp_media.c7
-rw-r--r--net/tls/Kconfig10
-rw-r--r--net/tls/Makefile5
-rw-r--r--net/tls/tls_device.c56
-rw-r--r--net/tls/tls_main.c175
-rw-r--r--net/tls/tls_proc.c49
-rw-r--r--net/tls/tls_sw.c59
-rw-r--r--net/tls/tls_toe.c139
-rw-r--r--net/tls/trace.c10
-rw-r--r--net/tls/trace.h202
-rw-r--r--net/unix/af_unix.c12
-rw-r--r--net/vmw_vsock/af_vsock.c399
-rw-r--r--net/vmw_vsock/hyperv_transport.c94
-rw-r--r--net/vmw_vsock/virtio_transport.c177
-rw-r--r--net/vmw_vsock/virtio_transport_common.c231
-rw-r--r--net/vmw_vsock/vmci_transport.c142
-rw-r--r--net/vmw_vsock/vmci_transport.h3
-rw-r--r--net/vmw_vsock/vmci_transport_notify.h1
-rw-r--r--net/wireless/chan.c5
-rw-r--r--net/wireless/nl80211.c19
-rw-r--r--net/wireless/reg.h2
-rw-r--r--net/wireless/util.c3
-rw-r--r--net/x25/af_x25.c4
-rw-r--r--net/xdp/xdp_umem.c6
-rw-r--r--net/xdp/xsk.c41
-rw-r--r--net/xfrm/Kconfig12
-rw-r--r--net/xfrm/xfrm_algo.c4
-rw-r--r--net/xfrm/xfrm_input.c3
-rw-r--r--net/xfrm/xfrm_interface.c23
-rw-r--r--net/xfrm/xfrm_state.c2
359 files changed, 14666 insertions, 4401 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 54728d2eda18..d4bcfd8f95bf 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -172,7 +172,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack)
if (err < 0)
goto out_uninit_mvrp;
- 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 93eadf179123..e5bff5cc6f97 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -489,36 +489,6 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
}
-/*
- * vlan network devices have devices nesting below it, and are a special
- * "super class" of normal network devices; split their locks off into a
- * separate class since they always nest.
- */
-static struct lock_class_key vlan_netdev_xmit_lock_key;
-static struct lock_class_key vlan_netdev_addr_lock_key;
-
-static void vlan_dev_set_lockdep_one(struct net_device *dev,
- struct netdev_queue *txq,
- void *_subclass)
-{
- lockdep_set_class_and_subclass(&txq->_xmit_lock,
- &vlan_netdev_xmit_lock_key,
- *(int *)_subclass);
-}
-
-static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass)
-{
- lockdep_set_class_and_subclass(&dev->addr_list_lock,
- &vlan_netdev_addr_lock_key,
- subclass);
- netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass);
-}
-
-static int vlan_dev_get_lock_subclass(struct net_device *dev)
-{
- return vlan_dev_priv(dev)->nest_level;
-}
-
static const struct header_ops vlan_header_ops = {
.create = vlan_dev_hard_header,
.parse = eth_header_parse,
@@ -609,8 +579,6 @@ static int vlan_dev_init(struct net_device *dev)
SET_NETDEV_DEVTYPE(dev, &vlan_type);
- vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev));
-
vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
if (!vlan->vlan_pcpu_stats)
return -ENOMEM;
@@ -812,7 +780,6 @@ static const struct net_device_ops vlan_netdev_ops = {
.ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup,
#endif
.ndo_fix_features = vlan_dev_fix_features,
- .ndo_get_lock_subclass = vlan_dev_get_lock_subclass,
.ndo_get_iflink = vlan_dev_get_iflink,
};
diff --git a/net/Kconfig b/net/Kconfig
index 3101bfcbdd7a..bd191f978a23 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -258,7 +258,7 @@ config XPS
default y
config HWBM
- bool
+ bool
config CGROUP_NET_PRIO
bool "Network priority cgroup"
@@ -309,12 +309,12 @@ config BPF_STREAM_PARSER
select STREAM_PARSER
select NET_SOCK_MSG
---help---
- Enabling this allows a stream parser to be used with
- BPF_MAP_TYPE_SOCKMAP.
+ Enabling this allows a stream parser to be used with
+ BPF_MAP_TYPE_SOCKMAP.
- BPF_MAP_TYPE_SOCKMAP provides a map type to use with network sockets.
- It can be used to enforce socket policy, implement socket redirects,
- etc.
+ BPF_MAP_TYPE_SOCKMAP provides a map type to use with network sockets.
+ It can be used to enforce socket policy, implement socket redirects,
+ etc.
config NET_FLOW_LIMIT
bool
@@ -349,12 +349,12 @@ config NET_DROP_MONITOR
tristate "Network packet drop alerting service"
depends on INET && TRACEPOINTS
---help---
- This feature provides an alerting service to userspace in the
- event that packets are discarded in the network stack. Alerts
- are broadcast via netlink socket to any listening user space
- process. If you don't need network drop alerts, or if you are ok
- just checking the various proc files and other utilities for
- drop statistics, say N here.
+ This feature provides an alerting service to userspace in the
+ event that packets are discarded in the network stack. Alerts
+ are broadcast via netlink socket to any listening user space
+ process. If you don't need network drop alerts, or if you are ok
+ just checking the various proc files and other utilities for
+ drop statistics, say N here.
endmenu
@@ -433,7 +433,7 @@ config NET_DEVLINK
imply NET_DROP_MONITOR
config PAGE_POOL
- bool
+ bool
config FAILOVER
tristate "Generic failover module"
diff --git a/net/atm/clip.c b/net/atm/clip.c
index a7972da7235d..294cb9efe3d3 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -89,7 +89,7 @@ static void unlink_clip_vcc(struct clip_vcc *clip_vcc)
struct clip_vcc **walk;
if (!entry) {
- pr_crit("!clip_vcc->entry (clip_vcc %p)\n", clip_vcc);
+ pr_err("!clip_vcc->entry (clip_vcc %p)\n", clip_vcc);
return;
}
netif_tx_lock_bh(entry->neigh->dev); /* block clip_start_xmit() */
@@ -109,10 +109,10 @@ static void unlink_clip_vcc(struct clip_vcc *clip_vcc)
error = neigh_update(entry->neigh, NULL, NUD_NONE,
NEIGH_UPDATE_F_ADMIN, 0);
if (error)
- pr_crit("neigh_update failed with %d\n", error);
+ pr_err("neigh_update failed with %d\n", error);
goto out;
}
- pr_crit("ATMARP: failed (entry %p, vcc 0x%p)\n", entry, clip_vcc);
+ pr_err("ATMARP: failed (entry %p, vcc 0x%p)\n", entry, clip_vcc);
out:
netif_tx_unlock_bh(entry->neigh->dev);
}
diff --git a/net/atm/common.c b/net/atm/common.c
index b7528e77997c..0ce530af534d 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -668,7 +668,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
mask |= EPOLLHUP;
/* readable? */
- if (!skb_queue_empty(&sk->sk_receive_queue))
+ if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* writable? */
diff --git a/net/atm/signaling.c b/net/atm/signaling.c
index 6c11cdf4dd4c..fbd0c5e7b299 100644
--- a/net/atm/signaling.c
+++ b/net/atm/signaling.c
@@ -109,7 +109,7 @@ static int sigd_send(struct atm_vcc *vcc, struct sk_buff *skb)
dev_kfree_skb(skb);
goto as_indicate_complete;
}
- sk->sk_ack_backlog++;
+ sk_acceptq_added(sk);
skb_queue_tail(&sk->sk_receive_queue, skb);
pr_debug("waking sk_sleep(sk) 0x%p\n", sk_sleep(sk));
sk->sk_state_change(sk);
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 908cbb8654f5..ba144d035e3d 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -381,7 +381,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags,
msg->pvc.sap_addr.vpi,
msg->pvc.sap_addr.vci);
dev_kfree_skb(skb);
- sk->sk_ack_backlog--;
+ sk_acceptq_removed(sk);
if (error) {
sigd_enq2(NULL, as_reject, old_vcc, NULL, NULL,
&old_vcc->qos, error);
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index bb222b882b67..324306d6fde0 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1384,7 +1384,7 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags,
/* Now attach up the new socket */
kfree_skb(skb);
- sk->sk_ack_backlog--;
+ sk_acceptq_removed(sk);
newsock->state = SS_CONNECTED;
out:
diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c
index dcdbaeeb2358..cd6afe895db9 100644
--- a/net/ax25/ax25_in.c
+++ b/net/ax25/ax25_in.c
@@ -356,7 +356,7 @@ static int ax25_rcv(struct sk_buff *skb, struct net_device *dev,
make->sk_state = TCP_ESTABLISHED;
- sk->sk_ack_backlog++;
+ sk_acceptq_added(sk);
bh_unlock_sock(sk);
} else {
if (!mine)
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index d78938e3e008..5b0b20e6da95 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -22,6 +22,8 @@
#include <linux/kernel.h>
#include <linux/kref.h>
#include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/netlink.h>
#include <linux/pkt_sched.h>
@@ -193,14 +195,18 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
unsigned char *ogm_buff;
u32 random_seqno;
+ mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex);
+
/* randomize initial seqno to avoid collision */
get_random_bytes(&random_seqno, sizeof(random_seqno));
atomic_set(&hard_iface->bat_iv.ogm_seqno, random_seqno);
hard_iface->bat_iv.ogm_buff_len = BATADV_OGM_HLEN;
ogm_buff = kmalloc(hard_iface->bat_iv.ogm_buff_len, GFP_ATOMIC);
- if (!ogm_buff)
+ if (!ogm_buff) {
+ mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
return -ENOMEM;
+ }
hard_iface->bat_iv.ogm_buff = ogm_buff;
@@ -212,35 +218,59 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
batadv_ogm_packet->reserved = 0;
batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE;
+ mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
+
return 0;
}
static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface)
{
+ mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex);
+
kfree(hard_iface->bat_iv.ogm_buff);
hard_iface->bat_iv.ogm_buff = NULL;
+
+ mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
}
static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface)
{
struct batadv_ogm_packet *batadv_ogm_packet;
- unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff;
+ void *ogm_buff;
- batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
+ mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex);
+
+ ogm_buff = hard_iface->bat_iv.ogm_buff;
+ if (!ogm_buff)
+ goto unlock;
+
+ batadv_ogm_packet = ogm_buff;
ether_addr_copy(batadv_ogm_packet->orig,
hard_iface->net_dev->dev_addr);
ether_addr_copy(batadv_ogm_packet->prev_sender,
hard_iface->net_dev->dev_addr);
+
+unlock:
+ mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
}
static void
batadv_iv_ogm_primary_iface_set(struct batadv_hard_iface *hard_iface)
{
struct batadv_ogm_packet *batadv_ogm_packet;
- unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff;
+ void *ogm_buff;
- batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
+ mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex);
+
+ ogm_buff = hard_iface->bat_iv.ogm_buff;
+ if (!ogm_buff)
+ goto unlock;
+
+ batadv_ogm_packet = ogm_buff;
batadv_ogm_packet->ttl = BATADV_TTL;
+
+unlock:
+ mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
}
/* when do we schedule our own ogm to be sent */
@@ -742,7 +772,11 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface)
}
}
-static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
+/**
+ * batadv_iv_ogm_schedule_buff() - schedule submission of hardif ogm buffer
+ * @hard_iface: interface whose ogm buffer should be transmitted
+ */
+static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface)
{
struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff;
@@ -753,9 +787,7 @@ 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;
+ lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex);
/* the interface gets activated here to avoid race conditions between
* the moment of activating the interface in
@@ -823,6 +855,17 @@ out:
batadv_hardif_put(primary_if);
}
+static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
+{
+ if (hard_iface->if_status == BATADV_IF_NOT_IN_USE ||
+ hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)
+ return;
+
+ mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex);
+ batadv_iv_ogm_schedule_buff(hard_iface);
+ mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
+}
+
/**
* batadv_iv_orig_ifinfo_sum() - Get bcast_own sum for originator over iterface
* @orig_node: originator which reproadcasted the OGMs directly
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 64054edc2e3c..4ff6cf1ecae7 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -1085,7 +1085,6 @@ void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface)
hard_iface->bat_v.aggr_len = 0;
skb_queue_head_init(&hard_iface->bat_v.aggr_list);
- spin_lock_init(&hard_iface->bat_v.aggr_list_lock);
INIT_DELAYED_WORK(&hard_iface->bat_v.aggr_wq,
batadv_v_ogm_aggr_work);
}
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index dc4f7430cb5a..714ce56cfcc8 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -18,6 +18,7 @@
#include <linux/kref.h>
#include <linux/list.h>
#include <linux/lockdep.h>
+#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/random.h>
#include <linux/rculist.h>
@@ -151,7 +152,7 @@ static unsigned int batadv_v_ogm_len(struct sk_buff *skb)
* @skb: the OGM to check
* @hard_iface: the interface to use to send the OGM
*
- * Caller needs to hold the hard_iface->bat_v.aggr_list_lock.
+ * Caller needs to hold the hard_iface->bat_v.aggr_list.lock.
*
* Return: True, if the given OGMv2 packet still fits, false otherwise.
*/
@@ -162,7 +163,7 @@ static bool batadv_v_ogm_queue_left(struct sk_buff *skb,
BATADV_MAX_AGGREGATION_BYTES);
unsigned int ogm_len = batadv_v_ogm_len(skb);
- lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock);
+ lockdep_assert_held(&hard_iface->bat_v.aggr_list.lock);
return hard_iface->bat_v.aggr_len + ogm_len <= max;
}
@@ -173,17 +174,13 @@ static bool batadv_v_ogm_queue_left(struct sk_buff *skb,
*
* Empties the OGMv2 aggregation queue and frees all the skbs it contained.
*
- * Caller needs to hold the hard_iface->bat_v.aggr_list_lock.
+ * Caller needs to hold the hard_iface->bat_v.aggr_list.lock.
*/
static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface)
{
- struct sk_buff *skb;
-
- lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock);
-
- while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list)))
- kfree_skb(skb);
+ lockdep_assert_held(&hard_iface->bat_v.aggr_list.lock);
+ __skb_queue_purge(&hard_iface->bat_v.aggr_list);
hard_iface->bat_v.aggr_len = 0;
}
@@ -196,7 +193,7 @@ static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface)
*
* The aggregation queue is empty after this call.
*
- * Caller needs to hold the hard_iface->bat_v.aggr_list_lock.
+ * Caller needs to hold the hard_iface->bat_v.aggr_list.lock.
*/
static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface)
{
@@ -205,7 +202,7 @@ static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface)
unsigned int ogm_len;
struct sk_buff *skb;
- lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock);
+ lockdep_assert_held(&hard_iface->bat_v.aggr_list.lock);
if (!aggr_len)
return;
@@ -219,7 +216,7 @@ static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface)
skb_reserve(skb_aggr, ETH_HLEN + NET_IP_ALIGN);
skb_reset_network_header(skb_aggr);
- while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list))) {
+ while ((skb = __skb_dequeue(&hard_iface->bat_v.aggr_list))) {
hard_iface->bat_v.aggr_len -= batadv_v_ogm_len(skb);
ogm_len = batadv_v_ogm_len(skb);
@@ -246,24 +243,22 @@ static void batadv_v_ogm_queue_on_if(struct sk_buff *skb,
return;
}
- spin_lock_bh(&hard_iface->bat_v.aggr_list_lock);
+ spin_lock_bh(&hard_iface->bat_v.aggr_list.lock);
if (!batadv_v_ogm_queue_left(skb, hard_iface))
batadv_v_ogm_aggr_send(hard_iface);
hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb);
- skb_queue_tail(&hard_iface->bat_v.aggr_list, skb);
- spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock);
+ __skb_queue_tail(&hard_iface->bat_v.aggr_list, skb);
+ spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock);
}
/**
- * batadv_v_ogm_send() - periodic worker broadcasting the own OGM
- * @work: work queue item
+ * batadv_v_ogm_send_softif() - periodic worker broadcasting the own OGM
+ * @bat_priv: the bat priv with all the soft interface information
*/
-static void batadv_v_ogm_send(struct work_struct *work)
+static void batadv_v_ogm_send_softif(struct batadv_priv *bat_priv)
{
struct batadv_hard_iface *hard_iface;
- struct batadv_priv_bat_v *bat_v;
- struct batadv_priv *bat_priv;
struct batadv_ogm2_packet *ogm_packet;
struct sk_buff *skb, *skb_tmp;
unsigned char *ogm_buff;
@@ -271,8 +266,7 @@ static void batadv_v_ogm_send(struct work_struct *work)
u16 tvlv_len = 0;
int ret;
- bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work);
- bat_priv = container_of(bat_v, struct batadv_priv, bat_v);
+ lockdep_assert_held(&bat_priv->bat_v.ogm_buff_mutex);
if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING)
goto out;
@@ -364,6 +358,23 @@ out:
}
/**
+ * batadv_v_ogm_send() - periodic worker broadcasting the own OGM
+ * @work: work queue item
+ */
+static void batadv_v_ogm_send(struct work_struct *work)
+{
+ struct batadv_priv_bat_v *bat_v;
+ struct batadv_priv *bat_priv;
+
+ bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work);
+ bat_priv = container_of(bat_v, struct batadv_priv, bat_v);
+
+ mutex_lock(&bat_priv->bat_v.ogm_buff_mutex);
+ batadv_v_ogm_send_softif(bat_priv);
+ mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex);
+}
+
+/**
* batadv_v_ogm_aggr_work() - OGM queue periodic task per interface
* @work: work queue item
*
@@ -377,9 +388,9 @@ void batadv_v_ogm_aggr_work(struct work_struct *work)
batv = container_of(work, struct batadv_hard_iface_bat_v, aggr_wq.work);
hard_iface = container_of(batv, struct batadv_hard_iface, bat_v);
- spin_lock_bh(&hard_iface->bat_v.aggr_list_lock);
+ spin_lock_bh(&hard_iface->bat_v.aggr_list.lock);
batadv_v_ogm_aggr_send(hard_iface);
- spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock);
+ spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock);
batadv_v_ogm_start_queue_timer(hard_iface);
}
@@ -410,9 +421,9 @@ void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface)
{
cancel_delayed_work_sync(&hard_iface->bat_v.aggr_wq);
- spin_lock_bh(&hard_iface->bat_v.aggr_list_lock);
+ spin_lock_bh(&hard_iface->bat_v.aggr_list.lock);
batadv_v_ogm_aggr_list_free(hard_iface);
- spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock);
+ spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock);
}
/**
@@ -424,11 +435,15 @@ void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface)
struct batadv_priv *bat_priv = netdev_priv(primary_iface->soft_iface);
struct batadv_ogm2_packet *ogm_packet;
+ mutex_lock(&bat_priv->bat_v.ogm_buff_mutex);
if (!bat_priv->bat_v.ogm_buff)
- return;
+ goto unlock;
ogm_packet = (struct batadv_ogm2_packet *)bat_priv->bat_v.ogm_buff;
ether_addr_copy(ogm_packet->orig, primary_iface->net_dev->dev_addr);
+
+unlock:
+ mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex);
}
/**
@@ -1050,6 +1065,8 @@ int batadv_v_ogm_init(struct batadv_priv *bat_priv)
atomic_set(&bat_priv->bat_v.ogm_seqno, random_seqno);
INIT_DELAYED_WORK(&bat_priv->bat_v.ogm_wq, batadv_v_ogm_send);
+ mutex_init(&bat_priv->bat_v.ogm_buff_mutex);
+
return 0;
}
@@ -1061,7 +1078,11 @@ void batadv_v_ogm_free(struct batadv_priv *bat_priv)
{
cancel_delayed_work_sync(&bat_priv->bat_v.ogm_wq);
+ mutex_lock(&bat_priv->bat_v.ogm_buff_mutex);
+
kfree(bat_priv->bat_v.ogm_buff);
bat_priv->bat_v.ogm_buff = NULL;
bat_priv->bat_v.ogm_buff_len = 0;
+
+ mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex);
}
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index c90e47342bb0..afb52282d5bd 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -18,6 +18,7 @@
#include <linux/kref.h>
#include <linux/limits.h>
#include <linux/list.h>
+#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/printk.h>
#include <linux/rculist.h>
@@ -929,6 +930,7 @@ batadv_hardif_add_interface(struct net_device *net_dev)
INIT_LIST_HEAD(&hard_iface->list);
INIT_HLIST_HEAD(&hard_iface->neigh_list);
+ mutex_init(&hard_iface->bat_iv.ogm_buff_mutex);
spin_lock_init(&hard_iface->neigh_list_lock);
kref_init(&hard_iface->refcount);
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 6967f2e4c3f4..c7b340ddd0e7 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -13,7 +13,7 @@
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2019.4"
+#define BATADV_SOURCE_VERSION "2019.5"
#endif
/* B.A.T.M.A.N. parameters */
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 1d5bdf3a4b65..f9ec8e7507b6 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -1421,7 +1421,7 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
if (*orig)
return BATADV_FORW_SINGLE;
- /* fall through */
+ fallthrough;
case 0:
return BATADV_FORW_NONE;
default:
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 9cbed6f5a85a..832e156c519e 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -22,7 +22,6 @@
#include <linux/kernel.h>
#include <linux/kref.h>
#include <linux/list.h>
-#include <linux/lockdep.h>
#include <linux/netdevice.h>
#include <linux/netlink.h>
#include <linux/percpu.h>
@@ -230,7 +229,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
break;
}
- /* fall through */
+ fallthrough;
case ETH_P_BATMAN:
goto dropped;
}
@@ -455,7 +454,7 @@ void batadv_interface_rx(struct net_device *soft_iface,
if (vhdr->h_vlan_encapsulated_proto != htons(ETH_P_BATMAN))
break;
- /* fall through */
+ fallthrough;
case ETH_P_BATMAN:
goto dropped;
}
@@ -740,36 +739,6 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto,
return 0;
}
-/* batman-adv network devices have devices nesting below it and are a special
- * "super class" of normal network devices; split their locks off into a
- * separate class since they always nest.
- */
-static struct lock_class_key batadv_netdev_xmit_lock_key;
-static struct lock_class_key batadv_netdev_addr_lock_key;
-
-/**
- * batadv_set_lockdep_class_one() - Set lockdep class for a single tx queue
- * @dev: device which owns the tx queue
- * @txq: tx queue to modify
- * @_unused: always NULL
- */
-static void batadv_set_lockdep_class_one(struct net_device *dev,
- struct netdev_queue *txq,
- void *_unused)
-{
- lockdep_set_class(&txq->_xmit_lock, &batadv_netdev_xmit_lock_key);
-}
-
-/**
- * batadv_set_lockdep_class() - Set txq and addr_list lockdep class
- * @dev: network device to modify
- */
-static void batadv_set_lockdep_class(struct net_device *dev)
-{
- lockdep_set_class(&dev->addr_list_lock, &batadv_netdev_addr_lock_key);
- netdev_for_each_tx_queue(dev, batadv_set_lockdep_class_one, NULL);
-}
-
/**
* batadv_softif_init_late() - late stage initialization of soft interface
* @dev: registered network device to modify
@@ -783,8 +752,6 @@ static int batadv_softif_init_late(struct net_device *dev)
int ret;
size_t cnt_len = sizeof(u64) * BATADV_CNT_NUM;
- batadv_set_lockdep_class(dev);
-
bat_priv = netdev_priv(dev);
bat_priv->soft_iface = dev;
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index be7c02aa91e2..47718a82eaf2 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -17,6 +17,7 @@
#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/kref.h>
+#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/netlink.h>
#include <linux/sched.h> /* for linux/wait.h */
@@ -81,6 +82,9 @@ struct batadv_hard_iface_bat_iv {
/** @ogm_seqno: OGM sequence number - used to identify each OGM */
atomic_t ogm_seqno;
+
+ /** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */
+ struct mutex ogm_buff_mutex;
};
/**
@@ -126,9 +130,6 @@ struct batadv_hard_iface_bat_v {
/** @aggr_len: size of the OGM aggregate (excluding ethernet header) */
unsigned int aggr_len;
- /** @aggr_list_lock: protects aggr_list */
- spinlock_t aggr_list_lock;
-
/**
* @throughput_override: throughput override to disable link
* auto-detection
@@ -1539,6 +1540,9 @@ struct batadv_priv_bat_v {
/** @ogm_seqno: OGM sequence number - used to identify each OGM */
atomic_t ogm_seqno;
+ /** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */
+ struct mutex ogm_buff_mutex;
+
/** @ogm_wq: workqueue used to schedule OGM transmissions */
struct delayed_work ogm_wq;
};
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index bb55d92691b0..4febc82a7c76 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -571,15 +571,7 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
return err < 0 ? NET_XMIT_DROP : err;
}
-static int bt_dev_init(struct net_device *dev)
-{
- netdev_lockdep_set_classes(dev);
-
- return 0;
-}
-
static const struct net_device_ops netdev_ops = {
- .ndo_init = bt_dev_init,
.ndo_start_xmit = bt_xmit,
};
diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig
index 3803135c88ff..165148c7c4ce 100644
--- a/net/bluetooth/Kconfig
+++ b/net/bluetooth/Kconfig
@@ -9,7 +9,7 @@ menuconfig BT
depends on RFKILL || !RFKILL
select CRC16
select CRYPTO
- select CRYPTO_BLKCIPHER
+ select CRYPTO_SKCIPHER
select CRYPTO_LIB_AES
imply CRYPTO_AES
select CRYPTO_CMAC
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 94ddf19998c7..3fd124927d4d 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -173,7 +173,7 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh)
else
release_sock(sk);
- parent->sk_ack_backlog++;
+ sk_acceptq_added(parent);
}
EXPORT_SYMBOL(bt_accept_enqueue);
@@ -185,7 +185,7 @@ void bt_accept_unlink(struct sock *sk)
BT_DBG("sk %p state %d", sk, sk->sk_state);
list_del_init(&bt_sk(sk)->accept_q);
- bt_sk(sk)->parent->sk_ack_backlog--;
+ sk_acceptq_removed(bt_sk(sk)->parent);
bt_sk(sk)->parent = NULL;
sock_put(sk);
}
@@ -460,7 +460,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock,
if (sk->sk_state == BT_LISTEN)
return bt_accept_poll(sk);
- if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+ if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
mask |= EPOLLERR |
(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
@@ -470,7 +470,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock,
if (sk->sk_shutdown == SHUTDOWN_MASK)
mask |= EPOLLHUP;
- if (!skb_queue_empty(&sk->sk_receive_queue))
+ if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
if (sk->sk_state == BT_CLOSED)
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index ad5b0ac1f9ce..87691404d0c6 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -934,6 +934,14 @@ static void hci_req_directed_advertising(struct hci_request *req,
return;
memset(&cp, 0, sizeof(cp));
+
+ /* Some controllers might reject command if intervals are not
+ * within range for undirected advertising.
+ * BCM20702A0 is known to be affected by this.
+ */
+ cp.min_interval = cpu_to_le16(0x0020);
+ cp.max_interval = cpu_to_le16(0x0020);
+
cp.type = LE_ADV_DIRECT_IND;
cp.own_address_type = own_addr_type;
cp.direct_addr_type = conn->dst_type;
@@ -1168,8 +1176,10 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst,
if (!conn)
return ERR_PTR(-ENOMEM);
- if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0)
+ if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0) {
+ hci_conn_del(conn);
return ERR_PTR(-EBUSY);
+ }
conn->state = BT_CONNECT;
set_bit(HCI_CONN_SCANNING, &conn->flags);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 04bc79359a17..9e19d5a3aac8 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -842,8 +842,8 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt)
if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) {
struct hci_cp_le_write_def_data_len cp;
- cp.tx_len = hdev->le_max_tx_len;
- cp.tx_time = hdev->le_max_tx_time;
+ cp.tx_len = cpu_to_le16(hdev->le_max_tx_len);
+ cp.tx_time = cpu_to_le16(hdev->le_max_tx_time);
hci_req_add(req, HCI_OP_LE_WRITE_DEF_DATA_LEN, sizeof(cp), &cp);
}
@@ -1444,11 +1444,20 @@ static int hci_dev_do_open(struct hci_dev *hdev)
if (hci_dev_test_flag(hdev, HCI_SETUP) ||
test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks)) {
+ bool invalid_bdaddr;
+
hci_sock_dev_event(hdev, HCI_DEV_SETUP);
if (hdev->setup)
ret = hdev->setup(hdev);
+ /* The transport driver can set the quirk to mark the
+ * BD_ADDR invalid before creating the HCI device or in
+ * its setup callback.
+ */
+ invalid_bdaddr = test_bit(HCI_QUIRK_INVALID_BDADDR,
+ &hdev->quirks);
+
if (ret)
goto setup_failed;
@@ -1457,20 +1466,33 @@ static int hci_dev_do_open(struct hci_dev *hdev)
hci_dev_get_bd_addr_from_property(hdev);
if (bacmp(&hdev->public_addr, BDADDR_ANY) &&
- hdev->set_bdaddr)
+ hdev->set_bdaddr) {
ret = hdev->set_bdaddr(hdev,
&hdev->public_addr);
+
+ /* If setting of the BD_ADDR from the device
+ * property succeeds, then treat the address
+ * as valid even if the invalid BD_ADDR
+ * quirk indicates otherwise.
+ */
+ if (!ret)
+ invalid_bdaddr = false;
+ }
}
setup_failed:
/* The transport driver can set these quirks before
* creating the HCI device or in its setup callback.
*
+ * For the invalid BD_ADDR quirk it is possible that
+ * it becomes a valid address if the bootloader does
+ * provide it (see above).
+ *
* In case any of them is set, the controller has to
* start up as unconfigured.
*/
if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) ||
- test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks))
+ invalid_bdaddr)
hci_dev_set_flag(hdev, HCI_UNCONFIGURED);
/* For an unconfigured controller it is required to
@@ -4440,7 +4462,14 @@ static void hci_rx_work(struct work_struct *work)
hci_send_to_sock(hdev, skb);
}
- if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
+ /* If the device has been opened in HCI_USER_CHANNEL,
+ * the userspace has exclusive access to device.
+ * When device is HCI_INIT, we still need to process
+ * the data packets to the driver in order
+ * to complete its setup().
+ */
+ if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL) &&
+ !test_bit(HCI_INIT, &hdev->flags)) {
kfree_skb(skb);
continue;
}
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 7f6a581b5b7e..2a1b64dbf76e 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -904,9 +904,9 @@ static u8 get_adv_instance_scan_rsp_len(struct hci_dev *hdev, u8 instance)
{
struct adv_info *adv_instance;
- /* Ignore instance 0 */
+ /* Instance 0x00 always set local name */
if (instance == 0x00)
- return 0;
+ return 1;
adv_instance = hci_find_adv_instance(hdev, instance);
if (!adv_instance)
@@ -923,9 +923,9 @@ static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev)
u8 instance = hdev->cur_adv_instance;
struct adv_info *adv_instance;
- /* Ignore instance 0 */
+ /* Instance 0x00 always set local name */
if (instance == 0x00)
- return 0;
+ return 1;
adv_instance = hci_find_adv_instance(hdev, instance);
if (!adv_instance)
@@ -1273,6 +1273,14 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
instance_flags = get_adv_instance_flags(hdev, instance);
+ /* If instance already has the flags set skip adding it once
+ * again.
+ */
+ if (adv_instance && eir_get_data(adv_instance->adv_data,
+ adv_instance->adv_data_len, EIR_FLAGS,
+ NULL))
+ goto skip_flags;
+
/* The Add Advertising command allows userspace to set both the general
* and limited discoverable flags.
*/
@@ -1305,6 +1313,7 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
}
}
+skip_flags:
if (adv_instance) {
memcpy(ptr, adv_instance->adv_data,
adv_instance->adv_data_len);
@@ -1690,7 +1699,7 @@ int __hci_req_enable_ext_advertising(struct hci_request *req, u8 instance)
* scheduling it.
*/
if (adv_instance && adv_instance->duration) {
- u16 duration = adv_instance->duration * MSEC_PER_SEC;
+ u16 duration = adv_instance->timeout * MSEC_PER_SEC;
/* Time = N * 10 ms */
adv_set->duration = cpu_to_le16(duration / 10);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index da7fdbdf9c41..a845786258a0 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4936,10 +4936,8 @@ void __l2cap_physical_cfm(struct l2cap_chan *chan, int result)
BT_DBG("chan %p, result %d, local_amp_id %d, remote_amp_id %d",
chan, result, local_amp_id, remote_amp_id);
- if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) {
- l2cap_chan_unlock(chan);
+ if (chan->state == BT_DISCONN || chan->state == BT_CLOSED)
return;
- }
if (chan->state != BT_CONNECTED) {
l2cap_do_create(chan, result, local_amp_id, remote_amp_id);
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 26e8cfad22b8..6b42be4b5861 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -502,15 +502,12 @@ bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16],
const bdaddr_t *bdaddr)
{
struct l2cap_chan *chan = hdev->smp_data;
- struct smp_dev *smp;
u8 hash[3];
int err;
if (!chan || !chan->data)
return false;
- smp = chan->data;
-
BT_DBG("RPA %pMR IRK %*phN", bdaddr, 16, irk);
err = smp_ah(irk, &bdaddr->b[3], hash);
@@ -523,14 +520,11 @@ bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16],
int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa)
{
struct l2cap_chan *chan = hdev->smp_data;
- struct smp_dev *smp;
int err;
if (!chan || !chan->data)
return -EOPNOTSUPP;
- smp = chan->data;
-
get_random_bytes(&rpa->b[3], 3);
rpa->b[5] &= 0x3f; /* Clear two most significant bits */
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 1153bbcdff72..915c2d6f7fb9 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -105,6 +105,40 @@ out:
return err;
}
+/* Integer types of various sizes and pointer combinations cover variety of
+ * architecture dependent calling conventions. 7+ can be supported in the
+ * future.
+ */
+int noinline bpf_fentry_test1(int a)
+{
+ return a + 1;
+}
+
+int noinline bpf_fentry_test2(int a, u64 b)
+{
+ return a + b;
+}
+
+int noinline bpf_fentry_test3(char a, int b, u64 c)
+{
+ return a + b + c;
+}
+
+int noinline bpf_fentry_test4(void *a, char b, int c, u64 d)
+{
+ return (long)a + b + c + d;
+}
+
+int noinline bpf_fentry_test5(u64 a, void *b, short c, int d, u64 e)
+{
+ return a + (long)b + c + d + e;
+}
+
+int noinline bpf_fentry_test6(u64 a, void *b, short c, int d, void *e, u64 f)
+{
+ return a + (long)b + c + d + (long)e + f;
+}
+
static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
u32 headroom, u32 tailroom)
{
@@ -122,6 +156,15 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
kfree(data);
return ERR_PTR(-EFAULT);
}
+ if (bpf_fentry_test1(1) != 2 ||
+ bpf_fentry_test2(2, 3) != 5 ||
+ bpf_fentry_test3(4, 5, 6) != 15 ||
+ bpf_fentry_test4((void *)7, 8, 9, 10) != 34 ||
+ bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 ||
+ bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111) {
+ kfree(data);
+ return ERR_PTR(-EFAULT);
+ }
return data;
}
@@ -218,10 +261,18 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) +
FIELD_SIZEOF(struct __sk_buff, cb),
+ offsetof(struct __sk_buff, tstamp)))
+ return -EINVAL;
+
+ /* tstamp is allowed */
+
+ if (!range_is_zero(__skb, offsetof(struct __sk_buff, tstamp) +
+ FIELD_SIZEOF(struct __sk_buff, tstamp),
sizeof(struct __sk_buff)))
return -EINVAL;
skb->priority = __skb->priority;
+ skb->tstamp = __skb->tstamp;
memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN);
return 0;
@@ -235,6 +286,7 @@ static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb)
return;
__skb->priority = skb->priority;
+ __skb->tstamp = skb->tstamp;
memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN);
}
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 681b72862c16..434effde02c3 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -24,8 +24,6 @@
const struct nf_br_ops __rcu *nf_br_ops __read_mostly;
EXPORT_SYMBOL_GPL(nf_br_ops);
-static struct lock_class_key bridge_netdev_addr_lock_key;
-
/* net device transmit always called with BH disabled */
netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
{
@@ -108,11 +106,6 @@ out:
return NETDEV_TX_OK;
}
-static void br_set_lockdep_class(struct net_device *dev)
-{
- lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key);
-}
-
static int br_dev_init(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
@@ -150,7 +143,6 @@ static int br_dev_init(struct net_device *dev)
br_mdb_hash_fini(br);
br_fdb_hash_fini(br);
}
- br_set_lockdep_class(dev);
return err;
}
@@ -271,6 +263,37 @@ static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info)
strlcpy(info->bus_info, "N/A", sizeof(info->bus_info));
}
+static int br_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct net_bridge *br = netdev_priv(dev);
+ struct net_bridge_port *p;
+
+ cmd->base.duplex = DUPLEX_UNKNOWN;
+ cmd->base.port = PORT_OTHER;
+ cmd->base.speed = SPEED_UNKNOWN;
+
+ list_for_each_entry(p, &br->port_list, list) {
+ struct ethtool_link_ksettings ecmd;
+ struct net_device *pdev = p->dev;
+
+ if (!netif_running(pdev) || !netif_oper_up(pdev))
+ continue;
+
+ if (__ethtool_get_link_ksettings(pdev, &ecmd))
+ continue;
+
+ if (ecmd.base.speed == (__u32)SPEED_UNKNOWN)
+ continue;
+
+ if (cmd->base.speed == (__u32)SPEED_UNKNOWN ||
+ cmd->base.speed < ecmd.base.speed)
+ cmd->base.speed = ecmd.base.speed;
+ }
+
+ return 0;
+}
+
static netdev_features_t br_fix_features(struct net_device *dev,
netdev_features_t features)
{
@@ -373,8 +396,9 @@ static int br_del_slave(struct net_device *dev, struct net_device *slave_dev)
}
static const struct ethtool_ops br_ethtool_ops = {
- .get_drvinfo = br_getinfo,
- .get_link = ethtool_op_get_link,
+ .get_drvinfo = br_getinfo,
+ .get_link = ethtool_op_get_link,
+ .get_link_ksettings = br_get_link_ksettings,
};
static const struct net_device_ops br_netdev_ops = {
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index b1d3248c0252..4877a0db16c6 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -75,8 +75,9 @@ static inline unsigned long hold_time(const struct net_bridge *br)
static inline int has_expired(const struct net_bridge *br,
const struct net_bridge_fdb_entry *fdb)
{
- return !fdb->is_static && !fdb->added_by_external_learn &&
- time_before_eq(fdb->updated + hold_time(br), jiffies);
+ return !test_bit(BR_FDB_STATIC, &fdb->flags) &&
+ !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags) &&
+ time_before_eq(fdb->updated + hold_time(br), jiffies);
}
static void fdb_rcu_free(struct rcu_head *head)
@@ -197,7 +198,7 @@ static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f,
{
trace_fdb_delete(br, f);
- if (f->is_static)
+ if (test_bit(BR_FDB_STATIC, &f->flags))
fdb_del_hw_addr(br, f->key.addr.addr);
hlist_del_init_rcu(&f->fdb_node);
@@ -224,7 +225,7 @@ static void fdb_delete_local(struct net_bridge *br,
if (op != p && ether_addr_equal(op->dev->dev_addr, addr) &&
(!vid || br_vlan_find(vg, vid))) {
f->dst = op;
- f->added_by_user = 0;
+ clear_bit(BR_FDB_ADDED_BY_USER, &f->flags);
return;
}
}
@@ -235,7 +236,7 @@ static void fdb_delete_local(struct net_bridge *br,
if (p && ether_addr_equal(br->dev->dev_addr, addr) &&
(!vid || (v && br_vlan_should_use(v)))) {
f->dst = NULL;
- f->added_by_user = 0;
+ clear_bit(BR_FDB_ADDED_BY_USER, &f->flags);
return;
}
@@ -250,7 +251,8 @@ void br_fdb_find_delete_local(struct net_bridge *br,
spin_lock_bh(&br->hash_lock);
f = br_fdb_find(br, addr, vid);
- if (f && f->is_local && !f->added_by_user && f->dst == p)
+ if (f && test_bit(BR_FDB_LOCAL, &f->flags) &&
+ !test_bit(BR_FDB_ADDED_BY_USER, &f->flags) && f->dst == p)
fdb_delete_local(br, p, f);
spin_unlock_bh(&br->hash_lock);
}
@@ -265,7 +267,8 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
spin_lock_bh(&br->hash_lock);
vg = nbp_vlan_group(p);
hlist_for_each_entry(f, &br->fdb_list, fdb_node) {
- if (f->dst == p && f->is_local && !f->added_by_user) {
+ if (f->dst == p && test_bit(BR_FDB_LOCAL, &f->flags) &&
+ !test_bit(BR_FDB_ADDED_BY_USER, &f->flags)) {
/* delete old one */
fdb_delete_local(br, p, f);
@@ -306,7 +309,8 @@ 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_find(br, br->dev->dev_addr, 0);
- if (f && f->is_local && !f->dst && !f->added_by_user)
+ if (f && test_bit(BR_FDB_LOCAL, &f->flags) &&
+ !f->dst && !test_bit(BR_FDB_ADDED_BY_USER, &f->flags))
fdb_delete_local(br, NULL, f);
fdb_insert(br, NULL, newaddr, 0);
@@ -321,7 +325,8 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
if (!br_vlan_should_use(v))
continue;
f = br_fdb_find(br, br->dev->dev_addr, v->vid);
- if (f && f->is_local && !f->dst && !f->added_by_user)
+ if (f && test_bit(BR_FDB_LOCAL, &f->flags) &&
+ !f->dst && !test_bit(BR_FDB_ADDED_BY_USER, &f->flags))
fdb_delete_local(br, NULL, f);
fdb_insert(br, NULL, newaddr, v->vid);
}
@@ -346,7 +351,8 @@ void br_fdb_cleanup(struct work_struct *work)
hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) {
unsigned long this_timer;
- if (f->is_static || f->added_by_external_learn)
+ if (test_bit(BR_FDB_STATIC, &f->flags) ||
+ test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags))
continue;
this_timer = f->updated + delay;
if (time_after(this_timer, now)) {
@@ -373,7 +379,7 @@ void br_fdb_flush(struct net_bridge *br)
spin_lock_bh(&br->hash_lock);
hlist_for_each_entry_safe(f, tmp, &br->fdb_list, fdb_node) {
- if (!f->is_static)
+ if (!test_bit(BR_FDB_STATIC, &f->flags))
fdb_delete(br, f, true);
}
spin_unlock_bh(&br->hash_lock);
@@ -397,10 +403,11 @@ void br_fdb_delete_by_port(struct net_bridge *br,
continue;
if (!do_all)
- if (f->is_static || (vid && f->key.vlan_id != vid))
+ if (test_bit(BR_FDB_STATIC, &f->flags) ||
+ (vid && f->key.vlan_id != vid))
continue;
- if (f->is_local)
+ if (test_bit(BR_FDB_LOCAL, &f->flags))
fdb_delete_local(br, p, f);
else
fdb_delete(br, f, true);
@@ -469,8 +476,8 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf,
fe->port_no = f->dst->port_no;
fe->port_hi = f->dst->port_no >> 8;
- fe->is_local = f->is_local;
- if (!f->is_static)
+ fe->is_local = test_bit(BR_FDB_LOCAL, &f->flags);
+ if (!test_bit(BR_FDB_STATIC, &f->flags))
fe->ageing_timer_value = jiffies_delta_to_clock_t(jiffies - f->updated);
++fe;
++num;
@@ -484,8 +491,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct net_bridge *br,
struct net_bridge_port *source,
const unsigned char *addr,
__u16 vid,
- unsigned char is_local,
- unsigned char is_static)
+ unsigned long flags)
{
struct net_bridge_fdb_entry *fdb;
@@ -494,12 +500,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct net_bridge *br,
memcpy(fdb->key.addr.addr, addr, ETH_ALEN);
fdb->dst = source;
fdb->key.vlan_id = vid;
- fdb->is_local = is_local;
- fdb->is_static = is_static;
- fdb->added_by_user = 0;
- fdb->added_by_external_learn = 0;
- fdb->offloaded = 0;
- fdb->is_sticky = 0;
+ fdb->flags = flags;
fdb->updated = fdb->used = jiffies;
if (rhashtable_lookup_insert_fast(&br->fdb_hash_tbl,
&fdb->rhnode,
@@ -526,14 +527,15 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
/* it is okay to have multiple ports with same
* address, just use the first one.
*/
- if (fdb->is_local)
+ if (test_bit(BR_FDB_LOCAL, &fdb->flags))
return 0;
br_warn(br, "adding interface %s with same address as a received packet (addr:%pM, vlan:%u)\n",
source ? source->dev->name : br->dev->name, addr, vid);
fdb_delete(br, fdb, true);
}
- fdb = fdb_create(br, source, addr, vid, 1, 1);
+ fdb = fdb_create(br, source, addr, vid,
+ BIT(BR_FDB_LOCAL) | BIT(BR_FDB_STATIC));
if (!fdb)
return -ENOMEM;
@@ -555,7 +557,7 @@ int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
}
void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
- const unsigned char *addr, u16 vid, bool added_by_user)
+ const unsigned char *addr, u16 vid, unsigned long flags)
{
struct net_bridge_fdb_entry *fdb;
bool fdb_modified = false;
@@ -564,15 +566,10 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
if (hold_time(br) == 0)
return;
- /* ignore packets unless we are using this port */
- if (!(source->state == BR_STATE_LEARNING ||
- source->state == BR_STATE_FORWARDING))
- return;
-
fdb = fdb_find_rcu(&br->fdb_hash_tbl, addr, vid);
if (likely(fdb)) {
/* attempt to update an entry for a local interface */
- if (unlikely(fdb->is_local)) {
+ if (unlikely(test_bit(BR_FDB_LOCAL, &fdb->flags))) {
if (net_ratelimit())
br_warn(br, "received packet on %s with own address as source address (addr:%pM, vlan:%u)\n",
source->dev->name, addr, vid);
@@ -580,30 +577,30 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
unsigned long now = jiffies;
/* fastpath: update of existing entry */
- if (unlikely(source != fdb->dst && !fdb->is_sticky)) {
+ if (unlikely(source != fdb->dst &&
+ !test_bit(BR_FDB_STICKY, &fdb->flags))) {
fdb->dst = source;
fdb_modified = true;
/* Take over HW learned entry */
- if (unlikely(fdb->added_by_external_learn))
- fdb->added_by_external_learn = 0;
+ if (unlikely(test_bit(BR_FDB_ADDED_BY_EXT_LEARN,
+ &fdb->flags)))
+ clear_bit(BR_FDB_ADDED_BY_EXT_LEARN,
+ &fdb->flags);
}
if (now != fdb->updated)
fdb->updated = now;
- if (unlikely(added_by_user))
- fdb->added_by_user = 1;
+ if (unlikely(test_bit(BR_FDB_ADDED_BY_USER, &flags)))
+ set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
if (unlikely(fdb_modified)) {
- trace_br_fdb_update(br, source, addr, vid, added_by_user);
+ trace_br_fdb_update(br, source, addr, vid, flags);
fdb_notify(br, fdb, RTM_NEWNEIGH, true);
}
}
} else {
spin_lock(&br->hash_lock);
- fdb = fdb_create(br, source, addr, vid, 0, 0);
+ fdb = fdb_create(br, source, addr, vid, flags);
if (fdb) {
- if (unlikely(added_by_user))
- fdb->added_by_user = 1;
- trace_br_fdb_update(br, source, addr, vid,
- added_by_user);
+ trace_br_fdb_update(br, source, addr, vid, flags);
fdb_notify(br, fdb, RTM_NEWNEIGH, true);
}
/* else we lose race and someone else inserts
@@ -616,9 +613,9 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
static int fdb_to_nud(const struct net_bridge *br,
const struct net_bridge_fdb_entry *fdb)
{
- if (fdb->is_local)
+ if (test_bit(BR_FDB_LOCAL, &fdb->flags))
return NUD_PERMANENT;
- else if (fdb->is_static)
+ else if (test_bit(BR_FDB_STATIC, &fdb->flags))
return NUD_NOARP;
else if (has_expired(br, fdb))
return NUD_STALE;
@@ -648,11 +645,11 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex;
ndm->ndm_state = fdb_to_nud(br, fdb);
- if (fdb->offloaded)
+ if (test_bit(BR_FDB_OFFLOADED, &fdb->flags))
ndm->ndm_flags |= NTF_OFFLOADED;
- if (fdb->added_by_external_learn)
+ if (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags))
ndm->ndm_flags |= NTF_EXT_LEARNED;
- if (fdb->is_sticky)
+ if (test_bit(BR_FDB_STICKY, &fdb->flags))
ndm->ndm_flags |= NTF_STICKY;
if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.addr))
@@ -799,7 +796,7 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
const u8 *addr, u16 state, u16 flags, u16 vid,
u8 ndm_flags)
{
- u8 is_sticky = !!(ndm_flags & NTF_STICKY);
+ bool is_sticky = !!(ndm_flags & NTF_STICKY);
struct net_bridge_fdb_entry *fdb;
bool modified = false;
@@ -823,7 +820,7 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
if (!(flags & NLM_F_CREATE))
return -ENOENT;
- fdb = fdb_create(br, source, addr, vid, 0, 0);
+ fdb = fdb_create(br, source, addr, vid, 0);
if (!fdb)
return -ENOMEM;
@@ -840,34 +837,28 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
if (fdb_to_nud(br, fdb) != state) {
if (state & NUD_PERMANENT) {
- fdb->is_local = 1;
- if (!fdb->is_static) {
- fdb->is_static = 1;
+ set_bit(BR_FDB_LOCAL, &fdb->flags);
+ if (!test_and_set_bit(BR_FDB_STATIC, &fdb->flags))
fdb_add_hw_addr(br, addr);
- }
} else if (state & NUD_NOARP) {
- fdb->is_local = 0;
- if (!fdb->is_static) {
- fdb->is_static = 1;
+ clear_bit(BR_FDB_LOCAL, &fdb->flags);
+ if (!test_and_set_bit(BR_FDB_STATIC, &fdb->flags))
fdb_add_hw_addr(br, addr);
- }
} else {
- fdb->is_local = 0;
- if (fdb->is_static) {
- fdb->is_static = 0;
+ clear_bit(BR_FDB_LOCAL, &fdb->flags);
+ if (test_and_clear_bit(BR_FDB_STATIC, &fdb->flags))
fdb_del_hw_addr(br, addr);
- }
}
modified = true;
}
- if (is_sticky != fdb->is_sticky) {
- fdb->is_sticky = is_sticky;
+ if (is_sticky != test_bit(BR_FDB_STICKY, &fdb->flags)) {
+ change_bit(BR_FDB_STICKY, &fdb->flags);
modified = true;
}
- fdb->added_by_user = 1;
+ set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
fdb->used = jiffies;
if (modified) {
@@ -890,9 +881,12 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
br->dev->name);
return -EINVAL;
}
+ if (!nbp_state_should_learn(p))
+ return 0;
+
local_bh_disable();
rcu_read_lock();
- br_fdb_update(br, p, addr, vid, true);
+ br_fdb_update(br, p, addr, vid, BIT(BR_FDB_ADDED_BY_USER));
rcu_read_unlock();
local_bh_enable();
} else if (ndm->ndm_flags & NTF_EXT_LEARNED) {
@@ -1064,7 +1058,7 @@ int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p)
rcu_read_lock();
hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) {
/* We only care for static entries */
- if (!f->is_static)
+ if (!test_bit(BR_FDB_STATIC, &f->flags))
continue;
err = dev_uc_add(p->dev, f->key.addr.addr);
if (err)
@@ -1078,7 +1072,7 @@ done:
rollback:
hlist_for_each_entry_rcu(tmp, &br->fdb_list, fdb_node) {
/* We only care for static entries */
- if (!tmp->is_static)
+ if (!test_bit(BR_FDB_STATIC, &tmp->flags))
continue;
if (tmp == f)
break;
@@ -1097,7 +1091,7 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p)
rcu_read_lock();
hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) {
/* We only care for static entries */
- if (!f->is_static)
+ if (!test_bit(BR_FDB_STATIC, &f->flags))
continue;
dev_uc_del(p->dev, f->key.addr.addr);
@@ -1119,14 +1113,15 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
fdb = br_fdb_find(br, addr, vid);
if (!fdb) {
- fdb = fdb_create(br, p, addr, vid, 0, 0);
+ unsigned long flags = BIT(BR_FDB_ADDED_BY_EXT_LEARN);
+
+ if (swdev_notify)
+ flags |= BIT(BR_FDB_ADDED_BY_USER);
+ fdb = fdb_create(br, p, addr, vid, flags);
if (!fdb) {
err = -ENOMEM;
goto err_unlock;
}
- if (swdev_notify)
- fdb->added_by_user = 1;
- fdb->added_by_external_learn = 1;
fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify);
} else {
fdb->updated = jiffies;
@@ -1136,17 +1131,17 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
modified = true;
}
- if (fdb->added_by_external_learn) {
+ if (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) {
/* Refresh entry */
fdb->used = jiffies;
- } else if (!fdb->added_by_user) {
+ } else if (!test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags)) {
/* Take over SW learned entry */
- fdb->added_by_external_learn = 1;
+ set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags);
modified = true;
}
if (swdev_notify)
- fdb->added_by_user = 1;
+ set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
if (modified)
fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify);
@@ -1168,7 +1163,7 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
spin_lock_bh(&br->hash_lock);
fdb = br_fdb_find(br, addr, vid);
- if (fdb && fdb->added_by_external_learn)
+ if (fdb && test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags))
fdb_delete(br, fdb, swdev_notify);
else
err = -ENOENT;
@@ -1186,8 +1181,8 @@ void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p,
spin_lock_bh(&br->hash_lock);
fdb = br_fdb_find(br, addr, vid);
- if (fdb)
- fdb->offloaded = offloaded;
+ if (fdb && offloaded != test_bit(BR_FDB_OFFLOADED, &fdb->flags))
+ change_bit(BR_FDB_OFFLOADED, &fdb->flags);
spin_unlock_bh(&br->hash_lock);
}
@@ -1206,7 +1201,7 @@ void br_fdb_clear_offload(const struct net_device *dev, u16 vid)
spin_lock_bh(&p->br->hash_lock);
hlist_for_each_entry(f, &p->br->fdb_list, fdb_node) {
if (f->dst == p && f->key.vlan_id == vid)
- f->offloaded = 0;
+ clear_bit(BR_FDB_OFFLOADED, &f->flags);
}
spin_unlock_bh(&p->br->hash_lock);
}
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 09b1dd8cd853..8944ceb47fe9 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -88,7 +88,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
/* insert into forwarding database after filtering to avoid spoofing */
br = p->br;
if (p->flags & BR_LEARNING)
- br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
+ br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0);
local_rcv = !!(br->dev->flags & IFF_PROMISC);
if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
@@ -151,7 +151,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
if (dst) {
unsigned long now = jiffies;
- if (dst->is_local)
+ if (test_bit(BR_FDB_LOCAL, &dst->flags))
return br_pass_frame_up(skb);
if (now != dst->used)
@@ -182,9 +182,10 @@ static void __br_handle_local_finish(struct sk_buff *skb)
/* check if vlan is allowed, to avoid spoofing */
if ((p->flags & BR_LEARNING) &&
+ nbp_state_should_learn(p) &&
!br_opt_get(p->br, BROPT_NO_LL_LEARN) &&
br_should_learn(p, skb, &vid))
- br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
+ br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, 0);
}
/* note: already called with rcu_read_lock */
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index ce2ab14ee605..36b0367ca1e0 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -172,6 +172,16 @@ struct net_bridge_vlan_group {
u16 pvid;
};
+/* bridge fdb flags */
+enum {
+ BR_FDB_LOCAL,
+ BR_FDB_STATIC,
+ BR_FDB_STICKY,
+ BR_FDB_ADDED_BY_USER,
+ BR_FDB_ADDED_BY_EXT_LEARN,
+ BR_FDB_OFFLOADED,
+};
+
struct net_bridge_fdb_key {
mac_addr addr;
u16 vlan_id;
@@ -183,12 +193,7 @@ struct net_bridge_fdb_entry {
struct net_bridge_fdb_key key;
struct hlist_node fdb_node;
- unsigned char is_local:1,
- is_static:1,
- is_sticky:1,
- added_by_user:1,
- added_by_external_learn:1,
- offloaded:1;
+ unsigned long flags;
/* write-heavy members should not affect lookups */
unsigned long updated ____cacheline_aligned_in_smp;
@@ -495,6 +500,11 @@ static inline bool br_vlan_should_use(const struct net_bridge_vlan *v)
return true;
}
+static inline bool nbp_state_should_learn(const struct net_bridge_port *p)
+{
+ return p->state == BR_STATE_LEARNING || p->state == BR_STATE_FORWARDING;
+}
+
static inline int br_opt_get(const struct net_bridge *br,
enum net_bridge_opts opt)
{
@@ -566,7 +576,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, unsigned long count,
int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr, u16 vid);
void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
- const unsigned char *addr, u16 vid, bool added_by_user);
+ const unsigned char *addr, u16 vid, unsigned long flags);
int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev, const unsigned char *addr, u16 vid);
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index 921310d3cbae..015209bf44aa 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -129,15 +129,19 @@ br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
br_switchdev_fdb_call_notifiers(false, fdb->key.addr.addr,
fdb->key.vlan_id,
fdb->dst->dev,
- fdb->added_by_user,
- fdb->offloaded);
+ test_bit(BR_FDB_ADDED_BY_USER,
+ &fdb->flags),
+ test_bit(BR_FDB_OFFLOADED,
+ &fdb->flags));
break;
case RTM_NEWNEIGH:
br_switchdev_fdb_call_notifiers(true, fdb->key.addr.addr,
fdb->key.vlan_id,
fdb->dst->dev,
- fdb->added_by_user,
- fdb->offloaded);
+ test_bit(BR_FDB_ADDED_BY_USER,
+ &fdb->flags),
+ test_bit(BR_FDB_OFFLOADED,
+ &fdb->flags));
break;
}
}
diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c
index ed91ea31978a..12a4f4d93681 100644
--- a/net/bridge/netfilter/ebt_dnat.c
+++ b/net/bridge/netfilter/ebt_dnat.c
@@ -20,7 +20,6 @@ static unsigned int
ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ebt_nat_info *info = par->targinfo;
- struct net_device *dev;
if (skb_ensure_writable(skb, ETH_ALEN))
return EBT_DROP;
@@ -33,10 +32,22 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
else
skb->pkt_type = PACKET_MULTICAST;
} else {
- if (xt_hooknum(par) != NF_BR_BROUTING)
- dev = br_port_get_rcu(xt_in(par))->br->dev;
- else
+ const struct net_device *dev;
+
+ switch (xt_hooknum(par)) {
+ case NF_BR_BROUTING:
dev = xt_in(par);
+ break;
+ case NF_BR_PRE_ROUTING:
+ dev = br_port_get_rcu(xt_in(par))->br->dev;
+ break;
+ default:
+ dev = NULL;
+ break;
+ }
+
+ if (!dev) /* NF_BR_LOCAL_OUT */
+ return info->target;
if (ether_addr_equal(info->mac, dev->dev_addr))
skb->pkt_type = PACKET_HOST;
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 506d6141e44e..809673222382 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -95,7 +95,7 @@ slow_path:
* This may also be a clone skbuff, we could preserve the geometry for
* the copies but probably not worth the effort.
*/
- ip_frag_init(skb, hlen, ll_rs, frag_max_size, &state);
+ ip_frag_init(skb, hlen, ll_rs, frag_max_size, false, &state);
while (state.left > 0) {
struct sk_buff *skb2;
diff --git a/net/caif/Kconfig b/net/caif/Kconfig
index eb83051c8330..b7532a79ca7a 100644
--- a/net/caif/Kconfig
+++ b/net/caif/Kconfig
@@ -13,11 +13,11 @@ menuconfig CAIF
with its modems. It is accessed from user space as sockets (PF_CAIF).
Say Y (or M) here if you build for a phone product (e.g. Android or
- MeeGo ) that uses CAIF as transport, if unsure say N.
+ MeeGo) that uses CAIF as transport. If unsure say N.
If you select to build it as module then CAIF_NETDEV also needs to be
- built as modules. You will also need to say yes to any CAIF physical
- devices that your platform requires.
+ built as a module. You will also need to say Y (or M) to any CAIF
+ physical devices that your platform requires.
See Documentation/networking/caif for a further explanation on how to
use and configure CAIF.
@@ -37,7 +37,7 @@ config CAIF_NETDEV
default CAIF
---help---
Say Y if you will be using a CAIF based GPRS network device.
- This can be either built-in or a loadable module,
+ This can be either built-in or a loadable module.
If you select to build it as a built-in then the main CAIF device must
also be a built-in.
If unsure say Y.
@@ -48,7 +48,7 @@ config CAIF_USB
default n
---help---
Say Y if you are using CAIF over USB CDC NCM.
- This can be either built-in or a loadable module,
+ This can be either built-in or a loadable module.
If you select to build it as a built-in then the main CAIF device must
also be a built-in.
If unsure say N.
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 13ea920600ae..ef14da50a981 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -953,7 +953,7 @@ static __poll_t caif_poll(struct file *file,
mask |= EPOLLRDHUP;
/* readable? */
- if (!skb_queue_empty(&sk->sk_receive_queue) ||
+ if (!skb_queue_empty_lockless(&sk->sk_receive_queue) ||
(sk->sk_shutdown & RCV_SHUTDOWN))
mask |= EPOLLIN | EPOLLRDNORM;
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 5518a7d9eed9..128d37a4c2e0 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -86,11 +86,12 @@ static atomic_t skbcounter = ATOMIC_INIT(0);
/* af_can socket functions */
-static void can_sock_destruct(struct sock *sk)
+void can_sock_destruct(struct sock *sk)
{
skb_queue_purge(&sk->sk_receive_queue);
skb_queue_purge(&sk->sk_error_queue);
}
+EXPORT_SYMBOL(can_sock_destruct);
static const struct can_proto *can_get_proto(int protocol)
{
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index def2f813ffce..137054bff9ec 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -51,6 +51,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data)
if (!skb)
return;
+ j1939_priv_get(priv);
can_skb_set_owner(skb, iskb->sk);
/* get a pointer to the header of the skb
@@ -104,6 +105,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data)
j1939_simple_recv(priv, skb);
j1939_sk_recv(priv, skb);
done:
+ j1939_priv_put(priv);
kfree_skb(skb);
}
@@ -150,6 +152,10 @@ static void __j1939_priv_release(struct kref *kref)
netdev_dbg(priv->ndev, "%s: 0x%p\n", __func__, priv);
+ WARN_ON_ONCE(!list_empty(&priv->active_session_list));
+ WARN_ON_ONCE(!list_empty(&priv->ecus));
+ WARN_ON_ONCE(!list_empty(&priv->j1939_socks));
+
dev_put(ndev);
kfree(priv);
}
@@ -207,6 +213,9 @@ static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev)
{
struct can_ml_priv *can_ml_priv = ndev->ml_priv;
+ if (!can_ml_priv)
+ return NULL;
+
return can_ml_priv->j1939_priv;
}
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 37c1040bcb9c..de09b0a65791 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -78,7 +78,6 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk)
{
jsk->state |= J1939_SOCK_BOUND;
j1939_priv_get(priv);
- jsk->priv = priv;
spin_lock_bh(&priv->j1939_socks_lock);
list_add_tail(&jsk->list, &priv->j1939_socks);
@@ -91,7 +90,6 @@ static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk)
list_del_init(&jsk->list);
spin_unlock_bh(&priv->j1939_socks_lock);
- jsk->priv = NULL;
j1939_priv_put(priv);
jsk->state &= ~J1939_SOCK_BOUND;
}
@@ -349,6 +347,34 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb)
spin_unlock_bh(&priv->j1939_socks_lock);
}
+static void j1939_sk_sock_destruct(struct sock *sk)
+{
+ struct j1939_sock *jsk = j1939_sk(sk);
+
+ /* This function will be call by the generic networking code, when then
+ * the socket is ultimately closed (sk->sk_destruct).
+ *
+ * The race between
+ * - processing a received CAN frame
+ * (can_receive -> j1939_can_recv)
+ * and accessing j1939_priv
+ * ... and ...
+ * - closing a socket
+ * (j1939_can_rx_unregister -> can_rx_unregister)
+ * and calling the final j1939_priv_put()
+ *
+ * is avoided by calling the final j1939_priv_put() from this
+ * RCU deferred cleanup call.
+ */
+ if (jsk->priv) {
+ j1939_priv_put(jsk->priv);
+ jsk->priv = NULL;
+ }
+
+ /* call generic CAN sock destruct */
+ can_sock_destruct(sk);
+}
+
static int j1939_sk_init(struct sock *sk)
{
struct j1939_sock *jsk = j1939_sk(sk);
@@ -371,6 +397,7 @@ static int j1939_sk_init(struct sock *sk)
atomic_set(&jsk->skb_pending, 0);
spin_lock_init(&jsk->sk_session_queue_lock);
INIT_LIST_HEAD(&jsk->sk_session_queue);
+ sk->sk_destruct = j1939_sk_sock_destruct;
return 0;
}
@@ -443,6 +470,12 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len)
}
jsk->ifindex = addr->can_ifindex;
+
+ /* the corresponding j1939_priv_put() is called via
+ * sk->sk_destruct, which points to j1939_sk_sock_destruct()
+ */
+ j1939_priv_get(priv);
+ jsk->priv = priv;
}
/* set default transmit pgn */
@@ -560,8 +593,8 @@ static int j1939_sk_release(struct socket *sock)
if (!sk)
return 0;
- jsk = j1939_sk(sk);
lock_sock(sk);
+ jsk = j1939_sk(sk);
if (jsk->state & J1939_SOCK_BOUND) {
struct j1939_priv *priv = jsk->priv;
@@ -580,6 +613,7 @@ static int j1939_sk_release(struct socket *sock)
j1939_netdev_stop(priv);
}
+ kfree(jsk->filters);
sock_orphan(sk);
sock->sk = NULL;
@@ -909,8 +943,10 @@ void j1939_sk_errqueue(struct j1939_session *session,
memset(serr, 0, sizeof(*serr));
switch (type) {
case J1939_ERRQUEUE_ACK:
- if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK))
+ if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) {
+ kfree_skb(skb);
return;
+ }
serr->ee.ee_errno = ENOMSG;
serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
@@ -918,8 +954,10 @@ void j1939_sk_errqueue(struct j1939_session *session,
state = "ACK";
break;
case J1939_ERRQUEUE_SCHED:
- if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED))
+ if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) {
+ kfree_skb(skb);
return;
+ }
serr->ee.ee_errno = ENOMSG;
serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
@@ -1054,51 +1092,72 @@ static int j1939_sk_sendmsg(struct socket *sock, struct msghdr *msg,
{
struct sock *sk = sock->sk;
struct j1939_sock *jsk = j1939_sk(sk);
- struct j1939_priv *priv = jsk->priv;
+ struct j1939_priv *priv;
int ifindex;
int ret;
+ lock_sock(sock->sk);
/* various socket state tests */
- if (!(jsk->state & J1939_SOCK_BOUND))
- return -EBADFD;
+ if (!(jsk->state & J1939_SOCK_BOUND)) {
+ ret = -EBADFD;
+ goto sendmsg_done;
+ }
+ priv = jsk->priv;
ifindex = jsk->ifindex;
- if (!jsk->addr.src_name && jsk->addr.sa == J1939_NO_ADDR)
+ if (!jsk->addr.src_name && jsk->addr.sa == J1939_NO_ADDR) {
/* no source address assigned yet */
- return -EBADFD;
+ ret = -EBADFD;
+ goto sendmsg_done;
+ }
/* deal with provided destination address info */
if (msg->msg_name) {
struct sockaddr_can *addr = msg->msg_name;
- if (msg->msg_namelen < J1939_MIN_NAMELEN)
- return -EINVAL;
+ if (msg->msg_namelen < J1939_MIN_NAMELEN) {
+ ret = -EINVAL;
+ goto sendmsg_done;
+ }
- if (addr->can_family != AF_CAN)
- return -EINVAL;
+ if (addr->can_family != AF_CAN) {
+ ret = -EINVAL;
+ goto sendmsg_done;
+ }
- if (addr->can_ifindex && addr->can_ifindex != ifindex)
- return -EBADFD;
+ if (addr->can_ifindex && addr->can_ifindex != ifindex) {
+ ret = -EBADFD;
+ goto sendmsg_done;
+ }
if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn) &&
- !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn))
- return -EINVAL;
+ !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) {
+ ret = -EINVAL;
+ goto sendmsg_done;
+ }
if (!addr->can_addr.j1939.name &&
addr->can_addr.j1939.addr == J1939_NO_ADDR &&
- !sock_flag(sk, SOCK_BROADCAST))
+ !sock_flag(sk, SOCK_BROADCAST)) {
/* broadcast, but SO_BROADCAST not set */
- return -EACCES;
+ ret = -EACCES;
+ goto sendmsg_done;
+ }
} else {
if (!jsk->addr.dst_name && jsk->addr.da == J1939_NO_ADDR &&
- !sock_flag(sk, SOCK_BROADCAST))
+ !sock_flag(sk, SOCK_BROADCAST)) {
/* broadcast, but SO_BROADCAST not set */
- return -EACCES;
+ ret = -EACCES;
+ goto sendmsg_done;
+ }
}
ret = j1939_sk_send_loop(priv, sk, msg, size);
+sendmsg_done:
+ release_sock(sock->sk);
+
return ret;
}
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index fe000ea757ea..9f99af5b0b11 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -255,6 +255,7 @@ static void __j1939_session_drop(struct j1939_session *session)
return;
j1939_sock_pending_del(session->sk);
+ sock_put(session->sk);
}
static void j1939_session_destroy(struct j1939_session *session)
@@ -266,6 +267,9 @@ static void j1939_session_destroy(struct j1939_session *session)
netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session);
+ WARN_ON_ONCE(!list_empty(&session->sk_session_queue_entry));
+ WARN_ON_ONCE(!list_empty(&session->active_session_list_entry));
+
skb_queue_purge(&session->skb_queue);
__j1939_session_drop(session);
j1939_priv_put(session->priv);
@@ -1042,12 +1046,13 @@ j1939_session_deactivate_activate_next(struct j1939_session *session)
j1939_sk_queue_activate_next(session);
}
-static void j1939_session_cancel(struct j1939_session *session,
+static void __j1939_session_cancel(struct j1939_session *session,
enum j1939_xtp_abort err)
{
struct j1939_priv *priv = session->priv;
WARN_ON_ONCE(!err);
+ lockdep_assert_held(&session->priv->active_session_list_lock);
session->err = j1939_xtp_abort_to_errno(priv, err);
/* do not send aborts on incoming broadcasts */
@@ -1062,6 +1067,20 @@ static void j1939_session_cancel(struct j1939_session *session,
j1939_sk_send_loop_abort(session->sk, session->err);
}
+static void j1939_session_cancel(struct j1939_session *session,
+ enum j1939_xtp_abort err)
+{
+ j1939_session_list_lock(session->priv);
+
+ if (session->state >= J1939_SESSION_ACTIVE &&
+ session->state < J1939_SESSION_WAITING_ABORT) {
+ j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS);
+ __j1939_session_cancel(session, err);
+ }
+
+ j1939_session_list_unlock(session->priv);
+}
+
static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer)
{
struct j1939_session *session =
@@ -1108,8 +1127,6 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer)
netdev_alert(priv->ndev, "%s: 0x%p: tx aborted with unknown reason: %i\n",
__func__, session, ret);
if (session->skcb.addr.type != J1939_SIMPLE) {
- j1939_tp_set_rxtimeout(session,
- J1939_XTP_ABORT_TIMEOUT_MS);
j1939_session_cancel(session, J1939_XTP_ABORT_OTHER);
} else {
session->err = ret;
@@ -1169,7 +1186,7 @@ static enum hrtimer_restart j1939_tp_rxtimer(struct hrtimer *hrtimer)
hrtimer_start(&session->rxtimer,
ms_to_ktime(J1939_XTP_ABORT_TIMEOUT_MS),
HRTIMER_MODE_REL_SOFT);
- j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT);
+ __j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT);
}
j1939_session_list_unlock(session->priv);
}
@@ -1273,9 +1290,27 @@ j1939_xtp_rx_abort(struct j1939_priv *priv, struct sk_buff *skb,
static void
j1939_xtp_rx_eoma_one(struct j1939_session *session, struct sk_buff *skb)
{
+ struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb);
+ const u8 *dat;
+ int len;
+
if (j1939_xtp_rx_cmd_bad_pgn(session, skb))
return;
+ dat = skb->data;
+
+ if (skcb->addr.type == J1939_ETP)
+ len = j1939_etp_ctl_to_size(dat);
+ else
+ len = j1939_tp_ctl_to_size(dat);
+
+ if (session->total_message_size != len) {
+ netdev_warn_once(session->priv->ndev,
+ "%s: 0x%p: Incorrect size. Expected: %i; got: %i.\n",
+ __func__, session, session->total_message_size,
+ len);
+ }
+
netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session);
session->pkt.tx_acked = session->pkt.total;
@@ -1357,7 +1392,6 @@ j1939_xtp_rx_cts_one(struct j1939_session *session, struct sk_buff *skb)
out_session_cancel:
j1939_session_timers_cancel(session);
- j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS);
j1939_session_cancel(session, err);
}
@@ -1432,7 +1466,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv,
skcb = j1939_skb_to_cb(skb);
memcpy(skcb, rel_skcb, sizeof(*skcb));
- session = j1939_session_new(priv, skb, skb->len);
+ session = j1939_session_new(priv, skb, size);
if (!session) {
kfree_skb(skb);
return NULL;
@@ -1554,7 +1588,6 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session,
/* RTS on active session */
j1939_session_timers_cancel(session);
- j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS);
j1939_session_cancel(session, J1939_XTP_ABORT_BUSY);
}
@@ -1565,7 +1598,6 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session,
session->last_cmd);
j1939_session_timers_cancel(session);
- j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS);
j1939_session_cancel(session, J1939_XTP_ABORT_BUSY);
return -EBUSY;
@@ -1767,7 +1799,6 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
out_session_cancel:
j1939_session_timers_cancel(session);
- j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS);
j1939_session_cancel(session, J1939_XTP_ABORT_FAULT);
j1939_session_put(session);
}
@@ -1848,6 +1879,7 @@ struct j1939_session *j1939_tp_send(struct j1939_priv *priv,
return ERR_PTR(-ENOMEM);
/* skb is recounted in j1939_session_new() */
+ sock_hold(skb->sk);
session->sk = skb->sk;
session->transmission = true;
session->pkt.total = (size + 6) / 7;
@@ -2010,7 +2042,11 @@ int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk)
&priv->active_session_list,
active_session_list_entry) {
if (!sk || sk == session->sk) {
- j1939_session_timers_cancel(session);
+ if (hrtimer_try_to_cancel(&session->txtimer) == 1)
+ j1939_session_put(session);
+ if (hrtimer_try_to_cancel(&session->rxtimer) == 1)
+ j1939_session_put(session);
+
session->err = ESHUTDOWN;
j1939_session_deactivate_locked(session);
}
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index da5639a5bd3b..458be6b3eda9 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -798,7 +798,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
* Try to grab map refcnt to make sure that it's still
* alive and prevent concurrent removal.
*/
- map = bpf_map_inc_not_zero(&smap->map, false);
+ map = bpf_map_inc_not_zero(&smap->map);
if (IS_ERR(map))
continue;
diff --git a/net/core/datagram.c b/net/core/datagram.c
index c210fc116103..da3c24ed129c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -97,7 +97,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
if (error)
goto out_err;
- if (sk->sk_receive_queue.prev != skb)
+ if (READ_ONCE(sk->sk_receive_queue.prev) != skb)
goto out;
/* Socket shut down? */
@@ -278,7 +278,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
break;
sk_busy_loop(sk, flags & MSG_DONTWAIT);
- } while (sk->sk_receive_queue.prev != *last);
+ } while (READ_ONCE(sk->sk_receive_queue.prev) != *last);
error = -EAGAIN;
@@ -767,7 +767,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
mask = 0;
/* exceptional events? */
- if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+ if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
mask |= EPOLLERR |
(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
@@ -777,7 +777,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
mask |= EPOLLHUP;
/* readable? */
- if (!skb_queue_empty(&sk->sk_receive_queue))
+ if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
diff --git a/net/core/dev.c b/net/core/dev.c
index c5d8882d100f..46580b290450 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -146,6 +146,7 @@
#include "net-sysfs.h"
#define MAX_GRO_SKBS 8
+#define MAX_NEST_DEV 8
/* This should be increased if a protocol with a bigger head is added. */
#define GRO_MAX_HEAD (MAX_HEADER + 128)
@@ -228,6 +229,122 @@ static inline void rps_unlock(struct softnet_data *sd)
#endif
}
+static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev,
+ const char *name)
+{
+ struct netdev_name_node *name_node;
+
+ name_node = kmalloc(sizeof(*name_node), GFP_KERNEL);
+ if (!name_node)
+ return NULL;
+ INIT_HLIST_NODE(&name_node->hlist);
+ name_node->dev = dev;
+ name_node->name = name;
+ return name_node;
+}
+
+static struct netdev_name_node *
+netdev_name_node_head_alloc(struct net_device *dev)
+{
+ struct netdev_name_node *name_node;
+
+ name_node = netdev_name_node_alloc(dev, dev->name);
+ if (!name_node)
+ return NULL;
+ INIT_LIST_HEAD(&name_node->list);
+ return name_node;
+}
+
+static void netdev_name_node_free(struct netdev_name_node *name_node)
+{
+ kfree(name_node);
+}
+
+static void netdev_name_node_add(struct net *net,
+ struct netdev_name_node *name_node)
+{
+ hlist_add_head_rcu(&name_node->hlist,
+ dev_name_hash(net, name_node->name));
+}
+
+static void netdev_name_node_del(struct netdev_name_node *name_node)
+{
+ hlist_del_rcu(&name_node->hlist);
+}
+
+static struct netdev_name_node *netdev_name_node_lookup(struct net *net,
+ const char *name)
+{
+ struct hlist_head *head = dev_name_hash(net, name);
+ struct netdev_name_node *name_node;
+
+ hlist_for_each_entry(name_node, head, hlist)
+ if (!strcmp(name_node->name, name))
+ return name_node;
+ return NULL;
+}
+
+static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net,
+ const char *name)
+{
+ struct hlist_head *head = dev_name_hash(net, name);
+ struct netdev_name_node *name_node;
+
+ hlist_for_each_entry_rcu(name_node, head, hlist)
+ if (!strcmp(name_node->name, name))
+ return name_node;
+ return NULL;
+}
+
+int netdev_name_node_alt_create(struct net_device *dev, const char *name)
+{
+ struct netdev_name_node *name_node;
+ struct net *net = dev_net(dev);
+
+ name_node = netdev_name_node_lookup(net, name);
+ if (name_node)
+ return -EEXIST;
+ name_node = netdev_name_node_alloc(dev, name);
+ if (!name_node)
+ return -ENOMEM;
+ netdev_name_node_add(net, name_node);
+ /* The node that holds dev->name acts as a head of per-device list. */
+ list_add_tail(&name_node->list, &dev->name_node->list);
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_name_node_alt_create);
+
+static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node)
+{
+ list_del(&name_node->list);
+ netdev_name_node_del(name_node);
+ kfree(name_node->name);
+ netdev_name_node_free(name_node);
+}
+
+int netdev_name_node_alt_destroy(struct net_device *dev, const char *name)
+{
+ struct netdev_name_node *name_node;
+ struct net *net = dev_net(dev);
+
+ name_node = netdev_name_node_lookup(net, name);
+ if (!name_node)
+ return -ENOENT;
+ __netdev_name_node_alt_destroy(name_node);
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_name_node_alt_destroy);
+
+static void netdev_name_node_alt_flush(struct net_device *dev)
+{
+ struct netdev_name_node *name_node, *tmp;
+
+ list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list)
+ __netdev_name_node_alt_destroy(name_node);
+}
+
/* Device list insertion */
static void list_netdevice(struct net_device *dev)
{
@@ -237,7 +354,7 @@ static void list_netdevice(struct net_device *dev)
write_lock_bh(&dev_base_lock);
list_add_tail_rcu(&dev->dev_list, &net->dev_base_head);
- hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
+ netdev_name_node_add(net, dev->name_node);
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
write_unlock_bh(&dev_base_lock);
@@ -255,7 +372,7 @@ static void unlist_netdevice(struct net_device *dev)
/* Unlink dev from the device chain */
write_lock_bh(&dev_base_lock);
list_del_rcu(&dev->dev_list);
- hlist_del_rcu(&dev->name_hlist);
+ netdev_name_node_del(dev->name_node);
hlist_del_rcu(&dev->index_hlist);
write_unlock_bh(&dev_base_lock);
@@ -276,88 +393,6 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
EXPORT_PER_CPU_SYMBOL(softnet_data);
-#ifdef CONFIG_LOCKDEP
-/*
- * register_netdevice() inits txq->_xmit_lock and sets lockdep class
- * according to dev->type
- */
-static const unsigned short netdev_lock_type[] = {
- ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
- ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
- ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
- ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
- ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
- ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
- ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
- ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
- ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
- ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
- ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
- ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
- ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
- ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
- ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
-
-static const char *const netdev_lock_name[] = {
- "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
- "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
- "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
- "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
- "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
- "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
- "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
- "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
- "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
- "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
- "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
- "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
- "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
- "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
- "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
-
-static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
-static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
-
-static inline unsigned short netdev_lock_pos(unsigned short dev_type)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++)
- if (netdev_lock_type[i] == dev_type)
- return i;
- /* the last key is used by default */
- return ARRAY_SIZE(netdev_lock_type) - 1;
-}
-
-static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
- unsigned short dev_type)
-{
- int i;
-
- i = netdev_lock_pos(dev_type);
- lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
- netdev_lock_name[i]);
-}
-
-static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
-{
- int i;
-
- i = netdev_lock_pos(dev->type);
- lockdep_set_class_and_name(&dev->addr_list_lock,
- &netdev_addr_lock_key[i],
- netdev_lock_name[i]);
-}
-#else
-static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
- unsigned short dev_type)
-{
-}
-static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
-{
-}
-#endif
-
/*******************************************************************************
*
* Protocol management and registration routines
@@ -733,14 +768,10 @@ EXPORT_SYMBOL_GPL(dev_fill_metadata_dst);
struct net_device *__dev_get_by_name(struct net *net, const char *name)
{
- struct net_device *dev;
- struct hlist_head *head = dev_name_hash(net, name);
-
- hlist_for_each_entry(dev, head, name_hlist)
- if (!strncmp(dev->name, name, IFNAMSIZ))
- return dev;
+ struct netdev_name_node *node_name;
- return NULL;
+ node_name = netdev_name_node_lookup(net, name);
+ return node_name ? node_name->dev : NULL;
}
EXPORT_SYMBOL(__dev_get_by_name);
@@ -758,14 +789,10 @@ EXPORT_SYMBOL(__dev_get_by_name);
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
{
- struct net_device *dev;
- struct hlist_head *head = dev_name_hash(net, name);
+ struct netdev_name_node *node_name;
- hlist_for_each_entry_rcu(dev, head, name_hlist)
- if (!strncmp(dev->name, name, IFNAMSIZ))
- return dev;
-
- return NULL;
+ node_name = netdev_name_node_lookup_rcu(net, name);
+ return node_name ? node_name->dev : NULL;
}
EXPORT_SYMBOL(dev_get_by_name_rcu);
@@ -1141,8 +1168,8 @@ int dev_alloc_name(struct net_device *dev, const char *name)
}
EXPORT_SYMBOL(dev_alloc_name);
-int dev_get_valid_name(struct net *net, struct net_device *dev,
- const char *name)
+static int dev_get_valid_name(struct net *net, struct net_device *dev,
+ const char *name)
{
BUG_ON(!net);
@@ -1158,7 +1185,6 @@ int dev_get_valid_name(struct net *net, struct net_device *dev,
return 0;
}
-EXPORT_SYMBOL(dev_get_valid_name);
/**
* dev_change_name - change name of a device
@@ -1232,13 +1258,13 @@ rollback:
netdev_adjacent_rename_links(dev, oldname);
write_lock_bh(&dev_base_lock);
- hlist_del_rcu(&dev->name_hlist);
+ netdev_name_node_del(dev->name_node);
write_unlock_bh(&dev_base_lock);
synchronize_rcu();
write_lock_bh(&dev_base_lock);
- hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
+ netdev_name_node_add(net, dev->name_node);
write_unlock_bh(&dev_base_lock);
ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
@@ -1617,6 +1643,62 @@ static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
return nb->notifier_call(nb, val, &info);
}
+static int call_netdevice_register_notifiers(struct notifier_block *nb,
+ struct net_device *dev)
+{
+ int err;
+
+ err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
+ err = notifier_to_errno(err);
+ if (err)
+ return err;
+
+ if (!(dev->flags & IFF_UP))
+ return 0;
+
+ call_netdevice_notifier(nb, NETDEV_UP, dev);
+ return 0;
+}
+
+static void call_netdevice_unregister_notifiers(struct notifier_block *nb,
+ struct net_device *dev)
+{
+ if (dev->flags & IFF_UP) {
+ call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+ dev);
+ call_netdevice_notifier(nb, NETDEV_DOWN, dev);
+ }
+ call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
+}
+
+static int call_netdevice_register_net_notifiers(struct notifier_block *nb,
+ struct net *net)
+{
+ struct net_device *dev;
+ int err;
+
+ for_each_netdev(net, dev) {
+ err = call_netdevice_register_notifiers(nb, dev);
+ if (err)
+ goto rollback;
+ }
+ return 0;
+
+rollback:
+ for_each_netdev_continue_reverse(net, dev)
+ call_netdevice_unregister_notifiers(nb, dev);
+ return err;
+}
+
+static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb,
+ struct net *net)
+{
+ struct net_device *dev;
+
+ for_each_netdev(net, dev)
+ call_netdevice_unregister_notifiers(nb, dev);
+}
+
static int dev_boot_phase = 1;
/**
@@ -1635,8 +1717,6 @@ static int dev_boot_phase = 1;
int register_netdevice_notifier(struct notifier_block *nb)
{
- struct net_device *dev;
- struct net_device *last;
struct net *net;
int err;
@@ -1649,17 +1729,9 @@ int register_netdevice_notifier(struct notifier_block *nb)
if (dev_boot_phase)
goto unlock;
for_each_net(net) {
- for_each_netdev(net, dev) {
- err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
- err = notifier_to_errno(err);
- if (err)
- goto rollback;
-
- if (!(dev->flags & IFF_UP))
- continue;
-
- call_netdevice_notifier(nb, NETDEV_UP, dev);
- }
+ err = call_netdevice_register_net_notifiers(nb, net);
+ if (err)
+ goto rollback;
}
unlock:
@@ -1668,22 +1740,9 @@ unlock:
return err;
rollback:
- last = dev;
- for_each_net(net) {
- for_each_netdev(net, dev) {
- if (dev == last)
- goto outroll;
-
- if (dev->flags & IFF_UP) {
- call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
- dev);
- call_netdevice_notifier(nb, NETDEV_DOWN, dev);
- }
- call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
- }
- }
+ for_each_net_continue_reverse(net)
+ call_netdevice_unregister_net_notifiers(nb, net);
-outroll:
raw_notifier_chain_unregister(&netdev_chain, nb);
goto unlock;
}
@@ -1734,6 +1793,80 @@ unlock:
EXPORT_SYMBOL(unregister_netdevice_notifier);
/**
+ * register_netdevice_notifier_net - register a per-netns network notifier block
+ * @net: network namespace
+ * @nb: notifier
+ *
+ * Register a notifier to be called when network device events occur.
+ * The notifier passed is linked into the kernel structures and must
+ * not be reused until it has been unregistered. A negative errno code
+ * is returned on a failure.
+ *
+ * When registered all registration and up events are replayed
+ * to the new notifier to allow device to have a race free
+ * view of the network device list.
+ */
+
+int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb)
+{
+ int err;
+
+ rtnl_lock();
+ err = raw_notifier_chain_register(&net->netdev_chain, nb);
+ if (err)
+ goto unlock;
+ if (dev_boot_phase)
+ goto unlock;
+
+ err = call_netdevice_register_net_notifiers(nb, net);
+ if (err)
+ goto chain_unregister;
+
+unlock:
+ rtnl_unlock();
+ return err;
+
+chain_unregister:
+ raw_notifier_chain_unregister(&netdev_chain, nb);
+ goto unlock;
+}
+EXPORT_SYMBOL(register_netdevice_notifier_net);
+
+/**
+ * unregister_netdevice_notifier_net - unregister a per-netns
+ * network notifier block
+ * @net: network namespace
+ * @nb: notifier
+ *
+ * Unregister a notifier previously registered by
+ * register_netdevice_notifier(). The notifier is unlinked into the
+ * kernel structures and may then be reused. A negative errno code
+ * is returned on a failure.
+ *
+ * After unregistering unregister and down device events are synthesized
+ * for all devices on the device list to the removed notifier to remove
+ * the need for special case cleanup code.
+ */
+
+int unregister_netdevice_notifier_net(struct net *net,
+ struct notifier_block *nb)
+{
+ int err;
+
+ rtnl_lock();
+ err = raw_notifier_chain_unregister(&net->netdev_chain, nb);
+ if (err)
+ goto unlock;
+
+ call_netdevice_unregister_net_notifiers(nb, net);
+
+unlock:
+ rtnl_unlock();
+ return err;
+}
+EXPORT_SYMBOL(unregister_netdevice_notifier_net);
+
+/**
* call_netdevice_notifiers_info - call all network notifier blocks
* @val: value passed unmodified to notifier function
* @info: notifier information data
@@ -1745,7 +1878,18 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
static int call_netdevice_notifiers_info(unsigned long val,
struct netdev_notifier_info *info)
{
+ struct net *net = dev_net(info->dev);
+ int ret;
+
ASSERT_RTNL();
+
+ /* Run per-netns notifier block chain first, then run the global one.
+ * Hopefully, one day, the global one is going to be removed after
+ * all notifier block registrators get converted to be per-netns.
+ */
+ ret = raw_notifier_call_chain(&net->netdev_chain, val, info);
+ if (ret & NOTIFY_STOP_MASK)
+ return ret;
return raw_notifier_call_chain(&netdev_chain, val, info);
}
@@ -2771,7 +2915,7 @@ static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
void netif_schedule_queue(struct netdev_queue *txq)
{
rcu_read_lock();
- if (!(txq->state & QUEUE_STATE_ANY_XOFF)) {
+ if (!netif_xmit_stopped(txq)) {
struct Qdisc *q = rcu_dereference(txq->qdisc);
__netif_schedule(q);
@@ -2939,12 +3083,9 @@ int skb_checksum_help(struct sk_buff *skb)
offset += skb->csum_offset;
BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));
- if (skb_cloned(skb) &&
- !skb_clone_writable(skb, offset + sizeof(__sum16))) {
- ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (ret)
- goto out;
- }
+ ret = skb_ensure_writable(skb, offset + sizeof(__sum16));
+ if (ret)
+ goto out;
*(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
out_set_summed:
@@ -2979,12 +3120,11 @@ int skb_crc32c_csum_help(struct sk_buff *skb)
ret = -EINVAL;
goto out;
}
- if (skb_cloned(skb) &&
- !skb_clone_writable(skb, offset + sizeof(__le32))) {
- ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (ret)
- goto out;
- }
+
+ ret = skb_ensure_writable(skb, offset + sizeof(__le32));
+ if (ret)
+ goto out;
+
crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start,
skb->len - start, ~(__u32)0,
crc32c_csum_stub));
@@ -3467,7 +3607,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
qdisc_calculate_pkt_len(skb, q);
if (q->flags & TCQ_F_NOLOCK) {
- if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty &&
+ if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) &&
qdisc_run_begin(q)) {
if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
&q->state))) {
@@ -5446,7 +5586,7 @@ static struct list_head *gro_list_prepare(struct napi_struct *napi,
diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb);
if (skb_vlan_tag_present(p))
- diffs |= p->vlan_tci ^ skb->vlan_tci;
+ diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb);
diffs |= skb_metadata_dst_cmp(p, skb);
diffs |= skb_metadata_differs(p, skb);
if (maclen == ETH_HLEN)
@@ -5471,8 +5611,7 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
NAPI_GRO_CB(skb)->frag0 = NULL;
NAPI_GRO_CB(skb)->frag0_len = 0;
- if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
- pinfo->nr_frags &&
+ if (!skb_headlen(skb) && pinfo->nr_frags &&
!PageHighMem(skb_frag_page(frag0))) {
NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
@@ -5663,6 +5802,26 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
}
EXPORT_SYMBOL(gro_find_complete_by_type);
+/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
+static void gro_normal_list(struct napi_struct *napi)
+{
+ if (!napi->rx_count)
+ return;
+ netif_receive_skb_list_internal(&napi->rx_list);
+ INIT_LIST_HEAD(&napi->rx_list);
+ napi->rx_count = 0;
+}
+
+/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
+ * pass the whole batch up to the stack.
+ */
+static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
+{
+ list_add_tail(&skb->list, &napi->rx_list);
+ if (++napi->rx_count >= gro_normal_batch)
+ gro_normal_list(napi);
+}
+
static void napi_skb_free_stolen_head(struct sk_buff *skb)
{
skb_dst_drop(skb);
@@ -5670,12 +5829,13 @@ static void napi_skb_free_stolen_head(struct sk_buff *skb)
kmem_cache_free(skbuff_head_cache, skb);
}
-static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
+static gro_result_t napi_skb_finish(struct napi_struct *napi,
+ struct sk_buff *skb,
+ gro_result_t ret)
{
switch (ret) {
case GRO_NORMAL:
- if (netif_receive_skb_internal(skb))
- ret = GRO_DROP;
+ gro_normal_one(napi, skb);
break;
case GRO_DROP:
@@ -5707,7 +5867,7 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
skb_gro_reset_offset(skb);
- ret = napi_skb_finish(dev_gro_receive(napi, skb), skb);
+ ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb));
trace_napi_gro_receive_exit(ret);
return ret;
@@ -5753,26 +5913,6 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
}
EXPORT_SYMBOL(napi_get_frags);
-/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
-static void gro_normal_list(struct napi_struct *napi)
-{
- if (!napi->rx_count)
- return;
- netif_receive_skb_list_internal(&napi->rx_list);
- INIT_LIST_HEAD(&napi->rx_list);
- napi->rx_count = 0;
-}
-
-/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
- * pass the whole batch up to the stack.
- */
-static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
-{
- list_add_tail(&skb->list, &napi->rx_list);
- if (++napi->rx_count >= gro_normal_batch)
- gro_normal_list(napi);
-}
-
static gro_result_t napi_frags_finish(struct napi_struct *napi,
struct sk_buff *skb,
gro_result_t ret)
@@ -6489,6 +6629,9 @@ struct netdev_adjacent {
/* upper master flag, there can only be one master device per list */
bool master;
+ /* lookup ignore flag */
+ bool ignore;
+
/* counter for the number of times this device was added to us */
u16 ref_nr;
@@ -6511,7 +6654,7 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev,
return NULL;
}
-static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data)
{
struct net_device *dev = data;
@@ -6532,7 +6675,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
{
ASSERT_RTNL();
- return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+ return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
upper_dev);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
@@ -6550,7 +6693,7 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev)
{
- return !!netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+ return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
upper_dev);
}
EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
@@ -6594,6 +6737,22 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_master_upper_dev_get);
+static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev)
+{
+ struct netdev_adjacent *upper;
+
+ ASSERT_RTNL();
+
+ if (list_empty(&dev->adj_list.upper))
+ return NULL;
+
+ upper = list_first_entry(&dev->adj_list.upper,
+ struct netdev_adjacent, list);
+ if (likely(upper->master) && !upper->ignore)
+ return upper->dev;
+ return NULL;
+}
+
/**
* netdev_has_any_lower_dev - Check if device is linked to some device
* @dev: device
@@ -6644,6 +6803,23 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+static struct net_device *__netdev_next_upper_dev(struct net_device *dev,
+ struct list_head **iter,
+ bool *ignore)
+{
+ struct netdev_adjacent *upper;
+
+ upper = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+ if (&upper->list == &dev->adj_list.upper)
+ return NULL;
+
+ *iter = &upper->list;
+ *ignore = upper->ignore;
+
+ return upper->dev;
+}
+
static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
@@ -6661,34 +6837,111 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
return upper->dev;
}
+static int __netdev_walk_all_upper_dev(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
+ bool ignore;
+
+ now = dev;
+ iter = &dev->adj_list.upper;
+
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ udev = __netdev_next_upper_dev(now, &iter, &ignore);
+ if (!udev)
+ break;
+ if (ignore)
+ continue;
+
+ next = udev;
+ niter = &udev->adj_list.upper;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
+ }
+
+ return 0;
+}
+
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *dev,
void *data),
void *data)
{
- struct net_device *udev;
- struct list_head *iter;
- int ret;
+ struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
- for (iter = &dev->adj_list.upper,
- udev = netdev_next_upper_dev_rcu(dev, &iter);
- udev;
- udev = netdev_next_upper_dev_rcu(dev, &iter)) {
- /* first is the upper device itself */
- ret = fn(udev, data);
- if (ret)
- return ret;
+ now = dev;
+ iter = &dev->adj_list.upper;
- /* then look at all of its upper devices */
- ret = netdev_walk_all_upper_dev_rcu(udev, fn, data);
- if (ret)
- return ret;
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ udev = netdev_next_upper_dev_rcu(now, &iter);
+ if (!udev)
+ break;
+
+ next = udev;
+ niter = &udev->adj_list.upper;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
}
return 0;
}
EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu);
+static bool __netdev_has_upper_dev(struct net_device *dev,
+ struct net_device *upper_dev)
+{
+ ASSERT_RTNL();
+
+ return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev,
+ upper_dev);
+}
+
/**
* netdev_lower_get_next_private - Get the next ->private from the
* lower neighbour list
@@ -6785,34 +7038,119 @@ static struct net_device *netdev_next_lower_dev(struct net_device *dev,
return lower->dev;
}
+static struct net_device *__netdev_next_lower_dev(struct net_device *dev,
+ struct list_head **iter,
+ bool *ignore)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ *iter = &lower->list;
+ *ignore = lower->ignore;
+
+ return lower->dev;
+}
+
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
void *data),
void *data)
{
- struct net_device *ldev;
- struct list_head *iter;
- int ret;
+ struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
- for (iter = &dev->adj_list.lower,
- ldev = netdev_next_lower_dev(dev, &iter);
- ldev;
- ldev = netdev_next_lower_dev(dev, &iter)) {
- /* first is the lower device itself */
- ret = fn(ldev, data);
- if (ret)
- return ret;
+ now = dev;
+ iter = &dev->adj_list.lower;
- /* then look at all of its lower devices */
- ret = netdev_walk_all_lower_dev(ldev, fn, data);
- if (ret)
- return ret;
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ ldev = netdev_next_lower_dev(now, &iter);
+ if (!ldev)
+ break;
+
+ next = ldev;
+ niter = &ldev->adj_list.lower;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
}
return 0;
}
EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
+static int __netdev_walk_all_lower_dev(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
+ bool ignore;
+
+ now = dev;
+ iter = &dev->adj_list.lower;
+
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ ldev = __netdev_next_lower_dev(now, &iter, &ignore);
+ if (!ldev)
+ break;
+ if (ignore)
+ continue;
+
+ next = ldev;
+ niter = &ldev->adj_list.lower;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
+ }
+
+ return 0;
+}
+
static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
@@ -6827,28 +7165,99 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
return lower->dev;
}
-int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
- int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+static u8 __netdev_upper_depth(struct net_device *dev)
+{
+ struct net_device *udev;
+ struct list_head *iter;
+ u8 max_depth = 0;
+ bool ignore;
+
+ for (iter = &dev->adj_list.upper,
+ udev = __netdev_next_upper_dev(dev, &iter, &ignore);
+ udev;
+ udev = __netdev_next_upper_dev(dev, &iter, &ignore)) {
+ if (ignore)
+ continue;
+ if (max_depth < udev->upper_level)
+ max_depth = udev->upper_level;
+ }
+
+ return max_depth;
+}
+
+static u8 __netdev_lower_depth(struct net_device *dev)
{
struct net_device *ldev;
struct list_head *iter;
- int ret;
+ u8 max_depth = 0;
+ bool ignore;
for (iter = &dev->adj_list.lower,
- ldev = netdev_next_lower_dev_rcu(dev, &iter);
+ ldev = __netdev_next_lower_dev(dev, &iter, &ignore);
ldev;
- ldev = netdev_next_lower_dev_rcu(dev, &iter)) {
- /* first is the lower device itself */
- ret = fn(ldev, data);
- if (ret)
- return ret;
+ ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) {
+ if (ignore)
+ continue;
+ if (max_depth < ldev->lower_level)
+ max_depth = ldev->lower_level;
+ }
- /* then look at all of its lower devices */
- ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data);
- if (ret)
- return ret;
+ return max_depth;
+}
+
+static int __netdev_update_upper_level(struct net_device *dev, void *data)
+{
+ dev->upper_level = __netdev_upper_depth(dev) + 1;
+ return 0;
+}
+
+static int __netdev_update_lower_level(struct net_device *dev, void *data)
+{
+ dev->lower_level = __netdev_lower_depth(dev) + 1;
+ return 0;
+}
+
+int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
+
+ now = dev;
+ iter = &dev->adj_list.lower;
+
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ ldev = netdev_next_lower_dev_rcu(now, &iter);
+ if (!ldev)
+ break;
+
+ next = ldev;
+ niter = &ldev->adj_list.lower;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
}
return 0;
@@ -6952,6 +7361,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
adj->master = master;
adj->ref_nr = 1;
adj->private = private;
+ adj->ignore = false;
dev_hold(adj_dev);
pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n",
@@ -7102,14 +7512,17 @@ static int __netdev_upper_dev_link(struct net_device *dev,
return -EBUSY;
/* To prevent loops, check if dev is not upper device to upper_dev. */
- if (netdev_has_upper_dev(upper_dev, dev))
+ if (__netdev_has_upper_dev(upper_dev, dev))
return -EBUSY;
+ if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV)
+ return -EMLINK;
+
if (!master) {
- if (netdev_has_upper_dev(dev, upper_dev))
+ if (__netdev_has_upper_dev(dev, upper_dev))
return -EEXIST;
} else {
- master_dev = netdev_master_upper_dev_get(dev);
+ master_dev = __netdev_master_upper_dev_get(dev);
if (master_dev)
return master_dev == upper_dev ? -EEXIST : -EBUSY;
}
@@ -7131,6 +7544,13 @@ static int __netdev_upper_dev_link(struct net_device *dev,
if (ret)
goto rollback;
+ __netdev_update_upper_level(dev, NULL);
+ __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+
+ __netdev_update_lower_level(upper_dev, NULL);
+ __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
+ NULL);
+
return 0;
rollback:
@@ -7213,9 +7633,96 @@ void netdev_upper_dev_unlink(struct net_device *dev,
call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
+
+ __netdev_update_upper_level(dev, NULL);
+ __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+
+ __netdev_update_lower_level(upper_dev, NULL);
+ __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
+ NULL);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
+static void __netdev_adjacent_dev_set(struct net_device *upper_dev,
+ struct net_device *lower_dev,
+ bool val)
+{
+ struct netdev_adjacent *adj;
+
+ adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower);
+ if (adj)
+ adj->ignore = val;
+
+ adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper);
+ if (adj)
+ adj->ignore = val;
+}
+
+static void netdev_adjacent_dev_disable(struct net_device *upper_dev,
+ struct net_device *lower_dev)
+{
+ __netdev_adjacent_dev_set(upper_dev, lower_dev, true);
+}
+
+static void netdev_adjacent_dev_enable(struct net_device *upper_dev,
+ struct net_device *lower_dev)
+{
+ __netdev_adjacent_dev_set(upper_dev, lower_dev, false);
+}
+
+int netdev_adjacent_change_prepare(struct net_device *old_dev,
+ struct net_device *new_dev,
+ struct net_device *dev,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ if (!new_dev)
+ return 0;
+
+ if (old_dev && new_dev != old_dev)
+ netdev_adjacent_dev_disable(dev, old_dev);
+
+ err = netdev_upper_dev_link(new_dev, dev, extack);
+ if (err) {
+ if (old_dev && new_dev != old_dev)
+ netdev_adjacent_dev_enable(dev, old_dev);
+ return err;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_adjacent_change_prepare);
+
+void netdev_adjacent_change_commit(struct net_device *old_dev,
+ struct net_device *new_dev,
+ struct net_device *dev)
+{
+ if (!new_dev || !old_dev)
+ return;
+
+ if (new_dev == old_dev)
+ return;
+
+ netdev_adjacent_dev_enable(dev, old_dev);
+ netdev_upper_dev_unlink(old_dev, dev);
+}
+EXPORT_SYMBOL(netdev_adjacent_change_commit);
+
+void netdev_adjacent_change_abort(struct net_device *old_dev,
+ struct net_device *new_dev,
+ struct net_device *dev)
+{
+ if (!new_dev)
+ return;
+
+ if (old_dev && new_dev != old_dev)
+ netdev_adjacent_dev_enable(dev, old_dev);
+
+ netdev_upper_dev_unlink(new_dev, dev);
+}
+EXPORT_SYMBOL(netdev_adjacent_change_abort);
+
/**
* netdev_bonding_info_change - Dispatch event about slave change
* @dev: device
@@ -7329,25 +7836,6 @@ 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)
-{
- struct net_device *lower = NULL;
- struct list_head *iter;
- int max_nest = -1;
- int nest;
-
- ASSERT_RTNL();
-
- netdev_for_each_lower_dev(dev, lower, iter) {
- nest = dev_get_nest_level(lower);
- if (max_nest < nest)
- max_nest = nest;
- }
-
- return max_nest + 1;
-}
-EXPORT_SYMBOL(dev_get_nest_level);
-
/**
* netdev_lower_change - Dispatch event about lower device state change
* @lower_dev: device
@@ -8154,7 +8642,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
return -EINVAL;
}
- if (prog->aux->id == prog_id) {
+ /* prog->aux->id may be 0 for orphaned device-bound progs */
+ if (prog->aux->id && prog->aux->id == prog_id) {
bpf_prog_put(prog);
return 0;
}
@@ -8264,6 +8753,9 @@ static void rollback_registered_many(struct list_head *head)
dev_uc_flush(dev);
dev_mc_flush(dev);
+ netdev_name_node_alt_flush(dev);
+ netdev_name_node_free(dev->name_node);
+
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
@@ -8619,7 +9111,7 @@ static void netdev_init_one_queue(struct net_device *dev,
{
/* Initialize queue lock */
spin_lock_init(&queue->_xmit_lock);
- netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
+ lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key);
queue->xmit_lock_owner = -1;
netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
queue->dev = dev;
@@ -8666,6 +9158,43 @@ void netif_tx_stop_all_queues(struct net_device *dev)
}
EXPORT_SYMBOL(netif_tx_stop_all_queues);
+static void netdev_register_lockdep_key(struct net_device *dev)
+{
+ lockdep_register_key(&dev->qdisc_tx_busylock_key);
+ lockdep_register_key(&dev->qdisc_running_key);
+ lockdep_register_key(&dev->qdisc_xmit_lock_key);
+ lockdep_register_key(&dev->addr_list_lock_key);
+}
+
+static void netdev_unregister_lockdep_key(struct net_device *dev)
+{
+ lockdep_unregister_key(&dev->qdisc_tx_busylock_key);
+ lockdep_unregister_key(&dev->qdisc_running_key);
+ lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
+ lockdep_unregister_key(&dev->addr_list_lock_key);
+}
+
+void netdev_update_lockdep_key(struct net_device *dev)
+{
+ struct netdev_queue *queue;
+ int i;
+
+ lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
+ lockdep_unregister_key(&dev->addr_list_lock_key);
+
+ lockdep_register_key(&dev->qdisc_xmit_lock_key);
+ lockdep_register_key(&dev->addr_list_lock_key);
+
+ lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
+ for (i = 0; i < dev->num_tx_queues; i++) {
+ queue = netdev_get_tx_queue(dev, i);
+
+ lockdep_set_class(&queue->_xmit_lock,
+ &dev->qdisc_xmit_lock_key);
+ }
+}
+EXPORT_SYMBOL(netdev_update_lockdep_key);
+
/**
* register_netdevice - register a network device
* @dev: device to register
@@ -8700,12 +9229,17 @@ int register_netdevice(struct net_device *dev)
BUG_ON(!net);
spin_lock_init(&dev->addr_list_lock);
- netdev_set_addr_lockdep_class(dev);
+ lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
ret = dev_get_valid_name(net, dev, dev->name);
if (ret < 0)
goto out;
+ ret = -ENOMEM;
+ dev->name_node = netdev_name_node_head_alloc(dev);
+ if (!dev->name_node)
+ goto out;
+
/* Init, if this function is available */
if (dev->netdev_ops->ndo_init) {
ret = dev->netdev_ops->ndo_init(dev);
@@ -8827,6 +9361,8 @@ out:
return ret;
err_uninit:
+ if (dev->name_node)
+ netdev_name_node_free(dev->name_node);
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
if (dev->priv_destructor)
@@ -9210,8 +9746,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev_net_set(dev, &init_net);
+ netdev_register_lockdep_key(dev);
+
dev->gso_max_size = GSO_MAX_SIZE;
dev->gso_max_segs = GSO_MAX_SEGS;
+ dev->upper_level = 1;
+ dev->lower_level = 1;
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
@@ -9292,6 +9832,8 @@ void free_netdev(struct net_device *dev)
free_percpu(dev->pcpu_refcnt);
dev->pcpu_refcnt = NULL;
+ netdev_unregister_lockdep_key(dev);
+
/* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED) {
netdev_freemem(dev);
@@ -9460,7 +10002,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
rcu_barrier();
- new_nsid = peernet2id_alloc(dev_net(dev), net);
+ new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL);
/* If there is an ifindex conflict assign a new one */
if (__dev_get_by_index(net, dev->ifindex))
new_ifindex = dev_new_index(net);
@@ -9635,6 +10177,8 @@ static int __net_init netdev_init(struct net *net)
if (net->dev_index_head == NULL)
goto err_idx;
+ RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain);
+
return 0;
err_idx:
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 6393ba930097..2f949b5a1eb9 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
@@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
@@ -691,7 +691,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from)
return;
netif_addr_lock_bh(from);
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
__hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
__dev_set_rx_mode(to);
netif_addr_unlock(to);
@@ -858,7 +858,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
@@ -888,7 +888,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
@@ -912,7 +912,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from)
return;
netif_addr_lock_bh(from);
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
__hw_addr_unsync(&to->mc, &from->mc, to->addr_len);
__dev_set_rx_mode(to);
netif_addr_unlock(to);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index f80151eeaf51..4c63c9a4c09e 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -95,16 +95,25 @@ static LIST_HEAD(devlink_list);
*/
static DEFINE_MUTEX(devlink_mutex);
-static struct net *devlink_net(const struct devlink *devlink)
+struct net *devlink_net(const struct devlink *devlink)
{
return read_pnet(&devlink->_net);
}
+EXPORT_SYMBOL_GPL(devlink_net);
-static void devlink_net_set(struct devlink *devlink, struct net *net)
+static void __devlink_net_set(struct devlink *devlink, struct net *net)
{
write_pnet(&devlink->_net, net);
}
+void devlink_net_set(struct devlink *devlink, struct net *net)
+{
+ if (WARN_ON(devlink->registered))
+ return;
+ __devlink_net_set(devlink, net);
+}
+EXPORT_SYMBOL_GPL(devlink_net_set);
+
static struct devlink *devlink_get_from_attrs(struct net *net,
struct nlattr **attrs)
{
@@ -434,8 +443,16 @@ static void devlink_nl_post_doit(const struct genl_ops *ops,
{
struct devlink *devlink;
- devlink = devlink_get_from_info(info);
- if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK)
+ /* When devlink changes netns, it would not be found
+ * by devlink_get_from_info(). So try if it is stored first.
+ */
+ if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) {
+ devlink = info->user_ptr[0];
+ } else {
+ devlink = devlink_get_from_info(info);
+ WARN_ON(IS_ERR(devlink));
+ }
+ if (!IS_ERR(devlink) && ~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK)
mutex_unlock(&devlink->lock);
mutex_unlock(&devlink_mutex);
}
@@ -1035,7 +1052,7 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg,
struct devlink_sb *devlink_sb;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -1058,6 +1075,9 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg,
out:
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -1233,7 +1253,7 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg,
struct devlink_sb *devlink_sb;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -1256,6 +1276,9 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg,
out:
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -1460,7 +1483,7 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
struct devlink_sb *devlink_sb;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -1485,6 +1508,9 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
out:
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -2674,6 +2700,72 @@ devlink_resources_validate(struct devlink *devlink,
return err;
}
+static struct net *devlink_netns_get(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID];
+ struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD];
+ struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID];
+ struct net *net;
+
+ if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) {
+ NL_SET_ERR_MSG(info->extack, "multiple netns identifying attributes specified");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (netns_pid_attr) {
+ net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr));
+ } else if (netns_fd_attr) {
+ net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr));
+ } else if (netns_id_attr) {
+ net = get_net_ns_by_id(sock_net(skb->sk),
+ nla_get_u32(netns_id_attr));
+ if (!net)
+ net = ERR_PTR(-EINVAL);
+ } else {
+ WARN_ON(1);
+ net = ERR_PTR(-EINVAL);
+ }
+ if (IS_ERR(net)) {
+ NL_SET_ERR_MSG(info->extack, "Unknown network namespace");
+ return ERR_PTR(-EINVAL);
+ }
+ if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+ put_net(net);
+ return ERR_PTR(-EPERM);
+ }
+ return net;
+}
+
+static void devlink_param_notify(struct devlink *devlink,
+ unsigned int port_index,
+ struct devlink_param_item *param_item,
+ enum devlink_command cmd);
+
+static void devlink_reload_netns_change(struct devlink *devlink,
+ struct net *dest_net)
+{
+ struct devlink_param_item *param_item;
+
+ /* Userspace needs to be notified about devlink objects
+ * removed from original and entering new network namespace.
+ * The rest of the devlink objects are re-created during
+ * reload process so the notifications are generated separatelly.
+ */
+
+ list_for_each_entry(param_item, &devlink->param_list, list)
+ devlink_param_notify(devlink, 0, param_item,
+ DEVLINK_CMD_PARAM_DEL);
+ devlink_notify(devlink, DEVLINK_CMD_DEL);
+
+ __devlink_net_set(devlink, dest_net);
+
+ devlink_notify(devlink, DEVLINK_CMD_NEW);
+ list_for_each_entry(param_item, &devlink->param_list, list)
+ devlink_param_notify(devlink, 0, param_item,
+ DEVLINK_CMD_PARAM_NEW);
+}
+
static bool devlink_reload_supported(struct devlink *devlink)
{
return devlink->ops->reload_down && devlink->ops->reload_up;
@@ -2694,12 +2786,33 @@ bool devlink_is_reload_failed(const struct devlink *devlink)
}
EXPORT_SYMBOL_GPL(devlink_is_reload_failed);
+static int devlink_reload(struct devlink *devlink, struct net *dest_net,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ if (!devlink->reload_enabled)
+ return -EOPNOTSUPP;
+
+ err = devlink->ops->reload_down(devlink, !!dest_net, extack);
+ if (err)
+ return err;
+
+ if (dest_net && !net_eq(dest_net, devlink_net(devlink)))
+ devlink_reload_netns_change(devlink, dest_net);
+
+ err = devlink->ops->reload_up(devlink, extack);
+ devlink_reload_failed_set(devlink, !!err);
+ return err;
+}
+
static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
{
struct devlink *devlink = info->user_ptr[0];
+ struct net *dest_net = NULL;
int err;
- if (!devlink_reload_supported(devlink))
+ if (!devlink_reload_supported(devlink) || !devlink->reload_enabled)
return -EOPNOTSUPP;
err = devlink_resources_validate(devlink, NULL, info);
@@ -2707,11 +2820,20 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed");
return err;
}
- err = devlink->ops->reload_down(devlink, info->extack);
- if (err)
- return err;
- err = devlink->ops->reload_up(devlink, info->extack);
- devlink_reload_failed_set(devlink, !!err);
+
+ if (info->attrs[DEVLINK_ATTR_NETNS_PID] ||
+ info->attrs[DEVLINK_ATTR_NETNS_FD] ||
+ info->attrs[DEVLINK_ATTR_NETNS_ID]) {
+ dest_net = devlink_netns_get(skb, info);
+ if (IS_ERR(dest_net))
+ return PTR_ERR(dest_net);
+ }
+
+ err = devlink_reload(devlink, dest_net, info->extack);
+
+ if (dest_net)
+ put_net(dest_net);
+
return err;
}
@@ -2884,6 +3006,11 @@ static const struct devlink_param devlink_param_generic[] = {
.name = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_NAME,
.type = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE,
},
+ {
+ .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+ .name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME,
+ .type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE,
+ },
};
static int devlink_param_generic_verify(const struct devlink_param *param)
@@ -3155,7 +3282,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg,
struct devlink *devlink;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -3183,6 +3310,9 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg,
out:
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -3411,7 +3541,7 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg,
struct devlink *devlink;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -3444,6 +3574,9 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg,
out:
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -3818,29 +3951,19 @@ static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb,
static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
struct netlink_callback *cb)
{
+ const struct genl_dumpit_info *info = genl_dumpit_info(cb);
u64 ret_offset, start_offset, end_offset = 0;
+ struct nlattr **attrs = info->attrs;
struct devlink_region *region;
struct nlattr *chunks_attr;
const char *region_name;
struct devlink *devlink;
- struct nlattr **attrs;
bool dump = true;
void *hdr;
int err;
start_offset = *((u64 *)&cb->args[0]);
- attrs = kmalloc_array(DEVLINK_ATTR_MAX + 1, sizeof(*attrs), GFP_KERNEL);
- if (!attrs)
- return -ENOMEM;
-
- err = nlmsg_parse_deprecated(cb->nlh,
- GENL_HDRLEN + devlink_nl_family.hdrsize,
- attrs, DEVLINK_ATTR_MAX,
- devlink_nl_family.policy, cb->extack);
- if (err)
- goto out_free;
-
mutex_lock(&devlink_mutex);
devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs);
if (IS_ERR(devlink)) {
@@ -3917,7 +4040,6 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
genlmsg_end(skb, hdr);
mutex_unlock(&devlink->lock);
mutex_unlock(&devlink_mutex);
- kfree(attrs);
return skb->len;
@@ -3927,8 +4049,6 @@ out_unlock:
mutex_unlock(&devlink->lock);
out_dev:
mutex_unlock(&devlink_mutex);
-out_free:
- kfree(attrs);
return err;
}
@@ -4066,7 +4186,7 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg,
struct devlink *devlink;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -4094,6 +4214,9 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg,
}
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -4296,12 +4419,11 @@ int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value)
}
EXPORT_SYMBOL_GPL(devlink_fmsg_string_put);
-int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value,
- u16 value_len)
+static int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value,
+ u16 value_len)
{
return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY);
}
-EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put);
int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name,
bool value)
@@ -4409,19 +4531,26 @@ int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name,
EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put);
int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name,
- const void *value, u16 value_len)
+ const void *value, u32 value_len)
{
+ u32 data_size;
+ u32 offset;
int err;
- err = devlink_fmsg_pair_nest_start(fmsg, name);
+ err = devlink_fmsg_arr_pair_nest_start(fmsg, name);
if (err)
return err;
- err = devlink_fmsg_binary_put(fmsg, value, value_len);
- if (err)
- return err;
+ for (offset = 0; offset < value_len; offset += data_size) {
+ data_size = value_len - offset;
+ if (data_size > DEVLINK_FMSG_MAX_SIZE)
+ data_size = DEVLINK_FMSG_MAX_SIZE;
+ err = devlink_fmsg_binary_put(fmsg, value + offset, data_size);
+ if (err)
+ return err;
+ }
- err = devlink_fmsg_pair_nest_end(fmsg);
+ err = devlink_fmsg_arr_pair_nest_end(fmsg);
if (err)
return err;
@@ -4618,6 +4747,7 @@ struct devlink_health_reporter {
bool auto_recover;
u8 health_state;
u64 dump_ts;
+ u64 dump_real_ts;
u64 error_count;
u64 recovery_count;
u64 last_recovery_ts;
@@ -4732,14 +4862,17 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update);
static int
devlink_health_reporter_recover(struct devlink_health_reporter *reporter,
- void *priv_ctx)
+ void *priv_ctx, struct netlink_ext_ack *extack)
{
int err;
+ if (reporter->health_state == DEVLINK_HEALTH_REPORTER_STATE_HEALTHY)
+ return 0;
+
if (!reporter->ops->recover)
return -EOPNOTSUPP;
- err = reporter->ops->recover(reporter, priv_ctx);
+ err = reporter->ops->recover(reporter, priv_ctx, extack);
if (err)
return err;
@@ -4760,7 +4893,8 @@ devlink_health_dump_clear(struct devlink_health_reporter *reporter)
}
static int devlink_health_do_dump(struct devlink_health_reporter *reporter,
- void *priv_ctx)
+ void *priv_ctx,
+ struct netlink_ext_ack *extack)
{
int err;
@@ -4781,7 +4915,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter,
goto dump_err;
err = reporter->ops->dump(reporter, reporter->dump_fmsg,
- priv_ctx);
+ priv_ctx, extack);
if (err)
goto dump_err;
@@ -4790,6 +4924,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter,
goto dump_err;
reporter->dump_ts = jiffies;
+ reporter->dump_real_ts = ktime_get_real_ns();
return 0;
@@ -4828,11 +4963,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
mutex_lock(&reporter->dump_lock);
/* store current dump of current error, for later analysis */
- devlink_health_do_dump(reporter, priv_ctx);
+ devlink_health_do_dump(reporter, priv_ctx, NULL);
mutex_unlock(&reporter->dump_lock);
if (reporter->auto_recover)
- return devlink_health_reporter_recover(reporter, priv_ctx);
+ return devlink_health_reporter_recover(reporter,
+ priv_ctx, NULL);
return 0;
}
@@ -4867,21 +5003,10 @@ devlink_health_reporter_get_from_info(struct devlink *devlink,
static struct devlink_health_reporter *
devlink_health_reporter_get_from_cb(struct netlink_callback *cb)
{
+ const struct genl_dumpit_info *info = genl_dumpit_info(cb);
struct devlink_health_reporter *reporter;
+ struct nlattr **attrs = info->attrs;
struct devlink *devlink;
- struct nlattr **attrs;
- int err;
-
- attrs = kmalloc_array(DEVLINK_ATTR_MAX + 1, sizeof(*attrs), GFP_KERNEL);
- if (!attrs)
- return NULL;
-
- err = nlmsg_parse_deprecated(cb->nlh,
- GENL_HDRLEN + devlink_nl_family.hdrsize,
- attrs, DEVLINK_ATTR_MAX,
- devlink_nl_family.policy, cb->extack);
- if (err)
- goto free;
mutex_lock(&devlink_mutex);
devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs);
@@ -4890,12 +5015,9 @@ devlink_health_reporter_get_from_cb(struct netlink_callback *cb)
reporter = devlink_health_reporter_get_from_attrs(devlink, attrs);
mutex_unlock(&devlink_mutex);
- kfree(attrs);
return reporter;
unlock:
mutex_unlock(&devlink_mutex);
-free:
- kfree(attrs);
return NULL;
}
@@ -4952,6 +5074,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg,
jiffies_to_msecs(reporter->dump_ts),
DEVLINK_ATTR_PAD))
goto reporter_nest_cancel;
+ if (reporter->dump_fmsg &&
+ nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS,
+ reporter->dump_real_ts, DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
nla_nest_end(msg, reporter_attr);
genlmsg_end(msg, hdr);
@@ -5084,7 +5210,7 @@ static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
if (!reporter)
return -EINVAL;
- err = devlink_health_reporter_recover(reporter, NULL);
+ err = devlink_health_reporter_recover(reporter, NULL, info->extack);
devlink_health_reporter_put(reporter);
return err;
@@ -5117,7 +5243,7 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb,
if (err)
goto out;
- err = reporter->ops->diagnose(reporter, fmsg);
+ err = reporter->ops->diagnose(reporter, fmsg, info->extack);
if (err)
goto out;
@@ -5152,7 +5278,7 @@ devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb,
}
mutex_lock(&reporter->dump_lock);
if (!start) {
- err = devlink_health_do_dump(reporter, NULL);
+ err = devlink_health_do_dump(reporter, NULL, cb->extack);
if (err)
goto unlock;
cb->args[1] = reporter->dump_ts;
@@ -5793,6 +5919,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 },
[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 },
};
static const struct genl_ops devlink_nl_ops[] = {
@@ -6023,7 +6152,8 @@ static const struct genl_ops devlink_nl_ops[] = {
},
{
.cmd = DEVLINK_CMD_REGION_READ,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
.dumpit = devlink_nl_cmd_region_read_dumpit,
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
@@ -6071,7 +6201,8 @@ static const struct genl_ops devlink_nl_ops[] = {
},
{
.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
.dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit,
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -6155,7 +6286,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
if (!devlink)
return NULL;
devlink->ops = ops;
- devlink_net_set(devlink, &init_net);
+ __devlink_net_set(devlink, &init_net);
INIT_LIST_HEAD(&devlink->port_list);
INIT_LIST_HEAD(&devlink->sb_list);
INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
@@ -6181,6 +6312,7 @@ int devlink_register(struct devlink *devlink, struct device *dev)
{
mutex_lock(&devlink_mutex);
devlink->dev = dev;
+ devlink->registered = true;
list_add_tail(&devlink->list, &devlink_list);
devlink_notify(devlink, DEVLINK_CMD_NEW);
mutex_unlock(&devlink_mutex);
@@ -6196,6 +6328,8 @@ EXPORT_SYMBOL_GPL(devlink_register);
void devlink_unregister(struct devlink *devlink)
{
mutex_lock(&devlink_mutex);
+ WARN_ON(devlink_reload_supported(devlink) &&
+ devlink->reload_enabled);
devlink_notify(devlink, DEVLINK_CMD_DEL);
list_del(&devlink->list);
mutex_unlock(&devlink_mutex);
@@ -6203,6 +6337,41 @@ void devlink_unregister(struct devlink *devlink)
EXPORT_SYMBOL_GPL(devlink_unregister);
/**
+ * devlink_reload_enable - Enable reload of devlink instance
+ *
+ * @devlink: devlink
+ *
+ * Should be called at end of device initialization
+ * process when reload operation is supported.
+ */
+void devlink_reload_enable(struct devlink *devlink)
+{
+ mutex_lock(&devlink_mutex);
+ devlink->reload_enabled = true;
+ mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_reload_enable);
+
+/**
+ * devlink_reload_disable - Disable reload of devlink instance
+ *
+ * @devlink: devlink
+ *
+ * Should be called at the beginning of device cleanup
+ * process when reload operation is supported.
+ */
+void devlink_reload_disable(struct devlink *devlink)
+{
+ mutex_lock(&devlink_mutex);
+ /* Mutex is taken which ensures that no reload operation is in
+ * progress while setting up forbidded flag.
+ */
+ devlink->reload_enabled = false;
+ mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_reload_disable);
+
+/**
* devlink_free - Free devlink instance resources
*
* @devlink: devlink
@@ -7490,6 +7659,21 @@ static const struct devlink_trap devlink_trap_generic[] = {
DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP),
DEVLINK_TRAP(TTL_ERROR, EXCEPTION),
DEVLINK_TRAP(TAIL_DROP, DROP),
+ DEVLINK_TRAP(NON_IP_PACKET, DROP),
+ DEVLINK_TRAP(UC_DIP_MC_DMAC, DROP),
+ DEVLINK_TRAP(DIP_LB, DROP),
+ DEVLINK_TRAP(SIP_MC, DROP),
+ DEVLINK_TRAP(SIP_LB, DROP),
+ DEVLINK_TRAP(CORRUPTED_IP_HDR, DROP),
+ DEVLINK_TRAP(IPV4_SIP_BC, DROP),
+ DEVLINK_TRAP(IPV6_MC_DIP_RESERVED_SCOPE, DROP),
+ DEVLINK_TRAP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, DROP),
+ DEVLINK_TRAP(MTU_ERROR, EXCEPTION),
+ DEVLINK_TRAP(UNRESOLVED_NEIGH, EXCEPTION),
+ DEVLINK_TRAP(RPF, EXCEPTION),
+ DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION),
+ DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION),
+ DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION),
};
#define DEVLINK_TRAP_GROUP(_id) \
@@ -8060,9 +8244,43 @@ int devlink_compat_switch_id_get(struct net_device *dev,
return 0;
}
+static void __net_exit devlink_pernet_pre_exit(struct net *net)
+{
+ struct devlink *devlink;
+ int err;
+
+ /* In case network namespace is getting destroyed, reload
+ * all devlink instances from this namespace into init_net.
+ */
+ mutex_lock(&devlink_mutex);
+ list_for_each_entry(devlink, &devlink_list, list) {
+ if (net_eq(devlink_net(devlink), net)) {
+ if (WARN_ON(!devlink_reload_supported(devlink)))
+ continue;
+ err = devlink_reload(devlink, &init_net, NULL);
+ if (err && err != -EOPNOTSUPP)
+ pr_warn("Failed to reload devlink instance into init_net\n");
+ }
+ }
+ mutex_unlock(&devlink_mutex);
+}
+
+static struct pernet_operations devlink_pernet_ops __net_initdata = {
+ .pre_exit = devlink_pernet_pre_exit,
+};
+
static int __init devlink_init(void)
{
- return genl_register_family(&devlink_nl_family);
+ int err;
+
+ err = genl_register_family(&devlink_nl_family);
+ if (err)
+ goto out;
+ err = register_pernet_subsys(&devlink_pernet_ops);
+
+out:
+ WARN_ON(err);
+ return err;
}
subsys_initcall(devlink_init);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index c763106c73fc..cd9bc67381b2 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1396,11 +1396,13 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr)
static int ethtool_get_wol(struct net_device *dev, char __user *useraddr)
{
- struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
+ struct ethtool_wolinfo wol;
if (!dev->ethtool_ops->get_wol)
return -EOPNOTSUPP;
+ memset(&wol, 0, sizeof(struct ethtool_wolinfo));
+ wol.cmd = ETHTOOL_GWOL;
dev->ethtool_ops->get_wol(dev, &wol);
if (copy_to_user(useraddr, &wol, sizeof(wol)))
diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c
index 470a606d5e8d..fc96259807b6 100644
--- a/net/core/fib_notifier.c
+++ b/net/core/fib_notifier.c
@@ -12,17 +12,15 @@ static unsigned int fib_notifier_net_id;
struct fib_notifier_net {
struct list_head fib_notifier_ops;
+ struct atomic_notifier_head fib_chain;
};
-static ATOMIC_NOTIFIER_HEAD(fib_chain);
-
-int call_fib_notifier(struct notifier_block *nb, struct net *net,
+int call_fib_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
struct fib_notifier_info *info)
{
int err;
- info->net = net;
err = nb->notifier_call(nb, event_type, info);
return notifier_to_errno(err);
}
@@ -31,106 +29,100 @@ EXPORT_SYMBOL(call_fib_notifier);
int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
struct fib_notifier_info *info)
{
+ struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
int err;
- info->net = net;
- err = atomic_notifier_call_chain(&fib_chain, event_type, info);
+ err = atomic_notifier_call_chain(&fn_net->fib_chain, event_type, info);
return notifier_to_errno(err);
}
EXPORT_SYMBOL(call_fib_notifiers);
-static unsigned int fib_seq_sum(void)
+static unsigned int fib_seq_sum(struct net *net)
{
- struct fib_notifier_net *fn_net;
+ struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
struct fib_notifier_ops *ops;
unsigned int fib_seq = 0;
- struct net *net;
rtnl_lock();
- down_read(&net_rwsem);
- for_each_net(net) {
- fn_net = net_generic(net, fib_notifier_net_id);
- rcu_read_lock();
- list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) {
- if (!try_module_get(ops->owner))
- continue;
- fib_seq += ops->fib_seq_read(net);
- module_put(ops->owner);
- }
- rcu_read_unlock();
+ rcu_read_lock();
+ list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) {
+ if (!try_module_get(ops->owner))
+ continue;
+ fib_seq += ops->fib_seq_read(net);
+ module_put(ops->owner);
}
- up_read(&net_rwsem);
+ rcu_read_unlock();
rtnl_unlock();
return fib_seq;
}
-static int fib_net_dump(struct net *net, struct notifier_block *nb)
+static int fib_net_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
struct fib_notifier_ops *ops;
+ int err = 0;
+ rcu_read_lock();
list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) {
- int err;
-
if (!try_module_get(ops->owner))
continue;
- err = ops->fib_dump(net, nb);
+ err = ops->fib_dump(net, nb, extack);
module_put(ops->owner);
if (err)
- return err;
+ goto unlock;
}
- return 0;
+unlock:
+ rcu_read_unlock();
+
+ return err;
}
-static bool fib_dump_is_consistent(struct notifier_block *nb,
+static bool fib_dump_is_consistent(struct net *net, struct notifier_block *nb,
void (*cb)(struct notifier_block *nb),
unsigned int fib_seq)
{
- atomic_notifier_chain_register(&fib_chain, nb);
- if (fib_seq == fib_seq_sum())
+ struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
+
+ atomic_notifier_chain_register(&fn_net->fib_chain, nb);
+ if (fib_seq == fib_seq_sum(net))
return true;
- atomic_notifier_chain_unregister(&fib_chain, nb);
+ atomic_notifier_chain_unregister(&fn_net->fib_chain, nb);
if (cb)
cb(nb);
return false;
}
#define FIB_DUMP_MAX_RETRIES 5
-int register_fib_notifier(struct notifier_block *nb,
- void (*cb)(struct notifier_block *nb))
+int register_fib_notifier(struct net *net, struct notifier_block *nb,
+ void (*cb)(struct notifier_block *nb),
+ struct netlink_ext_ack *extack)
{
int retries = 0;
int err;
do {
- unsigned int fib_seq = fib_seq_sum();
- struct net *net;
-
- rcu_read_lock();
- for_each_net_rcu(net) {
- err = fib_net_dump(net, nb);
- if (err)
- goto err_fib_net_dump;
- }
- rcu_read_unlock();
-
- if (fib_dump_is_consistent(nb, cb, fib_seq))
+ unsigned int fib_seq = fib_seq_sum(net);
+
+ err = fib_net_dump(net, nb, extack);
+ if (err)
+ return err;
+
+ if (fib_dump_is_consistent(net, nb, cb, fib_seq))
return 0;
} while (++retries < FIB_DUMP_MAX_RETRIES);
return -EBUSY;
-
-err_fib_net_dump:
- rcu_read_unlock();
- return err;
}
EXPORT_SYMBOL(register_fib_notifier);
-int unregister_fib_notifier(struct notifier_block *nb)
+int unregister_fib_notifier(struct net *net, struct notifier_block *nb)
{
- return atomic_notifier_chain_unregister(&fib_chain, nb);
+ struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
+
+ return atomic_notifier_chain_unregister(&fn_net->fib_chain, nb);
}
EXPORT_SYMBOL(unregister_fib_notifier);
@@ -181,6 +173,7 @@ static int __net_init fib_notifier_net_init(struct net *net)
struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
INIT_LIST_HEAD(&fn_net->fib_notifier_ops);
+ ATOMIC_INIT_NOTIFIER_HEAD(&fn_net->fib_chain);
return 0;
}
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index dd220ce7ca7a..3e7e15278c46 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -321,16 +321,18 @@ out:
}
EXPORT_SYMBOL_GPL(fib_rules_lookup);
-static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net,
+static int call_fib_rule_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
- struct fib_rule *rule, int family)
+ struct fib_rule *rule, int family,
+ struct netlink_ext_ack *extack)
{
struct fib_rule_notifier_info info = {
.info.family = family,
+ .info.extack = extack,
.rule = rule,
};
- return call_fib_notifier(nb, net, event_type, &info.info);
+ return call_fib_notifier(nb, event_type, &info.info);
}
static int call_fib_rule_notifiers(struct net *net,
@@ -350,20 +352,25 @@ static int call_fib_rule_notifiers(struct net *net,
}
/* Called with rcu_read_lock() */
-int fib_rules_dump(struct net *net, struct notifier_block *nb, int family)
+int fib_rules_dump(struct net *net, struct notifier_block *nb, int family,
+ struct netlink_ext_ack *extack)
{
struct fib_rules_ops *ops;
struct fib_rule *rule;
+ int err = 0;
ops = lookup_rules_ops(net, family);
if (!ops)
return -EAFNOSUPPORT;
- list_for_each_entry_rcu(rule, &ops->rules_list, list)
- call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule,
- family);
+ list_for_each_entry_rcu(rule, &ops->rules_list, list) {
+ err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD,
+ rule, family, extack);
+ if (err)
+ break;
+ }
rules_ops_put(ops);
- return 0;
+ return err;
}
EXPORT_SYMBOL_GPL(fib_rules_dump);
diff --git a/net/core/filter.c b/net/core/filter.c
index 3fed5755494b..b0ed048585ba 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2245,7 +2245,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
* account for the headroom.
*/
bytes_sg_total = start - offset + bytes;
- if (!msg->sg.copy[i] && bytes_sg_total <= len)
+ if (!test_bit(i, &msg->sg.copy) && bytes_sg_total <= len)
goto out;
/* At this point we need to linearize multiple scatterlist
@@ -2450,7 +2450,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
/* Place newly allocated data buffer */
sk_mem_charge(msg->sk, len);
msg->sg.size += len;
- msg->sg.copy[new] = false;
+ __clear_bit(new, &msg->sg.copy);
sg_set_page(&msg->sg.data[new], page, len + copy, 0);
if (rsge.length) {
get_page(sg_page(&rsge));
@@ -3798,7 +3798,7 @@ BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map,
if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK)))
return -EINVAL;
- if (unlikely(skb_size > skb->len))
+ if (unlikely(!skb || skb_size > skb->len))
return -EFAULT;
return bpf_event_output(map, flags, meta, meta_size, skb, skb_size,
@@ -3816,6 +3816,19 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = {
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
+static int bpf_skb_output_btf_ids[5];
+const struct bpf_func_proto bpf_skb_output_proto = {
+ .func = bpf_skb_event_output,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_BTF_ID,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_MEM,
+ .arg5_type = ARG_CONST_SIZE_OR_ZERO,
+ .btf_id = bpf_skb_output_btf_ids,
+};
+
static unsigned short bpf_tunnel_key_af(u64 flags)
{
return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET;
@@ -4089,7 +4102,7 @@ BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb)
return 0;
cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
- return cgrp->kn->id.id;
+ return cgroup_id(cgrp);
}
static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
@@ -4114,7 +4127,7 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
if (!ancestor)
return 0;
- return ancestor->kn->id.id;
+ return cgroup_id(ancestor);
}
static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
@@ -8671,16 +8684,6 @@ out:
}
#ifdef CONFIG_INET
-struct sk_reuseport_kern {
- struct sk_buff *skb;
- struct sock *sk;
- struct sock *selected_sk;
- void *data_end;
- u32 hash;
- u32 reuseport_id;
- bool bind_inany;
-};
-
static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
struct sock_reuseport *reuse,
struct sock *sk, struct sk_buff *skb,
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 7c09d87d3269..ca871657a4c4 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -114,19 +114,50 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
{
struct bpf_prog *attached;
struct net *net;
+ int ret = 0;
net = current->nsproxy->net_ns;
mutex_lock(&flow_dissector_mutex);
+
+ if (net == &init_net) {
+ /* BPF flow dissector in the root namespace overrides
+ * any per-net-namespace one. When attaching to root,
+ * make sure we don't have any BPF program attached
+ * to the non-root namespaces.
+ */
+ struct net *ns;
+
+ for_each_net(ns) {
+ if (ns == &init_net)
+ continue;
+ if (rcu_access_pointer(ns->flow_dissector_prog)) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+ } else {
+ /* Make sure root flow dissector is not attached
+ * when attaching to the non-root namespace.
+ */
+ if (rcu_access_pointer(init_net.flow_dissector_prog)) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+
attached = rcu_dereference_protected(net->flow_dissector_prog,
lockdep_is_held(&flow_dissector_mutex));
- if (attached) {
- /* Only one BPF program can be attached at a time */
- mutex_unlock(&flow_dissector_mutex);
- return -EEXIST;
+ if (attached == prog) {
+ /* The same program cannot be attached twice */
+ ret = -EINVAL;
+ goto out;
}
rcu_assign_pointer(net->flow_dissector_prog, prog);
+ if (attached)
+ bpf_prog_put(attached);
+out:
mutex_unlock(&flow_dissector_mutex);
- return 0;
+ return ret;
}
int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
@@ -147,27 +178,6 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
mutex_unlock(&flow_dissector_mutex);
return 0;
}
-/**
- * skb_flow_get_be16 - extract be16 entity
- * @skb: sk_buff to extract from
- * @poff: offset to extract at
- * @data: raw buffer pointer to the packet
- * @hlen: packet header length
- *
- * The function will try to retrieve a be32 entity at
- * offset poff
- */
-static __be16 skb_flow_get_be16(const struct sk_buff *skb, int poff,
- void *data, int hlen)
-{
- __be16 *u, _u;
-
- u = __skb_header_pointer(skb, poff, sizeof(_u), data, hlen, &_u);
- if (u)
- return *u;
-
- return 0;
-}
/**
* __skb_flow_get_ports - extract the upper layer ports and return them
@@ -203,6 +213,72 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
}
EXPORT_SYMBOL(__skb_flow_get_ports);
+static bool icmp_has_id(u8 type)
+{
+ switch (type) {
+ case ICMP_ECHO:
+ case ICMP_ECHOREPLY:
+ case ICMP_TIMESTAMP:
+ case ICMP_TIMESTAMPREPLY:
+ case ICMPV6_ECHO_REQUEST:
+ case ICMPV6_ECHO_REPLY:
+ return true;
+ }
+
+ return false;
+}
+
+/**
+ * skb_flow_get_icmp_tci - extract ICMP(6) Type, Code and Identifier fields
+ * @skb: sk_buff to extract from
+ * @key_icmp: struct flow_dissector_key_icmp to fill
+ * @data: raw buffer pointer to the packet
+ * @toff: offset to extract at
+ * @hlen: packet header length
+ */
+void skb_flow_get_icmp_tci(const struct sk_buff *skb,
+ struct flow_dissector_key_icmp *key_icmp,
+ void *data, int thoff, int hlen)
+{
+ struct icmphdr *ih, _ih;
+
+ ih = __skb_header_pointer(skb, thoff, sizeof(_ih), data, hlen, &_ih);
+ if (!ih)
+ return;
+
+ key_icmp->type = ih->type;
+ key_icmp->code = ih->code;
+
+ /* As we use 0 to signal that the Id field is not present,
+ * avoid confusion with packets without such field
+ */
+ if (icmp_has_id(ih->type))
+ key_icmp->id = ih->un.echo.id ? : 1;
+ else
+ key_icmp->id = 0;
+}
+EXPORT_SYMBOL(skb_flow_get_icmp_tci);
+
+/* If FLOW_DISSECTOR_KEY_ICMP is set, dissect an ICMP packet
+ * using skb_flow_get_icmp_tci().
+ */
+static void __skb_flow_dissect_icmp(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container,
+ void *data, int thoff, int hlen)
+{
+ struct flow_dissector_key_icmp *key_icmp;
+
+ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ICMP))
+ return;
+
+ key_icmp = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ICMP,
+ target_container);
+
+ skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen);
+}
+
void skb_flow_dissect_meta(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container)
@@ -853,7 +929,6 @@ bool __skb_flow_dissect(const struct net *net,
struct flow_dissector_key_basic *key_basic;
struct flow_dissector_key_addrs *key_addrs;
struct flow_dissector_key_ports *key_ports;
- struct flow_dissector_key_icmp *key_icmp;
struct flow_dissector_key_tags *key_tags;
struct flow_dissector_key_vlan *key_vlan;
struct bpf_prog *attached = NULL;
@@ -910,7 +985,10 @@ bool __skb_flow_dissect(const struct net *net,
WARN_ON_ONCE(!net);
if (net) {
rcu_read_lock();
- attached = rcu_dereference(net->flow_dissector_prog);
+ attached = rcu_dereference(init_net.flow_dissector_prog);
+
+ if (!attached)
+ attached = rcu_dereference(net->flow_dissector_prog);
if (attached) {
struct bpf_flow_keys flow_keys;
@@ -1295,6 +1373,12 @@ ip_proto_again:
data, nhoff, hlen);
break;
+ case IPPROTO_ICMP:
+ case IPPROTO_ICMPV6:
+ __skb_flow_dissect_icmp(skb, flow_dissector, target_container,
+ data, nhoff, hlen);
+ break;
+
default:
break;
}
@@ -1308,14 +1392,6 @@ ip_proto_again:
data, hlen);
}
- if (dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_ICMP)) {
- key_icmp = skb_flow_dissector_target(flow_dissector,
- FLOW_DISSECTOR_KEY_ICMP,
- target_container);
- key_icmp->icmp = skb_flow_get_be16(skb, nhoff, data, hlen);
- }
-
/* Process result of IP proto processing */
switch (fdret) {
case FLOW_DISSECT_RET_PROTO_AGAIN:
@@ -1350,32 +1426,23 @@ out_bad:
}
EXPORT_SYMBOL(__skb_flow_dissect);
-static u32 hashrnd __read_mostly;
+static siphash_key_t hashrnd __read_mostly;
static __always_inline void __flow_hash_secret_init(void)
{
net_get_random_once(&hashrnd, sizeof(hashrnd));
}
-static __always_inline u32 __flow_hash_words(const u32 *words, u32 length,
- u32 keyval)
-{
- return jhash2(words, length, keyval);
-}
-
-static inline const u32 *flow_keys_hash_start(const struct flow_keys *flow)
+static const void *flow_keys_hash_start(const struct flow_keys *flow)
{
- const void *p = flow;
-
- BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32));
- return (const u32 *)(p + FLOW_KEYS_HASH_OFFSET);
+ BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT);
+ return &flow->FLOW_KEYS_HASH_START_FIELD;
}
static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
{
size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs);
+
BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32));
- BUILD_BUG_ON(offsetof(typeof(*flow), addrs) !=
- sizeof(*flow) - sizeof(flow->addrs));
switch (flow->control.addr_type) {
case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
@@ -1388,7 +1455,7 @@ static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
diff -= sizeof(flow->addrs.tipckey);
break;
}
- return (sizeof(*flow) - diff) / sizeof(u32);
+ return sizeof(*flow) - diff;
}
__be32 flow_get_u32_src(const struct flow_keys *flow)
@@ -1421,6 +1488,9 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow)
}
EXPORT_SYMBOL(flow_get_u32_dst);
+/* Sort the source and destination IP (and the ports if the IP are the same),
+ * to have consistent hash within the two directions
+ */
static inline void __flow_hash_consistentify(struct flow_keys *keys)
{
int addr_diff, i;
@@ -1454,14 +1524,15 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
}
}
-static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
+static inline u32 __flow_hash_from_keys(struct flow_keys *keys,
+ const siphash_key_t *keyval)
{
u32 hash;
__flow_hash_consistentify(keys);
- hash = __flow_hash_words(flow_keys_hash_start(keys),
- flow_keys_hash_length(keys), keyval);
+ hash = siphash(flow_keys_hash_start(keys),
+ flow_keys_hash_length(keys), keyval);
if (!hash)
hash = 1;
@@ -1471,12 +1542,13 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
u32 flow_hash_from_keys(struct flow_keys *keys)
{
__flow_hash_secret_init();
- return __flow_hash_from_keys(keys, hashrnd);
+ return __flow_hash_from_keys(keys, &hashrnd);
}
EXPORT_SYMBOL(flow_hash_from_keys);
static inline u32 ___skb_get_hash(const struct sk_buff *skb,
- struct flow_keys *keys, u32 keyval)
+ struct flow_keys *keys,
+ const siphash_key_t *keyval)
{
skb_flow_dissect_flow_keys(skb, keys,
FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
@@ -1524,7 +1596,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
&keys, NULL, 0, 0, 0,
FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
- return __flow_hash_from_keys(&keys, hashrnd);
+ return __flow_hash_from_keys(&keys, &hashrnd);
}
EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);
@@ -1544,13 +1616,14 @@ void __skb_get_hash(struct sk_buff *skb)
__flow_hash_secret_init();
- hash = ___skb_get_hash(skb, &keys, hashrnd);
+ hash = ___skb_get_hash(skb, &keys, &hashrnd);
__skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
}
EXPORT_SYMBOL(__skb_get_hash);
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
+__u32 skb_get_hash_perturb(const struct sk_buff *skb,
+ const siphash_key_t *perturb)
{
struct flow_keys keys;
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index bfe7bdd4c340..80dbf2f4016e 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -48,7 +48,7 @@ struct net_rate_estimator {
u8 intvl_log; /* period : (250ms << intvl_log) */
seqcount_t seq;
- u32 last_packets;
+ u64 last_packets;
u64 last_bytes;
u64 avpps;
@@ -83,7 +83,7 @@ static void est_timer(struct timer_list *t)
brate = (b.bytes - est->last_bytes) << (10 - est->ewma_log - est->intvl_log);
brate -= (est->avbps >> est->ewma_log);
- rate = (u64)(b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log);
+ rate = (b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log);
rate -= (est->avpps >> est->ewma_log);
write_seqcount_begin(&est->seq);
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 36888f5e09eb..1d653fbfcf52 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -123,8 +123,7 @@ __gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats,
for_each_possible_cpu(i) {
struct gnet_stats_basic_cpu *bcpu = per_cpu_ptr(cpu, i);
unsigned int start;
- u64 bytes;
- u32 packets;
+ u64 bytes, packets;
do {
start = u64_stats_fetch_begin_irq(&bcpu->syncp);
@@ -176,12 +175,17 @@ ___gnet_stats_copy_basic(const seqcount_t *running,
if (d->tail) {
struct gnet_stats_basic sb;
+ int res;
memset(&sb, 0, sizeof(sb));
sb.bytes = bstats.bytes;
sb.packets = bstats.packets;
- return gnet_stats_copy(d, type, &sb, sizeof(sb),
- TCA_STATS_PAD);
+ res = gnet_stats_copy(d, type, &sb, sizeof(sb), TCA_STATS_PAD);
+ if (res < 0 || sb.packets == bstats.packets)
+ return res;
+ /* emit 64bit stats only if needed */
+ return gnet_stats_copy(d, TCA_STATS_PKT64, &bstats.packets,
+ sizeof(bstats.packets), TCA_STATS_PAD);
}
return 0;
}
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index f93785e5833c..74cfb8b5ab33 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -88,11 +88,16 @@ static int bpf_lwt_input_reroute(struct sk_buff *skb)
int err = -EINVAL;
if (skb->protocol == htons(ETH_P_IP)) {
+ struct net_device *dev = skb_dst(skb)->dev;
struct iphdr *iph = ip_hdr(skb);
+ dev_hold(dev);
+ skb_dst_drop(skb);
err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, skb_dst(skb)->dev);
+ iph->tos, dev);
+ dev_put(dev);
} else if (skb->protocol == htons(ETH_P_IPV6)) {
+ skb_dst_drop(skb);
err = ipv6_stub->ipv6_route_input(skb);
} else {
err = -EAFNOSUPPORT;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 5480edff0c86..652da6369037 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1197,7 +1197,7 @@ static void neigh_update_hhs(struct neighbour *neigh)
if (update) {
hh = &neigh->hh;
- if (hh->hh_len) {
+ if (READ_ONCE(hh->hh_len)) {
write_seqlock_bh(&hh->hh_lock);
update(hh, neigh->dev, neigh->ha);
write_sequnlock_bh(&hh->hh_lock);
@@ -1476,7 +1476,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
struct net_device *dev = neigh->dev;
unsigned int seq;
- if (dev->header_ops->cache && !neigh->hh.hh_len)
+ if (dev->header_ops->cache && !READ_ONCE(neigh->hh.hh_len))
neigh_hh_init(neigh);
do {
@@ -2052,8 +2052,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
goto nla_put_failure;
{
unsigned long now = jiffies;
- unsigned int flush_delta = now - tbl->last_flush;
- unsigned int rand_delta = now - tbl->last_rand;
+ long flush_delta = now - tbl->last_flush;
+ long rand_delta = now - tbl->last_rand;
struct neigh_hash_table *nht;
struct ndt_config ndc = {
.ndtc_key_len = tbl->key_len,
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 36347933ec3a..6bbd06f7dc7d 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -20,8 +20,8 @@ static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff
struct hlist_head *h;
unsigned int count = 0, offset = get_offset(*pos);
- h = &net->dev_name_head[get_bucket(*pos)];
- hlist_for_each_entry_rcu(dev, h, name_hlist) {
+ h = &net->dev_index_head[get_bucket(*pos)];
+ hlist_for_each_entry_rcu(dev, h, index_hlist) {
if (++count == offset)
return dev;
}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 865ba6ca16eb..ae3bcb1540ec 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -923,21 +923,23 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL,
"rx-%u", index);
if (error)
- return error;
+ goto err;
dev_hold(queue->dev);
if (dev->sysfs_rx_queue_group) {
error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group);
- if (error) {
- kobject_put(kobj);
- return error;
- }
+ if (error)
+ goto err;
}
kobject_uevent(kobj, KOBJ_ADD);
return error;
+
+err:
+ kobject_put(kobj);
+ return error;
}
#endif /* CONFIG_SYSFS */
@@ -1461,21 +1463,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL,
"tx-%u", index);
if (error)
- return error;
+ goto err;
dev_hold(queue->dev);
#ifdef CONFIG_BQL
error = sysfs_create_group(kobj, &dql_group);
- if (error) {
- kobject_put(kobj);
- return error;
- }
+ if (error)
+ goto err;
#endif
kobject_uevent(kobj, KOBJ_ADD);
-
return 0;
+
+err:
+ kobject_put(kobj);
+ return error;
}
#endif /* CONFIG_SYSFS */
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6d3e4821b02d..39402840025e 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -246,11 +246,11 @@ static int __peernet2id(struct net *net, struct net *peer)
}
static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
- struct nlmsghdr *nlh);
+ struct nlmsghdr *nlh, gfp_t gfp);
/* This function returns the id of a peer netns. If no id is assigned, one will
* be allocated and returned.
*/
-int peernet2id_alloc(struct net *net, struct net *peer)
+int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
{
bool alloc = false, alive = false;
int id;
@@ -269,7 +269,7 @@ int peernet2id_alloc(struct net *net, struct net *peer)
id = __peernet2id_alloc(net, peer, &alloc);
spin_unlock_bh(&net->nsid_lock);
if (alloc && id >= 0)
- rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL);
+ rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp);
if (alive)
put_net(peer);
return id;
@@ -479,6 +479,7 @@ struct net *copy_net_ns(unsigned long flags,
if (rv < 0) {
put_userns:
+ key_remove_domain(net->key_domain);
put_user_ns(user_ns);
net_drop_ns(net);
dec_ucounts:
@@ -533,7 +534,8 @@ static void unhash_nsid(struct net *net, struct net *last)
idr_remove(&tmp->netns_ids, id);
spin_unlock_bh(&tmp->nsid_lock);
if (id >= 0)
- rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL);
+ rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL,
+ GFP_KERNEL);
if (tmp == last)
break;
}
@@ -766,7 +768,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
spin_unlock_bh(&net->nsid_lock);
if (err >= 0) {
rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid,
- nlh);
+ nlh, GFP_KERNEL);
err = 0;
} else if (err == -ENOSPC && nsid >= 0) {
err = -EEXIST;
@@ -1054,7 +1056,7 @@ end:
}
static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
- struct nlmsghdr *nlh)
+ struct nlmsghdr *nlh, gfp_t gfp)
{
struct net_fill_args fillargs = {
.portid = portid,
@@ -1065,7 +1067,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
struct sk_buff *msg;
int err = -ENOMEM;
- msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
+ msg = nlmsg_new(rtnl_net_get_size(), gfp);
if (!msg)
goto out;
@@ -1073,7 +1075,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
if (err < 0)
goto err_out;
- rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, 0);
+ rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, gfp);
return;
err_out:
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 256b7954b720..8881dd943dd0 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -93,7 +93,7 @@ static int extend_netdev_table(struct net_device *dev, u32 target_idx)
static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev)
{
struct netprio_map *map = rcu_dereference_rtnl(dev->priomap);
- int id = css->cgroup->id;
+ int id = css->id;
if (map && id < map->priomap_len)
return map->priomap[id];
@@ -113,7 +113,7 @@ static int netprio_set_prio(struct cgroup_subsys_state *css,
struct net_device *dev, u32 prio)
{
struct netprio_map *map;
- int id = css->cgroup->id;
+ int id = css->id;
int ret;
/* avoid extending priomap for zero writes */
@@ -177,7 +177,7 @@ static void cgrp_css_free(struct cgroup_subsys_state *css)
static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft)
{
- return css->cgroup->id;
+ return css->id;
}
static int read_priomap(struct seq_file *sf, void *v)
@@ -237,7 +237,7 @@ static void net_prio_attach(struct cgroup_taskset *tset)
struct cgroup_subsys_state *css;
cgroup_taskset_for_each(p, css, tset) {
- void *v = (void *)(unsigned long)css->cgroup->id;
+ void *v = (void *)(unsigned long)css->id;
task_lock(p);
iterate_fd(p->files, 0, update_netprio, v);
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 5bc65587f1c4..a6aefe989043 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -18,6 +18,9 @@
#include <trace/events/page_pool.h>
+#define DEFER_TIME (msecs_to_jiffies(1000))
+#define DEFER_WARN_INTERVAL (60 * HZ)
+
static int page_pool_init(struct page_pool *pool,
const struct page_pool_params *params)
{
@@ -44,6 +47,21 @@ static int page_pool_init(struct page_pool *pool,
(pool->p.dma_dir != DMA_BIDIRECTIONAL))
return -EINVAL;
+ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) {
+ /* In order to request DMA-sync-for-device the page
+ * needs to be mapped
+ */
+ if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+ return -EINVAL;
+
+ if (!pool->p.max_len)
+ return -EINVAL;
+
+ /* pool->p.offset has to be set according to the address
+ * offset used by the DMA engine to start copying rx data
+ */
+ }
+
if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
return -ENOMEM;
@@ -112,6 +130,16 @@ static struct page *__page_pool_get_cached(struct page_pool *pool)
return page;
}
+static void page_pool_dma_sync_for_device(struct page_pool *pool,
+ struct page *page,
+ unsigned int dma_sync_size)
+{
+ dma_sync_size = min(dma_sync_size, pool->p.max_len);
+ dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
+ pool->p.offset, dma_sync_size,
+ pool->p.dma_dir);
+}
+
/* slow path */
noinline
static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
@@ -156,6 +184,9 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
}
page->dma_addr = dma;
+ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+ page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
+
skip_dma_map:
/* Track how many pages are held 'in-flight' */
pool->pages_state_hold_cnt++;
@@ -193,22 +224,14 @@ static s32 page_pool_inflight(struct page_pool *pool)
{
u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
- s32 distance;
+ s32 inflight;
- distance = _distance(hold_cnt, release_cnt);
+ inflight = _distance(hold_cnt, release_cnt);
- trace_page_pool_inflight(pool, distance, hold_cnt, release_cnt);
- return distance;
-}
-
-static bool __page_pool_safe_to_destroy(struct page_pool *pool)
-{
- s32 inflight = page_pool_inflight(pool);
-
- /* The distance should not be able to become negative */
+ trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight);
- return (inflight == 0);
+ return inflight;
}
/* Cleanup page_pool state from page */
@@ -216,6 +239,7 @@ static void __page_pool_clean_page(struct page_pool *pool,
struct page *page)
{
dma_addr_t dma;
+ int count;
if (!(pool->p.flags & PP_FLAG_DMA_MAP))
goto skip_dma_unmap;
@@ -227,9 +251,11 @@ static void __page_pool_clean_page(struct page_pool *pool,
DMA_ATTR_SKIP_CPU_SYNC);
page->dma_addr = 0;
skip_dma_unmap:
- atomic_inc(&pool->pages_state_release_cnt);
- trace_page_pool_state_release(pool, page,
- atomic_read(&pool->pages_state_release_cnt));
+ /* This may be the last page returned, releasing the pool, so
+ * it is not safe to reference pool afterwards.
+ */
+ count = atomic_inc_return(&pool->pages_state_release_cnt);
+ trace_page_pool_state_release(pool, page, count);
}
/* unmap the page and clean our state */
@@ -283,8 +309,19 @@ static bool __page_pool_recycle_direct(struct page *page,
return true;
}
-void __page_pool_put_page(struct page_pool *pool,
- struct page *page, bool allow_direct)
+/* page is NOT reusable when:
+ * 1) allocated when system is under some pressure. (page_is_pfmemalloc)
+ * 2) belongs to a different NUMA node than pool->p.nid.
+ *
+ * To update pool->p.nid users must call page_pool_update_nid.
+ */
+static bool pool_page_reusable(struct page_pool *pool, struct page *page)
+{
+ return !page_is_pfmemalloc(page) && page_to_nid(page) == pool->p.nid;
+}
+
+void __page_pool_put_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct)
{
/* This allocator is optimized for the XDP mode that uses
* one-frame-per-page, but have fallbacks that act like the
@@ -292,9 +329,14 @@ void __page_pool_put_page(struct page_pool *pool,
*
* refcnt == 1 means page_pool owns page, and can recycle it.
*/
- if (likely(page_ref_count(page) == 1)) {
+ if (likely(page_ref_count(page) == 1 &&
+ pool_page_reusable(pool, page))) {
/* Read barrier done in page_ref_count / READ_ONCE */
+ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+ page_pool_dma_sync_for_device(pool, page,
+ dma_sync_size);
+
if (allow_direct && in_serving_softirq())
if (__page_pool_recycle_direct(page, pool))
return;
@@ -338,31 +380,10 @@ static void __page_pool_empty_ring(struct page_pool *pool)
}
}
-static void __warn_in_flight(struct page_pool *pool)
+static void page_pool_free(struct page_pool *pool)
{
- u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
- u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
- s32 distance;
-
- distance = _distance(hold_cnt, release_cnt);
-
- /* Drivers should fix this, but only problematic when DMA is used */
- WARN(1, "Still in-flight pages:%d hold:%u released:%u",
- distance, hold_cnt, release_cnt);
-}
-
-void __page_pool_free(struct page_pool *pool)
-{
- /* Only last user actually free/release resources */
- if (!page_pool_put(pool))
- return;
-
- WARN(pool->alloc.count, "API usage violation");
- WARN(!ptr_ring_empty(&pool->ring), "ptr_ring is not empty");
-
- /* Can happen due to forced shutdown */
- if (!__page_pool_safe_to_destroy(pool))
- __warn_in_flight(pool);
+ if (pool->disconnect)
+ pool->disconnect(pool);
ptr_ring_cleanup(&pool->ring, NULL);
@@ -371,15 +392,14 @@ void __page_pool_free(struct page_pool *pool)
kfree(pool);
}
-EXPORT_SYMBOL(__page_pool_free);
-/* Request to shutdown: release pages cached by page_pool, and check
- * for in-flight pages
- */
-bool __page_pool_request_shutdown(struct page_pool *pool)
+static void page_pool_empty_alloc_cache_once(struct page_pool *pool)
{
struct page *page;
+ if (pool->destroy_cnt)
+ return;
+
/* Empty alloc cache, assume caller made sure this is
* no-longer in use, and page_pool_alloc_pages() cannot be
* call concurrently.
@@ -388,12 +408,83 @@ bool __page_pool_request_shutdown(struct page_pool *pool)
page = pool->alloc.cache[--pool->alloc.count];
__page_pool_return_page(pool, page);
}
+}
+
+static void page_pool_scrub(struct page_pool *pool)
+{
+ page_pool_empty_alloc_cache_once(pool);
+ pool->destroy_cnt++;
/* No more consumers should exist, but producers could still
* be in-flight.
*/
__page_pool_empty_ring(pool);
+}
+
+static int page_pool_release(struct page_pool *pool)
+{
+ int inflight;
+
+ page_pool_scrub(pool);
+ inflight = page_pool_inflight(pool);
+ if (!inflight)
+ page_pool_free(pool);
+
+ return inflight;
+}
+
+static void page_pool_release_retry(struct work_struct *wq)
+{
+ struct delayed_work *dwq = to_delayed_work(wq);
+ struct page_pool *pool = container_of(dwq, typeof(*pool), release_dw);
+ int inflight;
+
+ inflight = page_pool_release(pool);
+ if (!inflight)
+ return;
+
+ /* Periodic warning */
+ if (time_after_eq(jiffies, pool->defer_warn)) {
+ int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ;
+
+ pr_warn("%s() stalled pool shutdown %d inflight %d sec\n",
+ __func__, inflight, sec);
+ pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
+ }
+
+ /* Still not ready to be disconnected, retry later */
+ schedule_delayed_work(&pool->release_dw, DEFER_TIME);
+}
- return __page_pool_safe_to_destroy(pool);
+void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *))
+{
+ refcount_inc(&pool->user_cnt);
+ pool->disconnect = disconnect;
+}
+
+void page_pool_destroy(struct page_pool *pool)
+{
+ if (!pool)
+ return;
+
+ if (!page_pool_put(pool))
+ return;
+
+ if (!page_pool_release(pool))
+ return;
+
+ pool->defer_start = jiffies;
+ pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
+
+ INIT_DELAYED_WORK(&pool->release_dw, page_pool_release_retry);
+ schedule_delayed_work(&pool->release_dw, DEFER_TIME);
+}
+EXPORT_SYMBOL(page_pool_destroy);
+
+/* Caller must provide appropriate safe context, e.g. NAPI. */
+void page_pool_update_nid(struct page_pool *pool, int new_nid)
+{
+ trace_page_pool_update_nid(pool, new_nid);
+ pool->p.nid = new_nid;
}
-EXPORT_SYMBOL(__page_pool_request_shutdown);
+EXPORT_SYMBOL(page_pool_update_nid);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 48b1e429857c..294bfcf0ce0e 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3404,7 +3404,6 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
HARD_TX_LOCK(odev, txq, smp_processor_id());
if (unlikely(netif_xmit_frozen_or_drv_stopped(txq))) {
- ret = NETDEV_TX_BUSY;
pkt_dev->last_ok = 0;
goto unlock;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1ee6460f8275..9f7aa448bd11 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -980,6 +980,19 @@ static size_t rtnl_xdp_size(void)
return xdp_size;
}
+static size_t rtnl_prop_list_size(const struct net_device *dev)
+{
+ struct netdev_name_node *name_node;
+ size_t size;
+
+ if (list_empty(&dev->name_node->list))
+ return 0;
+ size = nla_total_size(0);
+ list_for_each_entry(name_node, &dev->name_node->list, list)
+ size += nla_total_size(ALTIFNAMSIZ);
+ return size;
+}
+
static noinline size_t if_nlmsg_size(const struct net_device *dev,
u32 ext_filter_mask)
{
@@ -1027,6 +1040,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */
+ nla_total_size(4) /* IFLA_MIN_MTU */
+ nla_total_size(4) /* IFLA_MAX_MTU */
+ + rtnl_prop_list_size(dev)
+ 0;
}
@@ -1523,7 +1537,7 @@ static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
static int rtnl_fill_link_netnsid(struct sk_buff *skb,
const struct net_device *dev,
- struct net *src_net)
+ struct net *src_net, gfp_t gfp)
{
bool put_iflink = false;
@@ -1531,7 +1545,7 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb,
struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
if (!net_eq(dev_net(dev), link_net)) {
- int id = peernet2id_alloc(src_net, link_net);
+ int id = peernet2id_alloc(src_net, link_net, gfp);
if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
return -EMSGSIZE;
@@ -1584,12 +1598,48 @@ static int rtnl_fill_link_af(struct sk_buff *skb,
return 0;
}
+static int rtnl_fill_alt_ifnames(struct sk_buff *skb,
+ const struct net_device *dev)
+{
+ struct netdev_name_node *name_node;
+ int count = 0;
+
+ list_for_each_entry(name_node, &dev->name_node->list, list) {
+ if (nla_put_string(skb, IFLA_ALT_IFNAME, name_node->name))
+ return -EMSGSIZE;
+ count++;
+ }
+ return count;
+}
+
+static int rtnl_fill_prop_list(struct sk_buff *skb,
+ const struct net_device *dev)
+{
+ struct nlattr *prop_list;
+ int ret;
+
+ prop_list = nla_nest_start(skb, IFLA_PROP_LIST);
+ if (!prop_list)
+ return -EMSGSIZE;
+
+ ret = rtnl_fill_alt_ifnames(skb, dev);
+ if (ret <= 0)
+ goto nest_cancel;
+
+ nla_nest_end(skb, prop_list);
+ return 0;
+
+nest_cancel:
+ nla_nest_cancel(skb, prop_list);
+ return ret;
+}
+
static int rtnl_fill_ifinfo(struct sk_buff *skb,
struct net_device *dev, struct net *src_net,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags, u32 ext_filter_mask,
u32 event, int *new_nsid, int new_ifindex,
- int tgt_netnsid)
+ int tgt_netnsid, gfp_t gfp)
{
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
@@ -1681,7 +1731,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
goto nla_put_failure;
}
- if (rtnl_fill_link_netnsid(skb, dev, src_net))
+ if (rtnl_fill_link_netnsid(skb, dev, src_net, gfp))
goto nla_put_failure;
if (new_nsid &&
@@ -1697,6 +1747,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
goto nla_put_failure_rcu;
rcu_read_unlock();
+ if (rtnl_fill_prop_list(skb, dev))
+ goto nla_put_failure;
+
nlmsg_end(skb, nlh);
return 0;
@@ -1750,6 +1803,9 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 },
[IFLA_MIN_MTU] = { .type = NLA_U32 },
[IFLA_MAX_MTU] = { .type = NLA_U32 },
+ [IFLA_PROP_LIST] = { .type = NLA_NESTED },
+ [IFLA_ALT_IFNAME] = { .type = NLA_STRING,
+ .len = ALTIFNAMSIZ - 1 },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2001,7 +2057,7 @@ walk_entries:
NETLINK_CB(cb->skb).portid,
nlh->nlmsg_seq, 0, flags,
ext_filter_mask, 0, NULL, 0,
- netnsid);
+ netnsid, GFP_KERNEL);
if (err < 0) {
if (likely(skb->len))
@@ -2195,6 +2251,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_MAC]) {
struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
+ if (ivm->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_mac)
err = ops->ndo_set_vf_mac(dev, ivm->vf,
@@ -2206,6 +2264,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_VLAN]) {
struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
+ if (ivv->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_vlan)
err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
@@ -2238,6 +2298,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (len == 0)
return -EINVAL;
+ if (ivvl[0]->vf >= INT_MAX)
+ return -EINVAL;
err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan,
ivvl[0]->qos, ivvl[0]->vlan_proto);
if (err < 0)
@@ -2248,6 +2310,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
struct ifla_vf_info ivf;
+ if (ivt->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_get_vf_config)
err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
@@ -2266,6 +2330,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_RATE]) {
struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);
+ if (ivt->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_rate)
err = ops->ndo_set_vf_rate(dev, ivt->vf,
@@ -2278,6 +2344,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_SPOOFCHK]) {
struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
+ if (ivs->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_spoofchk)
err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
@@ -2289,6 +2357,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_LINK_STATE]) {
struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
+ if (ivl->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_link_state)
err = ops->ndo_set_vf_link_state(dev, ivl->vf,
@@ -2302,6 +2372,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
err = -EOPNOTSUPP;
ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]);
+ if (ivrssq_en->vf >= INT_MAX)
+ return -EINVAL;
if (ops->ndo_set_vf_rss_query_en)
err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf,
ivrssq_en->setting);
@@ -2312,6 +2384,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_TRUST]) {
struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]);
+ if (ivt->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_trust)
err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting);
@@ -2322,15 +2396,18 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_IB_NODE_GUID]) {
struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]);
+ if (ivt->vf >= INT_MAX)
+ return -EINVAL;
if (!ops->ndo_set_vf_guid)
return -EOPNOTSUPP;
-
return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID);
}
if (tb[IFLA_VF_IB_PORT_GUID]) {
struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]);
+ if (ivt->vf >= INT_MAX)
+ return -EINVAL;
if (!ops->ndo_set_vf_guid)
return -EOPNOTSUPP;
@@ -2355,6 +2432,7 @@ static int do_set_master(struct net_device *dev, int ifindex,
err = ops->ndo_del_slave(upper_dev, dev);
if (err)
return err;
+ netdev_update_lockdep_key(dev);
} else {
return -EOPNOTSUPP;
}
@@ -2722,6 +2800,26 @@ errout:
return err;
}
+static struct net_device *rtnl_dev_get(struct net *net,
+ struct nlattr *ifname_attr,
+ struct nlattr *altifname_attr,
+ char *ifname)
+{
+ char buffer[ALTIFNAMSIZ];
+
+ if (!ifname) {
+ ifname = buffer;
+ if (ifname_attr)
+ nla_strlcpy(ifname, ifname_attr, IFNAMSIZ);
+ else if (altifname_attr)
+ nla_strlcpy(ifname, altifname_attr, ALTIFNAMSIZ);
+ else
+ return NULL;
+ }
+
+ return __dev_get_by_name(net, ifname);
+}
+
static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -2750,8 +2848,8 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(net, ifm->ifi_index);
- else if (tb[IFLA_IFNAME])
- dev = __dev_get_by_name(net, ifname);
+ else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
+ dev = rtnl_dev_get(net, NULL, tb[IFLA_ALT_IFNAME], ifname);
else
goto errout;
@@ -2824,7 +2922,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net *tgt_net = net;
struct net_device *dev = NULL;
struct ifinfomsg *ifm;
- char ifname[IFNAMSIZ];
struct nlattr *tb[IFLA_MAX+1];
int err;
int netnsid = -1;
@@ -2838,9 +2935,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
- if (tb[IFLA_IFNAME])
- nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
-
if (tb[IFLA_TARGET_NETNSID]) {
netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]);
tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid);
@@ -2852,8 +2946,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
- else if (tb[IFLA_IFNAME])
- dev = __dev_get_by_name(tgt_net, ifname);
+ else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
+ dev = rtnl_dev_get(net, tb[IFLA_IFNAME],
+ tb[IFLA_ALT_IFNAME], NULL);
else if (tb[IFLA_GROUP])
err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP]));
else
@@ -3024,12 +3119,10 @@ replay:
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(net, ifm->ifi_index);
- else {
- if (ifname[0])
- dev = __dev_get_by_name(net, ifname);
- else
- dev = NULL;
- }
+ else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
+ dev = rtnl_dev_get(net, NULL, tb[IFLA_ALT_IFNAME], ifname);
+ else
+ dev = NULL;
if (dev) {
master_dev = netdev_master_upper_dev_get(dev);
@@ -3291,6 +3384,7 @@ static int rtnl_valid_getlink_req(struct sk_buff *skb,
switch (i) {
case IFLA_IFNAME:
+ case IFLA_ALT_IFNAME:
case IFLA_EXT_MASK:
case IFLA_TARGET_NETNSID:
break;
@@ -3309,7 +3403,6 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net *net = sock_net(skb->sk);
struct net *tgt_net = net;
struct ifinfomsg *ifm;
- char ifname[IFNAMSIZ];
struct nlattr *tb[IFLA_MAX+1];
struct net_device *dev = NULL;
struct sk_buff *nskb;
@@ -3332,9 +3425,6 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
return PTR_ERR(tgt_net);
}
- if (tb[IFLA_IFNAME])
- nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
-
if (tb[IFLA_EXT_MASK])
ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
@@ -3342,8 +3432,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
- else if (tb[IFLA_IFNAME])
- dev = __dev_get_by_name(tgt_net, ifname);
+ else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
+ dev = rtnl_dev_get(tgt_net, tb[IFLA_IFNAME],
+ tb[IFLA_ALT_IFNAME], NULL);
else
goto out;
@@ -3359,7 +3450,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
err = rtnl_fill_ifinfo(nskb, dev, net,
RTM_NEWLINK, NETLINK_CB(skb).portid,
nlh->nlmsg_seq, 0, 0, ext_filter_mask,
- 0, NULL, 0, netnsid);
+ 0, NULL, 0, netnsid, GFP_KERNEL);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size */
WARN_ON(err == -EMSGSIZE);
@@ -3373,6 +3464,100 @@ out:
return err;
}
+static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr,
+ bool *changed, struct netlink_ext_ack *extack)
+{
+ char *alt_ifname;
+ int err;
+
+ err = nla_validate(attr, attr->nla_len, IFLA_MAX, ifla_policy, extack);
+ if (err)
+ return err;
+
+ alt_ifname = nla_data(attr);
+ if (cmd == RTM_NEWLINKPROP) {
+ alt_ifname = kstrdup(alt_ifname, GFP_KERNEL);
+ if (!alt_ifname)
+ return -ENOMEM;
+ err = netdev_name_node_alt_create(dev, alt_ifname);
+ if (err) {
+ kfree(alt_ifname);
+ return err;
+ }
+ } else if (cmd == RTM_DELLINKPROP) {
+ err = netdev_name_node_alt_destroy(dev, alt_ifname);
+ if (err)
+ return err;
+ } else {
+ WARN_ON(1);
+ return 0;
+ }
+
+ *changed = true;
+ return 0;
+}
+
+static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = sock_net(skb->sk);
+ struct nlattr *tb[IFLA_MAX + 1];
+ struct net_device *dev;
+ struct ifinfomsg *ifm;
+ bool changed = false;
+ struct nlattr *attr;
+ int err, rem;
+
+ err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
+ if (err)
+ return err;
+
+ err = rtnl_ensure_unique_netns(tb, extack, true);
+ if (err)
+ return err;
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->ifi_index > 0)
+ dev = __dev_get_by_index(net, ifm->ifi_index);
+ else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
+ dev = rtnl_dev_get(net, tb[IFLA_IFNAME],
+ tb[IFLA_ALT_IFNAME], NULL);
+ else
+ return -EINVAL;
+
+ if (!dev)
+ return -ENODEV;
+
+ if (!tb[IFLA_PROP_LIST])
+ return 0;
+
+ nla_for_each_nested(attr, tb[IFLA_PROP_LIST], rem) {
+ switch (nla_type(attr)) {
+ case IFLA_ALT_IFNAME:
+ err = rtnl_alt_ifname(cmd, dev, attr, &changed, extack);
+ if (err)
+ return err;
+ break;
+ }
+ }
+
+ if (changed)
+ netdev_state_change(dev);
+ return 0;
+}
+
+static int rtnl_newlinkprop(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ return rtnl_linkprop(RTM_NEWLINKPROP, skb, nlh, extack);
+}
+
+static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack);
+}
+
static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
@@ -3471,7 +3656,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
err = rtnl_fill_ifinfo(skb, dev, dev_net(dev),
type, 0, 0, change, 0, 0, event,
- new_nsid, new_ifindex, -1);
+ new_nsid, new_ifindex, -1, flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -3916,7 +4101,7 @@ static int valid_fdb_dump_strict(const struct nlmsghdr *nlh,
ndm = nlmsg_data(nlh);
if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state ||
ndm->ndm_flags || ndm->ndm_type) {
- NL_SET_ERR_MSG(extack, "Invalid values in header for fbd dump request");
+ NL_SET_ERR_MSG(extack, "Invalid values in header for fdb dump request");
return -EINVAL;
}
@@ -5331,6 +5516,9 @@ void __init rtnetlink_init(void)
rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, 0);
rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, 0);
+ rtnl_register(PF_UNSPEC, RTM_NEWLINKPROP, rtnl_newlinkprop, NULL, 0);
+ rtnl_register(PF_UNSPEC, RTM_DELLINKPROP, rtnl_dellinkprop, NULL, 0);
+
rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0);
rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0);
rtnl_register(PF_BRIDGE, RTM_GETNEIGH, rtnl_fdb_get, rtnl_fdb_dump, 0);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index cf390e0aa73d..a469d2124f3f 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -270,18 +270,28 @@ void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len)
msg->sg.data[i].length -= trim;
sk_mem_uncharge(sk, trim);
+ /* Adjust copybreak if it falls into the trimmed part of last buf */
+ if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length)
+ msg->sg.copybreak = msg->sg.data[i].length;
out:
- /* If we trim data before curr pointer update copybreak and current
- * so that any future copy operations start at new copy location.
+ sk_msg_iter_var_next(i);
+ msg->sg.end = i;
+
+ /* If we trim data a full sg elem before curr pointer update
+ * copybreak and current so that any future copy operations
+ * start at new copy location.
* However trimed data that has not yet been used in a copy op
* does not require an update.
*/
- if (msg->sg.curr >= i) {
+ if (!msg->sg.size) {
+ msg->sg.curr = msg->sg.start;
+ msg->sg.copybreak = 0;
+ } else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >=
+ sk_msg_iter_dist(msg->sg.start, msg->sg.end)) {
+ sk_msg_iter_var_prev(i);
msg->sg.curr = i;
msg->sg.copybreak = msg->sg.data[i].length;
}
- sk_msg_iter_var_next(i);
- msg->sg.end = i;
}
EXPORT_SYMBOL_GPL(sk_msg_trim);
@@ -783,15 +793,18 @@ static void sk_psock_strp_data_ready(struct sock *sk)
static void sk_psock_write_space(struct sock *sk)
{
struct sk_psock *psock;
- void (*write_space)(struct sock *sk);
+ void (*write_space)(struct sock *sk) = NULL;
rcu_read_lock();
psock = sk_psock(sk);
- if (likely(psock && sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)))
- schedule_work(&psock->work);
- write_space = psock->saved_write_space;
+ if (likely(psock)) {
+ if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+ schedule_work(&psock->work);
+ write_space = psock->saved_write_space;
+ }
rcu_read_unlock();
- write_space(sk);
+ if (write_space)
+ write_space(sk);
}
int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
diff --git a/net/core/sock.c b/net/core/sock.c
index a515392ba84b..71787f7c4f8c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -333,7 +333,6 @@ EXPORT_SYMBOL(__sk_backlog_rcv);
static int sock_get_timeout(long timeo, void *optval, bool old_timeval)
{
struct __kernel_sock_timeval tv;
- int size;
if (timeo == MAX_SCHEDULE_TIMEOUT) {
tv.tv_sec = 0;
@@ -354,13 +353,11 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval)
old_tv.tv_sec = tv.tv_sec;
old_tv.tv_usec = tv.tv_usec;
*(struct __kernel_old_timeval *)optval = old_tv;
- size = sizeof(old_tv);
- } else {
- *(struct __kernel_sock_timeval *)optval = tv;
- size = sizeof(tv);
+ return sizeof(old_tv);
}
- return size;
+ *(struct __kernel_sock_timeval *)optval = tv;
+ return sizeof(tv);
}
static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool old_timeval)
@@ -687,7 +684,8 @@ out:
return ret;
}
-static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
+static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit,
+ int valbool)
{
if (valbool)
sock_set_flag(sk, bit);
@@ -1127,7 +1125,7 @@ set_rcvbuf:
break;
}
case SO_INCOMING_CPU:
- sk->sk_incoming_cpu = val;
+ WRITE_ONCE(sk->sk_incoming_cpu, val);
break;
case SO_CNX_ADVICE:
@@ -1476,7 +1474,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_INCOMING_CPU:
- v.val = sk->sk_incoming_cpu;
+ v.val = READ_ONCE(sk->sk_incoming_cpu);
break;
case SO_MEMINFO:
@@ -3015,7 +3013,7 @@ int sock_gettstamp(struct socket *sock, void __user *userstamp,
return -ENOENT;
if (ts.tv_sec == 0) {
ktime_t kt = ktime_get_real();
- sock_write_timestamp(sk, kt);;
+ sock_write_timestamp(sk, kt);
ts = ktime_to_timespec64(kt);
}
@@ -3042,7 +3040,7 @@ int sock_gettstamp(struct socket *sock, void __user *userstamp,
}
EXPORT_SYMBOL(sock_gettstamp);
-void sock_enable_timestamp(struct sock *sk, int flag)
+void sock_enable_timestamp(struct sock *sk, enum sock_flags flag)
{
if (!sock_flag(sk, flag)) {
unsigned long previous_flags = sk->sk_flags;
@@ -3600,7 +3598,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time)
{
struct sock *sk = p;
- return !skb_queue_empty(&sk->sk_receive_queue) ||
+ return !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
sk_busy_loop_timeout(sk, start_time);
}
EXPORT_SYMBOL(sk_busy_loop_end);
diff --git a/net/core/xdp.c b/net/core/xdp.c
index d7bf62ffbb5e..e334fad0a6b8 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -70,77 +70,63 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu)
xa = container_of(rcu, struct xdp_mem_allocator, rcu);
- /* Allocator have indicated safe to remove before this is called */
- if (xa->mem.type == MEM_TYPE_PAGE_POOL)
- page_pool_free(xa->page_pool);
-
/* Allow this ID to be reused */
ida_simple_remove(&mem_id_pool, xa->mem.id);
- /* Poison memory */
- xa->mem.id = 0xFFFF;
- xa->mem.type = 0xF0F0;
- xa->allocator = (void *)0xDEAD9001;
-
kfree(xa);
}
-static bool __mem_id_disconnect(int id, bool force)
+static void mem_xa_remove(struct xdp_mem_allocator *xa)
{
- struct xdp_mem_allocator *xa;
- bool safe_to_remove = true;
+ trace_mem_disconnect(xa);
mutex_lock(&mem_id_lock);
- xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
- if (!xa) {
- mutex_unlock(&mem_id_lock);
- WARN(1, "Request remove non-existing id(%d), driver bug?", id);
- return true;
- }
- xa->disconnect_cnt++;
-
- /* Detects in-flight packet-pages for page_pool */
- if (xa->mem.type == MEM_TYPE_PAGE_POOL)
- safe_to_remove = page_pool_request_shutdown(xa->page_pool);
-
- trace_mem_disconnect(xa, safe_to_remove, force);
-
- if ((safe_to_remove || force) &&
- !rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
+ if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free);
mutex_unlock(&mem_id_lock);
- return (safe_to_remove|force);
}
-#define DEFER_TIME (msecs_to_jiffies(1000))
-#define DEFER_WARN_INTERVAL (30 * HZ)
-#define DEFER_MAX_RETRIES 120
+static void mem_allocator_disconnect(void *allocator)
+{
+ struct xdp_mem_allocator *xa;
+ struct rhashtable_iter iter;
+
+ rhashtable_walk_enter(mem_id_ht, &iter);
+ do {
+ rhashtable_walk_start(&iter);
+
+ while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) {
+ if (xa->allocator == allocator)
+ mem_xa_remove(xa);
+ }
+
+ rhashtable_walk_stop(&iter);
-static void mem_id_disconnect_defer_retry(struct work_struct *wq)
+ } while (xa == ERR_PTR(-EAGAIN));
+ rhashtable_walk_exit(&iter);
+}
+
+static void mem_id_disconnect(int id)
{
- struct delayed_work *dwq = to_delayed_work(wq);
- struct xdp_mem_allocator *xa = container_of(dwq, typeof(*xa), defer_wq);
- bool force = false;
+ struct xdp_mem_allocator *xa;
- if (xa->disconnect_cnt > DEFER_MAX_RETRIES)
- force = true;
+ mutex_lock(&mem_id_lock);
- if (__mem_id_disconnect(xa->mem.id, force))
+ xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
+ if (!xa) {
+ mutex_unlock(&mem_id_lock);
+ WARN(1, "Request remove non-existing id(%d), driver bug?", id);
return;
+ }
- /* Periodic warning */
- if (time_after_eq(jiffies, xa->defer_warn)) {
- int sec = (s32)((u32)jiffies - (u32)xa->defer_start) / HZ;
+ trace_mem_disconnect(xa);
- pr_warn("%s() stalled mem.id=%u shutdown %d attempts %d sec\n",
- __func__, xa->mem.id, xa->disconnect_cnt, sec);
- xa->defer_warn = jiffies + DEFER_WARN_INTERVAL;
- }
+ if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
+ call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free);
- /* Still not ready to be disconnected, retry later */
- schedule_delayed_work(&xa->defer_wq, DEFER_TIME);
+ mutex_unlock(&mem_id_lock);
}
void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
@@ -153,38 +139,21 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
return;
}
- if (xdp_rxq->mem.type != MEM_TYPE_PAGE_POOL &&
- xdp_rxq->mem.type != MEM_TYPE_ZERO_COPY) {
- return;
- }
-
if (id == 0)
return;
- if (__mem_id_disconnect(id, false))
- return;
-
- /* Could not disconnect, defer new disconnect attempt to later */
- mutex_lock(&mem_id_lock);
+ if (xdp_rxq->mem.type == MEM_TYPE_ZERO_COPY)
+ return mem_id_disconnect(id);
- xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
- if (!xa) {
- mutex_unlock(&mem_id_lock);
- return;
+ if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) {
+ rcu_read_lock();
+ xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params);
+ page_pool_destroy(xa->page_pool);
+ rcu_read_unlock();
}
- xa->defer_start = jiffies;
- xa->defer_warn = jiffies + DEFER_WARN_INTERVAL;
-
- INIT_DELAYED_WORK(&xa->defer_wq, mem_id_disconnect_defer_retry);
- mutex_unlock(&mem_id_lock);
- schedule_delayed_work(&xa->defer_wq, DEFER_TIME);
}
EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model);
-/* This unregister operation will also cleanup and destroy the
- * allocator. The page_pool_free() operation is first called when it's
- * safe to remove, possibly deferred to a workqueue.
- */
void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq)
{
/* Simplify driver cleanup code paths, allow unreg "unused" */
@@ -371,7 +340,7 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
}
if (type == MEM_TYPE_PAGE_POOL)
- page_pool_get(xdp_alloc->page_pool);
+ page_pool_use_xdp_mem(allocator, mem_allocator_disconnect);
mutex_unlock(&mem_id_lock);
@@ -386,7 +355,7 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
/* XDP RX runs under NAPI protection, and in different delivery error
* scenarios (e.g. queue full), it is possible to return the xdp_frame
- * while still leveraging this protection. The @napi_direct boolian
+ * while still leveraging this protection. The @napi_direct boolean
* is used for those calls sites. Thus, allowing for faster recycling
* of xdp_frames/pages in those cases.
*/
@@ -402,15 +371,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
page = virt_to_head_page(data);
- if (likely(xa)) {
- napi_direct &= !xdp_return_frame_no_direct();
- page_pool_put_page(xa->page_pool, page, napi_direct);
- } else {
- /* Hopefully stack show who to blame for late return */
- WARN_ONCE(1, "page_pool gone mem.id=%d", mem->id);
- trace_mem_return_failed(mem, page);
- put_page(page);
- }
+ napi_direct &= !xdp_return_frame_no_direct();
+ page_pool_put_page(xa->page_pool, page, napi_direct);
rcu_read_unlock();
break;
case MEM_TYPE_PAGE_SHARED:
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index d9b4200ed12d..d19557c6d04b 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -117,7 +117,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
inet->inet_daddr,
inet->inet_sport,
inet->inet_dport);
- inet->inet_id = dp->dccps_iss ^ jiffies;
+ inet->inet_id = prandom_u32();
err = dccp_connect(sk);
rt = NULL;
@@ -416,7 +416,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = ip_hdr(skb)->ttl;
- newinet->inet_id = jiffies;
+ newinet->inet_id = prandom_u32();
if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL)
goto put_and_exit;
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 5bad08dc4316..a52e8ba1ced0 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -944,7 +944,7 @@ int inet_dccp_listen(struct socket *sock, int backlog)
if (!((1 << old_state) & (DCCPF_CLOSED | DCCPF_LISTEN)))
goto out;
- sk->sk_max_ack_backlog = backlog;
+ WRITE_ONCE(sk->sk_max_ack_backlog, backlog);
/* Really, if the socket is already in listen state
* we can only allow the backlog to be adjusted.
*/
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 0ea75286abf4..e19a92a62e14 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1091,7 +1091,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags,
}
cb = DN_SKB_CB(skb);
- sk->sk_ack_backlog--;
+ sk_acceptq_removed(sk);
newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern);
if (newsk == NULL) {
release_sock(sk);
@@ -1205,7 +1205,7 @@ static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table *wai
struct dn_scp *scp = DN_SK(sk);
__poll_t mask = datagram_poll(file, sock, wait);
- if (!skb_queue_empty(&scp->other_receive_queue))
+ if (!skb_queue_empty_lockless(&scp->other_receive_queue))
mask |= EPOLLRDBAND;
return mask;
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index e4161e0c86aa..c68503a18025 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -328,7 +328,7 @@ static void dn_nsp_conn_init(struct sock *sk, struct sk_buff *skb)
return;
}
- sk->sk_ack_backlog++;
+ sk_acceptq_added(sk);
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_state_change(sk);
}
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 29e2bd5cc5af..1e6c3cac11e6 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -20,7 +20,7 @@ if NET_DSA
# tagging formats
config NET_DSA_TAG_8021Q
- tristate "Tag driver for switches using custom 802.1Q VLAN headers"
+ tristate
select VLAN_8021Q
help
Unlike the other tagging protocols, the 802.1Q config option simply
@@ -79,6 +79,13 @@ config NET_DSA_TAG_KSZ
Say Y if you want to enable support for tagging frames for the
Microchip 8795/9477/9893 families of switches.
+config NET_DSA_TAG_OCELOT
+ tristate "Tag driver for Ocelot family of switches"
+ select PACKING
+ help
+ Say Y or M if you want to enable support for tagging frames for the
+ Ocelot switches (VSC7511, VSC7512, VSC7513, VSC7514, VSC9959).
+
config NET_DSA_TAG_QCA
tristate "Tag driver for Qualcomm Atheros QCA8K switches"
help
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 2c6d286f0511..9a482c38bdb1 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o
obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o
obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o
obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o
+obj-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o
obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o
obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o
obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 43120a3fb06f..17281fec710c 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -246,7 +246,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
#ifdef CONFIG_PM_SLEEP
static bool dsa_is_port_initialized(struct dsa_switch *ds, int p)
{
- return dsa_is_user_port(ds, p) && ds->ports[p].slave;
+ const struct dsa_port *dp = dsa_to_port(ds, p);
+
+ return dp->type == DSA_PORT_TYPE_USER && dp->slave;
}
int dsa_switch_suspend(struct dsa_switch *ds)
@@ -258,7 +260,7 @@ int dsa_switch_suspend(struct dsa_switch *ds)
if (!dsa_is_port_initialized(ds, i))
continue;
- ret = dsa_slave_suspend(ds->ports[i].slave);
+ ret = dsa_slave_suspend(dsa_to_port(ds, i)->slave);
if (ret)
return ret;
}
@@ -285,7 +287,7 @@ int dsa_switch_resume(struct dsa_switch *ds)
if (!dsa_is_port_initialized(ds, i))
continue;
- ret = dsa_slave_resume(ds->ports[i].slave);
+ ret = dsa_slave_resume(dsa_to_port(ds, i)->slave);
if (ret)
return ret;
}
@@ -329,6 +331,91 @@ int call_dsa_notifiers(unsigned long val, struct net_device *dev,
}
EXPORT_SYMBOL_GPL(call_dsa_notifiers);
+int dsa_devlink_param_get(struct devlink *dl, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct dsa_devlink_priv *dl_priv;
+ struct dsa_switch *ds;
+
+ dl_priv = devlink_priv(dl);
+ ds = dl_priv->ds;
+
+ if (!ds->ops->devlink_param_get)
+ return -EOPNOTSUPP;
+
+ return ds->ops->devlink_param_get(ds, id, ctx);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_param_get);
+
+int dsa_devlink_param_set(struct devlink *dl, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct dsa_devlink_priv *dl_priv;
+ struct dsa_switch *ds;
+
+ dl_priv = devlink_priv(dl);
+ ds = dl_priv->ds;
+
+ if (!ds->ops->devlink_param_set)
+ return -EOPNOTSUPP;
+
+ return ds->ops->devlink_param_set(ds, id, ctx);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_param_set);
+
+int dsa_devlink_params_register(struct dsa_switch *ds,
+ const struct devlink_param *params,
+ size_t params_count)
+{
+ return devlink_params_register(ds->devlink, params, params_count);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_params_register);
+
+void dsa_devlink_params_unregister(struct dsa_switch *ds,
+ const struct devlink_param *params,
+ size_t params_count)
+{
+ devlink_params_unregister(ds->devlink, params, params_count);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_params_unregister);
+
+int dsa_devlink_resource_register(struct dsa_switch *ds,
+ const char *resource_name,
+ u64 resource_size,
+ u64 resource_id,
+ u64 parent_resource_id,
+ const struct devlink_resource_size_params *size_params)
+{
+ return devlink_resource_register(ds->devlink, resource_name,
+ resource_size, resource_id,
+ parent_resource_id,
+ size_params);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_resource_register);
+
+void dsa_devlink_resources_unregister(struct dsa_switch *ds)
+{
+ devlink_resources_unregister(ds->devlink, NULL);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_resources_unregister);
+
+void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds,
+ u64 resource_id,
+ devlink_resource_occ_get_t *occ_get,
+ void *occ_get_priv)
+{
+ return devlink_resource_occ_get_register(ds->devlink, resource_id,
+ occ_get, occ_get_priv);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_register);
+
+void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds,
+ u64 resource_id)
+{
+ devlink_resource_occ_get_unregister(ds->devlink, resource_id);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_unregister);
+
static int __init dsa_init_module(void)
{
int rc;
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 716d265ba8ca..9ef2caa13f27 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -45,6 +45,10 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index)
dst->index = index;
+ INIT_LIST_HEAD(&dst->rtable);
+
+ INIT_LIST_HEAD(&dst->ports);
+
INIT_LIST_HEAD(&dst->list);
list_add_tail(&dst->list, &dsa_tree_list);
@@ -111,24 +115,38 @@ static bool dsa_port_is_user(struct dsa_port *dp)
static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst,
struct device_node *dn)
{
- struct dsa_switch *ds;
struct dsa_port *dp;
- int device, port;
- for (device = 0; device < DSA_MAX_SWITCHES; device++) {
- ds = dst->ds[device];
- if (!ds)
- continue;
+ list_for_each_entry(dp, &dst->ports, list)
+ if (dp->dn == dn)
+ return dp;
- for (port = 0; port < ds->num_ports; port++) {
- dp = &ds->ports[port];
+ return NULL;
+}
- if (dp->dn == dn)
- return dp;
- }
- }
+struct dsa_link *dsa_link_touch(struct dsa_port *dp, struct dsa_port *link_dp)
+{
+ struct dsa_switch *ds = dp->ds;
+ struct dsa_switch_tree *dst;
+ struct dsa_link *dl;
- return NULL;
+ dst = ds->dst;
+
+ list_for_each_entry(dl, &dst->rtable, list)
+ if (dl->dp == dp && dl->link_dp == link_dp)
+ return dl;
+
+ dl = kzalloc(sizeof(*dl), GFP_KERNEL);
+ if (!dl)
+ return NULL;
+
+ dl->dp = dp;
+ dl->link_dp = link_dp;
+
+ INIT_LIST_HEAD(&dl->list);
+ list_add_tail(&dl->list, &dst->rtable);
+
+ return dl;
}
static bool dsa_port_setup_routing_table(struct dsa_port *dp)
@@ -138,6 +156,7 @@ static bool dsa_port_setup_routing_table(struct dsa_port *dp)
struct device_node *dn = dp->dn;
struct of_phandle_iterator it;
struct dsa_port *link_dp;
+ struct dsa_link *dl;
int err;
of_for_each_phandle(&it, err, dn, "link", NULL, 0) {
@@ -147,24 +166,22 @@ static bool dsa_port_setup_routing_table(struct dsa_port *dp)
return false;
}
- ds->rtable[link_dp->ds->index] = dp->index;
+ dl = dsa_link_touch(dp, link_dp);
+ if (!dl) {
+ of_node_put(it.node);
+ return false;
+ }
}
return true;
}
-static bool dsa_switch_setup_routing_table(struct dsa_switch *ds)
+static bool dsa_tree_setup_routing_table(struct dsa_switch_tree *dst)
{
bool complete = true;
struct dsa_port *dp;
- int i;
-
- for (i = 0; i < DSA_MAX_SWITCHES; i++)
- ds->rtable[i] = DSA_RTABLE_NONE;
-
- for (i = 0; i < ds->num_ports; i++) {
- dp = &ds->ports[i];
+ list_for_each_entry(dp, &dst->ports, list) {
if (dsa_port_is_dsa(dp)) {
complete = dsa_port_setup_routing_table(dp);
if (!complete)
@@ -175,81 +192,42 @@ static bool dsa_switch_setup_routing_table(struct dsa_switch *ds)
return complete;
}
-static bool dsa_tree_setup_routing_table(struct dsa_switch_tree *dst)
-{
- struct dsa_switch *ds;
- bool complete = true;
- int device;
-
- for (device = 0; device < DSA_MAX_SWITCHES; device++) {
- ds = dst->ds[device];
- if (!ds)
- continue;
-
- complete = dsa_switch_setup_routing_table(ds);
- if (!complete)
- break;
- }
-
- return complete;
-}
-
static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst)
{
- struct dsa_switch *ds;
struct dsa_port *dp;
- int device, port;
- for (device = 0; device < DSA_MAX_SWITCHES; device++) {
- ds = dst->ds[device];
- if (!ds)
- continue;
-
- for (port = 0; port < ds->num_ports; port++) {
- dp = &ds->ports[port];
-
- if (dsa_port_is_cpu(dp))
- return dp;
- }
- }
+ list_for_each_entry(dp, &dst->ports, list)
+ if (dsa_port_is_cpu(dp))
+ return dp;
return NULL;
}
static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst)
{
- struct dsa_switch *ds;
- struct dsa_port *dp;
- int device, port;
+ struct dsa_port *cpu_dp, *dp;
- /* DSA currently only supports a single CPU port */
- dst->cpu_dp = dsa_tree_find_first_cpu(dst);
- if (!dst->cpu_dp) {
- pr_warn("Tree has no master device\n");
+ cpu_dp = dsa_tree_find_first_cpu(dst);
+ if (!cpu_dp) {
+ pr_err("DSA: tree %d has no CPU port\n", dst->index);
return -EINVAL;
}
/* Assign the default CPU port to all ports of the fabric */
- for (device = 0; device < DSA_MAX_SWITCHES; device++) {
- ds = dst->ds[device];
- if (!ds)
- continue;
-
- for (port = 0; port < ds->num_ports; port++) {
- dp = &ds->ports[port];
-
- if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp))
- dp->cpu_dp = dst->cpu_dp;
- }
- }
+ list_for_each_entry(dp, &dst->ports, list)
+ if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp))
+ dp->cpu_dp = cpu_dp;
return 0;
}
static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst)
{
- /* DSA currently only supports a single CPU port */
- dst->cpu_dp = NULL;
+ struct dsa_port *dp;
+
+ list_for_each_entry(dp, &dst->ports, list)
+ if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp))
+ dp->cpu_dp = NULL;
}
static int dsa_port_setup(struct dsa_port *dp)
@@ -265,6 +243,9 @@ static int dsa_port_setup(struct dsa_port *dp)
bool dsa_port_enabled = false;
int err = 0;
+ if (dp->setup)
+ return 0;
+
switch (dp->type) {
case DSA_PORT_TYPE_UNUSED:
dsa_port_disable(dp);
@@ -333,14 +314,21 @@ static int dsa_port_setup(struct dsa_port *dp)
dsa_port_link_unregister_of(dp);
if (err && devlink_port_registered)
devlink_port_unregister(dlp);
+ if (err)
+ return err;
- return err;
+ dp->setup = true;
+
+ return 0;
}
static void dsa_port_teardown(struct dsa_port *dp)
{
struct devlink_port *dlp = &dp->devlink_port;
+ if (!dp->setup)
+ return;
+
switch (dp->type) {
case DSA_PORT_TYPE_UNUSED:
break;
@@ -363,11 +351,17 @@ static void dsa_port_teardown(struct dsa_port *dp)
}
break;
}
+
+ dp->setup = false;
}
static int dsa_switch_setup(struct dsa_switch *ds)
{
- int err = 0;
+ struct dsa_devlink_priv *dl_priv;
+ int err;
+
+ if (ds->setup)
+ return 0;
/* Initialize ds->phys_mii_mask before registering the slave MDIO bus
* driver and before ops->setup() has run, since the switch drivers and
@@ -379,9 +373,11 @@ static int dsa_switch_setup(struct dsa_switch *ds)
/* Add the switch to devlink before calling setup, so that setup can
* add dpipe tables
*/
- ds->devlink = devlink_alloc(&dsa_devlink_ops, 0);
+ ds->devlink = devlink_alloc(&dsa_devlink_ops, sizeof(*dl_priv));
if (!ds->devlink)
return -ENOMEM;
+ dl_priv = devlink_priv(ds->devlink);
+ dl_priv->ds = ds;
err = devlink_register(ds->devlink, ds->dev);
if (err)
@@ -395,6 +391,8 @@ static int dsa_switch_setup(struct dsa_switch *ds)
if (err < 0)
goto unregister_notifier;
+ devlink_params_publish(ds->devlink);
+
if (!ds->slave_mii_bus && ds->ops->phy_read) {
ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
if (!ds->slave_mii_bus) {
@@ -409,6 +407,8 @@ static int dsa_switch_setup(struct dsa_switch *ds)
goto unregister_notifier;
}
+ ds->setup = true;
+
return 0;
unregister_notifier:
@@ -424,6 +424,9 @@ free_devlink:
static void dsa_switch_teardown(struct dsa_switch *ds)
{
+ if (!ds->setup)
+ return;
+
if (ds->slave_mii_bus && ds->ops->phy_read)
mdiobus_unregister(ds->slave_mii_bus);
@@ -438,95 +441,72 @@ static void dsa_switch_teardown(struct dsa_switch *ds)
ds->devlink = NULL;
}
+ ds->setup = false;
}
static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
{
- struct dsa_switch *ds;
struct dsa_port *dp;
- int device, port, i;
- int err = 0;
-
- for (device = 0; device < DSA_MAX_SWITCHES; device++) {
- ds = dst->ds[device];
- if (!ds)
- continue;
+ int err;
- err = dsa_switch_setup(ds);
+ list_for_each_entry(dp, &dst->ports, list) {
+ err = dsa_switch_setup(dp->ds);
if (err)
- goto switch_teardown;
-
- for (port = 0; port < ds->num_ports; port++) {
- dp = &ds->ports[port];
+ goto teardown;
+ }
- err = dsa_port_setup(dp);
- if (err)
- goto ports_teardown;
- }
+ list_for_each_entry(dp, &dst->ports, list) {
+ err = dsa_port_setup(dp);
+ if (err)
+ goto teardown;
}
return 0;
-ports_teardown:
- for (i = 0; i < port; i++)
- dsa_port_teardown(&ds->ports[i]);
+teardown:
+ list_for_each_entry(dp, &dst->ports, list)
+ dsa_port_teardown(dp);
- dsa_switch_teardown(ds);
-
-switch_teardown:
- for (i = 0; i < device; i++) {
- ds = dst->ds[i];
- if (!ds)
- continue;
-
- for (port = 0; port < ds->num_ports; port++) {
- dp = &ds->ports[port];
-
- dsa_port_teardown(dp);
- }
-
- dsa_switch_teardown(ds);
- }
+ list_for_each_entry(dp, &dst->ports, list)
+ dsa_switch_teardown(dp->ds);
return err;
}
static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst)
{
- struct dsa_switch *ds;
struct dsa_port *dp;
- int device, port;
-
- for (device = 0; device < DSA_MAX_SWITCHES; device++) {
- ds = dst->ds[device];
- if (!ds)
- continue;
- for (port = 0; port < ds->num_ports; port++) {
- dp = &ds->ports[port];
+ list_for_each_entry(dp, &dst->ports, list)
+ dsa_port_teardown(dp);
- dsa_port_teardown(dp);
- }
-
- dsa_switch_teardown(ds);
- }
+ list_for_each_entry(dp, &dst->ports, list)
+ dsa_switch_teardown(dp->ds);
}
static int dsa_tree_setup_master(struct dsa_switch_tree *dst)
{
- struct dsa_port *cpu_dp = dst->cpu_dp;
- struct net_device *master = cpu_dp->master;
+ struct dsa_port *dp;
+ int err;
- /* DSA currently supports a single pair of CPU port and master device */
- return dsa_master_setup(master, cpu_dp);
+ list_for_each_entry(dp, &dst->ports, list) {
+ if (dsa_port_is_cpu(dp)) {
+ err = dsa_master_setup(dp->master, dp);
+ if (err)
+ return err;
+ }
+ }
+
+ return 0;
}
static void dsa_tree_teardown_master(struct dsa_switch_tree *dst)
{
- struct dsa_port *cpu_dp = dst->cpu_dp;
- struct net_device *master = cpu_dp->master;
+ struct dsa_port *dp;
- return dsa_master_teardown(master);
+ list_for_each_entry(dp, &dst->ports, list)
+ if (dsa_port_is_cpu(dp))
+ dsa_master_teardown(dp->master);
}
static int dsa_tree_setup(struct dsa_switch_tree *dst)
@@ -572,6 +552,8 @@ teardown_default_cpu:
static void dsa_tree_teardown(struct dsa_switch_tree *dst)
{
+ struct dsa_link *dl, *next;
+
if (!dst->setup)
return;
@@ -581,39 +563,36 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst)
dsa_tree_teardown_default_cpu(dst);
+ list_for_each_entry_safe(dl, next, &dst->rtable, list) {
+ list_del(&dl->list);
+ kfree(dl);
+ }
+
pr_info("DSA: tree %d torn down\n", dst->index);
dst->setup = false;
}
-static void dsa_tree_remove_switch(struct dsa_switch_tree *dst,
- unsigned int index)
+static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index)
{
- dsa_tree_teardown(dst);
+ struct dsa_switch_tree *dst = ds->dst;
+ struct dsa_port *dp;
- dst->ds[index] = NULL;
- dsa_tree_put(dst);
-}
+ list_for_each_entry(dp, &dst->ports, list)
+ if (dp->ds == ds && dp->index == index)
+ return dp;
-static int dsa_tree_add_switch(struct dsa_switch_tree *dst,
- struct dsa_switch *ds)
-{
- unsigned int index = ds->index;
- int err;
+ dp = kzalloc(sizeof(*dp), GFP_KERNEL);
+ if (!dp)
+ return NULL;
- if (dst->ds[index])
- return -EBUSY;
+ dp->ds = ds;
+ dp->index = index;
- dsa_tree_get(dst);
- dst->ds[index] = ds;
+ INIT_LIST_HEAD(&dp->list);
+ list_add_tail(&dp->list, &dst->ports);
- err = dsa_tree_setup(dst);
- if (err) {
- dst->ds[index] = NULL;
- dsa_tree_put(dst);
- }
-
- return err;
+ return dp;
}
static int dsa_port_parse_user(struct dsa_port *dp, const char *name)
@@ -708,7 +687,7 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds,
goto out_put_node;
}
- dp = &ds->ports[reg];
+ dp = dsa_to_port(ds, reg);
err = dsa_port_parse_of(dp, port);
if (err)
@@ -732,8 +711,6 @@ static int dsa_switch_parse_member_of(struct dsa_switch *ds,
return sz;
ds->index = m[1];
- if (ds->index >= DSA_MAX_SWITCHES)
- return -EINVAL;
ds->dst = dsa_tree_touch(m[0]);
if (!ds->dst)
@@ -742,6 +719,20 @@ static int dsa_switch_parse_member_of(struct dsa_switch *ds,
return 0;
}
+static int dsa_switch_touch_ports(struct dsa_switch *ds)
+{
+ struct dsa_port *dp;
+ int port;
+
+ for (port = 0; port < ds->num_ports; port++) {
+ dp = dsa_port_touch(ds, port);
+ if (!dp)
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn)
{
int err;
@@ -750,6 +741,10 @@ static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn)
if (err)
return err;
+ err = dsa_switch_touch_ports(ds);
+ if (err)
+ return err;
+
return dsa_switch_parse_ports_of(ds, dn);
}
@@ -787,7 +782,7 @@ static int dsa_switch_parse_ports(struct dsa_switch *ds,
for (i = 0; i < DSA_MAX_PORTS; i++) {
name = cd->port_names[i];
dev = cd->netdev[i];
- dp = &ds->ports[i];
+ dp = dsa_to_port(ds, i);
if (!name)
continue;
@@ -807,6 +802,8 @@ static int dsa_switch_parse_ports(struct dsa_switch *ds,
static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd)
{
+ int err;
+
ds->cd = cd;
/* We don't support interconnected switches nor multiple trees via
@@ -817,22 +814,29 @@ static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd)
if (!ds->dst)
return -ENOMEM;
- return dsa_switch_parse_ports(ds, cd);
-}
-
-static int dsa_switch_add(struct dsa_switch *ds)
-{
- struct dsa_switch_tree *dst = ds->dst;
+ err = dsa_switch_touch_ports(ds);
+ if (err)
+ return err;
- return dsa_tree_add_switch(dst, ds);
+ return dsa_switch_parse_ports(ds, cd);
}
static int dsa_switch_probe(struct dsa_switch *ds)
{
- struct dsa_chip_data *pdata = ds->dev->platform_data;
- struct device_node *np = ds->dev->of_node;
+ struct dsa_switch_tree *dst;
+ struct dsa_chip_data *pdata;
+ struct device_node *np;
int err;
+ if (!ds->dev)
+ return -ENODEV;
+
+ pdata = ds->dev->platform_data;
+ np = ds->dev->of_node;
+
+ if (!ds->num_ports)
+ return -EINVAL;
+
if (np)
err = dsa_switch_parse_of(ds, np);
else if (pdata)
@@ -843,29 +847,14 @@ static int dsa_switch_probe(struct dsa_switch *ds)
if (err)
return err;
- return dsa_switch_add(ds);
-}
-
-struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n)
-{
- struct dsa_switch *ds;
- int i;
-
- ds = devm_kzalloc(dev, struct_size(ds, ports, n), GFP_KERNEL);
- if (!ds)
- return NULL;
-
- ds->dev = dev;
- ds->num_ports = n;
-
- for (i = 0; i < ds->num_ports; ++i) {
- ds->ports[i].index = i;
- ds->ports[i].ds = ds;
- }
+ dst = ds->dst;
+ dsa_tree_get(dst);
+ err = dsa_tree_setup(dst);
+ if (err)
+ dsa_tree_put(dst);
- return ds;
+ return err;
}
-EXPORT_SYMBOL_GPL(dsa_switch_alloc);
int dsa_register_switch(struct dsa_switch *ds)
{
@@ -883,9 +872,16 @@ EXPORT_SYMBOL_GPL(dsa_register_switch);
static void dsa_switch_remove(struct dsa_switch *ds)
{
struct dsa_switch_tree *dst = ds->dst;
- unsigned int index = ds->index;
+ struct dsa_port *dp, *next;
- dsa_tree_remove_switch(dst, index);
+ dsa_tree_teardown(dst);
+
+ list_for_each_entry_safe(dp, next, &dst->ports, list) {
+ list_del(&dp->list);
+ kfree(dp);
+ }
+
+ dsa_tree_put(dst);
}
void dsa_unregister_switch(struct dsa_switch *ds)
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 12f8c7ee4dd8..2dd86d9bcda9 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -104,25 +104,14 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
struct dsa_switch_tree *dst = cpu_dp->dst;
- struct dsa_switch *ds;
- struct dsa_port *slave_port;
+ struct dsa_port *dp;
- if (device < 0 || device >= DSA_MAX_SWITCHES)
- return NULL;
+ list_for_each_entry(dp, &dst->ports, list)
+ if (dp->ds->index == device && dp->index == port &&
+ dp->type == DSA_PORT_TYPE_USER)
+ return dp->slave;
- ds = dst->ds[device];
- if (!ds)
- return NULL;
-
- if (port < 0 || port >= ds->num_ports)
- return NULL;
-
- slave_port = &ds->ports[port];
-
- if (unlikely(slave_port->type != DSA_PORT_TYPE_USER))
- return NULL;
-
- return slave_port->slave;
+ return NULL;
}
/* port.c */
@@ -164,8 +153,8 @@ void dsa_port_link_unregister_of(struct dsa_port *dp);
void dsa_port_phylink_validate(struct phylink_config *config,
unsigned long *supported,
struct phylink_link_state *state);
-int dsa_port_phylink_mac_link_state(struct phylink_config *config,
- struct phylink_link_state *state);
+void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config,
+ struct phylink_link_state *state);
void dsa_port_phylink_mac_config(struct phylink_config *config,
unsigned int mode,
const struct phylink_link_state *state);
diff --git a/net/dsa/master.c b/net/dsa/master.c
index a8e52c9967f4..3255dfc97f86 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -310,8 +310,6 @@ static void dsa_master_reset_mtu(struct net_device *dev)
rtnl_unlock();
}
-static struct lock_class_key dsa_master_addr_list_lock_key;
-
int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
{
int ret;
@@ -325,9 +323,6 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
wmb();
dev->dsa_ptr = cpu_dp;
- lockdep_set_class(&dev->addr_list_lock,
- &dsa_master_addr_list_lock_key);
-
ret = dsa_master_ethtool_setup(dev);
if (ret)
return ret;
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 9b54e5a76297..46ac9ba21987 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -429,19 +429,22 @@ void dsa_port_phylink_validate(struct phylink_config *config,
}
EXPORT_SYMBOL_GPL(dsa_port_phylink_validate);
-int dsa_port_phylink_mac_link_state(struct phylink_config *config,
- struct phylink_link_state *state)
+void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config,
+ struct phylink_link_state *state)
{
struct dsa_port *dp = container_of(config, struct dsa_port, pl_config);
struct dsa_switch *ds = dp->ds;
- /* Only called for SGMII and 802.3z */
- if (!ds->ops->phylink_mac_link_state)
- return -EOPNOTSUPP;
+ /* Only called for inband modes */
+ if (!ds->ops->phylink_mac_link_state) {
+ state->link = 0;
+ return;
+ }
- return ds->ops->phylink_mac_link_state(ds, dp->index, state);
+ if (ds->ops->phylink_mac_link_state(ds, dp->index, state) < 0)
+ state->link = 0;
}
-EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_state);
+EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_pcs_get_state);
void dsa_port_phylink_mac_config(struct phylink_config *config,
unsigned int mode,
@@ -510,7 +513,7 @@ EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_up);
const struct phylink_mac_ops dsa_port_phylink_mac_ops = {
.validate = dsa_port_phylink_validate,
- .mac_link_state = dsa_port_phylink_mac_link_state,
+ .mac_pcs_get_state = dsa_port_phylink_mac_pcs_get_state,
.mac_config = dsa_port_phylink_mac_config,
.mac_an_restart = dsa_port_phylink_mac_an_restart,
.mac_link_down = dsa_port_phylink_mac_link_down,
@@ -561,7 +564,7 @@ static int dsa_port_fixed_link_register_of(struct dsa_port *dp)
struct dsa_switch *ds = dp->ds;
struct phy_device *phydev;
int port = dp->index;
- int mode;
+ phy_interface_t mode;
int err;
err = of_phy_register_fixed_link(dn);
@@ -574,8 +577,8 @@ static int dsa_port_fixed_link_register_of(struct dsa_port *dp)
phydev = of_phy_find_device(dn);
- mode = of_get_phy_mode(dn);
- if (mode < 0)
+ err = of_get_phy_mode(dn, &mode);
+ if (err)
mode = PHY_INTERFACE_MODE_NA;
phydev->interface = mode;
@@ -593,10 +596,11 @@ static int dsa_port_phylink_register(struct dsa_port *dp)
{
struct dsa_switch *ds = dp->ds;
struct device_node *port_dn = dp->dn;
- int mode, err;
+ phy_interface_t mode;
+ int err;
- mode = of_get_phy_mode(port_dn);
- if (mode < 0)
+ err = of_get_phy_mode(port_dn, &mode);
+ if (err)
mode = PHY_INTERFACE_MODE_NA;
dp->pl_config.dev = ds->dev;
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 75d58229a4bd..78ffc87dc25e 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -789,6 +789,22 @@ static int dsa_slave_set_link_ksettings(struct net_device *dev,
return phylink_ethtool_ksettings_set(dp->pl, cmd);
}
+static void dsa_slave_get_pauseparam(struct net_device *dev,
+ struct ethtool_pauseparam *pause)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+
+ phylink_ethtool_get_pauseparam(dp->pl, pause);
+}
+
+static int dsa_slave_set_pauseparam(struct net_device *dev,
+ struct ethtool_pauseparam *pause)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+
+ return phylink_ethtool_set_pauseparam(dp->pl, pause);
+}
+
#ifdef CONFIG_NET_POLL_CONTROLLER
static int dsa_slave_netpoll_setup(struct net_device *dev,
struct netpoll_info *ni)
@@ -1192,6 +1208,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
.get_eee = dsa_slave_get_eee,
.get_link_ksettings = dsa_slave_get_link_ksettings,
.set_link_ksettings = dsa_slave_set_link_ksettings,
+ .get_pauseparam = dsa_slave_get_pauseparam,
+ .set_pauseparam = dsa_slave_set_pauseparam,
.get_rxnfc = dsa_slave_get_rxnfc,
.set_rxnfc = dsa_slave_set_rxnfc,
.get_ts_info = dsa_slave_get_ts_info,
@@ -1295,11 +1313,12 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev)
struct dsa_port *dp = dsa_slave_to_port(slave_dev);
struct device_node *port_dn = dp->dn;
struct dsa_switch *ds = dp->ds;
+ phy_interface_t mode;
u32 phy_flags = 0;
- int mode, ret;
+ int ret;
- mode = of_get_phy_mode(port_dn);
- if (mode < 0)
+ ret = of_get_phy_mode(port_dn, &mode);
+ if (ret)
mode = PHY_INTERFACE_MODE_NA;
dp->pl_config.dev = &slave_dev->dev;
@@ -1341,15 +1360,6 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev)
return ret;
}
-static struct lock_class_key dsa_slave_netdev_xmit_lock_key;
-static void dsa_slave_set_lockdep_class_one(struct net_device *dev,
- struct netdev_queue *txq,
- void *_unused)
-{
- lockdep_set_class(&txq->_xmit_lock,
- &dsa_slave_netdev_xmit_lock_key);
-}
-
int dsa_slave_suspend(struct net_device *slave_dev)
{
struct dsa_port *dp = dsa_slave_to_port(slave_dev);
@@ -1433,9 +1443,6 @@ int dsa_slave_create(struct dsa_port *port)
slave_dev->max_mtu = ETH_MAX_MTU;
SET_NETDEV_DEVTYPE(slave_dev, &dsa_type);
- netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one,
- NULL);
-
SET_NETDEV_DEV(slave_dev, port->ds->dev);
slave_dev->dev.of_node = port->dn;
slave_dev->vlan_features = master->vlan_features;
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 6a9607518823..df4abe897ed6 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -20,7 +20,7 @@ static unsigned int dsa_switch_fastest_ageing_time(struct dsa_switch *ds,
int i;
for (i = 0; i < ds->num_ports; ++i) {
- struct dsa_port *dp = &ds->ports[i];
+ struct dsa_port *dp = dsa_to_port(ds, i);
if (dp->ageing_time && dp->ageing_time < ageing_time)
ageing_time = dp->ageing_time;
@@ -98,7 +98,7 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
if (unset_vlan_filtering) {
struct switchdev_trans trans = {0};
- err = dsa_port_vlan_filtering(&ds->ports[info->port],
+ err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port),
false, &trans);
if (err && err != EOPNOTSUPP)
return err;
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 9c1cc2482b68..2fb6c26294b5 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -31,15 +31,14 @@
* Must be transmitted as zero and ignored on receive.
*
* SWITCH_ID - VID[8:6]:
- * Index of switch within DSA tree. Must be between 0 and
- * DSA_MAX_SWITCHES - 1.
+ * Index of switch within DSA tree. Must be between 0 and 7.
*
* RSV - VID[5:4]:
* To be used for further expansion of PORT or for other purposes.
* Must be transmitted as zero and ignored on receive.
*
* PORT - VID[3:0]:
- * Index of switch port. Must be between 0 and DSA_MAX_PORTS - 1.
+ * Index of switch port. Must be between 0 and 15.
*/
#define DSA_8021Q_DIR_SHIFT 10
@@ -103,10 +102,10 @@ static int dsa_8021q_restore_pvid(struct dsa_switch *ds, int port)
if (!dsa_is_user_port(ds, port))
return 0;
- slave = ds->ports[port].slave;
+ slave = dsa_to_port(ds, port)->slave;
err = br_vlan_get_pvid(slave, &pvid);
- if (err < 0)
+ if (!pvid || err < 0)
/* There is no pvid on the bridge for this port, which is
* perfectly valid. Nothing to restore, bye-bye!
*/
@@ -118,7 +117,7 @@ static int dsa_8021q_restore_pvid(struct dsa_switch *ds, int port)
return err;
}
- return dsa_port_vid_add(&ds->ports[port], pvid, vinfo.flags);
+ return dsa_port_vid_add(dsa_to_port(ds, port), pvid, vinfo.flags);
}
/* If @enabled is true, installs @vid with @flags into the switch port's HW
@@ -130,7 +129,7 @@ static int dsa_8021q_restore_pvid(struct dsa_switch *ds, int port)
static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid,
u16 flags, bool enabled)
{
- struct dsa_port *dp = &ds->ports[port];
+ struct dsa_port *dp = dsa_to_port(ds, port);
struct bridge_vlan_info vinfo;
int err;
@@ -342,13 +341,4 @@ struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(dsa_8021q_remove_header);
-static const struct dsa_device_ops dsa_8021q_netdev_ops = {
- .name = "8021q",
- .proto = DSA_TAG_PROTO_8021Q,
- .overhead = VLAN_HLEN,
-};
-
MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_8021Q);
-
-module_dsa_tag_driver(dsa_8021q_netdev_ops);
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
new file mode 100644
index 000000000000..8e3e7283d430
--- /dev/null
+++ b/net/dsa/tag_ocelot.c
@@ -0,0 +1,241 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2019 NXP Semiconductors
+ */
+#include <soc/mscc/ocelot.h>
+#include <linux/packing.h>
+#include "dsa_priv.h"
+
+/* The CPU injection header and the CPU extraction header can have 3 types of
+ * prefixes: long, short and no prefix. The format of the header itself is the
+ * same in all 3 cases.
+ *
+ * Extraction with long prefix:
+ *
+ * +-------------------+-------------------+------+------+------------+-------+
+ * | ff:ff:ff:ff:ff:ff | ff:ff:ff:ff:ff:ff | 8880 | 000a | extraction | frame |
+ * | | | | | header | |
+ * +-------------------+-------------------+------+------+------------+-------+
+ * 48 bits 48 bits 16 bits 16 bits 128 bits
+ *
+ * Extraction with short prefix:
+ *
+ * +------+------+------------+-------+
+ * | 8880 | 000a | extraction | frame |
+ * | | | header | |
+ * +------+------+------------+-------+
+ * 16 bits 16 bits 128 bits
+ *
+ * Extraction with no prefix:
+ *
+ * +------------+-------+
+ * | extraction | frame |
+ * | header | |
+ * +------------+-------+
+ * 128 bits
+ *
+ *
+ * Injection with long prefix:
+ *
+ * +-------------------+-------------------+------+------+------------+-------+
+ * | any dmac | any smac | 8880 | 000a | injection | frame |
+ * | | | | | header | |
+ * +-------------------+-------------------+------+------+------------+-------+
+ * 48 bits 48 bits 16 bits 16 bits 128 bits
+ *
+ * Injection with short prefix:
+ *
+ * +------+------+------------+-------+
+ * | 8880 | 000a | injection | frame |
+ * | | | header | |
+ * +------+------+------------+-------+
+ * 16 bits 16 bits 128 bits
+ *
+ * Injection with no prefix:
+ *
+ * +------------+-------+
+ * | injection | frame |
+ * | header | |
+ * +------------+-------+
+ * 128 bits
+ *
+ * The injection header looks like this (network byte order, bit 127
+ * is part of lowest address byte in memory, bit 0 is part of highest
+ * address byte):
+ *
+ * +------+------+------+------+------+------+------+------+
+ * 127:120 |BYPASS| MASQ | MASQ_PORT |REW_OP|REW_OP|
+ * +------+------+------+------+------+------+------+------+
+ * 119:112 | REW_OP |
+ * +------+------+------+------+------+------+------+------+
+ * 111:104 | REW_VAL |
+ * +------+------+------+------+------+------+------+------+
+ * 103: 96 | REW_VAL |
+ * +------+------+------+------+------+------+------+------+
+ * 95: 88 | REW_VAL |
+ * +------+------+------+------+------+------+------+------+
+ * 87: 80 | REW_VAL |
+ * +------+------+------+------+------+------+------+------+
+ * 79: 72 | RSV |
+ * +------+------+------+------+------+------+------+------+
+ * 71: 64 | RSV | DEST |
+ * +------+------+------+------+------+------+------+------+
+ * 63: 56 | DEST |
+ * +------+------+------+------+------+------+------+------+
+ * 55: 48 | RSV |
+ * +------+------+------+------+------+------+------+------+
+ * 47: 40 | RSV | SRC_PORT | RSV |TFRM_TIMER|
+ * +------+------+------+------+------+------+------+------+
+ * 39: 32 | TFRM_TIMER | RSV |
+ * +------+------+------+------+------+------+------+------+
+ * 31: 24 | RSV | DP | POP_CNT | CPUQ |
+ * +------+------+------+------+------+------+------+------+
+ * 23: 16 | CPUQ | QOS_CLASS |TAG_TYPE|
+ * +------+------+------+------+------+------+------+------+
+ * 15: 8 | PCP | DEI | VID |
+ * +------+------+------+------+------+------+------+------+
+ * 7: 0 | VID |
+ * +------+------+------+------+------+------+------+------+
+ *
+ * And the extraction header looks like this:
+ *
+ * +------+------+------+------+------+------+------+------+
+ * 127:120 | RSV | REW_OP |
+ * +------+------+------+------+------+------+------+------+
+ * 119:112 | REW_OP | REW_VAL |
+ * +------+------+------+------+------+------+------+------+
+ * 111:104 | REW_VAL |
+ * +------+------+------+------+------+------+------+------+
+ * 103: 96 | REW_VAL |
+ * +------+------+------+------+------+------+------+------+
+ * 95: 88 | REW_VAL |
+ * +------+------+------+------+------+------+------+------+
+ * 87: 80 | REW_VAL | LLEN |
+ * +------+------+------+------+------+------+------+------+
+ * 79: 72 | LLEN | WLEN |
+ * +------+------+------+------+------+------+------+------+
+ * 71: 64 | WLEN | RSV |
+ * +------+------+------+------+------+------+------+------+
+ * 63: 56 | RSV |
+ * +------+------+------+------+------+------+------+------+
+ * 55: 48 | RSV |
+ * +------+------+------+------+------+------+------+------+
+ * 47: 40 | RSV | SRC_PORT | ACL_ID |
+ * +------+------+------+------+------+------+------+------+
+ * 39: 32 | ACL_ID | RSV | SFLOW_ID |
+ * +------+------+------+------+------+------+------+------+
+ * 31: 24 |ACL_HIT| DP | LRN_FLAGS | CPUQ |
+ * +------+------+------+------+------+------+------+------+
+ * 23: 16 | CPUQ | QOS_CLASS |TAG_TYPE|
+ * +------+------+------+------+------+------+------+------+
+ * 15: 8 | PCP | DEI | VID |
+ * +------+------+------+------+------+------+------+------+
+ * 7: 0 | VID |
+ * +------+------+------+------+------+------+------+------+
+ */
+
+static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
+ struct net_device *netdev)
+{
+ struct dsa_port *dp = dsa_slave_to_port(netdev);
+ u64 bypass, dest, src, qos_class, rew_op;
+ struct dsa_switch *ds = dp->ds;
+ int port = dp->index;
+ struct ocelot *ocelot = ds->priv;
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
+ u8 *injection;
+
+ if (unlikely(skb_cow_head(skb, OCELOT_TAG_LEN) < 0)) {
+ netdev_err(netdev, "Cannot make room for tag.\n");
+ return NULL;
+ }
+
+ injection = skb_push(skb, OCELOT_TAG_LEN);
+
+ memset(injection, 0, OCELOT_TAG_LEN);
+
+ src = dsa_upstream_port(ds, port);
+ dest = BIT(port);
+ bypass = true;
+ qos_class = skb->priority;
+
+ packing(injection, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0);
+ packing(injection, &dest, 68, 56, OCELOT_TAG_LEN, PACK, 0);
+ packing(injection, &src, 46, 43, OCELOT_TAG_LEN, PACK, 0);
+ packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0);
+
+ if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
+ rew_op = ocelot_port->ptp_cmd;
+ if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) {
+ rew_op |= (ocelot_port->ts_id % 4) << 3;
+ ocelot_port->ts_id++;
+ }
+
+ packing(injection, &rew_op, 125, 117, OCELOT_TAG_LEN, PACK, 0);
+ }
+
+ return skb;
+}
+
+static struct sk_buff *ocelot_rcv(struct sk_buff *skb,
+ struct net_device *netdev,
+ struct packet_type *pt)
+{
+ u64 src_port, qos_class;
+ u8 *start = skb->data;
+ u8 *extraction;
+
+ /* Revert skb->data by the amount consumed by the DSA master,
+ * so it points to the beginning of the frame.
+ */
+ skb_push(skb, ETH_HLEN);
+ /* We don't care about the long prefix, it is just for easy entrance
+ * into the DSA master's RX filter. Discard it now by moving it into
+ * the headroom.
+ */
+ skb_pull(skb, OCELOT_LONG_PREFIX_LEN);
+ /* And skb->data now points to the extraction frame header.
+ * Keep a pointer to it.
+ */
+ extraction = skb->data;
+ /* Now the EFH is part of the headroom as well */
+ skb_pull(skb, OCELOT_TAG_LEN);
+ /* Reset the pointer to the real MAC header */
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+ /* And move skb->data to the correct location again */
+ skb_pull(skb, ETH_HLEN);
+
+ /* Remove from inet csum the extraction header */
+ skb_postpull_rcsum(skb, start, OCELOT_LONG_PREFIX_LEN + OCELOT_TAG_LEN);
+
+ packing(extraction, &src_port, 46, 43, OCELOT_TAG_LEN, UNPACK, 0);
+ packing(extraction, &qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0);
+
+ skb->dev = dsa_master_find_slave(netdev, 0, src_port);
+ if (!skb->dev)
+ /* The switch will reflect back some frames sent through
+ * sockets opened on the bare DSA master. These will come back
+ * with src_port equal to the index of the CPU port, for which
+ * there is no slave registered. So don't print any error
+ * message here (ignore and drop those frames).
+ */
+ return NULL;
+
+ skb->offload_fwd_mark = 1;
+ skb->priority = qos_class;
+
+ return skb;
+}
+
+static struct dsa_device_ops ocelot_netdev_ops = {
+ .name = "ocelot",
+ .proto = DSA_TAG_PROTO_OCELOT,
+ .xmit = ocelot_xmit,
+ .rcv = ocelot_rcv,
+ .overhead = OCELOT_TAG_LEN + OCELOT_LONG_PREFIX_LEN,
+};
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT);
+
+module_dsa_tag_driver(ocelot_netdev_ops);
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 17374afee28f..9040fe55e0f5 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -244,7 +244,12 @@ int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16
eth->h_proto = type;
memcpy(eth->h_source, dev->dev_addr, ETH_ALEN);
memcpy(eth->h_dest, neigh->ha, ETH_ALEN);
- hh->hh_len = ETH_HLEN;
+
+ /* Pairs with READ_ONCE() in neigh_resolve_output(),
+ * neigh_hh_output() and neigh_update_hhs().
+ */
+ smp_store_release(&hh->hh_len, ETH_HLEN);
+
return 0;
}
EXPORT_SYMBOL(eth_header_cache);
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 3297e7fa9945..c0b107cdd715 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -58,13 +58,6 @@ static const struct header_ops lowpan_header_ops = {
.create = lowpan_header_create,
};
-static int lowpan_dev_init(struct net_device *ldev)
-{
- netdev_lockdep_set_classes(ldev);
-
- return 0;
-}
-
static int lowpan_open(struct net_device *dev)
{
if (!open_count)
@@ -96,7 +89,6 @@ static int lowpan_get_iflink(const struct net_device *dev)
}
static const struct net_device_ops lowpan_netdev_ops = {
- .ndo_init = lowpan_dev_init,
.ndo_start_xmit = lowpan_xmit,
.ndo_open = lowpan_open,
.ndo_stop = lowpan_stop,
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index ffcfcef76291..7c5a1aa5adb4 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -236,21 +236,14 @@ nl802154_prepare_wpan_dev_dump(struct sk_buff *skb,
struct cfg802154_registered_device **rdev,
struct wpan_dev **wpan_dev)
{
+ const struct genl_dumpit_info *info = genl_dumpit_info(cb);
int err;
rtnl_lock();
if (!cb->args[0]) {
- err = nlmsg_parse_deprecated(cb->nlh,
- GENL_HDRLEN + nl802154_fam.hdrsize,
- genl_family_attrbuf(&nl802154_fam),
- nl802154_fam.maxattr,
- nl802154_policy, NULL);
- if (err)
- goto out_unlock;
-
*wpan_dev = __cfg802154_wpan_dev_from_attrs(sock_net(skb->sk),
- genl_family_attrbuf(&nl802154_fam));
+ info->attrs);
if (IS_ERR(*wpan_dev)) {
err = PTR_ERR(*wpan_dev);
goto out_unlock;
@@ -557,17 +550,8 @@ static int nl802154_dump_wpan_phy_parse(struct sk_buff *skb,
struct netlink_callback *cb,
struct nl802154_dump_wpan_phy_state *state)
{
- struct nlattr **tb = genl_family_attrbuf(&nl802154_fam);
- int ret = nlmsg_parse_deprecated(cb->nlh,
- GENL_HDRLEN + nl802154_fam.hdrsize,
- tb, nl802154_fam.maxattr,
- nl802154_policy, NULL);
-
- /* TODO check if we can handle error here,
- * we have no backward compatibility
- */
- if (ret)
- return 0;
+ const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+ struct nlattr **tb = info->attrs;
if (tb[NL802154_ATTR_WPAN_PHY])
state->filter_wpan_phy = nla_get_u32(tb[NL802154_ATTR_WPAN_PHY]);
@@ -2203,7 +2187,8 @@ static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
static const struct genl_ops nl802154_ops[] = {
{
.cmd = NL802154_CMD_GET_WPAN_PHY,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
.doit = nl802154_get_wpan_phy,
.dumpit = nl802154_dump_wpan_phy,
.done = nl802154_dump_wpan_phy_done,
@@ -2343,7 +2328,8 @@ static const struct genl_ops nl802154_ops[] = {
},
{
.cmd = NL802154_CMD_GET_SEC_KEY,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
/* TODO .doit by matching key id? */
.dumpit = nl802154_dump_llsec_key,
.flags = GENL_ADMIN_PERM,
@@ -2369,7 +2355,8 @@ static const struct genl_ops nl802154_ops[] = {
/* TODO unique identifier must short+pan OR extended_addr */
{
.cmd = NL802154_CMD_GET_SEC_DEV,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
/* TODO .doit by matching extended_addr? */
.dumpit = nl802154_dump_llsec_dev,
.flags = GENL_ADMIN_PERM,
@@ -2395,7 +2382,8 @@ static const struct genl_ops nl802154_ops[] = {
/* TODO remove complete devkey, put it as nested? */
{
.cmd = NL802154_CMD_GET_SEC_DEVKEY,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
/* TODO doit by matching ??? */
.dumpit = nl802154_dump_llsec_devkey,
.flags = GENL_ADMIN_PERM,
@@ -2420,7 +2408,8 @@ static const struct genl_ops nl802154_ops[] = {
},
{
.cmd = NL802154_CMD_GET_SEC_LEVEL,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
/* TODO .doit by matching frame_type? */
.dumpit = nl802154_dump_llsec_seclevel,
.flags = GENL_ADMIN_PERM,
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 03381f3e12ba..fc816b187170 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -180,8 +180,8 @@ config NET_IPIP
config NET_IPGRE_DEMUX
tristate "IP: GRE demultiplexer"
help
- This is helper module to demultiplex GRE packets on GRE version field criteria.
- Required by ip_gre and pptp modules.
+ This is helper module to demultiplex GRE packets on GRE version field criteria.
+ Required by ip_gre and pptp modules.
config NET_IP_TUNNEL
tristate
@@ -459,200 +459,200 @@ config TCP_CONG_BIC
tristate "Binary Increase Congestion (BIC) control"
default m
---help---
- BIC-TCP is a sender-side only change that ensures a linear RTT
- fairness under large windows while offering both scalability and
- bounded TCP-friendliness. The protocol combines two schemes
- called additive increase and binary search increase. When the
- congestion window is large, additive increase with a large
- increment ensures linear RTT fairness as well as good
- scalability. Under small congestion windows, binary search
- increase provides TCP friendliness.
- See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
+ BIC-TCP is a sender-side only change that ensures a linear RTT
+ fairness under large windows while offering both scalability and
+ bounded TCP-friendliness. The protocol combines two schemes
+ called additive increase and binary search increase. When the
+ congestion window is large, additive increase with a large
+ increment ensures linear RTT fairness as well as good
+ scalability. Under small congestion windows, binary search
+ increase provides TCP friendliness.
+ See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
config TCP_CONG_CUBIC
tristate "CUBIC TCP"
default y
---help---
- This is version 2.0 of BIC-TCP which uses a cubic growth function
- among other techniques.
- See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf
+ This is version 2.0 of BIC-TCP which uses a cubic growth function
+ among other techniques.
+ See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf
config TCP_CONG_WESTWOOD
tristate "TCP Westwood+"
default m
---help---
- TCP Westwood+ is a sender-side only modification of the TCP Reno
- protocol stack that optimizes the performance of TCP congestion
- control. It is based on end-to-end bandwidth estimation to set
- congestion window and slow start threshold after a congestion
- episode. Using this estimation, TCP Westwood+ adaptively sets a
- slow start threshold and a congestion window which takes into
- account the bandwidth used at the time congestion is experienced.
- TCP Westwood+ significantly increases fairness wrt TCP Reno in
- wired networks and throughput over wireless links.
+ TCP Westwood+ is a sender-side only modification of the TCP Reno
+ protocol stack that optimizes the performance of TCP congestion
+ control. It is based on end-to-end bandwidth estimation to set
+ congestion window and slow start threshold after a congestion
+ episode. Using this estimation, TCP Westwood+ adaptively sets a
+ slow start threshold and a congestion window which takes into
+ account the bandwidth used at the time congestion is experienced.
+ TCP Westwood+ significantly increases fairness wrt TCP Reno in
+ wired networks and throughput over wireless links.
config TCP_CONG_HTCP
tristate "H-TCP"
default m
---help---
- H-TCP is a send-side only modifications of the TCP Reno
- protocol stack that optimizes the performance of TCP
- congestion control for high speed network links. It uses a
- modeswitch to change the alpha and beta parameters of TCP Reno
- based on network conditions and in a way so as to be fair with
- other Reno and H-TCP flows.
+ H-TCP is a send-side only modifications of the TCP Reno
+ protocol stack that optimizes the performance of TCP
+ congestion control for high speed network links. It uses a
+ modeswitch to change the alpha and beta parameters of TCP Reno
+ based on network conditions and in a way so as to be fair with
+ other Reno and H-TCP flows.
config TCP_CONG_HSTCP
tristate "High Speed TCP"
default n
---help---
- Sally Floyd's High Speed TCP (RFC 3649) congestion control.
- A modification to TCP's congestion control mechanism for use
- with large congestion windows. A table indicates how much to
- increase the congestion window by when an ACK is received.
- For more detail see http://www.icir.org/floyd/hstcp.html
+ Sally Floyd's High Speed TCP (RFC 3649) congestion control.
+ A modification to TCP's congestion control mechanism for use
+ with large congestion windows. A table indicates how much to
+ increase the congestion window by when an ACK is received.
+ For more detail see http://www.icir.org/floyd/hstcp.html
config TCP_CONG_HYBLA
tristate "TCP-Hybla congestion control algorithm"
default n
---help---
- TCP-Hybla is a sender-side only change that eliminates penalization of
- long-RTT, large-bandwidth connections, like when satellite legs are
- involved, especially when sharing a common bottleneck with normal
- terrestrial connections.
+ TCP-Hybla is a sender-side only change that eliminates penalization of
+ long-RTT, large-bandwidth connections, like when satellite legs are
+ involved, especially when sharing a common bottleneck with normal
+ terrestrial connections.
config TCP_CONG_VEGAS
tristate "TCP Vegas"
default n
---help---
- TCP Vegas is a sender-side only change to TCP that anticipates
- the onset of congestion by estimating the bandwidth. TCP Vegas
- adjusts the sending rate by modifying the congestion
- window. TCP Vegas should provide less packet loss, but it is
- not as aggressive as TCP Reno.
+ TCP Vegas is a sender-side only change to TCP that anticipates
+ the onset of congestion by estimating the bandwidth. TCP Vegas
+ adjusts the sending rate by modifying the congestion
+ window. TCP Vegas should provide less packet loss, but it is
+ not as aggressive as TCP Reno.
config TCP_CONG_NV
- tristate "TCP NV"
- default n
- ---help---
- TCP NV is a follow up to TCP Vegas. It has been modified to deal with
- 10G networks, measurement noise introduced by LRO, GRO and interrupt
- coalescence. In addition, it will decrease its cwnd multiplicatively
- instead of linearly.
+ tristate "TCP NV"
+ default n
+ ---help---
+ TCP NV is a follow up to TCP Vegas. It has been modified to deal with
+ 10G networks, measurement noise introduced by LRO, GRO and interrupt
+ coalescence. In addition, it will decrease its cwnd multiplicatively
+ instead of linearly.
- Note that in general congestion avoidance (cwnd decreased when # packets
- queued grows) cannot coexist with congestion control (cwnd decreased only
- when there is packet loss) due to fairness issues. One scenario when they
- can coexist safely is when the CA flows have RTTs << CC flows RTTs.
+ Note that in general congestion avoidance (cwnd decreased when # packets
+ queued grows) cannot coexist with congestion control (cwnd decreased only
+ when there is packet loss) due to fairness issues. One scenario when they
+ can coexist safely is when the CA flows have RTTs << CC flows RTTs.
- For further details see http://www.brakmo.org/networking/tcp-nv/
+ For further details see http://www.brakmo.org/networking/tcp-nv/
config TCP_CONG_SCALABLE
tristate "Scalable TCP"
default n
---help---
- Scalable TCP is a sender-side only change to TCP which uses a
- MIMD congestion control algorithm which has some nice scaling
- properties, though is known to have fairness issues.
- See http://www.deneholme.net/tom/scalable/
+ Scalable TCP is a sender-side only change to TCP which uses a
+ MIMD congestion control algorithm which has some nice scaling
+ properties, though is known to have fairness issues.
+ See http://www.deneholme.net/tom/scalable/
config TCP_CONG_LP
tristate "TCP Low Priority"
default n
---help---
- TCP Low Priority (TCP-LP), a distributed algorithm whose goal is
- to utilize only the excess network bandwidth as compared to the
- ``fair share`` of bandwidth as targeted by TCP.
- See http://www-ece.rice.edu/networks/TCP-LP/
+ TCP Low Priority (TCP-LP), a distributed algorithm whose goal is
+ to utilize only the excess network bandwidth as compared to the
+ ``fair share`` of bandwidth as targeted by TCP.
+ See http://www-ece.rice.edu/networks/TCP-LP/
config TCP_CONG_VENO
tristate "TCP Veno"
default n
---help---
- TCP Veno is a sender-side only enhancement of TCP to obtain better
- throughput over wireless networks. TCP Veno makes use of state
- distinguishing to circumvent the difficult judgment of the packet loss
- type. TCP Veno cuts down less congestion window in response to random
- loss packets.
- See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186>
+ TCP Veno is a sender-side only enhancement of TCP to obtain better
+ throughput over wireless networks. TCP Veno makes use of state
+ distinguishing to circumvent the difficult judgment of the packet loss
+ type. TCP Veno cuts down less congestion window in response to random
+ loss packets.
+ See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186>
config TCP_CONG_YEAH
tristate "YeAH TCP"
select TCP_CONG_VEGAS
default n
---help---
- YeAH-TCP is a sender-side high-speed enabled TCP congestion control
- algorithm, which uses a mixed loss/delay approach to compute the
- congestion window. It's design goals target high efficiency,
- internal, RTT and Reno fairness, resilience to link loss while
- keeping network elements load as low as possible.
+ YeAH-TCP is a sender-side high-speed enabled TCP congestion control
+ algorithm, which uses a mixed loss/delay approach to compute the
+ congestion window. It's design goals target high efficiency,
+ internal, RTT and Reno fairness, resilience to link loss while
+ keeping network elements load as low as possible.
- For further details look here:
- http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf
+ For further details look here:
+ http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf
config TCP_CONG_ILLINOIS
tristate "TCP Illinois"
default n
---help---
- TCP-Illinois is a sender-side modification of TCP Reno for
- high speed long delay links. It uses round-trip-time to
- adjust the alpha and beta parameters to achieve a higher average
- throughput and maintain fairness.
+ TCP-Illinois is a sender-side modification of TCP Reno for
+ high speed long delay links. It uses round-trip-time to
+ adjust the alpha and beta parameters to achieve a higher average
+ throughput and maintain fairness.
- For further details see:
- http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
+ For further details see:
+ http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
config TCP_CONG_DCTCP
tristate "DataCenter TCP (DCTCP)"
default n
---help---
- DCTCP leverages Explicit Congestion Notification (ECN) in the network to
- provide multi-bit feedback to the end hosts. It is designed to provide:
+ DCTCP leverages Explicit Congestion Notification (ECN) in the network to
+ provide multi-bit feedback to the end hosts. It is designed to provide:
- - High burst tolerance (incast due to partition/aggregate),
- - Low latency (short flows, queries),
- - High throughput (continuous data updates, large file transfers) with
- commodity, shallow-buffered switches.
+ - High burst tolerance (incast due to partition/aggregate),
+ - Low latency (short flows, queries),
+ - High throughput (continuous data updates, large file transfers) with
+ commodity, shallow-buffered switches.
- All switches in the data center network running DCTCP must support
- ECN marking and be configured for marking when reaching defined switch
- buffer thresholds. The default ECN marking threshold heuristic for
- DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets
- (~100KB) at 10Gbps, but might need further careful tweaking.
+ All switches in the data center network running DCTCP must support
+ ECN marking and be configured for marking when reaching defined switch
+ buffer thresholds. The default ECN marking threshold heuristic for
+ DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets
+ (~100KB) at 10Gbps, but might need further careful tweaking.
- For further details see:
- http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+ For further details see:
+ http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
config TCP_CONG_CDG
tristate "CAIA Delay-Gradient (CDG)"
default n
---help---
- CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies
- the TCP sender in order to:
+ CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies
+ the TCP sender in order to:
o Use the delay gradient as a congestion signal.
o Back off with an average probability that is independent of the RTT.
o Coexist with flows that use loss-based congestion control.
o Tolerate packet loss unrelated to congestion.
- For further details see:
- D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
- delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg
+ For further details see:
+ D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
+ delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg
config TCP_CONG_BBR
tristate "BBR TCP"
default n
---help---
- BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to
- maximize network utilization and minimize queues. It builds an explicit
- model of the the bottleneck delivery rate and path round-trip
- propagation delay. It tolerates packet loss and delay unrelated to
- congestion. It can operate over LAN, WAN, cellular, wifi, or cable
- modem links. It can coexist with flows that use loss-based congestion
- control, and can operate with shallow buffers, deep buffers,
- bufferbloat, policers, or AQM schemes that do not provide a delay
- signal. It requires the fq ("Fair Queue") pacing packet scheduler.
+ BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to
+ maximize network utilization and minimize queues. It builds an explicit
+ model of the the bottleneck delivery rate and path round-trip
+ propagation delay. It tolerates packet loss and delay unrelated to
+ congestion. It can operate over LAN, WAN, cellular, wifi, or cable
+ modem links. It can coexist with flows that use loss-based congestion
+ control, and can operate with shallow buffers, deep buffers,
+ bufferbloat, policers, or AQM schemes that do not provide a delay
+ signal. It requires the fq ("Fair Queue") pacing packet scheduler.
choice
prompt "Default TCP congestion control"
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 70f92aaca411..53de8e00990e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -208,7 +208,7 @@ int inet_listen(struct socket *sock, int backlog)
if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN)))
goto out;
- sk->sk_max_ack_backlog = backlog;
+ WRITE_ONCE(sk->sk_max_ack_backlog, backlog);
/* Really, if the socket is already in listen state
* we can only allow the backlog to be adjusted.
*/
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 9a0fe0c2fa02..4a8550c49202 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
reuseport_has_conns(sk, true);
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
- inet->inet_id = jiffies;
+ inet->inet_id = prandom_u32();
sk_dst_set(sk, &rt->dst);
err = 0;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index dde77f72e03e..577db1d50a24 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -70,11 +70,6 @@ fail:
fib_free_table(main_table);
return -ENOMEM;
}
-
-static bool fib4_has_custom_rules(struct net *net)
-{
- return false;
-}
#else
struct fib_table *fib_new_table(struct net *net, u32 id)
@@ -131,11 +126,6 @@ struct fib_table *fib_get_table(struct net *net, u32 id)
}
return NULL;
}
-
-static bool fib4_has_custom_rules(struct net *net)
-{
- return net->ipv4.fib_has_custom_rules;
-}
#endif /* CONFIG_IP_MULTIPLE_TABLES */
static void fib_replace_table(struct net *net, struct fib_table *old,
@@ -1148,7 +1138,7 @@ void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric)
if (!(dev->flags & IFF_UP) ||
ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) ||
ipv4_is_zeronet(prefix) ||
- prefix == ifa->ifa_local || ifa->ifa_prefixlen == 32)
+ (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32))
return;
/* add the new */
diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c
index b804ccbdb241..0c28bd469a68 100644
--- a/net/ipv4/fib_notifier.c
+++ b/net/ipv4/fib_notifier.c
@@ -9,12 +9,12 @@
#include <net/netns/ipv4.h>
#include <net/ip_fib.h>
-int call_fib4_notifier(struct notifier_block *nb, struct net *net,
+int call_fib4_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
struct fib_notifier_info *info)
{
info->family = AF_INET;
- return call_fib_notifier(nb, net, event_type, info);
+ return call_fib_notifier(nb, event_type, info);
}
int call_fib4_notifiers(struct net *net, enum fib_event_type event_type,
@@ -34,17 +34,16 @@ static unsigned int fib4_seq_read(struct net *net)
return net->ipv4.fib_seq + fib4_rules_seq_read(net);
}
-static int fib4_dump(struct net *net, struct notifier_block *nb)
+static int fib4_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
int err;
- err = fib4_rules_dump(net, nb);
+ err = fib4_rules_dump(net, nb, extack);
if (err)
return err;
- fib_notify(net, nb);
-
- return 0;
+ return fib_notify(net, nb, extack);
}
static const struct fib_notifier_ops fib4_notifier_ops_template = {
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index b43a7ba5c6a4..f99e3bac5cab 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -65,9 +65,10 @@ bool fib4_rule_default(const struct fib_rule *rule)
}
EXPORT_SYMBOL_GPL(fib4_rule_default);
-int fib4_rules_dump(struct net *net, struct notifier_block *nb)
+int fib4_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
- return fib_rules_dump(net, nb, AF_INET);
+ return fib_rules_dump(net, nb, AF_INET, extack);
}
unsigned int fib4_rules_seq_read(struct net *net)
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 0913a090b2bf..f1888c683426 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1814,8 +1814,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
int ret = 0;
unsigned int hash = fib_laddr_hashfn(local);
struct hlist_head *head = &fib_info_laddrhash[hash];
+ int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
struct net *net = dev_net(dev);
- int tb_id = l3mdev_fib_table(dev);
struct fib_info *fi;
if (!fib_info_laddrhash || local == 0)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 1ab2fb6bb37d..b9df9c09b84e 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -74,11 +74,13 @@
#include <trace/events/fib.h>
#include "fib_lookup.h"
-static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
+static int call_fib_entry_notifier(struct notifier_block *nb,
enum fib_event_type event_type, u32 dst,
- int dst_len, struct fib_alias *fa)
+ int dst_len, struct fib_alias *fa,
+ struct netlink_ext_ack *extack)
{
struct fib_entry_notifier_info info = {
+ .info.extack = extack,
.dst = dst,
.dst_len = dst_len,
.fi = fa->fa_info,
@@ -86,7 +88,7 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
.type = fa->fa_type,
.tb_id = fa->tb_id,
};
- return call_fib4_notifier(nb, net, event_type, &info.info);
+ return call_fib4_notifier(nb, event_type, &info.info);
}
static int call_fib_entry_notifiers(struct net *net,
@@ -2015,10 +2017,12 @@ void fib_info_notify_update(struct net *net, struct nl_info *info)
}
}
-static void fib_leaf_notify(struct net *net, struct key_vector *l,
- struct fib_table *tb, struct notifier_block *nb)
+static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb,
+ struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
struct fib_alias *fa;
+ int err;
hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
struct fib_info *fi = fa->fa_info;
@@ -2032,39 +2036,53 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l,
if (tb->tb_id != fa->tb_id)
continue;
- call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key,
- KEYLENGTH - fa->fa_slen, fa);
+ err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_ADD, l->key,
+ KEYLENGTH - fa->fa_slen,
+ fa, extack);
+ if (err)
+ return err;
}
+ return 0;
}
-static void fib_table_notify(struct net *net, struct fib_table *tb,
- struct notifier_block *nb)
+static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
struct trie *t = (struct trie *)tb->tb_data;
struct key_vector *l, *tp = t->kv;
t_key key = 0;
+ int err;
while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
- fib_leaf_notify(net, l, tb, nb);
+ err = fib_leaf_notify(l, tb, nb, extack);
+ if (err)
+ return err;
key = l->key + 1;
/* stop in case of wrap around */
if (key < l->key)
break;
}
+ return 0;
}
-void fib_notify(struct net *net, struct notifier_block *nb)
+int fib_notify(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
unsigned int h;
+ int err;
for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
struct hlist_head *head = &net->ipv4.fib_table_hash[h];
struct fib_table *tb;
- hlist_for_each_entry_rcu(tb, head, tb_hlist)
- fib_table_notify(net, tb, nb);
+ hlist_for_each_entry_rcu(tb, head, tb_hlist) {
+ err = fib_table_notify(tb, nb, extack);
+ if (err)
+ return err;
+ }
}
+ return 0;
}
static void __trie_free_rcu(struct rcu_head *head)
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 4298aae74e0e..18068ed42f25 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -249,10 +249,11 @@ bool icmp_global_allow(void)
bool rc = false;
/* Check if token bucket is empty and cannot be refilled
- * without taking the spinlock.
+ * without taking the spinlock. The READ_ONCE() are paired
+ * with the following WRITE_ONCE() in this same function.
*/
- if (!icmp_global.credit) {
- delta = min_t(u32, now - icmp_global.stamp, HZ);
+ if (!READ_ONCE(icmp_global.credit)) {
+ delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ);
if (delta < HZ / 50)
return false;
}
@@ -262,14 +263,14 @@ bool icmp_global_allow(void)
if (delta >= HZ / 50) {
incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
if (incr)
- icmp_global.stamp = now;
+ WRITE_ONCE(icmp_global.stamp, now);
}
credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
if (credit) {
credit--;
rc = true;
}
- icmp_global.credit = credit;
+ WRITE_ONCE(icmp_global.credit, credit);
spin_unlock(&icmp_global.lock);
return rc;
}
@@ -682,7 +683,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
dev = dev_get_by_index_rcu(net, inet_iif(skb_in));
if (dev)
- saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK);
+ saddr = inet_select_addr(dev, iph->saddr,
+ RT_SCOPE_LINK);
else
saddr = 0;
rcu_read_unlock();
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 480d0b22db1a..3b9c7a2725a9 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1563,7 +1563,7 @@ static int ip_mc_check_igmp_msg(struct sk_buff *skb)
}
}
-static inline __sum16 ip_mc_validate_checksum(struct sk_buff *skb)
+static __sum16 ip_mc_validate_checksum(struct sk_buff *skb)
{
return skb_checksum_simple_validate(skb);
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index eb30fc1770de..e4c6e8b40490 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -716,7 +716,7 @@ static void reqsk_timer_handler(struct timer_list *t)
* ones are about to clog our table.
*/
qlen = reqsk_queue_len(queue);
- if ((qlen << 1) > max(8U, sk_listener->sk_max_ack_backlog)) {
+ if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) {
int young = reqsk_queue_len_young(queue) << 1;
while (thresh > 2) {
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 7dc79b973e6e..af154977904c 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -226,17 +226,17 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
r->idiag_timer = 1;
r->idiag_retrans = icsk->icsk_retransmits;
r->idiag_expires =
- jiffies_to_msecs(icsk->icsk_timeout - jiffies);
+ jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies);
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
r->idiag_timer = 4;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
- jiffies_to_msecs(icsk->icsk_timeout - jiffies);
+ jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies);
} else if (timer_pending(&sk->sk_timer)) {
r->idiag_timer = 2;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
- jiffies_to_msecs(sk->sk_timer.expires - jiffies);
+ jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies);
} else {
r->idiag_timer = 0;
r->idiag_expires = 0;
@@ -342,16 +342,13 @@ static int inet_twsk_diag_fill(struct sock *sk,
r = nlmsg_data(nlh);
BUG_ON(tw->tw_state != TCP_TIME_WAIT);
- tmo = tw->tw_timer.expires - jiffies;
- if (tmo < 0)
- tmo = 0;
-
inet_diag_msg_common_fill(r, sk);
r->idiag_retrans = 0;
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
- r->idiag_expires = jiffies_to_msecs(tmo);
+ tmo = tw->tw_timer.expires - jiffies;
+ r->idiag_expires = jiffies_delta_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
@@ -385,7 +382,7 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
offsetof(struct sock, sk_cookie));
tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies;
- r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0;
+ r->idiag_expires = jiffies_delta_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 97824864e40d..83fb00153018 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -240,7 +240,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score = sk->sk_family == PF_INET ? 2 : 1;
- if (sk->sk_incoming_cpu == raw_smp_processor_id())
+ if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
}
return score;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index be778599bfed..ff327a62c9ce 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -160,7 +160,12 @@ static void inet_peer_gc(struct inet_peer_base *base,
base->total / inet_peer_threshold * HZ;
for (i = 0; i < gc_cnt; i++) {
p = gc_stack[i];
- delta = (__u32)jiffies - p->dtime;
+
+ /* The READ_ONCE() pairs with the WRITE_ONCE()
+ * in inet_putpeer()
+ */
+ delta = (__u32)jiffies - READ_ONCE(p->dtime);
+
if (delta < ttl || !refcount_dec_if_one(&p->refcnt))
gc_stack[i] = NULL;
}
@@ -237,7 +242,10 @@ EXPORT_SYMBOL_GPL(inet_getpeer);
void inet_putpeer(struct inet_peer *p)
{
- p->dtime = (__u32)jiffies;
+ /* The WRITE_ONCE() pairs with itself (we run lockless)
+ * and the READ_ONCE() in inet_peer_gc()
+ */
+ WRITE_ONCE(p->dtime, (__u32)jiffies);
if (refcount_dec_and_test(&p->refcnt))
call_rcu(&p->rcu, inetpeer_free_rcu);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 52690bb3e40f..572b6307a2df 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -340,6 +340,8 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
iph->saddr, iph->daddr, tpi->key);
if (tunnel) {
+ const struct iphdr *tnl_params;
+
if (__iptunnel_pull_header(skb, hdr_len, tpi->proto,
raw_proto, false) < 0)
goto drop;
@@ -348,7 +350,9 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
skb_pop_mac_header(skb);
else
skb_reset_mac_header(skb);
- if (tunnel->collect_md) {
+
+ tnl_params = &tunnel->parms.iph;
+ if (tunnel->collect_md || tnl_params->daddr == 0) {
__be16 flags;
__be64 tun_id;
@@ -509,9 +513,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
key = &tun_info->key;
if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT))
goto err_free_skb;
- md = ip_tunnel_info_opts(tun_info);
- if (!md)
+ if (tun_info->options_len < sizeof(*md))
goto err_free_skb;
+ md = ip_tunnel_info_opts(tun_info);
/* ERSPAN has fixed 8 byte GRE header */
version = md->version;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index c59a78a267c3..aa438c6758a7 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -302,16 +302,31 @@ drop:
return true;
}
+static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph,
+ const struct sk_buff *hint)
+{
+ return hint && !skb_dst(skb) && ip_hdr(hint)->daddr == iph->daddr &&
+ ip_hdr(hint)->tos == iph->tos;
+}
+
INDIRECT_CALLABLE_DECLARE(int udp_v4_early_demux(struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int tcp_v4_early_demux(struct sk_buff *));
static int ip_rcv_finish_core(struct net *net, struct sock *sk,
- struct sk_buff *skb, struct net_device *dev)
+ struct sk_buff *skb, struct net_device *dev,
+ const struct sk_buff *hint)
{
const struct iphdr *iph = ip_hdr(skb);
int (*edemux)(struct sk_buff *skb);
struct rtable *rt;
int err;
+ if (ip_can_use_hint(skb, iph, hint)) {
+ err = ip_route_use_hint(skb, iph->daddr, iph->saddr, iph->tos,
+ dev, hint);
+ if (unlikely(err))
+ goto drop_error;
+ }
+
if (net->ipv4.sysctl_ip_early_demux &&
!skb_dst(skb) &&
!skb->sk &&
@@ -408,7 +423,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
if (!skb)
return NET_RX_SUCCESS;
- ret = ip_rcv_finish_core(net, sk, skb, dev);
+ ret = ip_rcv_finish_core(net, sk, skb, dev, NULL);
if (ret != NET_RX_DROP)
ret = dst_input(skb);
return ret;
@@ -535,11 +550,20 @@ static void ip_sublist_rcv_finish(struct list_head *head)
}
}
+static struct sk_buff *ip_extract_route_hint(const struct net *net,
+ struct sk_buff *skb, int rt_type)
+{
+ if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST)
+ return NULL;
+
+ return skb;
+}
+
static void ip_list_rcv_finish(struct net *net, struct sock *sk,
struct list_head *head)
{
+ struct sk_buff *skb, *next, *hint = NULL;
struct dst_entry *curr_dst = NULL;
- struct sk_buff *skb, *next;
struct list_head sublist;
INIT_LIST_HEAD(&sublist);
@@ -554,11 +578,14 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
skb = l3mdev_ip_rcv(skb);
if (!skb)
continue;
- if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP)
+ if (ip_rcv_finish_core(net, sk, skb, dev, hint) == NET_RX_DROP)
continue;
dst = skb_dst(skb);
if (curr_dst != dst) {
+ hint = ip_extract_route_hint(net, skb,
+ ((struct rtable *)dst)->rt_type);
+
/* dispatch old sublist */
if (!list_empty(&sublist))
ip_sublist_rcv_finish(&sublist);
@@ -611,5 +638,6 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt,
list_add_tail(&skb->list, &sublist);
}
/* dispatch final sublist */
- ip_sublist_rcv(&sublist, curr_dev, curr_net);
+ if (!list_empty(&sublist))
+ ip_sublist_rcv(&sublist, curr_dev, curr_net);
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 814b9b8882a0..9d83cb320dcb 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -422,7 +422,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net_device *dev = skb_dst(skb)->dev;
+ struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev;
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
@@ -430,7 +430,7 @@ int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
skb->protocol = htons(ETH_P_IP);
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
- net, sk, skb, NULL, dev,
+ net, sk, skb, indev, dev,
ip_finish_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
@@ -645,11 +645,12 @@ void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter)
EXPORT_SYMBOL(ip_fraglist_prepare);
void ip_frag_init(struct sk_buff *skb, unsigned int hlen,
- unsigned int ll_rs, unsigned int mtu,
+ unsigned int ll_rs, unsigned int mtu, bool DF,
struct ip_frag_state *state)
{
struct iphdr *iph = ip_hdr(skb);
+ state->DF = DF;
state->hlen = hlen;
state->ll_rs = ll_rs;
state->mtu = mtu;
@@ -668,9 +669,6 @@ static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to,
/* Copy the flags to each fragment. */
IPCB(to)->flags = IPCB(from)->flags;
- if (IPCB(from)->flags & IPSKB_FRAG_PMTU)
- state->iph->frag_off |= htons(IP_DF);
-
/* ANK: dirty, but effective trick. Upgrade options only if
* the segment to be fragmented was THE FIRST (otherwise,
* options are already fixed) and make it ONCE
@@ -738,6 +736,8 @@ struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state)
*/
iph = ip_hdr(skb2);
iph->frag_off = htons((state->offset >> 3));
+ if (state->DF)
+ iph->frag_off |= htons(IP_DF);
/*
* Added AC : If we are fragmenting a fragment that's not the
@@ -883,7 +883,8 @@ slow_path:
* Fragment the datagram.
*/
- ip_frag_init(skb, hlen, ll_rs, mtu, &state);
+ ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU,
+ &state);
/*
* Keep copying data until we run out.
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 1452a97914a0..47f8b947eef1 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -34,6 +34,9 @@
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/dst_metadata.h>
+#include <net/geneve.h>
+#include <net/vxlan.h>
+#include <net/erspan.h>
const struct ip_tunnel_encap_ops __rcu *
iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
@@ -126,15 +129,14 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
if (!md || md->type != METADATA_IP_TUNNEL ||
md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
-
return NULL;
- res = metadata_dst_alloc(0, METADATA_IP_TUNNEL, flags);
+ src = &md->u.tun_info;
+ res = metadata_dst_alloc(src->options_len, METADATA_IP_TUNNEL, flags);
if (!res)
return NULL;
dst = &res->u.tun_info;
- src = &md->u.tun_info;
dst->key.tun_id = src->key.tun_id;
if (src->mode & IP_TUNNEL_INFO_IPV6)
memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src,
@@ -143,6 +145,8 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
dst->key.u.ipv4.dst = src->key.u.ipv4.src;
dst->key.tun_flags = src->key.tun_flags;
dst->mode = src->mode | IP_TUNNEL_INFO_TX;
+ ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src),
+ src->options_len, 0);
return res;
}
@@ -211,30 +215,243 @@ void ip_tunnel_get_stats64(struct net_device *dev,
EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
+ [LWTUNNEL_IP_UNSPEC] = { .strict_start_type = LWTUNNEL_IP_OPTS },
[LWTUNNEL_IP_ID] = { .type = NLA_U64 },
[LWTUNNEL_IP_DST] = { .type = NLA_U32 },
[LWTUNNEL_IP_SRC] = { .type = NLA_U32 },
[LWTUNNEL_IP_TTL] = { .type = NLA_U8 },
[LWTUNNEL_IP_TOS] = { .type = NLA_U8 },
[LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 },
+ [LWTUNNEL_IP_OPTS] = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy ip_opts_policy[LWTUNNEL_IP_OPTS_MAX + 1] = {
+ [LWTUNNEL_IP_OPTS_GENEVE] = { .type = NLA_NESTED },
+ [LWTUNNEL_IP_OPTS_VXLAN] = { .type = NLA_NESTED },
+ [LWTUNNEL_IP_OPTS_ERSPAN] = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy
+geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = {
+ [LWTUNNEL_IP_OPT_GENEVE_CLASS] = { .type = NLA_U16 },
+ [LWTUNNEL_IP_OPT_GENEVE_TYPE] = { .type = NLA_U8 },
+ [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 },
+};
+
+static const struct nla_policy
+vxlan_opt_policy[LWTUNNEL_IP_OPT_VXLAN_MAX + 1] = {
+ [LWTUNNEL_IP_OPT_VXLAN_GBP] = { .type = NLA_U32 },
};
+static const struct nla_policy
+erspan_opt_policy[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1] = {
+ [LWTUNNEL_IP_OPT_ERSPAN_VER] = { .type = NLA_U8 },
+ [LWTUNNEL_IP_OPT_ERSPAN_INDEX] = { .type = NLA_U32 },
+ [LWTUNNEL_IP_OPT_ERSPAN_DIR] = { .type = NLA_U8 },
+ [LWTUNNEL_IP_OPT_ERSPAN_HWID] = { .type = NLA_U8 },
+};
+
+static int ip_tun_parse_opts_geneve(struct nlattr *attr,
+ struct ip_tunnel_info *info, int opts_len,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[LWTUNNEL_IP_OPT_GENEVE_MAX + 1];
+ int data_len, err;
+
+ err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_GENEVE_MAX, attr,
+ geneve_opt_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[LWTUNNEL_IP_OPT_GENEVE_CLASS] ||
+ !tb[LWTUNNEL_IP_OPT_GENEVE_TYPE] ||
+ !tb[LWTUNNEL_IP_OPT_GENEVE_DATA])
+ return -EINVAL;
+
+ attr = tb[LWTUNNEL_IP_OPT_GENEVE_DATA];
+ data_len = nla_len(attr);
+ if (data_len % 4)
+ return -EINVAL;
+
+ if (info) {
+ struct geneve_opt *opt = ip_tunnel_info_opts(info) + opts_len;
+
+ memcpy(opt->opt_data, nla_data(attr), data_len);
+ opt->length = data_len / 4;
+ attr = tb[LWTUNNEL_IP_OPT_GENEVE_CLASS];
+ opt->opt_class = nla_get_be16(attr);
+ attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE];
+ opt->type = nla_get_u8(attr);
+ info->key.tun_flags |= TUNNEL_GENEVE_OPT;
+ }
+
+ return sizeof(struct geneve_opt) + data_len;
+}
+
+static int ip_tun_parse_opts_vxlan(struct nlattr *attr,
+ struct ip_tunnel_info *info, int opts_len,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[LWTUNNEL_IP_OPT_VXLAN_MAX + 1];
+ int err;
+
+ err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_VXLAN_MAX, attr,
+ vxlan_opt_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[LWTUNNEL_IP_OPT_VXLAN_GBP])
+ return -EINVAL;
+
+ if (info) {
+ struct vxlan_metadata *md =
+ ip_tunnel_info_opts(info) + opts_len;
+
+ attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP];
+ md->gbp = nla_get_u32(attr);
+ info->key.tun_flags |= TUNNEL_VXLAN_OPT;
+ }
+
+ return sizeof(struct vxlan_metadata);
+}
+
+static int ip_tun_parse_opts_erspan(struct nlattr *attr,
+ struct ip_tunnel_info *info, int opts_len,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1];
+ int err;
+ u8 ver;
+
+ err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_ERSPAN_MAX, attr,
+ erspan_opt_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[LWTUNNEL_IP_OPT_ERSPAN_VER])
+ return -EINVAL;
+
+ ver = nla_get_u8(tb[LWTUNNEL_IP_OPT_ERSPAN_VER]);
+ if (ver == 1) {
+ if (!tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX])
+ return -EINVAL;
+ } else if (ver == 2) {
+ if (!tb[LWTUNNEL_IP_OPT_ERSPAN_DIR] ||
+ !tb[LWTUNNEL_IP_OPT_ERSPAN_HWID])
+ return -EINVAL;
+ } else {
+ return -EINVAL;
+ }
+
+ if (info) {
+ struct erspan_metadata *md =
+ ip_tunnel_info_opts(info) + opts_len;
+
+ md->version = ver;
+ if (ver == 1) {
+ attr = tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX];
+ md->u.index = nla_get_be32(attr);
+ } else {
+ attr = tb[LWTUNNEL_IP_OPT_ERSPAN_DIR];
+ md->u.md2.dir = nla_get_u8(attr);
+ attr = tb[LWTUNNEL_IP_OPT_ERSPAN_HWID];
+ set_hwid(&md->u.md2, nla_get_u8(attr));
+ }
+
+ info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
+ }
+
+ return sizeof(struct erspan_metadata);
+}
+
+static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info,
+ struct netlink_ext_ack *extack)
+{
+ int err, rem, opt_len, opts_len = 0, type = 0;
+ struct nlattr *nla;
+
+ if (!attr)
+ return 0;
+
+ err = nla_validate(nla_data(attr), nla_len(attr), LWTUNNEL_IP_OPTS_MAX,
+ ip_opts_policy, extack);
+ if (err)
+ return err;
+
+ nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) {
+ switch (nla_type(nla)) {
+ case LWTUNNEL_IP_OPTS_GENEVE:
+ if (type && type != TUNNEL_GENEVE_OPT)
+ return -EINVAL;
+ opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len,
+ extack);
+ if (opt_len < 0)
+ return opt_len;
+ opts_len += opt_len;
+ if (opts_len > IP_TUNNEL_OPTS_MAX)
+ return -EINVAL;
+ type = TUNNEL_GENEVE_OPT;
+ break;
+ case LWTUNNEL_IP_OPTS_VXLAN:
+ if (type)
+ return -EINVAL;
+ opt_len = ip_tun_parse_opts_vxlan(nla, info, opts_len,
+ extack);
+ if (opt_len < 0)
+ return opt_len;
+ opts_len += opt_len;
+ type = TUNNEL_VXLAN_OPT;
+ break;
+ case LWTUNNEL_IP_OPTS_ERSPAN:
+ if (type)
+ return -EINVAL;
+ opt_len = ip_tun_parse_opts_erspan(nla, info, opts_len,
+ extack);
+ if (opt_len < 0)
+ return opt_len;
+ opts_len += opt_len;
+ type = TUNNEL_ERSPAN_OPT;
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ return opts_len;
+}
+
+static int ip_tun_get_optlen(struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ return ip_tun_parse_opts(attr, NULL, extack);
+}
+
+static int ip_tun_set_opts(struct nlattr *attr, struct ip_tunnel_info *info,
+ struct netlink_ext_ack *extack)
+{
+ return ip_tun_parse_opts(attr, info, extack);
+}
+
static int ip_tun_build_state(struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
- struct ip_tunnel_info *tun_info;
- struct lwtunnel_state *new_state;
struct nlattr *tb[LWTUNNEL_IP_MAX + 1];
- int err;
+ struct lwtunnel_state *new_state;
+ struct ip_tunnel_info *tun_info;
+ int err, opt_len;
err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_MAX, attr,
ip_tun_policy, extack);
if (err < 0)
return err;
- new_state = lwtunnel_state_alloc(sizeof(*tun_info));
+ opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP_OPTS], extack);
+ if (opt_len < 0)
+ return opt_len;
+
+ new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len);
if (!new_state)
return -ENOMEM;
@@ -242,6 +459,12 @@ static int ip_tun_build_state(struct nlattr *attr,
tun_info = lwt_tun_info(new_state);
+ err = ip_tun_set_opts(tb[LWTUNNEL_IP_OPTS], tun_info, extack);
+ if (err < 0) {
+ lwtstate_free(new_state);
+ return err;
+ }
+
#ifdef CONFIG_DST_CACHE
err = dst_cache_init(&tun_info->dst_cache, GFP_KERNEL);
if (err) {
@@ -266,10 +489,12 @@ static int ip_tun_build_state(struct nlattr *attr,
tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]);
if (tb[LWTUNNEL_IP_FLAGS])
- tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP_FLAGS]);
+ tun_info->key.tun_flags |=
+ (nla_get_be16(tb[LWTUNNEL_IP_FLAGS]) &
+ ~TUNNEL_OPTIONS_PRESENT);
tun_info->mode = IP_TUNNEL_INFO_TX;
- tun_info->options_len = 0;
+ tun_info->options_len = opt_len;
*ts = new_state;
@@ -285,6 +510,114 @@ static void ip_tun_destroy_state(struct lwtunnel_state *lwtstate)
#endif
}
+static int ip_tun_fill_encap_opts_geneve(struct sk_buff *skb,
+ struct ip_tunnel_info *tun_info)
+{
+ struct geneve_opt *opt;
+ struct nlattr *nest;
+ int offset = 0;
+
+ nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_GENEVE);
+ if (!nest)
+ return -ENOMEM;
+
+ while (tun_info->options_len > offset) {
+ opt = ip_tunnel_info_opts(tun_info) + offset;
+ if (nla_put_be16(skb, LWTUNNEL_IP_OPT_GENEVE_CLASS,
+ opt->opt_class) ||
+ nla_put_u8(skb, LWTUNNEL_IP_OPT_GENEVE_TYPE, opt->type) ||
+ nla_put(skb, LWTUNNEL_IP_OPT_GENEVE_DATA, opt->length * 4,
+ opt->opt_data)) {
+ nla_nest_cancel(skb, nest);
+ return -ENOMEM;
+ }
+ offset += sizeof(*opt) + opt->length * 4;
+ }
+
+ nla_nest_end(skb, nest);
+ return 0;
+}
+
+static int ip_tun_fill_encap_opts_vxlan(struct sk_buff *skb,
+ struct ip_tunnel_info *tun_info)
+{
+ struct vxlan_metadata *md;
+ struct nlattr *nest;
+
+ nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_VXLAN);
+ if (!nest)
+ return -ENOMEM;
+
+ md = ip_tunnel_info_opts(tun_info);
+ if (nla_put_u32(skb, LWTUNNEL_IP_OPT_VXLAN_GBP, md->gbp)) {
+ nla_nest_cancel(skb, nest);
+ return -ENOMEM;
+ }
+
+ nla_nest_end(skb, nest);
+ return 0;
+}
+
+static int ip_tun_fill_encap_opts_erspan(struct sk_buff *skb,
+ struct ip_tunnel_info *tun_info)
+{
+ struct erspan_metadata *md;
+ struct nlattr *nest;
+
+ nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_ERSPAN);
+ if (!nest)
+ return -ENOMEM;
+
+ md = ip_tunnel_info_opts(tun_info);
+ if (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_VER, md->version))
+ goto err;
+
+ if (md->version == 1 &&
+ nla_put_be32(skb, LWTUNNEL_IP_OPT_ERSPAN_INDEX, md->u.index))
+ goto err;
+
+ if (md->version == 2 &&
+ (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_DIR, md->u.md2.dir) ||
+ nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_HWID,
+ get_hwid(&md->u.md2))))
+ goto err;
+
+ nla_nest_end(skb, nest);
+ return 0;
+err:
+ nla_nest_cancel(skb, nest);
+ return -ENOMEM;
+}
+
+static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type,
+ struct ip_tunnel_info *tun_info)
+{
+ struct nlattr *nest;
+ int err = 0;
+
+ if (!(tun_info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))
+ return 0;
+
+ nest = nla_nest_start_noflag(skb, type);
+ if (!nest)
+ return -ENOMEM;
+
+ if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT)
+ err = ip_tun_fill_encap_opts_geneve(skb, tun_info);
+ else if (tun_info->key.tun_flags & TUNNEL_VXLAN_OPT)
+ err = ip_tun_fill_encap_opts_vxlan(skb, tun_info);
+ else if (tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)
+ err = ip_tun_fill_encap_opts_erspan(skb, tun_info);
+
+ if (err) {
+ nla_nest_cancel(skb, nest);
+ return err;
+ }
+
+ nla_nest_end(skb, nest);
+ return 0;
+}
+
static int ip_tun_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
@@ -296,12 +629,52 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb,
nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) ||
nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) ||
nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) ||
- nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags))
+ nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags) ||
+ ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info))
return -ENOMEM;
return 0;
}
+static int ip_tun_opts_nlsize(struct ip_tunnel_info *info)
+{
+ int opt_len;
+
+ if (!(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))
+ return 0;
+
+ opt_len = nla_total_size(0); /* LWTUNNEL_IP_OPTS */
+ if (info->key.tun_flags & TUNNEL_GENEVE_OPT) {
+ struct geneve_opt *opt;
+ int offset = 0;
+
+ opt_len += nla_total_size(0); /* LWTUNNEL_IP_OPTS_GENEVE */
+ while (info->options_len > offset) {
+ opt = ip_tunnel_info_opts(info) + offset;
+ opt_len += nla_total_size(2) /* OPT_GENEVE_CLASS */
+ + nla_total_size(1) /* OPT_GENEVE_TYPE */
+ + nla_total_size(opt->length * 4);
+ /* OPT_GENEVE_DATA */
+ offset += sizeof(*opt) + opt->length * 4;
+ }
+ } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) {
+ opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_VXLAN */
+ + nla_total_size(4); /* OPT_VXLAN_GBP */
+ } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) {
+ struct erspan_metadata *md = ip_tunnel_info_opts(info);
+
+ opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_ERSPAN */
+ + nla_total_size(1) /* OPT_ERSPAN_VER */
+ + (md->version == 1 ? nla_total_size(4)
+ /* OPT_ERSPAN_INDEX (v1) */
+ : nla_total_size(1) +
+ nla_total_size(1));
+ /* OPT_ERSPAN_DIR + HWID (v2) */
+ }
+
+ return opt_len;
+}
+
static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
return nla_total_size_64bit(8) /* LWTUNNEL_IP_ID */
@@ -309,13 +682,21 @@ static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
+ nla_total_size(4) /* LWTUNNEL_IP_SRC */
+ nla_total_size(1) /* LWTUNNEL_IP_TOS */
+ nla_total_size(1) /* LWTUNNEL_IP_TTL */
- + nla_total_size(2); /* LWTUNNEL_IP_FLAGS */
+ + nla_total_size(2) /* LWTUNNEL_IP_FLAGS */
+ + ip_tun_opts_nlsize(lwt_tun_info(lwtstate));
+ /* LWTUNNEL_IP_OPTS */
}
static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
{
- return memcmp(lwt_tun_info(a), lwt_tun_info(b),
- sizeof(struct ip_tunnel_info));
+ struct ip_tunnel_info *info_a = lwt_tun_info(a);
+ struct ip_tunnel_info *info_b = lwt_tun_info(b);
+
+ return memcmp(info_a, info_b, sizeof(info_a->key)) ||
+ info_a->mode != info_b->mode ||
+ info_a->options_len != info_b->options_len ||
+ memcmp(ip_tunnel_info_opts(info_a),
+ ip_tunnel_info_opts(info_b), info_a->options_len);
}
static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
@@ -328,12 +709,14 @@ static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
};
static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
+ [LWTUNNEL_IP6_UNSPEC] = { .strict_start_type = LWTUNNEL_IP6_OPTS },
[LWTUNNEL_IP6_ID] = { .type = NLA_U64 },
[LWTUNNEL_IP6_DST] = { .len = sizeof(struct in6_addr) },
[LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) },
[LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 },
[LWTUNNEL_IP6_TC] = { .type = NLA_U8 },
[LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 },
+ [LWTUNNEL_IP6_OPTS] = { .type = NLA_NESTED },
};
static int ip6_tun_build_state(struct nlattr *attr,
@@ -341,17 +724,21 @@ static int ip6_tun_build_state(struct nlattr *attr,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
- struct ip_tunnel_info *tun_info;
- struct lwtunnel_state *new_state;
struct nlattr *tb[LWTUNNEL_IP6_MAX + 1];
- int err;
+ struct lwtunnel_state *new_state;
+ struct ip_tunnel_info *tun_info;
+ int err, opt_len;
err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP6_MAX, attr,
ip6_tun_policy, extack);
if (err < 0)
return err;
- new_state = lwtunnel_state_alloc(sizeof(*tun_info));
+ opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP6_OPTS], extack);
+ if (opt_len < 0)
+ return opt_len;
+
+ new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len);
if (!new_state)
return -ENOMEM;
@@ -359,6 +746,12 @@ static int ip6_tun_build_state(struct nlattr *attr,
tun_info = lwt_tun_info(new_state);
+ err = ip_tun_set_opts(tb[LWTUNNEL_IP6_OPTS], tun_info, extack);
+ if (err < 0) {
+ lwtstate_free(new_state);
+ return err;
+ }
+
if (tb[LWTUNNEL_IP6_ID])
tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP6_ID]);
@@ -375,10 +768,12 @@ static int ip6_tun_build_state(struct nlattr *attr,
tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]);
if (tb[LWTUNNEL_IP6_FLAGS])
- tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]);
+ tun_info->key.tun_flags |=
+ (nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]) &
+ ~TUNNEL_OPTIONS_PRESENT);
tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6;
- tun_info->options_len = 0;
+ tun_info->options_len = opt_len;
*ts = new_state;
@@ -396,7 +791,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb,
nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) ||
nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) ||
nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) ||
- nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags))
+ nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags) ||
+ ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info))
return -ENOMEM;
return 0;
@@ -409,7 +805,9 @@ static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
+ nla_total_size(16) /* LWTUNNEL_IP6_SRC */
+ nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */
+ nla_total_size(1) /* LWTUNNEL_IP6_TC */
- + nla_total_size(2); /* LWTUNNEL_IP6_FLAGS */
+ + nla_total_size(2) /* LWTUNNEL_IP6_FLAGS */
+ + ip_tun_opts_nlsize(lwt_tun_info(lwtstate));
+ /* LWTUNNEL_IP6_OPTS */
}
static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = {
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 9bcca08efec9..f35308ff84c3 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1412,6 +1412,9 @@ static int __init wait_for_devices(void)
struct net_device *dev;
int found = 0;
+ /* make sure deferred device probes are finished */
+ wait_for_device_probe();
+
rtnl_lock();
for_each_netdev(&init_net, dev) {
if (ic_is_init_dev(dev)) {
@@ -1483,10 +1486,10 @@ static int __init ip_auto_config(void)
* missing values.
*/
if (ic_myaddr == NONE ||
-#ifdef CONFIG_ROOT_NFS
+#if defined(CONFIG_ROOT_NFS) || defined(CONFIG_CIFS_ROOT)
(root_server_addr == NONE &&
ic_servaddr == NONE &&
- ROOT_DEV == Root_NFS) ||
+ (ROOT_DEV == Root_NFS || ROOT_DEV == Root_CIFS)) ||
#endif
ic_first_dev->next) {
#ifdef IPCONFIG_DYNAMIC
@@ -1513,6 +1516,12 @@ static int __init ip_auto_config(void)
goto try_try_again;
}
#endif
+#ifdef CONFIG_CIFS_ROOT
+ if (ROOT_DEV == Root_CIFS) {
+ pr_err("IP-Config: Retrying forever (CIFS root)...\n");
+ goto try_try_again;
+ }
+#endif
if (--retries) {
pr_err("IP-Config: Reopening network devices...\n");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 716d5472c022..6e68def66822 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -278,9 +278,10 @@ static void __net_exit ipmr_rules_exit(struct net *net)
rtnl_unlock();
}
-static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
- return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR);
+ return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR, extack);
}
static unsigned int ipmr_rules_seq_read(struct net *net)
@@ -336,7 +337,8 @@ static void __net_exit ipmr_rules_exit(struct net *net)
rtnl_unlock();
}
-static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
return 0;
}
@@ -2289,7 +2291,8 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
rcu_read_unlock();
return -ENODEV;
}
- skb2 = skb_clone(skb, GFP_ATOMIC);
+
+ skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr));
if (!skb2) {
read_unlock(&mrt_lock);
rcu_read_unlock();
@@ -3040,10 +3043,11 @@ static unsigned int ipmr_seq_read(struct net *net)
return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net);
}
-static int ipmr_dump(struct net *net, struct notifier_block *nb)
+static int ipmr_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
return mr_dump(net, nb, RTNL_FAMILY_IPMR, ipmr_rules_dump,
- ipmr_mr_table_iter, &mrt_lock);
+ ipmr_mr_table_iter, &mrt_lock, extack);
}
static const struct fib_notifier_ops ipmr_notifier_ops_template = {
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index ea48bd15a575..aa8738a91210 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -386,15 +386,17 @@ EXPORT_SYMBOL(mr_rtm_dumproute);
int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family,
int (*rules_dump)(struct net *net,
- struct notifier_block *nb),
+ struct notifier_block *nb,
+ struct netlink_ext_ack *extack),
struct mr_table *(*mr_iter)(struct net *net,
struct mr_table *mrt),
- rwlock_t *mrt_lock)
+ rwlock_t *mrt_lock,
+ struct netlink_ext_ack *extack)
{
struct mr_table *mrt;
int err;
- err = rules_dump(net, nb);
+ err = rules_dump(net, nb, extack);
if (err)
return err;
@@ -409,17 +411,25 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family,
if (!v->dev)
continue;
- mr_call_vif_notifier(nb, net, family,
- FIB_EVENT_VIF_ADD,
- v, vifi, mrt->id);
+ err = mr_call_vif_notifier(nb, family,
+ FIB_EVENT_VIF_ADD,
+ v, vifi, mrt->id, extack);
+ if (err)
+ break;
}
read_unlock(mrt_lock);
+ if (err)
+ return err;
+
/* Notify on table MFC entries */
- list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
- mr_call_mfc_notifier(nb, net, family,
- FIB_EVENT_ENTRY_ADD,
- mfc, mrt->id);
+ list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
+ err = mr_call_mfc_notifier(nb, family,
+ FIB_EVENT_ENTRY_ADD,
+ mfc, mrt->id, extack);
+ if (err)
+ return err;
+ }
}
return 0;
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index 012c4047c788..e32e41b99f0f 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -9,6 +9,8 @@
static struct nf_flowtable_type flowtable_ipv4 = {
.family = NFPROTO_IPV4,
.init = nf_flow_table_init,
+ .setup = nf_flow_table_offload_setup,
+ .action = nf_flow_rule_route_ipv4,
.free = nf_flow_table_free,
.hook = nf_flow_offload_ip_hook,
.owner = THIS_MODULE,
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
index 36a28d46149c..c94445b44d8c 100644
--- a/net/ipv4/netfilter/nf_socket_ipv4.c
+++ b/net/ipv4/netfilter/nf_socket_ipv4.c
@@ -31,16 +31,8 @@ extract_icmp4_fields(const struct sk_buff *skb, u8 *protocol,
if (icmph == NULL)
return 1;
- switch (icmph->type) {
- case ICMP_DEST_UNREACH:
- case ICMP_SOURCE_QUENCH:
- case ICMP_REDIRECT:
- case ICMP_TIME_EXCEEDED:
- case ICMP_PARAMETERPROB:
- break;
- default:
+ if (!icmp_is_err(icmph->type))
return 1;
- }
inside_iph = skb_header_pointer(skb, outside_hdrlen +
sizeof(struct icmphdr),
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index fc34fd1668d6..511eaa94e2d1 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -23,7 +23,6 @@ static void remove_nexthop(struct net *net, struct nexthop *nh,
#define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS)
static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = {
- [NHA_UNSPEC] = { .strict_start_type = NHA_UNSPEC + 1 },
[NHA_ID] = { .type = NLA_U32 },
[NHA_GROUP] = { .type = NLA_BINARY },
[NHA_GROUP_TYPE] = { .type = NLA_U16 },
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 621f83434b24..f88c93c38f11 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1894,10 +1894,7 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb,
if (!icmph)
goto out;
- if (icmph->type != ICMP_DEST_UNREACH &&
- icmph->type != ICMP_REDIRECT &&
- icmph->type != ICMP_TIME_EXCEEDED &&
- icmph->type != ICMP_PARAMETERPROB)
+ if (!icmp_is_err(icmph->type))
goto out;
inner_iph = skb_header_pointer(skb,
@@ -2022,10 +2019,52 @@ static int ip_mkroute_input(struct sk_buff *skb,
return __mkroute_input(skb, res, in_dev, daddr, saddr, tos);
}
+/* Implements all the saddr-related checks as ip_route_input_slow(),
+ * assuming daddr is valid and the destination is not a local broadcast one.
+ * Uses the provided hint instead of performing a route lookup.
+ */
+int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+ u8 tos, struct net_device *dev,
+ const struct sk_buff *hint)
+{
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+ struct rtable *rt = (struct rtable *)hint;
+ struct net *net = dev_net(dev);
+ int err = -EINVAL;
+ u32 tag = 0;
+
+ if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
+ goto martian_source;
+
+ if (ipv4_is_zeronet(saddr))
+ goto martian_source;
+
+ if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net))
+ goto martian_source;
+
+ if (rt->rt_type != RTN_LOCAL)
+ goto skip_validate_source;
+
+ tos &= IPTOS_RT_MASK;
+ err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag);
+ if (err < 0)
+ goto martian_source;
+
+skip_validate_source:
+ skb_dst_copy(skb, hint);
+ return 0;
+
+martian_source:
+ ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
+ return err;
+}
+
/*
* NOTE. We drop all the packets that has local source
* addresses, because every properly looped back packet
* must have correct destination already attached by output routine.
+ * Changes in the enforced policies must be applied also to
+ * ip_route_use_hint().
*
* Such approach solves two big problems:
* 1. Not simplex devices are handled properly.
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 535b69326f66..345b2b0ff618 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -62,10 +62,10 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
* Since subsequent timestamps use the normal tcp_time_stamp value, we
* must make sure that the resulting initial timestamp is <= tcp_time_stamp.
*/
-u64 cookie_init_timestamp(struct request_sock *req)
+u64 cookie_init_timestamp(struct request_sock *req, u64 now)
{
struct inet_request_sock *ireq;
- u32 ts, ts_now = tcp_time_stamp_raw();
+ u32 ts, ts_now = tcp_ns_to_ts(now);
u32 options = 0;
ireq = inet_rsk(req);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 59ded25acd04..fcb2cd167f64 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -340,6 +340,10 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
user_key[i * 4 + 1],
user_key[i * 4 + 2],
user_key[i * 4 + 3]);
+
+ if (WARN_ON_ONCE(off >= tbl.maxlen - 1))
+ break;
+
if (i + 1 < n_keys)
off += snprintf(tbl.data + off, tbl.maxlen - off, ",");
}
@@ -1037,7 +1041,7 @@ static struct ctl_table ipv4_net_table[] = {
.mode = 0644,
.proc_handler = proc_fib_multipath_hash_policy,
.extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
+ .extra2 = &two,
},
#endif
{
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 42187a3b82f4..9b48aec29aca 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -584,7 +584,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
}
/* This barrier is coupled with smp_wmb() in tcp_reset() */
smp_rmb();
- if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+ if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
mask |= EPOLLERR;
return mask;
@@ -1741,8 +1741,8 @@ static int tcp_zerocopy_receive(struct sock *sk,
struct tcp_zerocopy_receive *zc)
{
unsigned long address = (unsigned long)zc->address;
+ u32 length = 0, seq, offset, zap_len;
const skb_frag_t *frags = NULL;
- u32 length = 0, seq, offset;
struct vm_area_struct *vma;
struct sk_buff *skb = NULL;
struct tcp_sock *tp;
@@ -1769,12 +1769,12 @@ static int tcp_zerocopy_receive(struct sock *sk,
seq = tp->copied_seq;
inq = tcp_inq(sk);
zc->length = min_t(u32, zc->length, inq);
- zc->length &= ~(PAGE_SIZE - 1);
- if (zc->length) {
- zap_page_range(vma, address, zc->length);
+ zap_len = zc->length & ~(PAGE_SIZE - 1);
+ if (zap_len) {
+ zap_page_range(vma, address, zap_len);
zc->recv_skip_hint = 0;
} else {
- zc->recv_skip_hint = inq;
+ zc->recv_skip_hint = zc->length;
}
ret = 0;
while (length + PAGE_SIZE <= zc->length) {
@@ -1958,13 +1958,12 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
struct sk_buff *skb, *last;
u32 urg_hole = 0;
struct scm_timestamping_internal tss;
- bool has_tss = false;
- bool has_cmsg;
+ int cmsg_flags;
if (unlikely(flags & MSG_ERRQUEUE))
return inet_recv_error(sk, msg, len, addr_len);
- if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
+ if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) &&
(sk->sk_state == TCP_ESTABLISHED))
sk_busy_loop(sk, nonblock);
@@ -1974,7 +1973,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
if (sk->sk_state == TCP_LISTEN)
goto out;
- has_cmsg = tp->recvmsg_inq;
+ cmsg_flags = tp->recvmsg_inq ? 1 : 0;
timeo = sock_rcvtimeo(sk, nonblock);
/* Urgent data needs to be handled specially. */
@@ -2047,7 +2046,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
/* Well, if we have backlog, try to process it now yet. */
- if (copied >= target && !sk->sk_backlog.tail)
+ if (copied >= target && !READ_ONCE(sk->sk_backlog.tail))
break;
if (copied) {
@@ -2157,8 +2156,7 @@ skip_copy:
if (TCP_SKB_CB(skb)->has_rxtstamp) {
tcp_update_recv_tstamps(skb, &tss);
- has_tss = true;
- has_cmsg = true;
+ cmsg_flags |= 2;
}
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
@@ -2183,10 +2181,10 @@ found_fin_ok:
release_sock(sk);
- if (has_cmsg) {
- if (has_tss)
+ if (cmsg_flags) {
+ if (cmsg_flags & 2)
tcp_recv_timestamp(msg, sk, &tss);
- if (tp->recvmsg_inq) {
+ if (cmsg_flags & 1) {
inq = tcp_inq_hint(sk);
put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
}
@@ -2666,6 +2664,7 @@ int tcp_disconnect(struct sock *sk, int flags)
/* Clean up fastopen related fields */
tcp_free_fastopen_req(tp);
inet->defer_connect = 0;
+ tp->fastopen_client_fail = 0;
WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
@@ -3224,8 +3223,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
* tcpi_unacked -> Number of children ready for accept()
* tcpi_sacked -> max backlog
*/
- info->tcpi_unacked = sk->sk_ack_backlog;
- info->tcpi_sacked = sk->sk_max_ack_backlog;
+ info->tcpi_unacked = READ_ONCE(sk->sk_ack_backlog);
+ info->tcpi_sacked = READ_ONCE(sk->sk_max_ack_backlog);
return;
}
@@ -3305,6 +3304,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_reord_seen = tp->reord_seen;
info->tcpi_rcv_ooopack = tp->rcv_ooopack;
info->tcpi_snd_wnd = tp->snd_wnd;
+ info->tcpi_fastopen_client_fail = tp->fastopen_client_fail;
unlock_sock_fast(sk, slow);
}
EXPORT_SYMBOL_GPL(tcp_get_info);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index c445a81d144e..3737ec096650 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -256,6 +256,9 @@ void tcp_get_available_congestion_control(char *buf, size_t maxlen)
offs += snprintf(buf + offs, maxlen - offs,
"%s%s",
offs == 0 ? "" : " ", ca->name);
+
+ if (WARN_ON_ONCE(offs >= maxlen))
+ break;
}
rcu_read_unlock();
}
@@ -285,6 +288,9 @@ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen)
offs += snprintf(buf + offs, maxlen - offs,
"%s%s",
offs == 0 ? "" : " ", ca->name);
+
+ if (WARN_ON_ONCE(offs >= maxlen))
+ break;
}
rcu_read_unlock();
}
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 549506162dde..0d08f9e2d8d0 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -21,8 +21,8 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
struct tcp_info *info = _info;
if (inet_sk_state_load(sk) == TCP_LISTEN) {
- r->idiag_rqueue = sk->sk_ack_backlog;
- r->idiag_wqueue = sk->sk_max_ack_backlog;
+ r->idiag_rqueue = READ_ONCE(sk->sk_ack_backlog);
+ r->idiag_wqueue = READ_ONCE(sk->sk_max_ack_backlog);
} else if (sk->sk_type == SOCK_STREAM) {
const struct tcp_sock *tp = tcp_sk(sk);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index a915ade0c818..19ad9586c720 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -422,7 +422,10 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
cookie->len = -1;
return true;
}
- return cookie->len > 0;
+ if (cookie->len > 0)
+ return true;
+ tcp_sk(sk)->fastopen_client_fail = TFO_COOKIE_UNAVAILABLE;
+ return false;
}
/* This function checks if we want to defer sending SYN until the first
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a2e52ad7cdab..88b987ca9ebb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5814,6 +5814,10 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp);
if (data) { /* Retransmit unacked data in SYN */
+ if (tp->total_retrans)
+ tp->fastopen_client_fail = TFO_SYN_RETRANSMITTED;
+ else
+ tp->fastopen_client_fail = TFO_DATA_NOT_ACKED;
skb_rbtree_walk_from(data) {
if (__tcp_retransmit_skb(sk, data, 1))
break;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6be568334848..92282f98dc82 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -121,11 +121,9 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == AF_INET6) {
if (ipv6_addr_loopback(&tw->tw_v6_daddr) ||
- (ipv6_addr_v4mapped(&tw->tw_v6_daddr) &&
- (tw->tw_v6_daddr.s6_addr[12] == 127)) ||
+ ipv6_addr_v4mapped_loopback(&tw->tw_v6_daddr) ||
ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) ||
- (ipv6_addr_v4mapped(&tw->tw_v6_rcv_saddr) &&
- (tw->tw_v6_rcv_saddr.s6_addr[12] == 127)))
+ ipv6_addr_v4mapped_loopback(&tw->tw_v6_rcv_saddr))
loopback = true;
} else
#endif
@@ -303,7 +301,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
inet->inet_daddr);
}
- inet->inet_id = tp->write_seq ^ jiffies;
+ inet->inet_id = prandom_u32();
if (tcp_fastopen_defer_connect(sk, &err))
return err;
@@ -1450,7 +1448,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (inet_opt)
inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
- newinet->inet_id = newtp->write_seq ^ jiffies;
+ newinet->inet_id = prandom_u32();
if (!dst) {
dst = inet_csk_route_child_sock(sk, newsk, req);
@@ -2453,7 +2451,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
state = inet_sk_state_load(sk);
if (state == TCP_LISTEN)
- rx_queue = sk->sk_ack_backlog;
+ rx_queue = READ_ONCE(sk->sk_ack_backlog);
else
/* Because we don't lock the socket,
* we might find a transient negative value.
@@ -2681,7 +2679,7 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
- net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256);
+ net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128);
net->ipv4.sysctl_tcp_sack = 1;
net->ipv4.sysctl_tcp_window_scaling = 1;
net->ipv4.sysctl_tcp_timestamps = 1;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0488607c5cd3..be6d22b8190f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3290,7 +3290,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
now = tcp_clock_ns();
#ifdef CONFIG_SYN_COOKIES
if (unlikely(req->cookie_ts))
- skb->skb_mstamp_ns = cookie_init_timestamp(req);
+ skb->skb_mstamp_ns = cookie_init_timestamp(req, now);
else
#endif
{
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 4849edb62d52..12ab5db2b71c 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -92,6 +92,9 @@ void tcp_get_available_ulp(char *buf, size_t maxlen)
offs += snprintf(buf + offs, maxlen - offs,
"%s%s",
offs == 0 ? "" : " ", ulp_ops->name);
+
+ if (WARN_ON_ONCE(offs >= maxlen))
+ break;
}
rcu_read_unlock();
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 14bc654b6842..4da5758cc718 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -388,7 +388,7 @@ static int compute_score(struct sock *sk, struct net *net,
return -1;
score += 4;
- if (sk->sk_incoming_cpu == raw_smp_processor_id())
+ if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
return score;
}
@@ -1297,6 +1297,27 @@ out:
#define UDP_SKB_IS_STATELESS 0x80000000
+/* all head states (dst, sk, nf conntrack) except skb extensions are
+ * cleared by udp_rcv().
+ *
+ * We need to preserve secpath, if present, to eventually process
+ * IP_CMSG_PASSSEC at recvmsg() time.
+ *
+ * Other extensions can be cleared.
+ */
+static bool udp_try_make_stateless(struct sk_buff *skb)
+{
+ if (!skb_has_extensions(skb))
+ return true;
+
+ if (!secpath_exists(skb)) {
+ skb_ext_reset(skb);
+ return true;
+ }
+
+ return false;
+}
+
static void udp_set_dev_scratch(struct sk_buff *skb)
{
struct udp_dev_scratch *scratch = udp_skb_scratch(skb);
@@ -1308,14 +1329,24 @@ static void udp_set_dev_scratch(struct sk_buff *skb)
scratch->csum_unnecessary = !!skb_csum_unnecessary(skb);
scratch->is_linear = !skb_is_nonlinear(skb);
#endif
- /* all head states execept sp (dst, sk, nf) are always cleared by
- * udp_rcv() and we need to preserve secpath, if present, to eventually
- * process IP_CMSG_PASSSEC at recvmsg() time
- */
- if (likely(!skb_sec_path(skb)))
+ if (udp_try_make_stateless(skb))
scratch->_tsize_state |= UDP_SKB_IS_STATELESS;
}
+static void udp_skb_csum_unnecessary_set(struct sk_buff *skb)
+{
+ /* We come here after udp_lib_checksum_complete() returned 0.
+ * This means that __skb_checksum_complete() might have
+ * set skb->csum_valid to 1.
+ * On 64bit platforms, we can set csum_unnecessary
+ * to true, but only if the skb is not shared.
+ */
+#if BITS_PER_LONG == 64
+ if (!skb_shared(skb))
+ udp_skb_scratch(skb)->csum_unnecessary = true;
+#endif
+}
+
static int udp_skb_truesize(struct sk_buff *skb)
{
return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS;
@@ -1550,10 +1581,7 @@ static struct sk_buff *__first_packet_length(struct sock *sk,
*total += skb->truesize;
kfree_skb(skb);
} else {
- /* the csum related bits could be changed, refresh
- * the scratch area
- */
- udp_set_dev_scratch(skb);
+ udp_skb_csum_unnecessary_set(skb);
break;
}
}
@@ -1577,7 +1605,7 @@ static int first_packet_length(struct sock *sk)
spin_lock_bh(&rcvq->lock);
skb = __first_packet_length(sk, rcvq, &total);
- if (!skb && !skb_queue_empty(sk_queue)) {
+ if (!skb && !skb_queue_empty_lockless(sk_queue)) {
spin_lock(&sk_queue->lock);
skb_queue_splice_tail_init(sk_queue, rcvq);
spin_unlock(&sk_queue->lock);
@@ -1650,7 +1678,7 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
return skb;
}
- if (skb_queue_empty(sk_queue)) {
+ if (skb_queue_empty_lockless(sk_queue)) {
spin_unlock_bh(&queue->lock);
goto busy_check;
}
@@ -1676,7 +1704,7 @@ busy_check:
break;
sk_busy_loop(sk, flags & MSG_DONTWAIT);
- } while (!skb_queue_empty(sk_queue));
+ } while (!skb_queue_empty_lockless(sk_queue));
/* sk_queue is empty, reader_queue may contain peeked packets */
} while (timeo &&
@@ -2523,9 +2551,11 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
case UDP_ENCAP:
switch (val) {
case 0:
+#ifdef CONFIG_XFRM
case UDP_ENCAP_ESPINUDP:
case UDP_ENCAP_ESPINUDP_NON_IKE:
up->encap_rcv = xfrm4_udp_encap_rcv;
+#endif
/* FALLTHROUGH */
case UDP_ENCAP_L2TPINUDP:
up->encap_type = val;
@@ -2712,7 +2742,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
__poll_t mask = datagram_poll(file, sock, wait);
struct sock *sk = sock->sk;
- if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
+ if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* Check for false positives due to checksum errors */
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index ecff3fce9807..89ba7c87de5d 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -92,7 +92,7 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
- net, sk, skb, NULL, skb_dst(skb)->dev,
+ net, sk, skb, skb->dev, skb_dst(skb)->dev,
__xfrm4_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 34ccef18b40e..98d82305d6de 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5552,14 +5552,13 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr));
if (!nla)
goto nla_put_failure;
-
- if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->cnf.addr_gen_mode))
- goto nla_put_failure;
-
read_lock_bh(&idev->lock);
memcpy(nla_data(nla), idev->token.s6_addr, nla_len(nla));
read_unlock_bh(&idev->lock);
+ if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->cnf.addr_gen_mode))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 783f3c1466da..2fc079284ca4 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -7,6 +7,7 @@
#include <linux/export.h>
#include <net/ipv6.h>
#include <net/ipv6_stubs.h>
+#include <net/addrconf.h>
#include <net/ip.h>
/* if ipv6 module registers this function is used by xfrm to force all
diff --git a/net/ipv6/fib6_notifier.c b/net/ipv6/fib6_notifier.c
index 05f82baaa99e..f87ae33e1d01 100644
--- a/net/ipv6/fib6_notifier.c
+++ b/net/ipv6/fib6_notifier.c
@@ -7,12 +7,12 @@
#include <net/netns/ipv6.h>
#include <net/ip6_fib.h>
-int call_fib6_notifier(struct notifier_block *nb, struct net *net,
+int call_fib6_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
struct fib_notifier_info *info)
{
info->family = AF_INET6;
- return call_fib_notifier(nb, net, event_type, info);
+ return call_fib_notifier(nb, event_type, info);
}
int call_fib6_notifiers(struct net *net, enum fib_event_type event_type,
@@ -27,15 +27,16 @@ static unsigned int fib6_seq_read(struct net *net)
return fib6_tables_seq_read(net) + fib6_rules_seq_read(net);
}
-static int fib6_dump(struct net *net, struct notifier_block *nb)
+static int fib6_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
int err;
- err = fib6_rules_dump(net, nb);
+ err = fib6_rules_dump(net, nb, extack);
if (err)
return err;
- return fib6_tables_dump(net, nb);
+ return fib6_tables_dump(net, nb, extack);
}
static const struct fib_notifier_ops fib6_notifier_ops_template = {
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index f9e8fe3ff0c5..fafe556d21e0 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -47,9 +47,10 @@ bool fib6_rule_default(const struct fib_rule *rule)
}
EXPORT_SYMBOL_GPL(fib6_rule_default);
-int fib6_rules_dump(struct net *net, struct notifier_block *nb)
+int fib6_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
- return fib_rules_dump(net, nb, AF_INET6);
+ return fib_rules_dump(net, nb, AF_INET6, extack);
}
unsigned int fib6_rules_seq_read(struct net *net)
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 62c997201970..ef408a5090a2 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -516,13 +516,29 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
mip6_addr_swap(skb);
+ sk = icmpv6_xmit_lock(net);
+ if (!sk)
+ goto out_bh_enable;
+
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.daddr = hdr->saddr;
if (force_saddr)
saddr = force_saddr;
- if (saddr)
+ if (saddr) {
fl6.saddr = *saddr;
+ } else {
+ /* select a more meaningful saddr from input if */
+ struct net_device *in_netdev;
+
+ in_netdev = dev_get_by_index(net, IP6CB(skb)->iif);
+ if (in_netdev) {
+ ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr,
+ inet6_sk(sk)->srcprefs,
+ &fl6.saddr);
+ dev_put(in_netdev);
+ }
+ }
fl6.flowi6_mark = mark;
fl6.flowi6_oif = iif;
fl6.fl6_icmp_type = type;
@@ -531,10 +547,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
- sk = icmpv6_xmit_lock(net);
- if (!sk)
- goto out_bh_enable;
-
sk->sk_mark = mark;
np = inet6_sk(sk);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index cf60fae9533b..fbe9d4295eac 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -105,7 +105,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score = 1;
- if (sk->sk_incoming_cpu == raw_smp_processor_id())
+ if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
}
return score;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6e2af411cd9c..7bae6a91b487 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -357,15 +357,17 @@ unsigned int fib6_tables_seq_read(struct net *net)
return fib_seq;
}
-static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
+static int call_fib6_entry_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
- struct fib6_info *rt)
+ struct fib6_info *rt,
+ struct netlink_ext_ack *extack)
{
struct fib6_entry_notifier_info info = {
+ .info.extack = extack,
.rt = rt,
};
- return call_fib6_notifier(nb, net, event_type, &info.info);
+ return call_fib6_notifier(nb, event_type, &info.info);
}
int call_fib6_entry_notifiers(struct net *net,
@@ -401,40 +403,51 @@ int call_fib6_multipath_entry_notifiers(struct net *net,
struct fib6_dump_arg {
struct net *net;
struct notifier_block *nb;
+ struct netlink_ext_ack *extack;
};
-static void fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg)
+static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg)
{
if (rt == arg->net->ipv6.fib6_null_entry)
- return;
- call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt);
+ return 0;
+ return call_fib6_entry_notifier(arg->nb, FIB_EVENT_ENTRY_ADD,
+ rt, arg->extack);
}
static int fib6_node_dump(struct fib6_walker *w)
{
struct fib6_info *rt;
+ int err = 0;
- for_each_fib6_walker_rt(w)
- fib6_rt_dump(rt, w->args);
+ for_each_fib6_walker_rt(w) {
+ err = fib6_rt_dump(rt, w->args);
+ if (err)
+ break;
+ }
w->leaf = NULL;
- return 0;
+ return err;
}
-static void fib6_table_dump(struct net *net, struct fib6_table *tb,
- struct fib6_walker *w)
+static int fib6_table_dump(struct net *net, struct fib6_table *tb,
+ struct fib6_walker *w)
{
+ int err;
+
w->root = &tb->tb6_root;
spin_lock_bh(&tb->tb6_lock);
- fib6_walk(net, w);
+ err = fib6_walk(net, w);
spin_unlock_bh(&tb->tb6_lock);
+ return err;
}
/* Called with rcu_read_lock() */
-int fib6_tables_dump(struct net *net, struct notifier_block *nb)
+int fib6_tables_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
struct fib6_dump_arg arg;
struct fib6_walker *w;
unsigned int h;
+ int err = 0;
w = kzalloc(sizeof(*w), GFP_ATOMIC);
if (!w)
@@ -443,19 +456,24 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb)
w->func = fib6_node_dump;
arg.net = net;
arg.nb = nb;
+ arg.extack = extack;
w->args = &arg;
for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
struct hlist_head *head = &net->ipv6.fib_table_hash[h];
struct fib6_table *tb;
- hlist_for_each_entry_rcu(tb, head, tb6_hlist)
- fib6_table_dump(net, tb, w);
+ hlist_for_each_entry_rcu(tb, head, tb6_hlist) {
+ err = fib6_table_dump(net, tb, w);
+ if (err < 0)
+ goto out;
+ }
}
+out:
kfree(w);
- return 0;
+ return err;
}
static int fib6_dump_node(struct fib6_walker *w)
@@ -1443,6 +1461,8 @@ out:
}
#endif
goto failure;
+ } else if (fib6_requires_src(rt)) {
+ fib6_routes_require_src_inc(info->nl_net);
}
return err;
@@ -1915,6 +1935,8 @@ int fib6_del(struct fib6_info *rt, struct nl_info *info)
struct fib6_info *cur = rcu_dereference_protected(*rtp,
lockdep_is_held(&table->tb6_lock));
if (rt == cur) {
+ if (fib6_requires_src(cur))
+ fib6_routes_require_src_dec(info->nl_net);
fib6_del_route(table, fn, rtp, info);
return 0;
}
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 787d9f2a6e99..923034c52ce4 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -980,9 +980,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
dsfield = key->tos;
if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT))
goto tx_err;
- md = ip_tunnel_info_opts(tun_info);
- if (!md)
+ if (tun_info->options_len < sizeof(*md))
goto tx_err;
+ md = ip_tunnel_info_opts(tun_info);
tun_id = tunnel_id_to_key32(key->tun_id);
if (md->version == 1) {
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 3d71c7d6102c..7b089d0ac8cd 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -86,11 +86,27 @@ static void ip6_sublist_rcv_finish(struct list_head *head)
}
}
+static bool ip6_can_use_hint(const struct sk_buff *skb,
+ const struct sk_buff *hint)
+{
+ return hint && !skb_dst(skb) &&
+ ipv6_addr_equal(&ipv6_hdr(hint)->daddr, &ipv6_hdr(skb)->daddr);
+}
+
+static struct sk_buff *ip6_extract_route_hint(const struct net *net,
+ struct sk_buff *skb)
+{
+ if (fib6_routes_require_src(net) || fib6_has_custom_rules(net))
+ return NULL;
+
+ return skb;
+}
+
static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
struct list_head *head)
{
+ struct sk_buff *skb, *next, *hint = NULL;
struct dst_entry *curr_dst = NULL;
- struct sk_buff *skb, *next;
struct list_head sublist;
INIT_LIST_HEAD(&sublist);
@@ -104,9 +120,15 @@ static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
skb = l3mdev_ip6_rcv(skb);
if (!skb)
continue;
- ip6_rcv_finish_core(net, sk, skb);
+
+ if (ip6_can_use_hint(skb, hint))
+ skb_dst_copy(skb, hint);
+ else
+ ip6_rcv_finish_core(net, sk, skb);
dst = skb_dst(skb);
if (curr_dst != dst) {
+ hint = ip6_extract_route_hint(net, skb);
+
/* dispatch old sublist */
if (!list_empty(&sublist))
ip6_sublist_rcv_finish(&sublist);
@@ -325,7 +347,8 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
list_add_tail(&skb->list, &sublist);
}
/* dispatch final sublist */
- ip6_sublist_rcv(&sublist, curr_dev, curr_net);
+ if (!list_empty(&sublist))
+ ip6_sublist_rcv(&sublist, curr_dev, curr_net);
}
INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *));
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 71827b56c006..945508a7cb0f 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -160,7 +160,7 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net_device *dev = skb_dst(skb)->dev;
+ struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev;
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
skb->protocol = htons(ETH_P_IPV6);
@@ -173,7 +173,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
}
return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
- net, sk, skb, NULL, dev,
+ net, sk, skb, indev, dev,
ip6_finish_output,
!(IP6CB(skb)->flags & IP6SKB_REROUTED));
}
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 857a89ad4d6c..bfa49ff70531 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -265,9 +265,10 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
rtnl_unlock();
}
-static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb)
+static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
- return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR);
+ return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR, extack);
}
static unsigned int ip6mr_rules_seq_read(struct net *net)
@@ -324,7 +325,8 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
rtnl_unlock();
}
-static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb)
+static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
return 0;
}
@@ -1256,10 +1258,11 @@ static unsigned int ip6mr_seq_read(struct net *net)
return net->ipv6.ipmr_seq + ip6mr_rules_seq_read(net);
}
-static int ip6mr_dump(struct net *net, struct notifier_block *nb)
+static int ip6mr_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump,
- ip6mr_mr_table_iter, &mrt_lock);
+ ip6mr_mr_table_iter, &mrt_lock, extack);
}
static struct notifier_block ip6_mr_notifier = {
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 264c292e7dcc..79fc012dd2ca 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -363,8 +363,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
break;
case IPV6_TRANSPARENT:
- if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) &&
- !ns_capable(net->user_ns, CAP_NET_RAW)) {
+ if (valbool && !ns_capable(net->user_ns, CAP_NET_RAW) &&
+ !ns_capable(net->user_ns, CAP_NET_ADMIN)) {
retv = -EPERM;
break;
}
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 69443e9a3aa5..0594131fa46d 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -128,9 +128,9 @@ config IP6_NF_MATCH_HL
depends on NETFILTER_ADVANCED
select NETFILTER_XT_MATCH_HL
---help---
- This is a backwards-compat option for the user's convenience
- (e.g. when running oldconfig). It selects
- CONFIG_NETFILTER_XT_MATCH_HL.
+ This is a backwards-compat option for the user's convenience
+ (e.g. when running oldconfig). It selects
+ CONFIG_NETFILTER_XT_MATCH_HL.
config IP6_NF_MATCH_IPV6HEADER
tristate '"ipv6header" IPv6 Extension Headers Match'
@@ -184,9 +184,9 @@ config IP6_NF_TARGET_HL
depends on NETFILTER_ADVANCED && IP6_NF_MANGLE
select NETFILTER_XT_TARGET_HL
---help---
- This is a backwards-compatible option for the user's convenience
- (e.g. when running oldconfig). It selects
- CONFIG_NETFILTER_XT_TARGET_HL.
+ This is a backwards-compatible option for the user's convenience
+ (e.g. when running oldconfig). It selects
+ CONFIG_NETFILTER_XT_TARGET_HL.
config IP6_NF_FILTER
tristate "Packet filtering"
@@ -245,14 +245,14 @@ config IP6_NF_RAW
# security table for MAC policy
config IP6_NF_SECURITY
- tristate "Security table"
- depends on SECURITY
- depends on NETFILTER_ADVANCED
- help
- This option adds a `security' table to iptables, for use
- with Mandatory Access Control (MAC) policy.
-
- If unsure, say N.
+ tristate "Security table"
+ depends on SECURITY
+ depends on NETFILTER_ADVANCED
+ help
+ This option adds a `security' table to iptables, for use
+ with Mandatory Access Control (MAC) policy.
+
+ If unsure, say N.
config IP6_NF_NAT
tristate "ip6tables NAT support"
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
index f6d9a48c7a2a..a8566ee12e83 100644
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c
@@ -10,6 +10,8 @@
static struct nf_flowtable_type flowtable_ipv6 = {
.family = NFPROTO_IPV6,
.init = nf_flow_table_init,
+ .setup = nf_flow_table_offload_setup,
+ .action = nf_flow_rule_route_ipv6,
.free = nf_flow_table_free,
.hook = nf_flow_offload_ipv6_hook,
.owner = THIS_MODULE,
diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c
index 34d51cd426b0..6bac68fb27a3 100644
--- a/net/ipv6/netfilter/nf_tproxy_ipv6.c
+++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c
@@ -150,4 +150,4 @@ EXPORT_SYMBOL_GPL(nf_tproxy_get_sock_v6);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs");
-MODULE_DESCRIPTION("Netfilter IPv4 transparent proxy support");
+MODULE_DESCRIPTION("Netfilter IPv6 transparent proxy support");
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a63ff85fe141..b59940416cb5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -621,6 +621,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
{
struct __rt6_probe_work *work = NULL;
const struct in6_addr *nh_gw;
+ unsigned long last_probe;
struct neighbour *neigh;
struct net_device *dev;
struct inet6_dev *idev;
@@ -633,12 +634,13 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
* Router Reachability Probe MUST be rate-limited
* to no more than one per minute.
*/
- if (fib6_nh->fib_nh_gw_family)
+ if (!fib6_nh->fib_nh_gw_family)
return;
nh_gw = &fib6_nh->fib_nh_gw6;
dev = fib6_nh->fib_nh_dev;
rcu_read_lock_bh();
+ last_probe = READ_ONCE(fib6_nh->last_probe);
idev = __in6_dev_get(dev);
neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
if (neigh) {
@@ -654,13 +656,15 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
__neigh_set_probe_once(neigh);
}
write_unlock(&neigh->lock);
- } else if (time_after(jiffies, fib6_nh->last_probe +
+ } else if (time_after(jiffies, last_probe +
idev->cnf.rtr_probe_interval)) {
work = kmalloc(sizeof(*work), GFP_ATOMIC);
}
- if (work) {
- fib6_nh->last_probe = jiffies;
+ if (!work || cmpxchg(&fib6_nh->last_probe,
+ last_probe, jiffies) != last_probe) {
+ kfree(work);
+ } else {
INIT_WORK(&work->work, rt6_probe_deferred);
work->target = *nh_gw;
dev_hold(dev);
@@ -1475,11 +1479,11 @@ static u32 rt6_exception_hash(const struct in6_addr *dst,
u32 val;
net_get_random_once(&seed, sizeof(seed));
- val = jhash(dst, sizeof(*dst), seed);
+ val = jhash2((const u32 *)dst, sizeof(*dst)/sizeof(u32), seed);
#ifdef CONFIG_IPV6_SUBTREES
if (src)
- val = jhash(src, sizeof(*src), val);
+ val = jhash2((const u32 *)src, sizeof(*src)/sizeof(u32), val);
#endif
return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT);
}
@@ -2291,10 +2295,7 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb,
if (!icmph)
goto out;
- if (icmph->icmp6_type != ICMPV6_DEST_UNREACH &&
- icmph->icmp6_type != ICMPV6_PKT_TOOBIG &&
- icmph->icmp6_type != ICMPV6_TIME_EXCEED &&
- icmph->icmp6_type != ICMPV6_PARAMPROB)
+ if (!icmpv6_is_err(icmph->icmp6_type))
goto out;
inner_iph = skb_header_pointer(skb,
@@ -3383,6 +3384,9 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
int err;
fib6_nh->fib_nh_family = AF_INET6;
+#ifdef CONFIG_IPV6_ROUTER_PREF
+ fib6_nh->last_probe = jiffies;
+#endif
err = -ENODEV;
if (cfg->fc_ifindex) {
@@ -6195,6 +6199,9 @@ static int __net_init ip6_route_net_init(struct net *net)
dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
ip6_template_metrics, true);
INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->rt6i_uncached);
+#ifdef CONFIG_IPV6_SUBTREES
+ net->ipv6.fib6_routes_require_src = 0;
+#endif
#endif
net->ipv6.sysctl.flush_delay = 0;
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 9d4f75e0d33a..85a5447a3e8d 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -81,6 +81,11 @@ static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb)
if (!pskb_may_pull(skb, srhoff + len))
return NULL;
+ /* note that pskb_may_pull may change pointers in header;
+ * for this reason it is necessary to reload them when needed.
+ */
+ srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
+
if (!seg6_validate_srh(srh, len))
return NULL;
@@ -144,8 +149,9 @@ static void advance_nextseg(struct ipv6_sr_hdr *srh, struct in6_addr *daddr)
*daddr = *addr;
}
-int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
- u32 tbl_id)
+static int
+seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
+ u32 tbl_id, bool local_delivery)
{
struct net *net = dev_net(skb->dev);
struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -153,6 +159,7 @@ int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
struct dst_entry *dst = NULL;
struct rt6_info *rt;
struct flowi6 fl6;
+ int dev_flags = 0;
fl6.flowi6_iif = skb->dev->ifindex;
fl6.daddr = nhaddr ? *nhaddr : hdr->daddr;
@@ -177,7 +184,13 @@ int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
dst = &rt->dst;
}
- if (dst && dst->dev->flags & IFF_LOOPBACK && !dst->error) {
+ /* we want to discard traffic destined for local packet processing,
+ * if @local_delivery is set to false.
+ */
+ if (!local_delivery)
+ dev_flags |= IFF_LOOPBACK;
+
+ if (dst && (dst->dev->flags & dev_flags) && !dst->error) {
dst_release(dst);
dst = NULL;
}
@@ -194,6 +207,12 @@ out:
return dst->error;
}
+int seg6_lookup_nexthop(struct sk_buff *skb,
+ struct in6_addr *nhaddr, u32 tbl_id)
+{
+ return seg6_lookup_any_nexthop(skb, nhaddr, tbl_id, false);
+}
+
/* regular endpoint function */
static int input_action_end(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
@@ -336,6 +355,8 @@ static int input_action_end_dx6(struct sk_buff *skb,
if (!ipv6_addr_any(&slwt->nh6))
nhaddr = &slwt->nh6;
+ skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+
seg6_lookup_nexthop(skb, nhaddr, 0);
return dst_input(skb);
@@ -365,6 +386,8 @@ static int input_action_end_dx4(struct sk_buff *skb,
skb_dst_drop(skb);
+ skb_set_transport_header(skb, sizeof(struct iphdr));
+
err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev);
if (err)
goto drop;
@@ -385,7 +408,9 @@ static int input_action_end_dt6(struct sk_buff *skb,
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto drop;
- seg6_lookup_nexthop(skb, NULL, slwt->table);
+ skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+
+ seg6_lookup_any_nexthop(skb, NULL, slwt->table, true);
return dst_input(skb);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4804b6dc5e65..81f51335e326 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1891,7 +1891,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
state = inet_sk_state_load(sp);
if (state == TCP_LISTEN)
- rx_queue = sp->sk_ack_backlog;
+ rx_queue = READ_ONCE(sp->sk_ack_backlog);
else
/* Because we don't lock the socket,
* we might find a transient negative value.
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6324d3a8cb53..9fec580c968e 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -135,7 +135,7 @@ static int compute_score(struct sock *sk, struct net *net,
return -1;
score++;
- if (sk->sk_incoming_cpu == raw_smp_processor_id())
+ if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
return score;
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index eecac1b7148e..fbe51d40bd7e 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -187,7 +187,7 @@ skip_frag:
int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
- net, sk, skb, NULL, skb_dst(skb)->dev,
+ net, sk, skb, skb->dev, skb_dst(skb)->dev,
__xfrm6_output,
!(IP6CB(skb)->flags & IP6SKB_REROUTED));
}
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index fd5ac2788e45..d3b520b9b2c9 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -56,7 +56,6 @@ static int l2tp_eth_dev_init(struct net_device *dev)
{
eth_hw_addr_random(dev);
eth_broadcast_addr(dev->broadcast);
- netdev_lockdep_set_classes(dev);
return 0;
}
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c74f44dfaa22..2922d4150d88 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -705,7 +705,7 @@ static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags,
/* put original socket back into a clean listen state. */
sk->sk_state = TCP_LISTEN;
- sk->sk_ack_backlog--;
+ sk_acceptq_removed(sk);
dprintk("%s: ok success on %02X, client on %02X\n", __func__,
llc_sk(sk)->addr.sllc_sap, newllc->daddr.lsap);
frees:
@@ -780,7 +780,7 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
}
/* Well, if we have backlog, try to process it now yet. */
- if (copied >= target && !sk->sk_backlog.tail)
+ if (copied >= target && !READ_ONCE(sk->sk_backlog.tail))
break;
if (copied) {
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index 4f03ebe732fa..6cbb1286d6c0 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -32,7 +32,8 @@ mac80211-y := \
chan.o \
trace.o mlme.o \
tdls.o \
- ocb.o
+ ocb.o \
+ airtime.o
mac80211-$(CONFIG_MAC80211_LEDS) += led.o
mac80211-$(CONFIG_MAC80211_DEBUGFS) += \
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index b11883d26875..33da6f738c99 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -485,7 +485,14 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
params.ssn = sta->tid_seq[tid] >> 4;
ret = drv_ampdu_action(local, sdata, &params);
- if (ret) {
+ if (ret == IEEE80211_AMPDU_TX_START_IMMEDIATE) {
+ /*
+ * We didn't send the request yet, so don't need to check
+ * here if we already got a response, just mark as driver
+ * ready immediately.
+ */
+ set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state);
+ } else if (ret) {
ht_dbg(sdata,
"BA request denied - HW unavailable for %pM tid %d\n",
sta->sta.addr, tid);
diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c
new file mode 100644
index 000000000000..63cb0028b02d
--- /dev/null
+++ b/net/mac80211/airtime.c
@@ -0,0 +1,597 @@
+// SPDX-License-Identifier: ISC
+/*
+ * Copyright (C) 2019 Felix Fietkau <nbd@nbd.name>
+ */
+
+#include <net/mac80211.h>
+#include "ieee80211_i.h"
+#include "sta_info.h"
+
+#define AVG_PKT_SIZE 1024
+
+/* Number of bits for an average sized packet */
+#define MCS_NBITS (AVG_PKT_SIZE << 3)
+
+/* Number of kilo-symbols (symbols * 1024) for a packet with (bps) bits per
+ * symbol. We use k-symbols to avoid rounding in the _TIME macros below.
+ */
+#define MCS_N_KSYMS(bps) DIV_ROUND_UP(MCS_NBITS << 10, (bps))
+
+/* Transmission time (in 1024 * usec) for a packet containing (ksyms) * 1024
+ * symbols.
+ */
+#define MCS_SYMBOL_TIME(sgi, ksyms) \
+ (sgi ? \
+ ((ksyms) * 4 * 18) / 20 : /* 3.6 us per sym */ \
+ ((ksyms) * 4) /* 4.0 us per sym */ \
+ )
+
+/* Transmit duration for the raw data part of an average sized packet */
+#define MCS_DURATION(streams, sgi, bps) \
+ ((u32)MCS_SYMBOL_TIME(sgi, MCS_N_KSYMS((streams) * (bps))))
+
+#define MCS_DURATION_S(shift, streams, sgi, bps) \
+ ((u16)((MCS_DURATION(streams, sgi, bps) >> shift)))
+
+/* These should match the values in enum nl80211_he_gi */
+#define HE_GI_08 0
+#define HE_GI_16 1
+#define HE_GI_32 2
+
+/* Transmission time (1024 usec) for a packet containing (ksyms) * k-symbols */
+#define HE_SYMBOL_TIME(gi, ksyms) \
+ (gi == HE_GI_08 ? \
+ ((ksyms) * 16 * 17) / 20 : /* 13.6 us per sym */ \
+ (gi == HE_GI_16 ? \
+ ((ksyms) * 16 * 18) / 20 : /* 14.4 us per sym */ \
+ ((ksyms) * 16) /* 16.0 us per sym */ \
+ ))
+
+/* Transmit duration for the raw data part of an average sized packet */
+#define HE_DURATION(streams, gi, bps) \
+ ((u32)HE_SYMBOL_TIME(gi, MCS_N_KSYMS((streams) * (bps))))
+
+#define HE_DURATION_S(shift, streams, gi, bps) \
+ (HE_DURATION(streams, gi, bps) >> shift)
+
+#define BW_20 0
+#define BW_40 1
+#define BW_80 2
+#define BW_160 3
+
+/*
+ * Define group sort order: HT40 -> SGI -> #streams
+ */
+#define IEEE80211_MAX_STREAMS 4
+#define IEEE80211_HT_STREAM_GROUPS 4 /* BW(=2) * SGI(=2) */
+#define IEEE80211_VHT_STREAM_GROUPS 8 /* BW(=4) * SGI(=2) */
+
+#define IEEE80211_HE_MAX_STREAMS 8
+#define IEEE80211_HE_STREAM_GROUPS 12 /* BW(=4) * GI(=3) */
+
+#define IEEE80211_HT_GROUPS_NB (IEEE80211_MAX_STREAMS * \
+ IEEE80211_HT_STREAM_GROUPS)
+#define IEEE80211_VHT_GROUPS_NB (IEEE80211_MAX_STREAMS * \
+ IEEE80211_VHT_STREAM_GROUPS)
+#define IEEE80211_HE_GROUPS_NB (IEEE80211_HE_MAX_STREAMS * \
+ IEEE80211_HE_STREAM_GROUPS)
+#define IEEE80211_GROUPS_NB (IEEE80211_HT_GROUPS_NB + \
+ IEEE80211_VHT_GROUPS_NB + \
+ IEEE80211_HE_GROUPS_NB)
+
+#define IEEE80211_HT_GROUP_0 0
+#define IEEE80211_VHT_GROUP_0 (IEEE80211_HT_GROUP_0 + IEEE80211_HT_GROUPS_NB)
+#define IEEE80211_HE_GROUP_0 (IEEE80211_VHT_GROUP_0 + IEEE80211_VHT_GROUPS_NB)
+
+#define MCS_GROUP_RATES 12
+
+#define HT_GROUP_IDX(_streams, _sgi, _ht40) \
+ IEEE80211_HT_GROUP_0 + \
+ IEEE80211_MAX_STREAMS * 2 * _ht40 + \
+ IEEE80211_MAX_STREAMS * _sgi + \
+ _streams - 1
+
+#define _MAX(a, b) (((a)>(b))?(a):(b))
+
+#define GROUP_SHIFT(duration) \
+ _MAX(0, 16 - __builtin_clz(duration))
+
+/* MCS rate information for an MCS group */
+#define __MCS_GROUP(_streams, _sgi, _ht40, _s) \
+ [HT_GROUP_IDX(_streams, _sgi, _ht40)] = { \
+ .shift = _s, \
+ .duration = { \
+ MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 54 : 26), \
+ MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 108 : 52), \
+ MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 162 : 78), \
+ MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 216 : 104), \
+ MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 324 : 156), \
+ MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 432 : 208), \
+ MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 486 : 234), \
+ MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 540 : 260) \
+ } \
+}
+
+#define MCS_GROUP_SHIFT(_streams, _sgi, _ht40) \
+ GROUP_SHIFT(MCS_DURATION(_streams, _sgi, _ht40 ? 54 : 26))
+
+#define MCS_GROUP(_streams, _sgi, _ht40) \
+ __MCS_GROUP(_streams, _sgi, _ht40, \
+ MCS_GROUP_SHIFT(_streams, _sgi, _ht40))
+
+#define VHT_GROUP_IDX(_streams, _sgi, _bw) \
+ (IEEE80211_VHT_GROUP_0 + \
+ IEEE80211_MAX_STREAMS * 2 * (_bw) + \
+ IEEE80211_MAX_STREAMS * (_sgi) + \
+ (_streams) - 1)
+
+#define BW2VBPS(_bw, r4, r3, r2, r1) \
+ (_bw == BW_160 ? r4 : _bw == BW_80 ? r3 : _bw == BW_40 ? r2 : r1)
+
+#define __VHT_GROUP(_streams, _sgi, _bw, _s) \
+ [VHT_GROUP_IDX(_streams, _sgi, _bw)] = { \
+ .shift = _s, \
+ .duration = { \
+ MCS_DURATION_S(_s, _streams, _sgi, \
+ BW2VBPS(_bw, 234, 117, 54, 26)), \
+ MCS_DURATION_S(_s, _streams, _sgi, \
+ BW2VBPS(_bw, 468, 234, 108, 52)), \
+ MCS_DURATION_S(_s, _streams, _sgi, \
+ BW2VBPS(_bw, 702, 351, 162, 78)), \
+ MCS_DURATION_S(_s, _streams, _sgi, \
+ BW2VBPS(_bw, 936, 468, 216, 104)), \
+ MCS_DURATION_S(_s, _streams, _sgi, \
+ BW2VBPS(_bw, 1404, 702, 324, 156)), \
+ MCS_DURATION_S(_s, _streams, _sgi, \
+ BW2VBPS(_bw, 1872, 936, 432, 208)), \
+ MCS_DURATION_S(_s, _streams, _sgi, \
+ BW2VBPS(_bw, 2106, 1053, 486, 234)), \
+ MCS_DURATION_S(_s, _streams, _sgi, \
+ BW2VBPS(_bw, 2340, 1170, 540, 260)), \
+ MCS_DURATION_S(_s, _streams, _sgi, \
+ BW2VBPS(_bw, 2808, 1404, 648, 312)), \
+ MCS_DURATION_S(_s, _streams, _sgi, \
+ BW2VBPS(_bw, 3120, 1560, 720, 346)) \
+ } \
+}
+
+#define VHT_GROUP_SHIFT(_streams, _sgi, _bw) \
+ GROUP_SHIFT(MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 243, 117, 54, 26)))
+
+#define VHT_GROUP(_streams, _sgi, _bw) \
+ __VHT_GROUP(_streams, _sgi, _bw, \
+ VHT_GROUP_SHIFT(_streams, _sgi, _bw))
+
+
+#define HE_GROUP_IDX(_streams, _gi, _bw) \
+ (IEEE80211_HE_GROUP_0 + \
+ IEEE80211_HE_MAX_STREAMS * 3 * (_bw) + \
+ IEEE80211_HE_MAX_STREAMS * (_gi) + \
+ (_streams) - 1)
+
+#define __HE_GROUP(_streams, _gi, _bw, _s) \
+ [HE_GROUP_IDX(_streams, _gi, _bw)] = { \
+ .shift = _s, \
+ .duration = { \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 979, 489, 230, 115)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 1958, 979, 475, 230)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 2937, 1468, 705, 345)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 3916, 1958, 936, 475)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 5875, 2937, 1411, 705)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 7833, 3916, 1872, 936)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 8827, 4406, 2102, 1051)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 9806, 4896, 2347, 1166)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 11764, 5875, 2808, 1411)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 13060, 6523, 3124, 1555)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 14702, 7344, 3513, 1756)), \
+ HE_DURATION_S(_s, _streams, _gi, \
+ BW2VBPS(_bw, 16329, 8164, 3902, 1944)) \
+ } \
+}
+
+#define HE_GROUP_SHIFT(_streams, _gi, _bw) \
+ GROUP_SHIFT(HE_DURATION(_streams, _gi, \
+ BW2VBPS(_bw, 979, 489, 230, 115)))
+
+#define HE_GROUP(_streams, _gi, _bw) \
+ __HE_GROUP(_streams, _gi, _bw, \
+ HE_GROUP_SHIFT(_streams, _gi, _bw))
+struct mcs_group {
+ u8 shift;
+ u16 duration[MCS_GROUP_RATES];
+};
+
+static const struct mcs_group airtime_mcs_groups[] = {
+ MCS_GROUP(1, 0, BW_20),
+ MCS_GROUP(2, 0, BW_20),
+ MCS_GROUP(3, 0, BW_20),
+ MCS_GROUP(4, 0, BW_20),
+
+ MCS_GROUP(1, 1, BW_20),
+ MCS_GROUP(2, 1, BW_20),
+ MCS_GROUP(3, 1, BW_20),
+ MCS_GROUP(4, 1, BW_20),
+
+ MCS_GROUP(1, 0, BW_40),
+ MCS_GROUP(2, 0, BW_40),
+ MCS_GROUP(3, 0, BW_40),
+ MCS_GROUP(4, 0, BW_40),
+
+ MCS_GROUP(1, 1, BW_40),
+ MCS_GROUP(2, 1, BW_40),
+ MCS_GROUP(3, 1, BW_40),
+ MCS_GROUP(4, 1, BW_40),
+
+ VHT_GROUP(1, 0, BW_20),
+ VHT_GROUP(2, 0, BW_20),
+ VHT_GROUP(3, 0, BW_20),
+ VHT_GROUP(4, 0, BW_20),
+
+ VHT_GROUP(1, 1, BW_20),
+ VHT_GROUP(2, 1, BW_20),
+ VHT_GROUP(3, 1, BW_20),
+ VHT_GROUP(4, 1, BW_20),
+
+ VHT_GROUP(1, 0, BW_40),
+ VHT_GROUP(2, 0, BW_40),
+ VHT_GROUP(3, 0, BW_40),
+ VHT_GROUP(4, 0, BW_40),
+
+ VHT_GROUP(1, 1, BW_40),
+ VHT_GROUP(2, 1, BW_40),
+ VHT_GROUP(3, 1, BW_40),
+ VHT_GROUP(4, 1, BW_40),
+
+ VHT_GROUP(1, 0, BW_80),
+ VHT_GROUP(2, 0, BW_80),
+ VHT_GROUP(3, 0, BW_80),
+ VHT_GROUP(4, 0, BW_80),
+
+ VHT_GROUP(1, 1, BW_80),
+ VHT_GROUP(2, 1, BW_80),
+ VHT_GROUP(3, 1, BW_80),
+ VHT_GROUP(4, 1, BW_80),
+
+ VHT_GROUP(1, 0, BW_160),
+ VHT_GROUP(2, 0, BW_160),
+ VHT_GROUP(3, 0, BW_160),
+ VHT_GROUP(4, 0, BW_160),
+
+ VHT_GROUP(1, 1, BW_160),
+ VHT_GROUP(2, 1, BW_160),
+ VHT_GROUP(3, 1, BW_160),
+ VHT_GROUP(4, 1, BW_160),
+
+ HE_GROUP(1, HE_GI_08, BW_20),
+ HE_GROUP(2, HE_GI_08, BW_20),
+ HE_GROUP(3, HE_GI_08, BW_20),
+ HE_GROUP(4, HE_GI_08, BW_20),
+ HE_GROUP(5, HE_GI_08, BW_20),
+ HE_GROUP(6, HE_GI_08, BW_20),
+ HE_GROUP(7, HE_GI_08, BW_20),
+ HE_GROUP(8, HE_GI_08, BW_20),
+
+ HE_GROUP(1, HE_GI_16, BW_20),
+ HE_GROUP(2, HE_GI_16, BW_20),
+ HE_GROUP(3, HE_GI_16, BW_20),
+ HE_GROUP(4, HE_GI_16, BW_20),
+ HE_GROUP(5, HE_GI_16, BW_20),
+ HE_GROUP(6, HE_GI_16, BW_20),
+ HE_GROUP(7, HE_GI_16, BW_20),
+ HE_GROUP(8, HE_GI_16, BW_20),
+
+ HE_GROUP(1, HE_GI_32, BW_20),
+ HE_GROUP(2, HE_GI_32, BW_20),
+ HE_GROUP(3, HE_GI_32, BW_20),
+ HE_GROUP(4, HE_GI_32, BW_20),
+ HE_GROUP(5, HE_GI_32, BW_20),
+ HE_GROUP(6, HE_GI_32, BW_20),
+ HE_GROUP(7, HE_GI_32, BW_20),
+ HE_GROUP(8, HE_GI_32, BW_20),
+
+ HE_GROUP(1, HE_GI_08, BW_40),
+ HE_GROUP(2, HE_GI_08, BW_40),
+ HE_GROUP(3, HE_GI_08, BW_40),
+ HE_GROUP(4, HE_GI_08, BW_40),
+ HE_GROUP(5, HE_GI_08, BW_40),
+ HE_GROUP(6, HE_GI_08, BW_40),
+ HE_GROUP(7, HE_GI_08, BW_40),
+ HE_GROUP(8, HE_GI_08, BW_40),
+
+ HE_GROUP(1, HE_GI_16, BW_40),
+ HE_GROUP(2, HE_GI_16, BW_40),
+ HE_GROUP(3, HE_GI_16, BW_40),
+ HE_GROUP(4, HE_GI_16, BW_40),
+ HE_GROUP(5, HE_GI_16, BW_40),
+ HE_GROUP(6, HE_GI_16, BW_40),
+ HE_GROUP(7, HE_GI_16, BW_40),
+ HE_GROUP(8, HE_GI_16, BW_40),
+
+ HE_GROUP(1, HE_GI_32, BW_40),
+ HE_GROUP(2, HE_GI_32, BW_40),
+ HE_GROUP(3, HE_GI_32, BW_40),
+ HE_GROUP(4, HE_GI_32, BW_40),
+ HE_GROUP(5, HE_GI_32, BW_40),
+ HE_GROUP(6, HE_GI_32, BW_40),
+ HE_GROUP(7, HE_GI_32, BW_40),
+ HE_GROUP(8, HE_GI_32, BW_40),
+
+ HE_GROUP(1, HE_GI_08, BW_80),
+ HE_GROUP(2, HE_GI_08, BW_80),
+ HE_GROUP(3, HE_GI_08, BW_80),
+ HE_GROUP(4, HE_GI_08, BW_80),
+ HE_GROUP(5, HE_GI_08, BW_80),
+ HE_GROUP(6, HE_GI_08, BW_80),
+ HE_GROUP(7, HE_GI_08, BW_80),
+ HE_GROUP(8, HE_GI_08, BW_80),
+
+ HE_GROUP(1, HE_GI_16, BW_80),
+ HE_GROUP(2, HE_GI_16, BW_80),
+ HE_GROUP(3, HE_GI_16, BW_80),
+ HE_GROUP(4, HE_GI_16, BW_80),
+ HE_GROUP(5, HE_GI_16, BW_80),
+ HE_GROUP(6, HE_GI_16, BW_80),
+ HE_GROUP(7, HE_GI_16, BW_80),
+ HE_GROUP(8, HE_GI_16, BW_80),
+
+ HE_GROUP(1, HE_GI_32, BW_80),
+ HE_GROUP(2, HE_GI_32, BW_80),
+ HE_GROUP(3, HE_GI_32, BW_80),
+ HE_GROUP(4, HE_GI_32, BW_80),
+ HE_GROUP(5, HE_GI_32, BW_80),
+ HE_GROUP(6, HE_GI_32, BW_80),
+ HE_GROUP(7, HE_GI_32, BW_80),
+ HE_GROUP(8, HE_GI_32, BW_80),
+
+ HE_GROUP(1, HE_GI_08, BW_160),
+ HE_GROUP(2, HE_GI_08, BW_160),
+ HE_GROUP(3, HE_GI_08, BW_160),
+ HE_GROUP(4, HE_GI_08, BW_160),
+ HE_GROUP(5, HE_GI_08, BW_160),
+ HE_GROUP(6, HE_GI_08, BW_160),
+ HE_GROUP(7, HE_GI_08, BW_160),
+ HE_GROUP(8, HE_GI_08, BW_160),
+
+ HE_GROUP(1, HE_GI_16, BW_160),
+ HE_GROUP(2, HE_GI_16, BW_160),
+ HE_GROUP(3, HE_GI_16, BW_160),
+ HE_GROUP(4, HE_GI_16, BW_160),
+ HE_GROUP(5, HE_GI_16, BW_160),
+ HE_GROUP(6, HE_GI_16, BW_160),
+ HE_GROUP(7, HE_GI_16, BW_160),
+ HE_GROUP(8, HE_GI_16, BW_160),
+
+ HE_GROUP(1, HE_GI_32, BW_160),
+ HE_GROUP(2, HE_GI_32, BW_160),
+ HE_GROUP(3, HE_GI_32, BW_160),
+ HE_GROUP(4, HE_GI_32, BW_160),
+ HE_GROUP(5, HE_GI_32, BW_160),
+ HE_GROUP(6, HE_GI_32, BW_160),
+ HE_GROUP(7, HE_GI_32, BW_160),
+ HE_GROUP(8, HE_GI_32, BW_160),
+};
+
+static u32
+ieee80211_calc_legacy_rate_duration(u16 bitrate, bool short_pre,
+ bool cck, int len)
+{
+ u32 duration;
+
+ if (cck) {
+ duration = 144 + 48; /* preamble + PLCP */
+ if (short_pre)
+ duration >>= 1;
+
+ duration += 10; /* SIFS */
+ } else {
+ duration = 20 + 16; /* premable + SIFS */
+ }
+
+ len <<= 3;
+ duration += (len * 10) / bitrate;
+
+ return duration;
+}
+
+u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw,
+ struct ieee80211_rx_status *status,
+ int len)
+{
+ struct ieee80211_supported_band *sband;
+ const struct ieee80211_rate *rate;
+ bool sgi = status->enc_flags & RX_ENC_FLAG_SHORT_GI;
+ bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE;
+ int bw, streams;
+ int group, idx;
+ u32 duration;
+ bool cck;
+
+ switch (status->bw) {
+ case RATE_INFO_BW_20:
+ bw = BW_20;
+ break;
+ case RATE_INFO_BW_40:
+ bw = BW_40;
+ break;
+ case RATE_INFO_BW_80:
+ bw = BW_80;
+ break;
+ case RATE_INFO_BW_160:
+ bw = BW_160;
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return 0;
+ }
+
+ switch (status->encoding) {
+ case RX_ENC_LEGACY:
+ if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ))
+ return 0;
+
+ sband = hw->wiphy->bands[status->band];
+ if (!sband || status->rate_idx > sband->n_bitrates)
+ return 0;
+
+ rate = &sband->bitrates[status->rate_idx];
+ cck = rate->flags & IEEE80211_RATE_MANDATORY_B;
+
+ return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp,
+ cck, len);
+
+ case RX_ENC_VHT:
+ streams = status->nss;
+ idx = status->rate_idx;
+ group = VHT_GROUP_IDX(streams, sgi, bw);
+ break;
+ case RX_ENC_HT:
+ streams = ((status->rate_idx >> 3) & 3) + 1;
+ idx = status->rate_idx & 7;
+ group = HT_GROUP_IDX(streams, sgi, bw);
+ break;
+ case RX_ENC_HE:
+ streams = status->nss;
+ idx = status->rate_idx;
+ group = HE_GROUP_IDX(streams, status->he_gi, bw);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return 0;
+ }
+
+ if (WARN_ON_ONCE((status->encoding != RX_ENC_HE && streams > 4) ||
+ (status->encoding == RX_ENC_HE && streams > 8)))
+ return 0;
+
+ duration = airtime_mcs_groups[group].duration[idx];
+ duration <<= airtime_mcs_groups[group].shift;
+ duration *= len;
+ duration /= AVG_PKT_SIZE;
+ duration /= 1024;
+
+ duration += 36 + (streams << 2);
+
+ return duration;
+}
+EXPORT_SYMBOL_GPL(ieee80211_calc_rx_airtime);
+
+static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw,
+ struct ieee80211_tx_rate *rate,
+ u8 band, int len)
+{
+ struct ieee80211_rx_status stat = {
+ .band = band,
+ };
+
+ if (rate->idx < 0 || !rate->count)
+ return 0;
+
+ if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+ stat.bw = RATE_INFO_BW_80;
+ else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+ stat.bw = RATE_INFO_BW_40;
+ else
+ stat.bw = RATE_INFO_BW_20;
+
+ stat.enc_flags = 0;
+ if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)
+ stat.enc_flags |= RX_ENC_FLAG_SHORTPRE;
+ if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
+ stat.enc_flags |= RX_ENC_FLAG_SHORT_GI;
+
+ stat.rate_idx = rate->idx;
+ if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+ stat.encoding = RX_ENC_VHT;
+ stat.rate_idx = ieee80211_rate_get_vht_mcs(rate);
+ stat.nss = ieee80211_rate_get_vht_nss(rate);
+ } else if (rate->flags & IEEE80211_TX_RC_MCS) {
+ stat.encoding = RX_ENC_HT;
+ } else {
+ stat.encoding = RX_ENC_LEGACY;
+ }
+
+ return ieee80211_calc_rx_airtime(hw, &stat, len);
+}
+
+u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw,
+ struct ieee80211_tx_info *info,
+ int len)
+{
+ u32 duration = 0;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(info->status.rates); i++) {
+ struct ieee80211_tx_rate *rate = &info->status.rates[i];
+ u32 cur_duration;
+
+ cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate,
+ info->band, len);
+ if (!cur_duration)
+ break;
+
+ duration += cur_duration * rate->count;
+ }
+
+ return duration;
+}
+EXPORT_SYMBOL_GPL(ieee80211_calc_tx_airtime);
+
+u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct ieee80211_sta *pubsta,
+ int len)
+{
+ struct ieee80211_supported_band *sband;
+ struct ieee80211_chanctx_conf *conf;
+ int rateidx, shift = 0;
+ bool cck, short_pream;
+ u32 basic_rates;
+ u8 band = 0;
+ u16 rate;
+
+ len += 38; /* Ethernet header length */
+
+ conf = rcu_dereference(vif->chanctx_conf);
+ if (conf) {
+ band = conf->def.chan->band;
+ shift = ieee80211_chandef_get_shift(&conf->def);
+ }
+
+ if (pubsta) {
+ struct sta_info *sta = container_of(pubsta, struct sta_info,
+ sta);
+
+ return ieee80211_calc_tx_airtime_rate(hw,
+ &sta->tx_stats.last_rate,
+ band, len);
+ }
+
+ if (!conf)
+ return 0;
+
+ /* No station to get latest rate from, so calculate the worst-case
+ * duration using the lowest configured basic rate.
+ */
+ sband = hw->wiphy->bands[band];
+
+ basic_rates = vif->bss_conf.basic_rates;
+ short_pream = vif->bss_conf.use_short_preamble;
+
+ rateidx = basic_rates ? ffs(basic_rates) - 1 : 0;
+ rate = sband->bitrates[rateidx].bitrate << shift;
+ cck = sband->bitrates[rateidx].flags & IEEE80211_RATE_MANDATORY_B;
+
+ return ieee80211_calc_legacy_rate_duration(rate, short_pream, cck, len);
+}
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 70739e746c13..4fb7f1f12109 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3428,7 +3428,7 @@ int ieee80211_attach_ack_skb(struct ieee80211_local *local, struct sk_buff *skb,
spin_lock_irqsave(&local->ack_status_lock, spin_flags);
id = idr_alloc(&local->ack_status_frames, ack_skb,
- 1, 0x10000, GFP_ATOMIC);
+ 1, 0x40, GFP_ATOMIC);
spin_unlock_irqrestore(&local->ack_status_lock, spin_flags);
if (id < 0) {
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 568b3b276931..ad41d74530c6 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -59,6 +59,8 @@ static const struct file_operations name## _ops = { \
debugfs_create_file(#name, mode, phyd, local, &name## _ops);
+DEBUGFS_READONLY_FILE(hw_conf, "%x",
+ local->hw.conf.flags);
DEBUGFS_READONLY_FILE(user_power, "%d",
local->user_power_level);
DEBUGFS_READONLY_FILE(power, "%d",
@@ -148,6 +150,87 @@ static const struct file_operations aqm_ops = {
.llseek = default_llseek,
};
+static ssize_t aql_txq_limit_read(struct file *file,
+ char __user *user_buf,
+ size_t count,
+ loff_t *ppos)
+{
+ struct ieee80211_local *local = file->private_data;
+ char buf[400];
+ int len = 0;
+
+ len = scnprintf(buf, sizeof(buf),
+ "AC AQL limit low AQL limit high\n"
+ "VO %u %u\n"
+ "VI %u %u\n"
+ "BE %u %u\n"
+ "BK %u %u\n",
+ local->aql_txq_limit_low[IEEE80211_AC_VO],
+ local->aql_txq_limit_high[IEEE80211_AC_VO],
+ local->aql_txq_limit_low[IEEE80211_AC_VI],
+ local->aql_txq_limit_high[IEEE80211_AC_VI],
+ local->aql_txq_limit_low[IEEE80211_AC_BE],
+ local->aql_txq_limit_high[IEEE80211_AC_BE],
+ local->aql_txq_limit_low[IEEE80211_AC_BK],
+ local->aql_txq_limit_high[IEEE80211_AC_BK]);
+ return simple_read_from_buffer(user_buf, count, ppos,
+ buf, len);
+}
+
+static ssize_t aql_txq_limit_write(struct file *file,
+ const char __user *user_buf,
+ size_t count,
+ loff_t *ppos)
+{
+ struct ieee80211_local *local = file->private_data;
+ char buf[100];
+ size_t len;
+ u32 ac, q_limit_low, q_limit_high, q_limit_low_old, q_limit_high_old;
+ struct sta_info *sta;
+
+ if (count > sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(buf, user_buf, count))
+ return -EFAULT;
+
+ buf[sizeof(buf) - 1] = 0;
+ len = strlen(buf);
+ if (len > 0 && buf[len - 1] == '\n')
+ buf[len - 1] = 0;
+
+ if (sscanf(buf, "%u %u %u", &ac, &q_limit_low, &q_limit_high) != 3)
+ return -EINVAL;
+
+ if (ac >= IEEE80211_NUM_ACS)
+ return -EINVAL;
+
+ q_limit_low_old = local->aql_txq_limit_low[ac];
+ q_limit_high_old = local->aql_txq_limit_high[ac];
+
+ local->aql_txq_limit_low[ac] = q_limit_low;
+ local->aql_txq_limit_high[ac] = q_limit_high;
+
+ mutex_lock(&local->sta_mtx);
+ list_for_each_entry(sta, &local->sta_list, list) {
+ /* If a sta has customized queue limits, keep it */
+ if (sta->airtime[ac].aql_limit_low == q_limit_low_old &&
+ sta->airtime[ac].aql_limit_high == q_limit_high_old) {
+ sta->airtime[ac].aql_limit_low = q_limit_low;
+ sta->airtime[ac].aql_limit_high = q_limit_high;
+ }
+ }
+ mutex_unlock(&local->sta_mtx);
+ return count;
+}
+
+static const struct file_operations aql_txq_limit_ops = {
+ .write = aql_txq_limit_write,
+ .read = aql_txq_limit_read,
+ .open = simple_open,
+ .llseek = default_llseek,
+};
+
static ssize_t force_tx_status_read(struct file *file,
char __user *user_buf,
size_t count,
@@ -433,6 +516,7 @@ void debugfs_hw_add(struct ieee80211_local *local)
DEBUGFS_ADD(hwflags);
DEBUGFS_ADD(user_power);
DEBUGFS_ADD(power);
+ DEBUGFS_ADD(hw_conf);
DEBUGFS_ADD_MODE(force_tx_status, 0600);
if (local->ops->wake_tx_queue)
@@ -441,6 +525,10 @@ void debugfs_hw_add(struct ieee80211_local *local)
debugfs_create_u16("airtime_flags", 0600,
phyd, &local->airtime_flags);
+ DEBUGFS_ADD(aql_txq_limit);
+ debugfs_create_u32("aql_threshold", 0600,
+ phyd, &local->aql_threshold);
+
statsd = debugfs_create_dir("statistics", phyd);
/* if the dir failed, don't put all the other things into the root! */
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index c8ad20c28c43..0185e6e5e5d1 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -197,10 +197,12 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf,
{
struct sta_info *sta = file->private_data;
struct ieee80211_local *local = sta->sdata->local;
- size_t bufsz = 200;
+ size_t bufsz = 400;
char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf;
u64 rx_airtime = 0, tx_airtime = 0;
s64 deficit[IEEE80211_NUM_ACS];
+ u32 q_depth[IEEE80211_NUM_ACS];
+ u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS];
ssize_t rv;
int ac;
@@ -212,19 +214,22 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf,
rx_airtime += sta->airtime[ac].rx_airtime;
tx_airtime += sta->airtime[ac].tx_airtime;
deficit[ac] = sta->airtime[ac].deficit;
+ q_limit_l[ac] = sta->airtime[ac].aql_limit_low;
+ q_limit_h[ac] = sta->airtime[ac].aql_limit_high;
spin_unlock_bh(&local->active_txq_lock[ac]);
+ q_depth[ac] = atomic_read(&sta->airtime[ac].aql_tx_pending);
}
p += scnprintf(p, bufsz + buf - p,
"RX: %llu us\nTX: %llu us\nWeight: %u\n"
- "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n",
- rx_airtime,
- tx_airtime,
- sta->airtime_weight,
- deficit[0],
- deficit[1],
- deficit[2],
- deficit[3]);
+ "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n"
+ "Q depth: VO: %u us VI: %u us BE: %u us BK: %u us\n"
+ "Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n",
+ rx_airtime, tx_airtime, sta->airtime_weight,
+ deficit[0], deficit[1], deficit[2], deficit[3],
+ q_depth[0], q_depth[1], q_depth[2], q_depth[3],
+ q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1],
+ q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]),
rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
kfree(buf);
@@ -236,7 +241,25 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf,
{
struct sta_info *sta = file->private_data;
struct ieee80211_local *local = sta->sdata->local;
- int ac;
+ u32 ac, q_limit_l, q_limit_h;
+ char _buf[100] = {}, *buf = _buf;
+
+ if (count > sizeof(_buf))
+ return -EINVAL;
+
+ if (copy_from_user(buf, userbuf, count))
+ return -EFAULT;
+
+ buf[sizeof(_buf) - 1] = '\0';
+ if (sscanf(buf, "queue limit %u %u %u", &ac, &q_limit_l, &q_limit_h)
+ != 3)
+ return -EINVAL;
+
+ if (ac >= IEEE80211_NUM_ACS)
+ return -EINVAL;
+
+ sta->airtime[ac].aql_limit_low = q_limit_l;
+ sta->airtime[ac].aql_limit_high = q_limit_h;
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
spin_lock_bh(&local->active_txq_lock[ac]);
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 0a6ff01c68a9..d40744903fa9 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -538,7 +538,6 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
struct cfg80211_bss *cbss;
- int err, changed = 0;
sdata_assert_lock(sdata);
@@ -560,13 +559,7 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata)
ifibss->chandef = sdata->csa_chandef;
/* generate the beacon */
- err = ieee80211_ibss_csa_beacon(sdata, NULL);
- if (err < 0)
- return err;
-
- changed |= err;
-
- return changed;
+ return ieee80211_ibss_csa_beacon(sdata, NULL);
}
void ieee80211_ibss_stop(struct ieee80211_sub_if_data *sdata)
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 05406e9c05b3..ad15b3be8bb3 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1142,6 +1142,10 @@ struct ieee80211_local {
u16 schedule_round[IEEE80211_NUM_ACS];
u16 airtime_flags;
+ u32 aql_txq_limit_low[IEEE80211_NUM_ACS];
+ u32 aql_txq_limit_high[IEEE80211_NUM_ACS];
+ u32 aql_threshold;
+ atomic_t aql_total_pending_airtime;
const struct ieee80211_ops *ops;
@@ -2249,6 +2253,10 @@ const char *ieee80211_get_reason_code_string(u16 reason_code);
extern const struct ethtool_ops ieee80211_ethtool_ops;
+u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct ieee80211_sta *pubsta,
+ int len);
#ifdef CONFIG_MAC80211_NOINLINE
#define debug_noinline noinline
#else
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index aba094b4ccfc..6cca0853f183 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -667,8 +667,16 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
for (i = 0; i < IEEE80211_NUM_ACS; i++) {
INIT_LIST_HEAD(&local->active_txqs[i]);
spin_lock_init(&local->active_txq_lock[i]);
+ local->aql_txq_limit_low[i] = IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L;
+ local->aql_txq_limit_high[i] =
+ IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H;
}
- local->airtime_flags = AIRTIME_USE_TX | AIRTIME_USE_RX;
+
+ local->airtime_flags = AIRTIME_USE_TX |
+ AIRTIME_USE_RX |
+ AIRTIME_USE_AQL;
+ local->aql_threshold = IEEE80211_AQL_THRESHOLD;
+ atomic_set(&local->aql_total_pending_airtime, 0);
INIT_LIST_HEAD(&local->chanctx_list);
mutex_init(&local->chanctx_mtx);
@@ -1292,8 +1300,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
ieee80211_remove_interfaces(local);
fail_rate:
rtnl_unlock();
- ieee80211_led_exit(local);
fail_flows:
+ ieee80211_led_exit(local);
destroy_workqueue(local->workqueue);
fail_workqueue:
wiphy_unregister(local->hw.wiphy);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 54dd8849d1cc..5fa13176036f 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3186,15 +3186,14 @@ static int ieee80211_recalc_twt_req(struct ieee80211_sub_if_data *sdata,
static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
struct cfg80211_bss *cbss,
- struct ieee80211_mgmt *mgmt, size_t len)
+ struct ieee80211_mgmt *mgmt, size_t len,
+ struct ieee802_11_elems *elems)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct ieee80211_local *local = sdata->local;
struct ieee80211_supported_band *sband;
struct sta_info *sta;
- u8 *pos;
u16 capab_info, aid;
- struct ieee802_11_elems elems;
struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf;
const struct cfg80211_bss_ies *bss_ies = NULL;
struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data;
@@ -3222,19 +3221,15 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
ifmgd->broken_ap = true;
}
- pos = mgmt->u.assoc_resp.variable;
- ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, &elems,
- mgmt->bssid, assoc_data->bss->bssid);
-
- if (!elems.supp_rates) {
+ if (!elems->supp_rates) {
sdata_info(sdata, "no SuppRates element in AssocResp\n");
return false;
}
ifmgd->aid = aid;
ifmgd->tdls_chan_switch_prohibited =
- elems.ext_capab && elems.ext_capab_len >= 5 &&
- (elems.ext_capab[4] & WLAN_EXT_CAPA5_TDLS_CH_SW_PROHIBITED);
+ elems->ext_capab && elems->ext_capab_len >= 5 &&
+ (elems->ext_capab[4] & WLAN_EXT_CAPA5_TDLS_CH_SW_PROHIBITED);
/*
* Some APs are erroneously not including some information in their
@@ -3243,11 +3238,11 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
* 2G/3G/4G wifi routers, reported models include the "Onda PN51T",
* "Vodafone PocketWiFi 2", "ZTE MF60" and a similar T-Mobile device.
*/
- if ((assoc_data->wmm && !elems.wmm_param) ||
+ if ((assoc_data->wmm && !elems->wmm_param) ||
(!(ifmgd->flags & IEEE80211_STA_DISABLE_HT) &&
- (!elems.ht_cap_elem || !elems.ht_operation)) ||
+ (!elems->ht_cap_elem || !elems->ht_operation)) ||
(!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT) &&
- (!elems.vht_cap_elem || !elems.vht_operation))) {
+ (!elems->vht_cap_elem || !elems->vht_operation))) {
const struct cfg80211_bss_ies *ies;
struct ieee802_11_elems bss_elems;
@@ -3265,8 +3260,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
mgmt->bssid,
assoc_data->bss->bssid);
if (assoc_data->wmm &&
- !elems.wmm_param && bss_elems.wmm_param) {
- elems.wmm_param = bss_elems.wmm_param;
+ !elems->wmm_param && bss_elems.wmm_param) {
+ elems->wmm_param = bss_elems.wmm_param;
sdata_info(sdata,
"AP bug: WMM param missing from AssocResp\n");
}
@@ -3275,27 +3270,27 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
* Also check if we requested HT/VHT, otherwise the AP doesn't
* have to include the IEs in the (re)association response.
*/
- if (!elems.ht_cap_elem && bss_elems.ht_cap_elem &&
+ if (!elems->ht_cap_elem && bss_elems.ht_cap_elem &&
!(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) {
- elems.ht_cap_elem = bss_elems.ht_cap_elem;
+ elems->ht_cap_elem = bss_elems.ht_cap_elem;
sdata_info(sdata,
"AP bug: HT capability missing from AssocResp\n");
}
- if (!elems.ht_operation && bss_elems.ht_operation &&
+ if (!elems->ht_operation && bss_elems.ht_operation &&
!(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) {
- elems.ht_operation = bss_elems.ht_operation;
+ elems->ht_operation = bss_elems.ht_operation;
sdata_info(sdata,
"AP bug: HT operation missing from AssocResp\n");
}
- if (!elems.vht_cap_elem && bss_elems.vht_cap_elem &&
+ if (!elems->vht_cap_elem && bss_elems.vht_cap_elem &&
!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) {
- elems.vht_cap_elem = bss_elems.vht_cap_elem;
+ elems->vht_cap_elem = bss_elems.vht_cap_elem;
sdata_info(sdata,
"AP bug: VHT capa missing from AssocResp\n");
}
- if (!elems.vht_operation && bss_elems.vht_operation &&
+ if (!elems->vht_operation && bss_elems.vht_operation &&
!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) {
- elems.vht_operation = bss_elems.vht_operation;
+ elems->vht_operation = bss_elems.vht_operation;
sdata_info(sdata,
"AP bug: VHT operation missing from AssocResp\n");
}
@@ -3306,7 +3301,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
* they should be present here. This is just a safety net.
*/
if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT) &&
- (!elems.wmm_param || !elems.ht_cap_elem || !elems.ht_operation)) {
+ (!elems->wmm_param || !elems->ht_cap_elem || !elems->ht_operation)) {
sdata_info(sdata,
"HT AP is missing WMM params or HT capability/operation\n");
ret = false;
@@ -3314,7 +3309,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
}
if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT) &&
- (!elems.vht_cap_elem || !elems.vht_operation)) {
+ (!elems->vht_cap_elem || !elems->vht_operation)) {
sdata_info(sdata,
"VHT AP is missing VHT capability/operation\n");
ret = false;
@@ -3341,7 +3336,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
}
if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
- (!elems.he_cap || !elems.he_operation)) {
+ (!elems->he_cap || !elems->he_operation)) {
mutex_unlock(&sdata->local->sta_mtx);
sdata_info(sdata,
"HE AP is missing HE capability/operation\n");
@@ -3350,23 +3345,23 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
}
/* Set up internal HT/VHT capabilities */
- if (elems.ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_HT))
+ if (elems->ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_HT))
ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband,
- elems.ht_cap_elem, sta);
+ elems->ht_cap_elem, sta);
- if (elems.vht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
+ if (elems->vht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
- elems.vht_cap_elem, sta);
+ elems->vht_cap_elem, sta);
- if (elems.he_operation && !(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
- elems.he_cap) {
+ if (elems->he_operation && !(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
+ elems->he_cap) {
ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband,
- elems.he_cap,
- elems.he_cap_len,
+ elems->he_cap,
+ elems->he_cap_len,
sta);
bss_conf->he_support = sta->sta.he_cap.has_he;
- changed |= ieee80211_recalc_twt_req(sdata, sta, &elems);
+ changed |= ieee80211_recalc_twt_req(sdata, sta, elems);
} else {
bss_conf->he_support = false;
bss_conf->twt_requester = false;
@@ -3374,14 +3369,14 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
if (bss_conf->he_support) {
bss_conf->bss_color =
- le32_get_bits(elems.he_operation->he_oper_params,
+ le32_get_bits(elems->he_operation->he_oper_params,
IEEE80211_HE_OPERATION_BSS_COLOR_MASK);
bss_conf->htc_trig_based_pkt_ext =
- le32_get_bits(elems.he_operation->he_oper_params,
+ le32_get_bits(elems->he_operation->he_oper_params,
IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK);
bss_conf->frame_time_rts_th =
- le32_get_bits(elems.he_operation->he_oper_params,
+ le32_get_bits(elems->he_operation->he_oper_params,
IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK);
bss_conf->multi_sta_back_32bit =
@@ -3392,12 +3387,12 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
sta->sta.he_cap.he_cap_elem.mac_cap_info[2] &
IEEE80211_HE_MAC_CAP2_ACK_EN;
- bss_conf->uora_exists = !!elems.uora_element;
- if (elems.uora_element)
- bss_conf->uora_ocw_range = elems.uora_element[0];
+ bss_conf->uora_exists = !!elems->uora_element;
+ if (elems->uora_element)
+ bss_conf->uora_ocw_range = elems->uora_element[0];
- ieee80211_he_op_ie_to_bss_conf(&sdata->vif, elems.he_operation);
- ieee80211_he_spr_ie_to_bss_conf(&sdata->vif, elems.he_spr);
+ ieee80211_he_op_ie_to_bss_conf(&sdata->vif, elems->he_operation);
+ ieee80211_he_spr_ie_to_bss_conf(&sdata->vif, elems->he_spr);
/* TODO: OPEN: what happens if BSS color disable is set? */
}
@@ -3421,11 +3416,11 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
* NSS calculation (that would be done in rate_control_rate_init())
* and use the # of streams from that element.
*/
- if (elems.opmode_notif &&
- !(*elems.opmode_notif & IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF)) {
+ if (elems->opmode_notif &&
+ !(*elems->opmode_notif & IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF)) {
u8 nss;
- nss = *elems.opmode_notif & IEEE80211_OPMODE_NOTIF_RX_NSS_MASK;
+ nss = *elems->opmode_notif & IEEE80211_OPMODE_NOTIF_RX_NSS_MASK;
nss >>= IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT;
nss += 1;
sta->sta.rx_nss = nss;
@@ -3440,7 +3435,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
sta->sta.mfp = false;
}
- sta->sta.wme = elems.wmm_param && local->hw.queues >= IEEE80211_NUM_ACS;
+ sta->sta.wme = elems->wmm_param && local->hw.queues >= IEEE80211_NUM_ACS;
err = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
if (!err && !(ifmgd->flags & IEEE80211_STA_CONTROL_PORT))
@@ -3468,9 +3463,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
if (ifmgd->flags & IEEE80211_STA_DISABLE_WMM) {
ieee80211_set_wmm_default(sdata, false, false);
- } else if (!ieee80211_sta_wmm_params(local, sdata, elems.wmm_param,
- elems.wmm_param_len,
- elems.mu_edca_param_set)) {
+ } else if (!ieee80211_sta_wmm_params(local, sdata, elems->wmm_param,
+ elems->wmm_param_len,
+ elems->mu_edca_param_set)) {
/* still enable QoS since we might have HT/VHT */
ieee80211_set_wmm_default(sdata, false, true);
/* set the disable-WMM flag in this case to disable
@@ -3484,11 +3479,11 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
}
changed |= BSS_CHANGED_QOS;
- if (elems.max_idle_period_ie) {
+ if (elems->max_idle_period_ie) {
bss_conf->max_idle_period =
- le16_to_cpu(elems.max_idle_period_ie->max_idle_period);
+ le16_to_cpu(elems->max_idle_period_ie->max_idle_period);
bss_conf->protected_keep_alive =
- !!(elems.max_idle_period_ie->idle_options &
+ !!(elems->max_idle_period_ie->idle_options &
WLAN_IDLE_OPTIONS_PROTECTED_KEEP_ALIVE);
changed |= BSS_CHANGED_KEEP_ALIVE;
} else {
@@ -3598,7 +3593,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
event.u.mlme.reason = status_code;
drv_event_callback(sdata->local, sdata, &event);
} else {
- if (!ieee80211_assoc_success(sdata, bss, mgmt, len)) {
+ if (!ieee80211_assoc_success(sdata, bss, mgmt, len, &elems)) {
/* oops -- internal error -- send timeout for now */
ieee80211_destroy_assoc_data(sdata, false, false);
cfg80211_assoc_timeout(sdata->dev, bss);
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index ee86c3333999..86bc469a28bc 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -70,7 +70,7 @@ rix_to_ndx(struct minstrel_sta_info *mi, int rix)
}
/* return current EMWA throughput */
-int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_ewma)
+int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_avg)
{
int usecs;
@@ -79,13 +79,13 @@ int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_ewma)
usecs = 1000000;
/* reset thr. below 10% success */
- if (mr->stats.prob_ewma < MINSTREL_FRAC(10, 100))
+ if (mr->stats.prob_avg < MINSTREL_FRAC(10, 100))
return 0;
- if (prob_ewma > MINSTREL_FRAC(90, 100))
+ if (prob_avg > MINSTREL_FRAC(90, 100))
return MINSTREL_TRUNC(100000 * (MINSTREL_FRAC(90, 100) / usecs));
else
- return MINSTREL_TRUNC(100000 * (prob_ewma / usecs));
+ return MINSTREL_TRUNC(100000 * (prob_avg / usecs));
}
/* find & sort topmost throughput rates */
@@ -98,8 +98,8 @@ minstrel_sort_best_tp_rates(struct minstrel_sta_info *mi, int i, u8 *tp_list)
for (j = MAX_THR_RATES; j > 0; --j) {
tmp_mrs = &mi->r[tp_list[j - 1]].stats;
- if (minstrel_get_tp_avg(&mi->r[i], cur_mrs->prob_ewma) <=
- minstrel_get_tp_avg(&mi->r[tp_list[j - 1]], tmp_mrs->prob_ewma))
+ if (minstrel_get_tp_avg(&mi->r[i], cur_mrs->prob_avg) <=
+ minstrel_get_tp_avg(&mi->r[tp_list[j - 1]], tmp_mrs->prob_avg))
break;
}
@@ -157,20 +157,24 @@ minstrel_update_rates(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
* Recalculate statistics and counters of a given rate
*/
void
-minstrel_calc_rate_stats(struct minstrel_rate_stats *mrs)
+minstrel_calc_rate_stats(struct minstrel_priv *mp,
+ struct minstrel_rate_stats *mrs)
{
unsigned int cur_prob;
if (unlikely(mrs->attempts > 0)) {
mrs->sample_skipped = 0;
cur_prob = MINSTREL_FRAC(mrs->success, mrs->attempts);
- if (unlikely(!mrs->att_hist)) {
- mrs->prob_ewma = cur_prob;
+ if (mp->new_avg) {
+ minstrel_filter_avg_add(&mrs->prob_avg,
+ &mrs->prob_avg_1, cur_prob);
+ } else if (unlikely(!mrs->att_hist)) {
+ mrs->prob_avg = cur_prob;
} else {
/*update exponential weighted moving avarage */
- mrs->prob_ewma = minstrel_ewma(mrs->prob_ewma,
- cur_prob,
- EWMA_LEVEL);
+ mrs->prob_avg = minstrel_ewma(mrs->prob_avg,
+ cur_prob,
+ EWMA_LEVEL);
}
mrs->att_hist += mrs->attempts;
mrs->succ_hist += mrs->success;
@@ -200,12 +204,12 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
struct minstrel_rate_stats *tmp_mrs = &mi->r[tmp_prob_rate].stats;
/* Update statistics of success probability per rate */
- minstrel_calc_rate_stats(mrs);
+ minstrel_calc_rate_stats(mp, mrs);
/* Sample less often below the 10% chance of success.
* Sample less often above the 95% chance of success. */
- if (mrs->prob_ewma > MINSTREL_FRAC(95, 100) ||
- mrs->prob_ewma < MINSTREL_FRAC(10, 100)) {
+ if (mrs->prob_avg > MINSTREL_FRAC(95, 100) ||
+ mrs->prob_avg < MINSTREL_FRAC(10, 100)) {
mr->adjusted_retry_count = mrs->retry_count >> 1;
if (mr->adjusted_retry_count > 2)
mr->adjusted_retry_count = 2;
@@ -225,14 +229,14 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
* choose the maximum throughput rate as max_prob_rate
* (2) if all success probabilities < 95%, the rate with
* highest success probability is chosen as max_prob_rate */
- if (mrs->prob_ewma >= MINSTREL_FRAC(95, 100)) {
- tmp_cur_tp = minstrel_get_tp_avg(mr, mrs->prob_ewma);
+ if (mrs->prob_avg >= MINSTREL_FRAC(95, 100)) {
+ tmp_cur_tp = minstrel_get_tp_avg(mr, mrs->prob_avg);
tmp_prob_tp = minstrel_get_tp_avg(&mi->r[tmp_prob_rate],
- tmp_mrs->prob_ewma);
+ tmp_mrs->prob_avg);
if (tmp_cur_tp >= tmp_prob_tp)
tmp_prob_rate = i;
} else {
- if (mrs->prob_ewma >= tmp_mrs->prob_ewma)
+ if (mrs->prob_avg >= tmp_mrs->prob_avg)
tmp_prob_rate = i;
}
}
@@ -290,7 +294,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband,
mi->sample_deferred--;
if (time_after(jiffies, mi->last_stats_update +
- (mp->update_interval * HZ) / 1000))
+ mp->update_interval / (mp->new_avg ? 2 : 1)))
minstrel_update_stats(mp, mi);
}
@@ -422,7 +426,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta,
* has a probability of >95%, we shouldn't be attempting
* to use it, as this only wastes precious airtime */
if (!mrr_capable &&
- (mi->r[ndx].stats.prob_ewma > MINSTREL_FRAC(95, 100)))
+ (mi->r[ndx].stats.prob_avg > MINSTREL_FRAC(95, 100)))
return;
mi->prev_sample = true;
@@ -573,7 +577,7 @@ static u32 minstrel_get_expected_throughput(void *priv_sta)
* computing cur_tp
*/
tmp_mrs = &mi->r[idx].stats;
- tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma) * 10;
+ tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_avg) * 10;
tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024;
return tmp_cur_tp;
diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h
index 51d8b2c846e7..dbb43bcd3c45 100644
--- a/net/mac80211/rc80211_minstrel.h
+++ b/net/mac80211/rc80211_minstrel.h
@@ -19,6 +19,21 @@
#define MAX_THR_RATES 4
/*
+ * Coefficients for moving average with noise filter (period=16),
+ * scaled by 10 bits
+ *
+ * a1 = exp(-pi * sqrt(2) / period)
+ * coeff2 = 2 * a1 * cos(sqrt(2) * 2 * pi / period)
+ * coeff3 = -sqr(a1)
+ * coeff1 = 1 - coeff2 - coeff3
+ */
+#define MINSTREL_AVG_COEFF1 (MINSTREL_FRAC(1, 1) - \
+ MINSTREL_AVG_COEFF2 - \
+ MINSTREL_AVG_COEFF3)
+#define MINSTREL_AVG_COEFF2 0x00001499
+#define MINSTREL_AVG_COEFF3 -0x0000092e
+
+/*
* Perform EWMA (Exponentially Weighted Moving Average) calculation
*/
static inline int
@@ -32,6 +47,37 @@ minstrel_ewma(int old, int new, int weight)
return old + incr;
}
+static inline int minstrel_filter_avg_add(u16 *prev_1, u16 *prev_2, s32 in)
+{
+ s32 out_1 = *prev_1;
+ s32 out_2 = *prev_2;
+ s32 val;
+
+ if (!in)
+ in += 1;
+
+ if (!out_1) {
+ val = out_1 = in;
+ goto out;
+ }
+
+ val = MINSTREL_AVG_COEFF1 * in;
+ val += MINSTREL_AVG_COEFF2 * out_1;
+ val += MINSTREL_AVG_COEFF3 * out_2;
+ val >>= MINSTREL_SCALE;
+
+ if (val > 1 << MINSTREL_SCALE)
+ val = 1 << MINSTREL_SCALE;
+ if (val < 0)
+ val = 1;
+
+out:
+ *prev_2 = out_1;
+ *prev_1 = val;
+
+ return val;
+}
+
struct minstrel_rate_stats {
/* current / last sampling period attempts/success counters */
u16 attempts, last_attempts;
@@ -40,8 +86,9 @@ struct minstrel_rate_stats {
/* total attempts/success counters */
u32 att_hist, succ_hist;
- /* prob_ewma - exponential weighted moving average of prob */
- u16 prob_ewma;
+ /* prob_avg - moving average of prob */
+ u16 prob_avg;
+ u16 prob_avg_1;
/* maximum retry counts */
u8 retry_count;
@@ -95,6 +142,7 @@ struct minstrel_sta_info {
struct minstrel_priv {
struct ieee80211_hw *hw;
bool has_mrr;
+ bool new_avg;
u32 sample_switch;
unsigned int cw_min;
unsigned int cw_max;
@@ -126,8 +174,9 @@ extern const struct rate_control_ops mac80211_minstrel;
void minstrel_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir);
/* Recalculate success probabilities and counters for a given rate using EWMA */
-void minstrel_calc_rate_stats(struct minstrel_rate_stats *mrs);
-int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_ewma);
+void minstrel_calc_rate_stats(struct minstrel_priv *mp,
+ struct minstrel_rate_stats *mrs);
+int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_avg);
/* debugfs */
int minstrel_stats_open(struct inode *inode, struct file *file);
diff --git a/net/mac80211/rc80211_minstrel_debugfs.c b/net/mac80211/rc80211_minstrel_debugfs.c
index c8afd85b51a0..9b8e0daeb7bb 100644
--- a/net/mac80211/rc80211_minstrel_debugfs.c
+++ b/net/mac80211/rc80211_minstrel_debugfs.c
@@ -90,8 +90,8 @@ minstrel_stats_open(struct inode *inode, struct file *file)
p += sprintf(p, "%6u ", mr->perfect_tx_time);
tp_max = minstrel_get_tp_avg(mr, MINSTREL_FRAC(100,100));
- tp_avg = minstrel_get_tp_avg(mr, mrs->prob_ewma);
- eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000);
+ tp_avg = minstrel_get_tp_avg(mr, mrs->prob_avg);
+ eprob = MINSTREL_TRUNC(mrs->prob_avg * 1000);
p += sprintf(p, "%4u.%1u %4u.%1u %3u.%1u"
" %3u %3u %-3u "
@@ -147,8 +147,8 @@ minstrel_stats_csv_open(struct inode *inode, struct file *file)
p += sprintf(p, "%u,",mr->perfect_tx_time);
tp_max = minstrel_get_tp_avg(mr, MINSTREL_FRAC(100,100));
- tp_avg = minstrel_get_tp_avg(mr, mrs->prob_ewma);
- eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000);
+ tp_avg = minstrel_get_tp_avg(mr, mrs->prob_avg);
+ eprob = MINSTREL_TRUNC(mrs->prob_avg * 1000);
p += sprintf(p, "%u.%u,%u.%u,%u.%u,%u,%u,%u,"
"%llu,%llu,%d,%d\n",
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 0ef2633349b5..694a31978a04 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -346,12 +346,12 @@ minstrel_ht_avg_ampdu_len(struct minstrel_ht_sta *mi)
*/
int
minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate,
- int prob_ewma)
+ int prob_avg)
{
unsigned int nsecs = 0;
/* do not account throughput if sucess prob is below 10% */
- if (prob_ewma < MINSTREL_FRAC(10, 100))
+ if (prob_avg < MINSTREL_FRAC(10, 100))
return 0;
if (group != MINSTREL_CCK_GROUP)
@@ -365,11 +365,11 @@ minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate,
* account for collision related packet error rate fluctuation
* (prob is scaled - see MINSTREL_FRAC above)
*/
- if (prob_ewma > MINSTREL_FRAC(90, 100))
+ if (prob_avg > MINSTREL_FRAC(90, 100))
return MINSTREL_TRUNC(100000 * ((MINSTREL_FRAC(90, 100) * 1000)
/ nsecs));
else
- return MINSTREL_TRUNC(100000 * ((prob_ewma * 1000) / nsecs));
+ return MINSTREL_TRUNC(100000 * ((prob_avg * 1000) / nsecs));
}
/*
@@ -389,13 +389,13 @@ minstrel_ht_sort_best_tp_rates(struct minstrel_ht_sta *mi, u16 index,
cur_group = index / MCS_GROUP_RATES;
cur_idx = index % MCS_GROUP_RATES;
- cur_prob = mi->groups[cur_group].rates[cur_idx].prob_ewma;
+ cur_prob = mi->groups[cur_group].rates[cur_idx].prob_avg;
cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, cur_prob);
do {
tmp_group = tp_list[j - 1] / MCS_GROUP_RATES;
tmp_idx = tp_list[j - 1] % MCS_GROUP_RATES;
- tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma;
+ tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg;
tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx,
tmp_prob);
if (cur_tp_avg < tmp_tp_avg ||
@@ -432,7 +432,7 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index)
tmp_group = mi->max_prob_rate / MCS_GROUP_RATES;
tmp_idx = mi->max_prob_rate % MCS_GROUP_RATES;
- tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma;
+ tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg;
tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob);
/* if max_tp_rate[0] is from MCS_GROUP max_prob_rate get selected from
@@ -444,11 +444,11 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index)
max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES;
max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES;
- max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma;
+ max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_avg;
- if (mrs->prob_ewma > MINSTREL_FRAC(75, 100)) {
+ if (mrs->prob_avg > MINSTREL_FRAC(75, 100)) {
cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx,
- mrs->prob_ewma);
+ mrs->prob_avg);
if (cur_tp_avg > tmp_tp_avg)
mi->max_prob_rate = index;
@@ -458,9 +458,9 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index)
if (cur_tp_avg > max_gpr_tp_avg)
mg->max_group_prob_rate = index;
} else {
- if (mrs->prob_ewma > tmp_prob)
+ if (mrs->prob_avg > tmp_prob)
mi->max_prob_rate = index;
- if (mrs->prob_ewma > max_gpr_prob)
+ if (mrs->prob_avg > max_gpr_prob)
mg->max_group_prob_rate = index;
}
}
@@ -482,12 +482,12 @@ minstrel_ht_assign_best_tp_rates(struct minstrel_ht_sta *mi,
tmp_group = tmp_cck_tp_rate[0] / MCS_GROUP_RATES;
tmp_idx = tmp_cck_tp_rate[0] % MCS_GROUP_RATES;
- tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma;
+ tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg;
tmp_cck_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob);
tmp_group = tmp_mcs_tp_rate[0] / MCS_GROUP_RATES;
tmp_idx = tmp_mcs_tp_rate[0] % MCS_GROUP_RATES;
- tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma;
+ tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg;
tmp_mcs_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob);
if (tmp_cck_tp_rate && tmp_cck_tp > tmp_mcs_tp) {
@@ -518,7 +518,7 @@ minstrel_ht_prob_rate_reduce_streams(struct minstrel_ht_sta *mi)
continue;
tmp_idx = mg->max_group_prob_rate % MCS_GROUP_RATES;
- tmp_prob = mi->groups[group].rates[tmp_idx].prob_ewma;
+ tmp_prob = mi->groups[group].rates[tmp_idx].prob_avg;
if (tmp_tp < minstrel_ht_get_tp_avg(mi, group, tmp_idx, tmp_prob) &&
(minstrel_mcs_groups[group].streams < tmp_max_streams)) {
@@ -623,7 +623,7 @@ minstrel_ht_rate_sample_switch(struct minstrel_priv *mp,
* If that fails, look again for a rate that is at least as fast
*/
mrs = minstrel_get_ratestats(mi, mi->max_tp_rate[0]);
- faster_rate = mrs->prob_ewma > MINSTREL_FRAC(75, 100);
+ faster_rate = mrs->prob_avg > MINSTREL_FRAC(75, 100);
minstrel_ht_find_probe_rates(mi, rates, &n_rates, faster_rate);
if (!n_rates && faster_rate)
minstrel_ht_find_probe_rates(mi, rates, &n_rates, false);
@@ -737,8 +737,8 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
mrs = &mg->rates[i];
mrs->retry_updated = false;
- minstrel_calc_rate_stats(mrs);
- cur_prob = mrs->prob_ewma;
+ minstrel_calc_rate_stats(mp, mrs);
+ cur_prob = mrs->prob_avg;
if (minstrel_ht_get_tp_avg(mi, group, i, cur_prob) == 0)
continue;
@@ -773,6 +773,8 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
/* try to sample all available rates during each interval */
mi->sample_count *= 8;
+ if (mp->new_avg)
+ mi->sample_count /= 2;
if (sample)
minstrel_ht_rate_sample_switch(mp, mi);
@@ -889,6 +891,7 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband,
struct ieee80211_tx_rate *ar = info->status.rates;
struct minstrel_rate_stats *rate, *rate2, *rate_sample = NULL;
struct minstrel_priv *mp = priv;
+ u32 update_interval = mp->update_interval / 2;
bool last, update = false;
bool sample_status = false;
int i;
@@ -943,6 +946,10 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband,
switch (mi->sample_mode) {
case MINSTREL_SAMPLE_IDLE:
+ if (mp->new_avg &&
+ (mp->hw->max_rates > 1 ||
+ mi->total_packets_cur < SAMPLE_SWITCH_THR))
+ update_interval /= 2;
break;
case MINSTREL_SAMPLE_ACTIVE:
@@ -970,23 +977,20 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband,
*/
rate = minstrel_get_ratestats(mi, mi->max_tp_rate[0]);
if (rate->attempts > 30 &&
- MINSTREL_FRAC(rate->success, rate->attempts) <
- MINSTREL_FRAC(20, 100)) {
+ rate->success < rate->attempts / 4) {
minstrel_downgrade_rate(mi, &mi->max_tp_rate[0], true);
update = true;
}
rate2 = minstrel_get_ratestats(mi, mi->max_tp_rate[1]);
if (rate2->attempts > 30 &&
- MINSTREL_FRAC(rate2->success, rate2->attempts) <
- MINSTREL_FRAC(20, 100)) {
+ rate2->success < rate2->attempts / 4) {
minstrel_downgrade_rate(mi, &mi->max_tp_rate[1], false);
update = true;
}
}
- if (time_after(jiffies, mi->last_stats_update +
- (mp->update_interval / 2 * HZ) / 1000)) {
+ if (time_after(jiffies, mi->last_stats_update + update_interval)) {
update = true;
minstrel_ht_update_stats(mp, mi, true);
}
@@ -1008,7 +1012,7 @@ minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
unsigned int overhead = 0, overhead_rtscts = 0;
mrs = minstrel_get_ratestats(mi, index);
- if (mrs->prob_ewma < MINSTREL_FRAC(1, 10)) {
+ if (mrs->prob_avg < MINSTREL_FRAC(1, 10)) {
mrs->retry_count = 1;
mrs->retry_count_rtscts = 1;
return;
@@ -1065,7 +1069,7 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
if (!mrs->retry_updated)
minstrel_calc_retransmit(mp, mi, index);
- if (mrs->prob_ewma < MINSTREL_FRAC(20, 100) || !mrs->retry_count) {
+ if (mrs->prob_avg < MINSTREL_FRAC(20, 100) || !mrs->retry_count) {
ratetbl->rate[offset].count = 2;
ratetbl->rate[offset].count_rts = 2;
ratetbl->rate[offset].count_cts = 2;
@@ -1099,11 +1103,11 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
}
static inline int
-minstrel_ht_get_prob_ewma(struct minstrel_ht_sta *mi, int rate)
+minstrel_ht_get_prob_avg(struct minstrel_ht_sta *mi, int rate)
{
int group = rate / MCS_GROUP_RATES;
rate %= MCS_GROUP_RATES;
- return mi->groups[group].rates[rate].prob_ewma;
+ return mi->groups[group].rates[rate].prob_avg;
}
static int
@@ -1115,7 +1119,7 @@ minstrel_ht_get_max_amsdu_len(struct minstrel_ht_sta *mi)
unsigned int duration;
/* Disable A-MSDU if max_prob_rate is bad */
- if (mi->groups[group].rates[rate].prob_ewma < MINSTREL_FRAC(50, 100))
+ if (mi->groups[group].rates[rate].prob_avg < MINSTREL_FRAC(50, 100))
return 1;
duration = g->duration[rate];
@@ -1138,7 +1142,7 @@ minstrel_ht_get_max_amsdu_len(struct minstrel_ht_sta *mi)
* data packet size
*/
if (duration > MCS_DURATION(1, 0, 260) ||
- (minstrel_ht_get_prob_ewma(mi, mi->max_tp_rate[0]) <
+ (minstrel_ht_get_prob_avg(mi, mi->max_tp_rate[0]) <
MINSTREL_FRAC(75, 100)))
return 3200;
@@ -1243,7 +1247,7 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi)
* rate, to avoid wasting airtime.
*/
sample_dur = minstrel_get_duration(sample_idx);
- if (mrs->prob_ewma > MINSTREL_FRAC(95, 100) ||
+ if (mrs->prob_avg > MINSTREL_FRAC(95, 100) ||
minstrel_get_duration(mi->max_prob_rate) * 3 < sample_dur)
return -1;
@@ -1666,7 +1670,8 @@ minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
mp->has_mrr = true;
mp->hw = hw;
- mp->update_interval = 100;
+ mp->update_interval = HZ / 10;
+ mp->new_avg = true;
#ifdef CONFIG_MAC80211_DEBUGFS
mp->fixed_rate_idx = (u32) -1;
@@ -1674,6 +1679,8 @@ minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
&mp->fixed_rate_idx);
debugfs_create_u32("sample_switch", S_IRUGO | S_IWUSR, debugfsdir,
&mp->sample_switch);
+ debugfs_create_bool("new_avg", S_IRUGO | S_IWUSR, debugfsdir,
+ &mp->new_avg);
#endif
minstrel_ht_init_cck_rates(mp);
@@ -1698,7 +1705,7 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta)
i = mi->max_tp_rate[0] / MCS_GROUP_RATES;
j = mi->max_tp_rate[0] % MCS_GROUP_RATES;
- prob = mi->groups[i].rates[j].prob_ewma;
+ prob = mi->groups[i].rates[j].prob_avg;
/* convert tp_avg from pkt per second in kbps */
tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10;
diff --git a/net/mac80211/rc80211_minstrel_ht.h b/net/mac80211/rc80211_minstrel_ht.h
index f938701e7ab7..53ea3c29debf 100644
--- a/net/mac80211/rc80211_minstrel_ht.h
+++ b/net/mac80211/rc80211_minstrel_ht.h
@@ -119,6 +119,6 @@ struct minstrel_ht_sta_priv {
void minstrel_ht_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir);
int minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate,
- int prob_ewma);
+ int prob_avg);
#endif
diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c
index 5a6e9f3edc04..bebb71917742 100644
--- a/net/mac80211/rc80211_minstrel_ht_debugfs.c
+++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c
@@ -98,8 +98,8 @@ minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p)
p += sprintf(p, "%6u ", tx_time);
tp_max = minstrel_ht_get_tp_avg(mi, i, j, MINSTREL_FRAC(100, 100));
- tp_avg = minstrel_ht_get_tp_avg(mi, i, j, mrs->prob_ewma);
- eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000);
+ tp_avg = minstrel_ht_get_tp_avg(mi, i, j, mrs->prob_avg);
+ eprob = MINSTREL_TRUNC(mrs->prob_avg * 1000);
p += sprintf(p, "%4u.%1u %4u.%1u %3u.%1u"
" %3u %3u %-3u "
@@ -243,8 +243,8 @@ minstrel_ht_stats_csv_dump(struct minstrel_ht_sta *mi, int i, char *p)
p += sprintf(p, "%u,", tx_time);
tp_max = minstrel_ht_get_tp_avg(mi, i, j, MINSTREL_FRAC(100, 100));
- tp_avg = minstrel_ht_get_tp_avg(mi, i, j, mrs->prob_ewma);
- eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000);
+ tp_avg = minstrel_ht_get_tp_avg(mi, i, j, mrs->prob_avg);
+ eprob = MINSTREL_TRUNC(mrs->prob_avg * 1000);
p += sprintf(p, "%u.%u,%u.%u,%u.%u,%u,%u,"
"%u,%llu,%llu,",
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index bd11fef2139f..8eafd81e97b4 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -210,6 +210,20 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata,
return NULL;
}
+struct sta_info *sta_info_get_by_addrs(struct ieee80211_local *local,
+ const u8 *sta_addr, const u8 *vif_addr)
+{
+ struct rhlist_head *tmp;
+ struct sta_info *sta;
+
+ for_each_sta_info(local, sta_addr, sta, tmp) {
+ if (ether_addr_equal(vif_addr, sta->sdata->vif.addr))
+ return sta;
+ }
+
+ return NULL;
+}
+
struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
int idx)
{
@@ -396,6 +410,9 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
skb_queue_head_init(&sta->ps_tx_buf[i]);
skb_queue_head_init(&sta->tx_filtered[i]);
sta->airtime[i].deficit = sta->airtime_weight;
+ atomic_set(&sta->airtime[i].aql_tx_pending, 0);
+ sta->airtime[i].aql_limit_low = local->aql_txq_limit_low[i];
+ sta->airtime[i].aql_limit_high = local->aql_txq_limit_high[i];
}
for (i = 0; i < IEEE80211_NUM_TIDS; i++)
@@ -1893,6 +1910,41 @@ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid,
}
EXPORT_SYMBOL(ieee80211_sta_register_airtime);
+void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local,
+ struct sta_info *sta, u8 ac,
+ u16 tx_airtime, bool tx_completed)
+{
+ int tx_pending;
+
+ if (!tx_completed) {
+ if (sta)
+ atomic_add(tx_airtime,
+ &sta->airtime[ac].aql_tx_pending);
+
+ atomic_add(tx_airtime, &local->aql_total_pending_airtime);
+ return;
+ }
+
+ if (sta) {
+ tx_pending = atomic_sub_return(tx_airtime,
+ &sta->airtime[ac].aql_tx_pending);
+ if (WARN_ONCE(tx_pending < 0,
+ "STA %pM AC %d txq pending airtime underflow: %u, %u",
+ sta->addr, ac, tx_pending, tx_airtime))
+ atomic_cmpxchg(&sta->airtime[ac].aql_tx_pending,
+ tx_pending, 0);
+ }
+
+ tx_pending = atomic_sub_return(tx_airtime,
+ &local->aql_total_pending_airtime);
+ if (WARN_ONCE(tx_pending < 0,
+ "Device %s AC %d pending airtime underflow: %u, %u",
+ wiphy_name(local->hw.wiphy), ac, tx_pending,
+ tx_airtime))
+ atomic_cmpxchg(&local->aql_total_pending_airtime,
+ tx_pending, 0);
+}
+
int sta_info_move_state(struct sta_info *sta,
enum ieee80211_sta_state new_state)
{
@@ -2457,7 +2509,8 @@ unsigned long ieee80211_sta_last_active(struct sta_info *sta)
{
struct ieee80211_sta_rx_stats *stats = sta_get_last_rx_stats(sta);
- if (time_after(stats->last_rx, sta->status_stats.last_ack))
+ if (!sta->status_stats.last_ack ||
+ time_after(stats->last_rx, sta->status_stats.last_ack))
return stats->last_rx;
return sta->status_stats.last_ack;
}
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 369c2dddce52..ad5d8a4ae56d 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -127,13 +127,21 @@ enum ieee80211_agg_stop_reason {
/* Debugfs flags to enable/disable use of RX/TX airtime in scheduler */
#define AIRTIME_USE_TX BIT(0)
#define AIRTIME_USE_RX BIT(1)
+#define AIRTIME_USE_AQL BIT(2)
struct airtime_info {
u64 rx_airtime;
u64 tx_airtime;
s64 deficit;
+ atomic_t aql_tx_pending; /* Estimated airtime for frames pending */
+ u32 aql_limit_low;
+ u32 aql_limit_high;
};
+void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local,
+ struct sta_info *sta, u8 ac,
+ u16 tx_airtime, bool tx_completed);
+
struct sta_info;
/**
@@ -725,6 +733,10 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata,
const u8 *addr);
+/* user must hold sta_mtx or be in RCU critical section */
+struct sta_info *sta_info_get_by_addrs(struct ieee80211_local *local,
+ const u8 *sta_addr, const u8 *vif_addr);
+
#define for_each_sta_info(local, _addr, _sta, _tmp) \
rhl_for_each_entry_rcu(_sta, _tmp, \
sta_info_hash_lookup(local, _addr), hash_node)
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index ab8ba5835ca0..b720feaf9a74 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -670,12 +670,26 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local,
struct sk_buff *skb, bool dropped)
{
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ u16 tx_time_est = ieee80211_info_get_tx_time_est(info);
struct ieee80211_hdr *hdr = (void *)skb->data;
bool acked = info->flags & IEEE80211_TX_STAT_ACK;
if (dropped)
acked = false;
+ if (tx_time_est) {
+ struct sta_info *sta;
+
+ rcu_read_lock();
+
+ sta = sta_info_get_by_addrs(local, hdr->addr1, hdr->addr2);
+ ieee80211_sta_update_pending_airtime(local, sta,
+ skb_get_queue_mapping(skb),
+ tx_time_est,
+ true);
+ rcu_read_unlock();
+ }
+
if (info->flags & IEEE80211_TX_INTFL_MLME_CONN_TX) {
struct ieee80211_sub_if_data *sdata;
@@ -877,6 +891,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
struct ieee80211_bar *bar;
int shift = 0;
int tid = IEEE80211_NUM_TIDS;
+ u16 tx_time_est;
rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
@@ -986,6 +1001,17 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
ieee80211_sta_register_airtime(&sta->sta, tid,
info->status.tx_time, 0);
+ if ((tx_time_est = ieee80211_info_get_tx_time_est(info)) > 0) {
+ /* Do this here to avoid the expensive lookup of the sta
+ * in ieee80211_report_used_skb().
+ */
+ ieee80211_sta_update_pending_airtime(local, sta,
+ skb_get_queue_mapping(skb),
+ tx_time_est,
+ true);
+ ieee80211_info_set_tx_time_est(info, 0);
+ }
+
if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) {
if (info->flags & IEEE80211_TX_STAT_ACK) {
if (sta->status_stats.lost_packets)
@@ -1030,7 +1056,8 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
I802_DEBUG_INC(local->dot11FailedCount);
}
- if (ieee80211_is_nullfunc(fc) && ieee80211_has_pm(fc) &&
+ if ((ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)) &&
+ ieee80211_has_pm(fc) &&
ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) &&
!(info->flags & IEEE80211_TX_CTL_INJECTED) &&
local->ps_sdata && !(local->scanning)) {
@@ -1073,19 +1100,13 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
.skb = skb,
.info = IEEE80211_SKB_CB(skb),
};
- struct rhlist_head *tmp;
struct sta_info *sta;
rcu_read_lock();
- for_each_sta_info(local, hdr->addr1, sta, tmp) {
- /* skip wrong virtual interface */
- if (!ether_addr_equal(hdr->addr2, sta->sdata->vif.addr))
- continue;
-
+ sta = sta_info_get_by_addrs(local, hdr->addr1, hdr->addr2);
+ if (sta)
status.sta = &sta->sta;
- break;
- }
__ieee80211_tx_status(hw, &status);
rcu_read_unlock();
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 1fa422782905..b696b9136f4c 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1617,7 +1617,7 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local,
static bool ieee80211_tx_frags(struct ieee80211_local *local,
struct ieee80211_vif *vif,
- struct ieee80211_sta *sta,
+ struct sta_info *sta,
struct sk_buff_head *skbs,
bool txpending)
{
@@ -1679,7 +1679,7 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
info->control.vif = vif;
- control.sta = sta;
+ control.sta = sta ? &sta->sta : NULL;
__skb_unlink(skb, skbs);
drv_tx(local, &control, skb);
@@ -1698,7 +1698,6 @@ static bool __ieee80211_tx(struct ieee80211_local *local,
struct ieee80211_tx_info *info;
struct ieee80211_sub_if_data *sdata;
struct ieee80211_vif *vif;
- struct ieee80211_sta *pubsta;
struct sk_buff *skb;
bool result = true;
__le16 fc;
@@ -1713,11 +1712,6 @@ static bool __ieee80211_tx(struct ieee80211_local *local,
if (sta && !sta->uploaded)
sta = NULL;
- if (sta)
- pubsta = &sta->sta;
- else
- pubsta = NULL;
-
switch (sdata->vif.type) {
case NL80211_IFTYPE_MONITOR:
if (sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) {
@@ -1744,8 +1738,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local,
break;
}
- result = ieee80211_tx_frags(local, vif, pubsta, skbs,
- txpending);
+ result = ieee80211_tx_frags(local, vif, sta, skbs, txpending);
ieee80211_tpt_led_trig_tx(local, fc, led_len);
@@ -2277,6 +2270,9 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
* isn't always enough to find the interface to use; for proper
* VLAN/WDS support we will need a different mechanism (which
* likely isn't going to be monitor interfaces).
+ *
+ * This is necessary, for example, for old hostapd versions that
+ * don't use nl80211-based management TX/RX.
*/
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
@@ -2424,6 +2420,33 @@ static int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata,
return 0;
}
+static int ieee80211_store_ack_skb(struct ieee80211_local *local,
+ struct sk_buff *skb,
+ u32 *info_flags)
+{
+ struct sk_buff *ack_skb = skb_clone_sk(skb);
+ u16 info_id = 0;
+
+ if (ack_skb) {
+ unsigned long flags;
+ int id;
+
+ spin_lock_irqsave(&local->ack_status_lock, flags);
+ id = idr_alloc(&local->ack_status_frames, ack_skb,
+ 1, 0x40, GFP_ATOMIC);
+ spin_unlock_irqrestore(&local->ack_status_lock, flags);
+
+ if (id >= 0) {
+ info_id = id;
+ *info_flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
+ } else {
+ kfree_skb(ack_skb);
+ }
+ }
+
+ return info_id;
+}
+
/**
* ieee80211_build_hdr - build 802.11 header in the given frame
* @sdata: virtual interface to build the header for
@@ -2717,26 +2740,8 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
}
if (unlikely(!multicast && skb->sk &&
- skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) {
- struct sk_buff *ack_skb = skb_clone_sk(skb);
-
- if (ack_skb) {
- unsigned long flags;
- int id;
-
- spin_lock_irqsave(&local->ack_status_lock, flags);
- id = idr_alloc(&local->ack_status_frames, ack_skb,
- 1, 0x10000, GFP_ATOMIC);
- spin_unlock_irqrestore(&local->ack_status_lock, flags);
-
- if (id >= 0) {
- info_id = id;
- info_flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
- } else {
- kfree_skb(ack_skb);
- }
- }
- }
+ skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS))
+ info_id = ieee80211_store_ack_skb(local, skb, &info_flags);
/*
* If the skb is shared we need to obtain our own copy.
@@ -3529,7 +3534,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
struct ieee80211_sub_if_data, u.ap);
__skb_queue_tail(&tx.skbs, skb);
- ieee80211_tx_frags(local, &sdata->vif, &sta->sta, &tx.skbs, false);
+ ieee80211_tx_frags(local, &sdata->vif, sta, &tx.skbs, false);
return true;
}
@@ -3549,6 +3554,9 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
WARN_ON_ONCE(softirq_count() == 0);
+ if (!ieee80211_txq_airtime_check(hw, txq))
+ return NULL;
+
begin:
spin_lock_bh(&fq->lock);
@@ -3659,6 +3667,21 @@ begin:
}
IEEE80211_SKB_CB(skb)->control.vif = vif;
+
+ if (local->airtime_flags & AIRTIME_USE_AQL) {
+ u32 airtime;
+
+ airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta,
+ skb->len);
+ if (airtime) {
+ airtime = ieee80211_info_set_tx_time_est(info, airtime);
+ ieee80211_sta_update_pending_airtime(local, tx.sta,
+ txq->ac,
+ airtime,
+ false);
+ }
+ }
+
return skb;
out:
@@ -3672,7 +3695,8 @@ struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
{
struct ieee80211_local *local = hw_to_local(hw);
struct ieee80211_txq *ret = NULL;
- struct txq_info *txqi = NULL;
+ struct txq_info *txqi = NULL, *head = NULL;
+ bool found_eligible_txq = false;
spin_lock_bh(&local->active_txq_lock[ac]);
@@ -3683,13 +3707,30 @@ struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
if (!txqi)
goto out;
+ if (txqi == head) {
+ if (!found_eligible_txq)
+ goto out;
+ else
+ found_eligible_txq = false;
+ }
+
+ if (!head)
+ head = txqi;
+
if (txqi->txq.sta) {
struct sta_info *sta = container_of(txqi->txq.sta,
- struct sta_info, sta);
+ struct sta_info, sta);
+ bool aql_check = ieee80211_txq_airtime_check(hw, &txqi->txq);
+ s64 deficit = sta->airtime[txqi->txq.ac].deficit;
+
+ if (aql_check)
+ found_eligible_txq = true;
- if (sta->airtime[txqi->txq.ac].deficit < 0) {
+ if (deficit < 0)
sta->airtime[txqi->txq.ac].deficit +=
sta->airtime_weight;
+
+ if (deficit < 0 || !aql_check) {
list_move_tail(&txqi->schedule_order,
&local->active_txqs[txqi->txq.ac]);
goto begin;
@@ -3743,6 +3784,33 @@ void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
}
EXPORT_SYMBOL(__ieee80211_schedule_txq);
+bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw,
+ struct ieee80211_txq *txq)
+{
+ struct sta_info *sta;
+ struct ieee80211_local *local = hw_to_local(hw);
+
+ if (!(local->airtime_flags & AIRTIME_USE_AQL))
+ return true;
+
+ if (!txq->sta)
+ return true;
+
+ sta = container_of(txq->sta, struct sta_info, sta);
+ if (atomic_read(&sta->airtime[txq->ac].aql_tx_pending) <
+ sta->airtime[txq->ac].aql_limit_low)
+ return true;
+
+ if (atomic_read(&local->aql_total_pending_airtime) <
+ local->aql_threshold &&
+ atomic_read(&sta->airtime[txq->ac].aql_tx_pending) <
+ sta->airtime[txq->ac].aql_limit_high)
+ return true;
+
+ return false;
+}
+EXPORT_SYMBOL(ieee80211_txq_airtime_check);
+
bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
struct ieee80211_txq *txq)
{
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 4fc075b612fe..5e9b2eb24349 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -120,7 +120,8 @@ obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o
# flow table infrastructure
obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o
-nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o
+nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o \
+ nf_flow_table_offload.o
obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 5d5bdf450091..78f046ec506f 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -536,6 +536,26 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state,
}
EXPORT_SYMBOL(nf_hook_slow);
+void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state,
+ const struct nf_hook_entries *e)
+{
+ struct sk_buff *skb, *next;
+ struct list_head sublist;
+ int ret;
+
+ INIT_LIST_HEAD(&sublist);
+
+ list_for_each_entry_safe(skb, next, head, list) {
+ skb_list_del_init(skb);
+ ret = nf_hook_slow(skb, state, e, 0);
+ if (ret == 1)
+ list_add_tail(&skb->list, &sublist);
+ }
+ /* Put passed packets back on main list */
+ list_splice(&sublist, head);
+}
+EXPORT_SYMBOL(nf_hook_slow_list);
+
/* This needs to be compiled in any case to avoid dependencies between the
* nfnetlink_queue code and nf_conntrack.
*/
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 063df74b4647..1abd6f0dc227 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -192,7 +192,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
}
#ifndef IP_SET_BITMAP_STORED_TIMEOUT
-static inline bool
+static bool
mtype_is_filled(const struct mtype_elem *x)
{
return true;
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index 11ff9d4a7006..abe8f77d7d23 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -55,7 +55,7 @@ struct bitmap_ip_adt_elem {
u16 id;
};
-static inline u32
+static u32
ip_to_id(const struct bitmap_ip *m, u32 ip)
{
return ((ip & ip_set_hostmask(m->netmask)) - m->first_ip) / m->hosts;
@@ -63,33 +63,33 @@ ip_to_id(const struct bitmap_ip *m, u32 ip)
/* Common functions */
-static inline int
+static int
bitmap_ip_do_test(const struct bitmap_ip_adt_elem *e,
struct bitmap_ip *map, size_t dsize)
{
return !!test_bit(e->id, map->members);
}
-static inline int
+static int
bitmap_ip_gc_test(u16 id, const struct bitmap_ip *map, size_t dsize)
{
return !!test_bit(id, map->members);
}
-static inline int
+static int
bitmap_ip_do_add(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map,
u32 flags, size_t dsize)
{
return !!test_bit(e->id, map->members);
}
-static inline int
+static int
bitmap_ip_do_del(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map)
{
return !test_and_clear_bit(e->id, map->members);
}
-static inline int
+static int
bitmap_ip_do_list(struct sk_buff *skb, const struct bitmap_ip *map, u32 id,
size_t dsize)
{
@@ -97,7 +97,7 @@ bitmap_ip_do_list(struct sk_buff *skb, const struct bitmap_ip *map, u32 id,
htonl(map->first_ip + id * map->hosts));
}
-static inline int
+static int
bitmap_ip_do_head(struct sk_buff *skb, const struct bitmap_ip *map)
{
return nla_put_ipaddr4(skb, IPSET_ATTR_IP, htonl(map->first_ip)) ||
@@ -237,6 +237,18 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
return true;
}
+static u32
+range_to_mask(u32 from, u32 to, u8 *bits)
+{
+ u32 mask = 0xFFFFFFFE;
+
+ *bits = 32;
+ while (--(*bits) > 0 && mask && (to & mask) != from)
+ mask <<= 1;
+
+ return mask;
+}
+
static int
bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
u32 flags)
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 1d4e63326e68..b618713297da 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -65,7 +65,7 @@ struct bitmap_ipmac_elem {
unsigned char filled;
} __aligned(__alignof__(u64));
-static inline u32
+static u32
ip_to_id(const struct bitmap_ipmac *m, u32 ip)
{
return ip - m->first_ip;
@@ -79,7 +79,7 @@ ip_to_id(const struct bitmap_ipmac *m, u32 ip)
/* Common functions */
-static inline int
+static int
bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e,
const struct bitmap_ipmac *map, size_t dsize)
{
@@ -94,7 +94,7 @@ bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e,
return -EAGAIN;
}
-static inline int
+static int
bitmap_ipmac_gc_test(u16 id, const struct bitmap_ipmac *map, size_t dsize)
{
const struct bitmap_ipmac_elem *elem;
@@ -106,13 +106,13 @@ bitmap_ipmac_gc_test(u16 id, const struct bitmap_ipmac *map, size_t dsize)
return elem->filled == MAC_FILLED;
}
-static inline int
+static int
bitmap_ipmac_is_filled(const struct bitmap_ipmac_elem *elem)
{
return elem->filled == MAC_FILLED;
}
-static inline int
+static int
bitmap_ipmac_add_timeout(unsigned long *timeout,
const struct bitmap_ipmac_adt_elem *e,
const struct ip_set_ext *ext, struct ip_set *set,
@@ -139,7 +139,7 @@ bitmap_ipmac_add_timeout(unsigned long *timeout,
return 0;
}
-static inline int
+static int
bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e,
struct bitmap_ipmac *map, u32 flags, size_t dsize)
{
@@ -177,14 +177,14 @@ bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e,
return IPSET_ADD_STORE_PLAIN_TIMEOUT;
}
-static inline int
+static int
bitmap_ipmac_do_del(const struct bitmap_ipmac_adt_elem *e,
struct bitmap_ipmac *map)
{
return !test_and_clear_bit(e->id, map->members);
}
-static inline int
+static int
bitmap_ipmac_do_list(struct sk_buff *skb, const struct bitmap_ipmac *map,
u32 id, size_t dsize)
{
@@ -197,7 +197,7 @@ bitmap_ipmac_do_list(struct sk_buff *skb, const struct bitmap_ipmac *map,
nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, elem->ether));
}
-static inline int
+static int
bitmap_ipmac_do_head(struct sk_buff *skb, const struct bitmap_ipmac *map)
{
return nla_put_ipaddr4(skb, IPSET_ATTR_IP, htonl(map->first_ip)) ||
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 704a0dda1609..23d6095cb196 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -46,7 +46,7 @@ struct bitmap_port_adt_elem {
u16 id;
};
-static inline u16
+static u16
port_to_id(const struct bitmap_port *m, u16 port)
{
return port - m->first_port;
@@ -54,34 +54,34 @@ port_to_id(const struct bitmap_port *m, u16 port)
/* Common functions */
-static inline int
+static int
bitmap_port_do_test(const struct bitmap_port_adt_elem *e,
const struct bitmap_port *map, size_t dsize)
{
return !!test_bit(e->id, map->members);
}
-static inline int
+static int
bitmap_port_gc_test(u16 id, const struct bitmap_port *map, size_t dsize)
{
return !!test_bit(id, map->members);
}
-static inline int
+static int
bitmap_port_do_add(const struct bitmap_port_adt_elem *e,
struct bitmap_port *map, u32 flags, size_t dsize)
{
return !!test_bit(e->id, map->members);
}
-static inline int
+static int
bitmap_port_do_del(const struct bitmap_port_adt_elem *e,
struct bitmap_port *map)
{
return !test_and_clear_bit(e->id, map->members);
}
-static inline int
+static int
bitmap_port_do_list(struct sk_buff *skb, const struct bitmap_port *map, u32 id,
size_t dsize)
{
@@ -89,13 +89,40 @@ bitmap_port_do_list(struct sk_buff *skb, const struct bitmap_port *map, u32 id,
htons(map->first_port + id));
}
-static inline int
+static int
bitmap_port_do_head(struct sk_buff *skb, const struct bitmap_port *map)
{
return nla_put_net16(skb, IPSET_ATTR_PORT, htons(map->first_port)) ||
nla_put_net16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port));
}
+static bool
+ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, __be16 *port)
+{
+ bool ret;
+ u8 proto;
+
+ switch (pf) {
+ case NFPROTO_IPV4:
+ ret = ip_set_get_ip4_port(skb, src, port, &proto);
+ break;
+ case NFPROTO_IPV6:
+ ret = ip_set_get_ip6_port(skb, src, port, &proto);
+ break;
+ default:
+ return false;
+ }
+ if (!ret)
+ return ret;
+ switch (proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ return true;
+ default:
+ return false;
+ }
+}
+
static int
bitmap_port_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index e64d5f9a89dd..169e0a04f814 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -35,7 +35,7 @@ struct ip_set_net {
static unsigned int ip_set_net_id __read_mostly;
-static inline struct ip_set_net *ip_set_pernet(struct net *net)
+static struct ip_set_net *ip_set_pernet(struct net *net)
{
return net_generic(net, ip_set_net_id);
}
@@ -67,13 +67,13 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
* serialized by ip_set_type_mutex.
*/
-static inline void
+static void
ip_set_type_lock(void)
{
mutex_lock(&ip_set_type_mutex);
}
-static inline void
+static void
ip_set_type_unlock(void)
{
mutex_unlock(&ip_set_type_mutex);
@@ -277,7 +277,7 @@ ip_set_free(void *members)
}
EXPORT_SYMBOL_GPL(ip_set_free);
-static inline bool
+static bool
flag_nested(const struct nlattr *nla)
{
return nla->nla_type & NLA_F_NESTED;
@@ -296,7 +296,8 @@ ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr)
if (unlikely(!flag_nested(nla)))
return -IPSET_ERR_PROTOCOL;
- if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL))
+ if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla,
+ ipaddr_policy, NULL))
return -IPSET_ERR_PROTOCOL;
if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV4)))
return -IPSET_ERR_PROTOCOL;
@@ -314,7 +315,8 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
if (unlikely(!flag_nested(nla)))
return -IPSET_ERR_PROTOCOL;
- if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL))
+ if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla,
+ ipaddr_policy, NULL))
return -IPSET_ERR_PROTOCOL;
if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV6)))
return -IPSET_ERR_PROTOCOL;
@@ -325,6 +327,83 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
}
EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6);
+static u32
+ip_set_timeout_get(const unsigned long *timeout)
+{
+ u32 t;
+
+ if (*timeout == IPSET_ELEM_PERMANENT)
+ return 0;
+
+ t = jiffies_to_msecs(*timeout - jiffies) / MSEC_PER_SEC;
+ /* Zero value in userspace means no timeout */
+ return t == 0 ? 1 : t;
+}
+
+static char *
+ip_set_comment_uget(struct nlattr *tb)
+{
+ return nla_data(tb);
+}
+
+/* Called from uadd only, protected by the set spinlock.
+ * The kadt functions don't use the comment extensions in any way.
+ */
+void
+ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,
+ const struct ip_set_ext *ext)
+{
+ struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1);
+ size_t len = ext->comment ? strlen(ext->comment) : 0;
+
+ if (unlikely(c)) {
+ set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
+ kfree_rcu(c, rcu);
+ rcu_assign_pointer(comment->c, NULL);
+ }
+ if (!len)
+ return;
+ if (unlikely(len > IPSET_MAX_COMMENT_SIZE))
+ len = IPSET_MAX_COMMENT_SIZE;
+ c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC);
+ if (unlikely(!c))
+ return;
+ strlcpy(c->str, ext->comment, len + 1);
+ set->ext_size += sizeof(*c) + strlen(c->str) + 1;
+ rcu_assign_pointer(comment->c, c);
+}
+EXPORT_SYMBOL_GPL(ip_set_init_comment);
+
+/* Used only when dumping a set, protected by rcu_read_lock() */
+static int
+ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment)
+{
+ struct ip_set_comment_rcu *c = rcu_dereference(comment->c);
+
+ if (!c)
+ return 0;
+ return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str);
+}
+
+/* Called from uadd/udel, flush or the garbage collectors protected
+ * by the set spinlock.
+ * Called when the set is destroyed and when there can't be any user
+ * of the set data anymore.
+ */
+static void
+ip_set_comment_free(struct ip_set *set, void *ptr)
+{
+ struct ip_set_comment *comment = ptr;
+ struct ip_set_comment_rcu *c;
+
+ c = rcu_dereference_protected(comment->c, 1);
+ if (unlikely(!c))
+ return;
+ set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
+ kfree_rcu(c, rcu);
+ rcu_assign_pointer(comment->c, NULL);
+}
+
typedef void (*destroyer)(struct ip_set *, void *);
/* ipset data extension types, in size order */
@@ -351,12 +430,12 @@ const struct ip_set_ext_type ip_set_extensions[] = {
.flag = IPSET_FLAG_WITH_COMMENT,
.len = sizeof(struct ip_set_comment),
.align = __alignof__(struct ip_set_comment),
- .destroy = (destroyer) ip_set_comment_free,
+ .destroy = ip_set_comment_free,
},
};
EXPORT_SYMBOL_GPL(ip_set_extensions);
-static inline bool
+static bool
add_extension(enum ip_set_ext_id id, u32 flags, struct nlattr *tb[])
{
return ip_set_extensions[id].flag ?
@@ -446,6 +525,46 @@ ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
}
EXPORT_SYMBOL_GPL(ip_set_get_extensions);
+static u64
+ip_set_get_bytes(const struct ip_set_counter *counter)
+{
+ return (u64)atomic64_read(&(counter)->bytes);
+}
+
+static u64
+ip_set_get_packets(const struct ip_set_counter *counter)
+{
+ return (u64)atomic64_read(&(counter)->packets);
+}
+
+static bool
+ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter)
+{
+ return nla_put_net64(skb, IPSET_ATTR_BYTES,
+ cpu_to_be64(ip_set_get_bytes(counter)),
+ IPSET_ATTR_PAD) ||
+ nla_put_net64(skb, IPSET_ATTR_PACKETS,
+ cpu_to_be64(ip_set_get_packets(counter)),
+ IPSET_ATTR_PAD);
+}
+
+static bool
+ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo)
+{
+ /* Send nonzero parameters only */
+ return ((skbinfo->skbmark || skbinfo->skbmarkmask) &&
+ nla_put_net64(skb, IPSET_ATTR_SKBMARK,
+ cpu_to_be64((u64)skbinfo->skbmark << 32 |
+ skbinfo->skbmarkmask),
+ IPSET_ATTR_PAD)) ||
+ (skbinfo->skbprio &&
+ nla_put_net32(skb, IPSET_ATTR_SKBPRIO,
+ cpu_to_be32(skbinfo->skbprio))) ||
+ (skbinfo->skbqueue &&
+ nla_put_net16(skb, IPSET_ATTR_SKBQUEUE,
+ cpu_to_be16(skbinfo->skbqueue)));
+}
+
int
ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set,
const void *e, bool active)
@@ -471,6 +590,55 @@ ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set,
}
EXPORT_SYMBOL_GPL(ip_set_put_extensions);
+static bool
+ip_set_match_counter(u64 counter, u64 match, u8 op)
+{
+ switch (op) {
+ case IPSET_COUNTER_NONE:
+ return true;
+ case IPSET_COUNTER_EQ:
+ return counter == match;
+ case IPSET_COUNTER_NE:
+ return counter != match;
+ case IPSET_COUNTER_LT:
+ return counter < match;
+ case IPSET_COUNTER_GT:
+ return counter > match;
+ }
+ return false;
+}
+
+static void
+ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter)
+{
+ atomic64_add((long long)bytes, &(counter)->bytes);
+}
+
+static void
+ip_set_add_packets(u64 packets, struct ip_set_counter *counter)
+{
+ atomic64_add((long long)packets, &(counter)->packets);
+}
+
+static void
+ip_set_update_counter(struct ip_set_counter *counter,
+ const struct ip_set_ext *ext, u32 flags)
+{
+ if (ext->packets != ULLONG_MAX &&
+ !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) {
+ ip_set_add_bytes(ext->bytes, counter);
+ ip_set_add_packets(ext->packets, counter);
+ }
+}
+
+static void
+ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo,
+ const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
+{
+ mext->skbinfo = *skbinfo;
+}
+
bool
ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext,
struct ip_set_ext *mext, u32 flags, void *data)
@@ -506,7 +674,7 @@ EXPORT_SYMBOL_GPL(ip_set_match_extensions);
* The set behind an index may change by swapping only, from userspace.
*/
-static inline void
+static void
__ip_set_get(struct ip_set *set)
{
write_lock_bh(&ip_set_ref_lock);
@@ -514,7 +682,7 @@ __ip_set_get(struct ip_set *set)
write_unlock_bh(&ip_set_ref_lock);
}
-static inline void
+static void
__ip_set_put(struct ip_set *set)
{
write_lock_bh(&ip_set_ref_lock);
@@ -526,7 +694,7 @@ __ip_set_put(struct ip_set *set)
/* set->ref can be swapped out by ip_set_swap, netlink events (like dump) need
* a separate reference counter
*/
-static inline void
+static void
__ip_set_put_netlink(struct ip_set *set)
{
write_lock_bh(&ip_set_ref_lock);
@@ -541,7 +709,7 @@ __ip_set_put_netlink(struct ip_set *set)
* so it can't be destroyed (or changed) under our foot.
*/
-static inline struct ip_set *
+static struct ip_set *
ip_set_rcu_get(struct net *net, ip_set_id_t index)
{
struct ip_set *set;
@@ -670,7 +838,7 @@ EXPORT_SYMBOL_GPL(ip_set_get_byname);
*
*/
-static inline void
+static void
__ip_set_put_byindex(struct ip_set_net *inst, ip_set_id_t index)
{
struct ip_set *set;
@@ -934,7 +1102,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
/* Without holding any locks, create private part. */
if (attr[IPSET_ATTR_DATA] &&
- nla_parse_nested_deprecated(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], set->type->create_policy, NULL)) {
+ nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA],
+ set->type->create_policy, NULL)) {
ret = -IPSET_ERR_PROTOCOL;
goto put_out;
}
@@ -1252,6 +1421,30 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb,
#define DUMP_TYPE(arg) (((u32)(arg)) & 0x0000FFFF)
#define DUMP_FLAGS(arg) (((u32)(arg)) >> 16)
+int
+ip_set_put_flags(struct sk_buff *skb, struct ip_set *set)
+{
+ u32 cadt_flags = 0;
+
+ if (SET_WITH_TIMEOUT(set))
+ if (unlikely(nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
+ htonl(set->timeout))))
+ return -EMSGSIZE;
+ if (SET_WITH_COUNTER(set))
+ cadt_flags |= IPSET_FLAG_WITH_COUNTERS;
+ if (SET_WITH_COMMENT(set))
+ cadt_flags |= IPSET_FLAG_WITH_COMMENT;
+ if (SET_WITH_SKBINFO(set))
+ cadt_flags |= IPSET_FLAG_WITH_SKBINFO;
+ if (SET_WITH_FORCEADD(set))
+ cadt_flags |= IPSET_FLAG_WITH_FORCEADD;
+
+ if (!cadt_flags)
+ return 0;
+ return nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(cadt_flags));
+}
+EXPORT_SYMBOL_GPL(ip_set_put_flags);
+
static int
ip_set_dump_done(struct netlink_callback *cb)
{
@@ -1281,6 +1474,14 @@ dump_attrs(struct nlmsghdr *nlh)
}
}
+static const struct nla_policy
+ip_set_dump_policy[IPSET_ATTR_CMD_MAX + 1] = {
+ [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 },
+ [IPSET_ATTR_SETNAME] = { .type = NLA_NUL_STRING,
+ .len = IPSET_MAXNAMELEN - 1 },
+ [IPSET_ATTR_FLAGS] = { .type = NLA_U32 },
+};
+
static int
dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
{
@@ -1292,9 +1493,9 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
ip_set_id_t index;
int ret;
- ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, attr,
- nlh->nlmsg_len - min_len,
- ip_set_setname_policy, NULL);
+ ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, attr,
+ nlh->nlmsg_len - min_len,
+ ip_set_dump_policy, NULL);
if (ret)
return ret;
@@ -1543,9 +1744,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
memcpy(&errmsg->msg, nlh, nlh->nlmsg_len);
cmdattr = (void *)&errmsg->msg + min_len;
- ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, cmdattr,
- nlh->nlmsg_len - min_len,
- ip_set_adt_policy, NULL);
+ ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, cmdattr,
+ nlh->nlmsg_len - min_len, ip_set_adt_policy,
+ NULL);
if (ret) {
nlmsg_free(skb2);
@@ -1596,7 +1797,9 @@ static int ip_set_ad(struct net *net, struct sock *ctnl,
use_lineno = !!attr[IPSET_ATTR_LINENO];
if (attr[IPSET_ATTR_DATA]) {
- if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL))
+ if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX,
+ attr[IPSET_ATTR_DATA],
+ set->type->adt_policy, NULL))
return -IPSET_ERR_PROTOCOL;
ret = call_ad(ctnl, skb, set, tb, adt, flags,
use_lineno);
@@ -1606,7 +1809,8 @@ static int ip_set_ad(struct net *net, struct sock *ctnl,
nla_for_each_nested(nla, attr[IPSET_ATTR_ADT], nla_rem) {
if (nla_type(nla) != IPSET_ATTR_DATA ||
!flag_nested(nla) ||
- nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, nla, set->type->adt_policy, NULL))
+ nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla,
+ set->type->adt_policy, NULL))
return -IPSET_ERR_PROTOCOL;
ret = call_ad(ctnl, skb, set, tb, adt,
flags, use_lineno);
@@ -1655,7 +1859,8 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb,
if (!set)
return -ENOENT;
- if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL))
+ if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA],
+ set->type->adt_policy, NULL))
return -IPSET_ERR_PROTOCOL;
rcu_read_lock_bh();
@@ -1961,7 +2166,7 @@ static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = {
[IPSET_CMD_LIST] = {
.call = ip_set_dump,
.attr_count = IPSET_ATTR_CMD_MAX,
- .policy = ip_set_setname_policy,
+ .policy = ip_set_dump_policy,
},
[IPSET_CMD_SAVE] = {
.call = ip_set_dump,
@@ -2069,8 +2274,9 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
}
req_version->version = IPSET_PROTOCOL;
- ret = copy_to_user(user, req_version,
- sizeof(struct ip_set_req_version));
+ if (copy_to_user(user, req_version,
+ sizeof(struct ip_set_req_version)))
+ ret = -EFAULT;
goto done;
}
case IP_SET_OP_GET_BYNAME: {
@@ -2129,7 +2335,8 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
} /* end of switch(op) */
copy:
- ret = copy_to_user(user, data, copylen);
+ if (copy_to_user(user, data, copylen))
+ ret = -EFAULT;
done:
vfree(data);
diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c
index 2b8f959574b4..36615eb3eae1 100644
--- a/net/netfilter/ipset/ip_set_getport.c
+++ b/net/netfilter/ipset/ip_set_getport.c
@@ -148,31 +148,3 @@ ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
}
EXPORT_SYMBOL_GPL(ip_set_get_ip6_port);
#endif
-
-bool
-ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, __be16 *port)
-{
- bool ret;
- u8 proto;
-
- switch (pf) {
- case NFPROTO_IPV4:
- ret = ip_set_get_ip4_port(skb, src, port, &proto);
- break;
- case NFPROTO_IPV6:
- ret = ip_set_get_ip6_port(skb, src, port, &proto);
- break;
- default:
- return false;
- }
- if (!ret)
- return ret;
- switch (proto) {
- case IPPROTO_TCP:
- case IPPROTO_UDP:
- return true;
- default:
- return false;
- }
-}
-EXPORT_SYMBOL_GPL(ip_set_get_ip_port);
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index d098d87bc331..7480ce55b5c8 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -39,7 +39,7 @@
#ifdef IP_SET_HASH_WITH_MULTI
#define AHASH_MAX(h) ((h)->ahash_max)
-static inline u8
+static u8
tune_ahash_max(u8 curr, u32 multi)
{
u32 n;
@@ -909,7 +909,7 @@ out:
return ret;
}
-static inline int
+static int
mtype_data_match(struct mtype_elem *data, const struct ip_set_ext *ext,
struct ip_set_ext *mext, struct ip_set *set, u32 flags)
{
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index f4432d9fcad0..5d6d68eaf6a9 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -44,7 +44,7 @@ struct hash_ip4_elem {
/* Common functions */
-static inline bool
+static bool
hash_ip4_data_equal(const struct hash_ip4_elem *e1,
const struct hash_ip4_elem *e2,
u32 *multi)
@@ -63,7 +63,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ip4_data_next(struct hash_ip4_elem *next, const struct hash_ip4_elem *e)
{
next->ip = e->ip;
@@ -171,7 +171,7 @@ struct hash_ip6_elem {
/* Common functions */
-static inline bool
+static bool
hash_ip6_data_equal(const struct hash_ip6_elem *ip1,
const struct hash_ip6_elem *ip2,
u32 *multi)
@@ -179,7 +179,7 @@ hash_ip6_data_equal(const struct hash_ip6_elem *ip1,
return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6);
}
-static inline void
+static void
hash_ip6_netmask(union nf_inet_addr *ip, u8 prefix)
{
ip6_netmask(ip, prefix);
@@ -196,7 +196,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ip6_data_next(struct hash_ip6_elem *next, const struct hash_ip6_elem *e)
{
}
diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c
index 24d8f4df4230..eceb7bc4a93a 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmac.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmac.c
@@ -47,7 +47,7 @@ struct hash_ipmac4_elem {
/* Common functions */
-static inline bool
+static bool
hash_ipmac4_data_equal(const struct hash_ipmac4_elem *e1,
const struct hash_ipmac4_elem *e2,
u32 *multi)
@@ -67,7 +67,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ipmac4_data_next(struct hash_ipmac4_elem *next,
const struct hash_ipmac4_elem *e)
{
@@ -154,7 +154,7 @@ struct hash_ipmac6_elem {
/* Common functions */
-static inline bool
+static bool
hash_ipmac6_data_equal(const struct hash_ipmac6_elem *e1,
const struct hash_ipmac6_elem *e2,
u32 *multi)
@@ -175,7 +175,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ipmac6_data_next(struct hash_ipmac6_elem *next,
const struct hash_ipmac6_elem *e)
{
@@ -209,7 +209,7 @@ hash_ipmac6_kadt(struct ip_set *set, const struct sk_buff *skb,
(skb_mac_header(skb) + ETH_HLEN) > skb->data)
return -EINVAL;
- if (opt->flags & IPSET_DIM_ONE_SRC)
+ if (opt->flags & IPSET_DIM_TWO_SRC)
ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
else
ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
index 7a1734aad0c5..aba1df617d6e 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmark.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -42,7 +42,7 @@ struct hash_ipmark4_elem {
/* Common functions */
-static inline bool
+static bool
hash_ipmark4_data_equal(const struct hash_ipmark4_elem *ip1,
const struct hash_ipmark4_elem *ip2,
u32 *multi)
@@ -64,7 +64,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ipmark4_data_next(struct hash_ipmark4_elem *next,
const struct hash_ipmark4_elem *d)
{
@@ -165,7 +165,7 @@ struct hash_ipmark6_elem {
/* Common functions */
-static inline bool
+static bool
hash_ipmark6_data_equal(const struct hash_ipmark6_elem *ip1,
const struct hash_ipmark6_elem *ip2,
u32 *multi)
@@ -187,7 +187,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ipmark6_data_next(struct hash_ipmark6_elem *next,
const struct hash_ipmark6_elem *d)
{
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 32e240658334..1ff228717e29 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -47,7 +47,7 @@ struct hash_ipport4_elem {
/* Common functions */
-static inline bool
+static bool
hash_ipport4_data_equal(const struct hash_ipport4_elem *ip1,
const struct hash_ipport4_elem *ip2,
u32 *multi)
@@ -71,7 +71,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ipport4_data_next(struct hash_ipport4_elem *next,
const struct hash_ipport4_elem *d)
{
@@ -202,7 +202,7 @@ struct hash_ipport6_elem {
/* Common functions */
-static inline bool
+static bool
hash_ipport6_data_equal(const struct hash_ipport6_elem *ip1,
const struct hash_ipport6_elem *ip2,
u32 *multi)
@@ -226,7 +226,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ipport6_data_next(struct hash_ipport6_elem *next,
const struct hash_ipport6_elem *d)
{
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index 15d419353179..fa88afd812fa 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -46,7 +46,7 @@ struct hash_ipportip4_elem {
u8 padding;
};
-static inline bool
+static bool
hash_ipportip4_data_equal(const struct hash_ipportip4_elem *ip1,
const struct hash_ipportip4_elem *ip2,
u32 *multi)
@@ -72,7 +72,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ipportip4_data_next(struct hash_ipportip4_elem *next,
const struct hash_ipportip4_elem *d)
{
@@ -210,7 +210,7 @@ struct hash_ipportip6_elem {
/* Common functions */
-static inline bool
+static bool
hash_ipportip6_data_equal(const struct hash_ipportip6_elem *ip1,
const struct hash_ipportip6_elem *ip2,
u32 *multi)
@@ -236,7 +236,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ipportip6_data_next(struct hash_ipportip6_elem *next,
const struct hash_ipportip6_elem *d)
{
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 7a4d7afd4121..eef6ecfcb409 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -59,7 +59,7 @@ struct hash_ipportnet4_elem {
/* Common functions */
-static inline bool
+static bool
hash_ipportnet4_data_equal(const struct hash_ipportnet4_elem *ip1,
const struct hash_ipportnet4_elem *ip2,
u32 *multi)
@@ -71,25 +71,25 @@ hash_ipportnet4_data_equal(const struct hash_ipportnet4_elem *ip1,
ip1->proto == ip2->proto;
}
-static inline int
+static int
hash_ipportnet4_do_data_match(const struct hash_ipportnet4_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_ipportnet4_data_set_flags(struct hash_ipportnet4_elem *elem, u32 flags)
{
elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
}
-static inline void
+static void
hash_ipportnet4_data_reset_flags(struct hash_ipportnet4_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_ipportnet4_data_netmask(struct hash_ipportnet4_elem *elem, u8 cidr)
{
elem->ip2 &= ip_set_netmask(cidr);
@@ -116,7 +116,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ipportnet4_data_next(struct hash_ipportnet4_elem *next,
const struct hash_ipportnet4_elem *d)
{
@@ -308,7 +308,7 @@ struct hash_ipportnet6_elem {
/* Common functions */
-static inline bool
+static bool
hash_ipportnet6_data_equal(const struct hash_ipportnet6_elem *ip1,
const struct hash_ipportnet6_elem *ip2,
u32 *multi)
@@ -320,25 +320,25 @@ hash_ipportnet6_data_equal(const struct hash_ipportnet6_elem *ip1,
ip1->proto == ip2->proto;
}
-static inline int
+static int
hash_ipportnet6_do_data_match(const struct hash_ipportnet6_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_ipportnet6_data_set_flags(struct hash_ipportnet6_elem *elem, u32 flags)
{
elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
}
-static inline void
+static void
hash_ipportnet6_data_reset_flags(struct hash_ipportnet6_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_ipportnet6_data_netmask(struct hash_ipportnet6_elem *elem, u8 cidr)
{
ip6_netmask(&elem->ip2, cidr);
@@ -365,7 +365,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_ipportnet6_data_next(struct hash_ipportnet6_elem *next,
const struct hash_ipportnet6_elem *d)
{
diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c
index d94c585d33c5..0b61593165ef 100644
--- a/net/netfilter/ipset/ip_set_hash_mac.c
+++ b/net/netfilter/ipset/ip_set_hash_mac.c
@@ -37,7 +37,7 @@ struct hash_mac4_elem {
/* Common functions */
-static inline bool
+static bool
hash_mac4_data_equal(const struct hash_mac4_elem *e1,
const struct hash_mac4_elem *e2,
u32 *multi)
@@ -45,7 +45,7 @@ hash_mac4_data_equal(const struct hash_mac4_elem *e1,
return ether_addr_equal(e1->ether, e2->ether);
}
-static inline bool
+static bool
hash_mac4_data_list(struct sk_buff *skb, const struct hash_mac4_elem *e)
{
if (nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, e->ether))
@@ -56,7 +56,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_mac4_data_next(struct hash_mac4_elem *next,
const struct hash_mac4_elem *e)
{
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index c259cbc3ef45..136cf0781d3a 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -47,7 +47,7 @@ struct hash_net4_elem {
/* Common functions */
-static inline bool
+static bool
hash_net4_data_equal(const struct hash_net4_elem *ip1,
const struct hash_net4_elem *ip2,
u32 *multi)
@@ -56,25 +56,25 @@ hash_net4_data_equal(const struct hash_net4_elem *ip1,
ip1->cidr == ip2->cidr;
}
-static inline int
+static int
hash_net4_do_data_match(const struct hash_net4_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_net4_data_set_flags(struct hash_net4_elem *elem, u32 flags)
{
elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
}
-static inline void
+static void
hash_net4_data_reset_flags(struct hash_net4_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_net4_data_netmask(struct hash_net4_elem *elem, u8 cidr)
{
elem->ip &= ip_set_netmask(cidr);
@@ -97,7 +97,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_net4_data_next(struct hash_net4_elem *next,
const struct hash_net4_elem *d)
{
@@ -212,7 +212,7 @@ struct hash_net6_elem {
/* Common functions */
-static inline bool
+static bool
hash_net6_data_equal(const struct hash_net6_elem *ip1,
const struct hash_net6_elem *ip2,
u32 *multi)
@@ -221,25 +221,25 @@ hash_net6_data_equal(const struct hash_net6_elem *ip1,
ip1->cidr == ip2->cidr;
}
-static inline int
+static int
hash_net6_do_data_match(const struct hash_net6_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_net6_data_set_flags(struct hash_net6_elem *elem, u32 flags)
{
elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
}
-static inline void
+static void
hash_net6_data_reset_flags(struct hash_net6_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_net6_data_netmask(struct hash_net6_elem *elem, u8 cidr)
{
ip6_netmask(&elem->ip, cidr);
@@ -262,7 +262,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_net6_data_next(struct hash_net6_elem *next,
const struct hash_net6_elem *d)
{
@@ -368,6 +368,7 @@ static struct ip_set_type hash_net_type __read_mostly = {
[IPSET_ATTR_IP_TO] = { .type = NLA_NESTED },
[IPSET_ATTR_CIDR] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 87b29f971226..be5e95a0d876 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -25,7 +25,8 @@
/* 3 Counters support added */
/* 4 Comments support added */
/* 5 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 6 /* skbinfo support added */
+/* 6 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 7 /* interface wildcard support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -57,12 +58,13 @@ struct hash_netiface4_elem {
u8 cidr;
u8 nomatch;
u8 elem;
+ u8 wildcard;
char iface[IFNAMSIZ];
};
/* Common functions */
-static inline bool
+static bool
hash_netiface4_data_equal(const struct hash_netiface4_elem *ip1,
const struct hash_netiface4_elem *ip2,
u32 *multi)
@@ -71,28 +73,30 @@ hash_netiface4_data_equal(const struct hash_netiface4_elem *ip1,
ip1->cidr == ip2->cidr &&
(++*multi) &&
ip1->physdev == ip2->physdev &&
- strcmp(ip1->iface, ip2->iface) == 0;
+ (ip1->wildcard ?
+ strncmp(ip1->iface, ip2->iface, strlen(ip1->iface)) == 0 :
+ strcmp(ip1->iface, ip2->iface) == 0);
}
-static inline int
+static int
hash_netiface4_do_data_match(const struct hash_netiface4_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_netiface4_data_set_flags(struct hash_netiface4_elem *elem, u32 flags)
{
elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
}
-static inline void
+static void
hash_netiface4_data_reset_flags(struct hash_netiface4_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_netiface4_data_netmask(struct hash_netiface4_elem *elem, u8 cidr)
{
elem->ip &= ip_set_netmask(cidr);
@@ -103,7 +107,8 @@ static bool
hash_netiface4_data_list(struct sk_buff *skb,
const struct hash_netiface4_elem *data)
{
- u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0;
+ u32 flags = (data->physdev ? IPSET_FLAG_PHYSDEV : 0) |
+ (data->wildcard ? IPSET_FLAG_IFACE_WILDCARD : 0);
if (data->nomatch)
flags |= IPSET_FLAG_NOMATCH;
@@ -119,7 +124,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_netiface4_data_next(struct hash_netiface4_elem *next,
const struct hash_netiface4_elem *d)
{
@@ -229,6 +234,8 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
e.physdev = 1;
if (cadt_flags & IPSET_FLAG_NOMATCH)
flags |= (IPSET_FLAG_NOMATCH << 16);
+ if (cadt_flags & IPSET_FLAG_IFACE_WILDCARD)
+ e.wildcard = 1;
}
if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) {
e.ip = htonl(ip & ip_set_hostmask(e.cidr));
@@ -280,12 +287,13 @@ struct hash_netiface6_elem {
u8 cidr;
u8 nomatch;
u8 elem;
+ u8 wildcard;
char iface[IFNAMSIZ];
};
/* Common functions */
-static inline bool
+static bool
hash_netiface6_data_equal(const struct hash_netiface6_elem *ip1,
const struct hash_netiface6_elem *ip2,
u32 *multi)
@@ -294,28 +302,30 @@ hash_netiface6_data_equal(const struct hash_netiface6_elem *ip1,
ip1->cidr == ip2->cidr &&
(++*multi) &&
ip1->physdev == ip2->physdev &&
- strcmp(ip1->iface, ip2->iface) == 0;
+ (ip1->wildcard ?
+ strncmp(ip1->iface, ip2->iface, strlen(ip1->iface)) == 0 :
+ strcmp(ip1->iface, ip2->iface) == 0);
}
-static inline int
+static int
hash_netiface6_do_data_match(const struct hash_netiface6_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_netiface6_data_set_flags(struct hash_netiface6_elem *elem, u32 flags)
{
elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
}
-static inline void
+static void
hash_netiface6_data_reset_flags(struct hash_netiface6_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_netiface6_data_netmask(struct hash_netiface6_elem *elem, u8 cidr)
{
ip6_netmask(&elem->ip, cidr);
@@ -326,7 +336,8 @@ static bool
hash_netiface6_data_list(struct sk_buff *skb,
const struct hash_netiface6_elem *data)
{
- u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0;
+ u32 flags = (data->physdev ? IPSET_FLAG_PHYSDEV : 0) |
+ (data->wildcard ? IPSET_FLAG_IFACE_WILDCARD : 0);
if (data->nomatch)
flags |= IPSET_FLAG_NOMATCH;
@@ -342,7 +353,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_netiface6_data_next(struct hash_netiface6_elem *next,
const struct hash_netiface6_elem *d)
{
@@ -440,6 +451,8 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[],
e.physdev = 1;
if (cadt_flags & IPSET_FLAG_NOMATCH)
flags |= (IPSET_FLAG_NOMATCH << 16);
+ if (cadt_flags & IPSET_FLAG_IFACE_WILDCARD)
+ e.wildcard = 1;
}
ret = adtfn(set, &e, &ext, &ext, flags);
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index a3ae69bfee66..da4ef910b12d 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -52,7 +52,7 @@ struct hash_netnet4_elem {
/* Common functions */
-static inline bool
+static bool
hash_netnet4_data_equal(const struct hash_netnet4_elem *ip1,
const struct hash_netnet4_elem *ip2,
u32 *multi)
@@ -61,32 +61,32 @@ hash_netnet4_data_equal(const struct hash_netnet4_elem *ip1,
ip1->ccmp == ip2->ccmp;
}
-static inline int
+static int
hash_netnet4_do_data_match(const struct hash_netnet4_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_netnet4_data_set_flags(struct hash_netnet4_elem *elem, u32 flags)
{
elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
}
-static inline void
+static void
hash_netnet4_data_reset_flags(struct hash_netnet4_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_netnet4_data_reset_elem(struct hash_netnet4_elem *elem,
struct hash_netnet4_elem *orig)
{
elem->ip[1] = orig->ip[1];
}
-static inline void
+static void
hash_netnet4_data_netmask(struct hash_netnet4_elem *elem, u8 cidr, bool inner)
{
if (inner) {
@@ -117,7 +117,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_netnet4_data_next(struct hash_netnet4_elem *next,
const struct hash_netnet4_elem *d)
{
@@ -282,7 +282,7 @@ struct hash_netnet6_elem {
/* Common functions */
-static inline bool
+static bool
hash_netnet6_data_equal(const struct hash_netnet6_elem *ip1,
const struct hash_netnet6_elem *ip2,
u32 *multi)
@@ -292,32 +292,32 @@ hash_netnet6_data_equal(const struct hash_netnet6_elem *ip1,
ip1->ccmp == ip2->ccmp;
}
-static inline int
+static int
hash_netnet6_do_data_match(const struct hash_netnet6_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_netnet6_data_set_flags(struct hash_netnet6_elem *elem, u32 flags)
{
elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
}
-static inline void
+static void
hash_netnet6_data_reset_flags(struct hash_netnet6_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_netnet6_data_reset_elem(struct hash_netnet6_elem *elem,
struct hash_netnet6_elem *orig)
{
elem->ip[1] = orig->ip[1];
}
-static inline void
+static void
hash_netnet6_data_netmask(struct hash_netnet6_elem *elem, u8 cidr, bool inner)
{
if (inner) {
@@ -348,7 +348,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_netnet6_data_next(struct hash_netnet6_elem *next,
const struct hash_netnet6_elem *d)
{
@@ -476,6 +476,7 @@ static struct ip_set_type hash_netnet_type __read_mostly = {
[IPSET_ATTR_CIDR] = { .type = NLA_U8 },
[IPSET_ATTR_CIDR2] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 799f2272cc65..34448df80fb9 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -57,7 +57,7 @@ struct hash_netport4_elem {
/* Common functions */
-static inline bool
+static bool
hash_netport4_data_equal(const struct hash_netport4_elem *ip1,
const struct hash_netport4_elem *ip2,
u32 *multi)
@@ -68,25 +68,25 @@ hash_netport4_data_equal(const struct hash_netport4_elem *ip1,
ip1->cidr == ip2->cidr;
}
-static inline int
+static int
hash_netport4_do_data_match(const struct hash_netport4_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_netport4_data_set_flags(struct hash_netport4_elem *elem, u32 flags)
{
elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
}
-static inline void
+static void
hash_netport4_data_reset_flags(struct hash_netport4_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_netport4_data_netmask(struct hash_netport4_elem *elem, u8 cidr)
{
elem->ip &= ip_set_netmask(cidr);
@@ -112,7 +112,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_netport4_data_next(struct hash_netport4_elem *next,
const struct hash_netport4_elem *d)
{
@@ -270,7 +270,7 @@ struct hash_netport6_elem {
/* Common functions */
-static inline bool
+static bool
hash_netport6_data_equal(const struct hash_netport6_elem *ip1,
const struct hash_netport6_elem *ip2,
u32 *multi)
@@ -281,25 +281,25 @@ hash_netport6_data_equal(const struct hash_netport6_elem *ip1,
ip1->cidr == ip2->cidr;
}
-static inline int
+static int
hash_netport6_do_data_match(const struct hash_netport6_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_netport6_data_set_flags(struct hash_netport6_elem *elem, u32 flags)
{
elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
}
-static inline void
+static void
hash_netport6_data_reset_flags(struct hash_netport6_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_netport6_data_netmask(struct hash_netport6_elem *elem, u8 cidr)
{
ip6_netmask(&elem->ip, cidr);
@@ -325,7 +325,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_netport6_data_next(struct hash_netport6_elem *next,
const struct hash_netport6_elem *d)
{
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index a82b70e8b9a6..934c1712cba8 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -56,7 +56,7 @@ struct hash_netportnet4_elem {
/* Common functions */
-static inline bool
+static bool
hash_netportnet4_data_equal(const struct hash_netportnet4_elem *ip1,
const struct hash_netportnet4_elem *ip2,
u32 *multi)
@@ -67,32 +67,32 @@ hash_netportnet4_data_equal(const struct hash_netportnet4_elem *ip1,
ip1->proto == ip2->proto;
}
-static inline int
+static int
hash_netportnet4_do_data_match(const struct hash_netportnet4_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_netportnet4_data_set_flags(struct hash_netportnet4_elem *elem, u32 flags)
{
elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
}
-static inline void
+static void
hash_netportnet4_data_reset_flags(struct hash_netportnet4_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_netportnet4_data_reset_elem(struct hash_netportnet4_elem *elem,
struct hash_netportnet4_elem *orig)
{
elem->ip[1] = orig->ip[1];
}
-static inline void
+static void
hash_netportnet4_data_netmask(struct hash_netportnet4_elem *elem,
u8 cidr, bool inner)
{
@@ -126,7 +126,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_netportnet4_data_next(struct hash_netportnet4_elem *next,
const struct hash_netportnet4_elem *d)
{
@@ -331,7 +331,7 @@ struct hash_netportnet6_elem {
/* Common functions */
-static inline bool
+static bool
hash_netportnet6_data_equal(const struct hash_netportnet6_elem *ip1,
const struct hash_netportnet6_elem *ip2,
u32 *multi)
@@ -343,32 +343,32 @@ hash_netportnet6_data_equal(const struct hash_netportnet6_elem *ip1,
ip1->proto == ip2->proto;
}
-static inline int
+static int
hash_netportnet6_do_data_match(const struct hash_netportnet6_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
-static inline void
+static void
hash_netportnet6_data_set_flags(struct hash_netportnet6_elem *elem, u32 flags)
{
elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
}
-static inline void
+static void
hash_netportnet6_data_reset_flags(struct hash_netportnet6_elem *elem, u8 *flags)
{
swap(*flags, elem->nomatch);
}
-static inline void
+static void
hash_netportnet6_data_reset_elem(struct hash_netportnet6_elem *elem,
struct hash_netportnet6_elem *orig)
{
elem->ip[1] = orig->ip[1];
}
-static inline void
+static void
hash_netportnet6_data_netmask(struct hash_netportnet6_elem *elem,
u8 cidr, bool inner)
{
@@ -402,7 +402,7 @@ nla_put_failure:
return true;
}
-static inline void
+static void
hash_netportnet6_data_next(struct hash_netportnet6_elem *next,
const struct hash_netportnet6_elem *d)
{
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 67ac50104e6f..cd747c0962fd 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -149,7 +149,7 @@ __list_set_del_rcu(struct rcu_head * rcu)
kfree(e);
}
-static inline void
+static void
list_set_del(struct ip_set *set, struct set_elem *e)
{
struct list_set *map = set->data;
@@ -160,7 +160,7 @@ list_set_del(struct ip_set *set, struct set_elem *e)
call_rcu(&e->rcu, __list_set_del_rcu);
}
-static inline void
+static void
list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old)
{
struct list_set *map = set->data;
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 4515056ef1c2..f9b16f2b2219 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -193,21 +193,29 @@ struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *
mutex_lock(&__ip_vs_app_mutex);
+ /* increase the module use count */
+ if (!ip_vs_use_count_inc()) {
+ err = -ENOENT;
+ goto out_unlock;
+ }
+
list_for_each_entry(a, &ipvs->app_list, a_list) {
if (!strcmp(app->name, a->name)) {
err = -EEXIST;
+ /* decrease the module use count */
+ ip_vs_use_count_dec();
goto out_unlock;
}
}
a = kmemdup(app, sizeof(*app), GFP_KERNEL);
if (!a) {
err = -ENOMEM;
+ /* decrease the module use count */
+ ip_vs_use_count_dec();
goto out_unlock;
}
INIT_LIST_HEAD(&a->incs_list);
list_add(&a->a_list, &ipvs->app_list);
- /* increase the module use count */
- ip_vs_use_count_inc();
out_unlock:
mutex_unlock(&__ip_vs_app_mutex);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 8b80ab794a92..512259f579d7 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -2402,18 +2402,22 @@ estimator_fail:
return -ENOMEM;
}
-static void __net_exit __ip_vs_cleanup(struct net *net)
+static void __net_exit __ip_vs_cleanup_batch(struct list_head *net_list)
{
- struct netns_ipvs *ipvs = net_ipvs(net);
-
- ip_vs_service_net_cleanup(ipvs); /* ip_vs_flush() with locks */
- ip_vs_conn_net_cleanup(ipvs);
- ip_vs_app_net_cleanup(ipvs);
- ip_vs_protocol_net_cleanup(ipvs);
- ip_vs_control_net_cleanup(ipvs);
- ip_vs_estimator_net_cleanup(ipvs);
- IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen);
- net->ipvs = NULL;
+ struct netns_ipvs *ipvs;
+ struct net *net;
+
+ ip_vs_service_nets_cleanup(net_list); /* ip_vs_flush() with locks */
+ list_for_each_entry(net, net_list, exit_list) {
+ ipvs = net_ipvs(net);
+ ip_vs_conn_net_cleanup(ipvs);
+ ip_vs_app_net_cleanup(ipvs);
+ ip_vs_protocol_net_cleanup(ipvs);
+ ip_vs_control_net_cleanup(ipvs);
+ ip_vs_estimator_net_cleanup(ipvs);
+ IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen);
+ net->ipvs = NULL;
+ }
}
static int __net_init __ip_vs_dev_init(struct net *net)
@@ -2429,27 +2433,32 @@ hook_fail:
return ret;
}
-static void __net_exit __ip_vs_dev_cleanup(struct net *net)
+static void __net_exit __ip_vs_dev_cleanup_batch(struct list_head *net_list)
{
- struct netns_ipvs *ipvs = net_ipvs(net);
+ struct netns_ipvs *ipvs;
+ struct net *net;
+
EnterFunction(2);
- nf_unregister_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
- ipvs->enable = 0; /* Disable packet reception */
- smp_wmb();
- ip_vs_sync_net_cleanup(ipvs);
+ list_for_each_entry(net, net_list, exit_list) {
+ ipvs = net_ipvs(net);
+ nf_unregister_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
+ ipvs->enable = 0; /* Disable packet reception */
+ smp_wmb();
+ ip_vs_sync_net_cleanup(ipvs);
+ }
LeaveFunction(2);
}
static struct pernet_operations ipvs_core_ops = {
.init = __ip_vs_init,
- .exit = __ip_vs_cleanup,
+ .exit_batch = __ip_vs_cleanup_batch,
.id = &ip_vs_net_id,
.size = sizeof(struct netns_ipvs),
};
static struct pernet_operations ipvs_core_dev_ops = {
.init = __ip_vs_dev_init,
- .exit = __ip_vs_dev_cleanup,
+ .exit_batch = __ip_vs_dev_cleanup_batch,
};
/*
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 8b48e7ce1c2c..3be7398901e0 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -93,7 +93,6 @@ static bool __ip_vs_addr_is_local_v6(struct net *net,
static void update_defense_level(struct netns_ipvs *ipvs)
{
struct sysinfo i;
- static int old_secure_tcp = 0;
int availmem;
int nomem;
int to_change = -1;
@@ -174,35 +173,35 @@ static void update_defense_level(struct netns_ipvs *ipvs)
spin_lock(&ipvs->securetcp_lock);
switch (ipvs->sysctl_secure_tcp) {
case 0:
- if (old_secure_tcp >= 2)
+ if (ipvs->old_secure_tcp >= 2)
to_change = 0;
break;
case 1:
if (nomem) {
- if (old_secure_tcp < 2)
+ if (ipvs->old_secure_tcp < 2)
to_change = 1;
ipvs->sysctl_secure_tcp = 2;
} else {
- if (old_secure_tcp >= 2)
+ if (ipvs->old_secure_tcp >= 2)
to_change = 0;
}
break;
case 2:
if (nomem) {
- if (old_secure_tcp < 2)
+ if (ipvs->old_secure_tcp < 2)
to_change = 1;
} else {
- if (old_secure_tcp >= 2)
+ if (ipvs->old_secure_tcp >= 2)
to_change = 0;
ipvs->sysctl_secure_tcp = 1;
}
break;
case 3:
- if (old_secure_tcp < 2)
+ if (ipvs->old_secure_tcp < 2)
to_change = 1;
break;
}
- old_secure_tcp = ipvs->sysctl_secure_tcp;
+ ipvs->old_secure_tcp = ipvs->sysctl_secure_tcp;
if (to_change >= 0)
ip_vs_protocol_timeout_change(ipvs,
ipvs->sysctl_secure_tcp > 1);
@@ -1275,7 +1274,8 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
struct ip_vs_service *svc = NULL;
/* increase the module use count */
- ip_vs_use_count_inc();
+ if (!ip_vs_use_count_inc())
+ return -ENOPROTOOPT;
/* Lookup the scheduler by 'u->sched_name' */
if (strcmp(u->sched_name, "none")) {
@@ -1607,14 +1607,20 @@ static int ip_vs_flush(struct netns_ipvs *ipvs, bool cleanup)
/*
* Delete service by {netns} in the service table.
- * Called by __ip_vs_cleanup()
+ * Called by __ip_vs_batch_cleanup()
*/
-void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs)
+void ip_vs_service_nets_cleanup(struct list_head *net_list)
{
+ struct netns_ipvs *ipvs;
+ struct net *net;
+
EnterFunction(2);
/* Check for "full" addressed entries */
mutex_lock(&__ip_vs_mutex);
- ip_vs_flush(ipvs, true);
+ list_for_each_entry(net, net_list, exit_list) {
+ ipvs = net_ipvs(net);
+ ip_vs_flush(ipvs, true);
+ }
mutex_unlock(&__ip_vs_mutex);
LeaveFunction(2);
}
@@ -2435,9 +2441,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
if (copy_from_user(arg, user, len) != 0)
return -EFAULT;
- /* increase the module use count */
- ip_vs_use_count_inc();
-
/* Handle daemons since they have another lock */
if (cmd == IP_VS_SO_SET_STARTDAEMON ||
cmd == IP_VS_SO_SET_STOPDAEMON) {
@@ -2450,13 +2453,13 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
ret = -EINVAL;
if (strscpy(cfg.mcast_ifn, dm->mcast_ifn,
sizeof(cfg.mcast_ifn)) <= 0)
- goto out_dec;
+ return ret;
cfg.syncid = dm->syncid;
ret = start_sync_thread(ipvs, &cfg, dm->state);
} else {
ret = stop_sync_thread(ipvs, dm->state);
}
- goto out_dec;
+ return ret;
}
mutex_lock(&__ip_vs_mutex);
@@ -2551,10 +2554,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
out_unlock:
mutex_unlock(&__ip_vs_mutex);
- out_dec:
- /* decrease the module use count */
- ip_vs_use_count_dec();
-
return ret;
}
diff --git a/net/netfilter/ipvs/ip_vs_ovf.c b/net/netfilter/ipvs/ip_vs_ovf.c
index 78b074cd5464..c03066fdd5ca 100644
--- a/net/netfilter/ipvs/ip_vs_ovf.c
+++ b/net/netfilter/ipvs/ip_vs_ovf.c
@@ -5,7 +5,7 @@
* Authors: Raducu Deaconu <rhadoo_io@yahoo.com>
*
* Scheduler implements "overflow" loadbalancing according to number of active
- * connections , will keep all conections to the node with the highest weight
+ * connections , will keep all connections to the node with the highest weight
* and overflow to the next node if the number of connections exceeds the node's
* weight.
* Note that this scheduler might not be suitable for UDP because it only uses
diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c
index 8e104dff7abc..166c669f0763 100644
--- a/net/netfilter/ipvs/ip_vs_pe.c
+++ b/net/netfilter/ipvs/ip_vs_pe.c
@@ -68,7 +68,8 @@ int register_ip_vs_pe(struct ip_vs_pe *pe)
struct ip_vs_pe *tmp;
/* increase the module use count */
- ip_vs_use_count_inc();
+ if (!ip_vs_use_count_inc())
+ return -ENOENT;
mutex_lock(&ip_vs_pe_mutex);
/* Make sure that the pe with this name doesn't exist
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 2f9d5cd5daee..d4903723be7e 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -179,7 +179,8 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
}
/* increase the module use count */
- ip_vs_use_count_inc();
+ if (!ip_vs_use_count_inc())
+ return -ENOENT;
mutex_lock(&ip_vs_sched_mutex);
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index a4a78c4b06de..8dc892a9dc91 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1762,6 +1762,10 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n",
sizeof(struct ip_vs_sync_conn_v0));
+ /* increase the module use count */
+ if (!ip_vs_use_count_inc())
+ return -ENOPROTOOPT;
+