aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-11-15 11:56:19 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-15 11:56:19 -0800
commit5bbcc0f595fadb4cac0eddc4401035ec0bd95b09 (patch)
tree3b65e490cc36a6c6fecac1fa24d9e0ac9ced4455 /net
parentMerge tag 'mips_4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/jhogan/mips (diff)
parenttcp: highest_sack fix (diff)
downloadlinux-dev-5bbcc0f595fadb4cac0eddc4401035ec0bd95b09.tar.xz
linux-dev-5bbcc0f595fadb4cac0eddc4401035ec0bd95b09.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Highlights: 1) Maintain the TCP retransmit queue using an rbtree, with 1GB windows at 100Gb this really has become necessary. From Eric Dumazet. 2) Multi-program support for cgroup+bpf, from Alexei Starovoitov. 3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew Lunn. 4) Add meter action support to openvswitch, from Andy Zhou. 5) Add a data meta pointer for BPF accessible packets, from Daniel Borkmann. 6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet. 7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli. 8) More work to move the RTNL mutex down, from Florian Westphal. 9) Add 'bpftool' utility, to help with bpf program introspection. From Jakub Kicinski. 10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper Dangaard Brouer. 11) Support 'blocks' of transformations in the packet scheduler which can span multiple network devices, from Jiri Pirko. 12) TC flower offload support in cxgb4, from Kumar Sanghvi. 13) Priority based stream scheduler for SCTP, from Marcelo Ricardo Leitner. 14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg. 15) Add RED qdisc offloadability, and use it in mlxsw driver. From Nogah Frankel. 16) eBPF based device controller for cgroup v2, from Roman Gushchin. 17) Add some fundamental tracepoints for TCP, from Song Liu. 18) Remove garbage collection from ipv6 route layer, this is a significant accomplishment. From Wei Wang. 19) Add multicast route offload support to mlxsw, from Yotam Gigi" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits) tcp: highest_sack fix geneve: fix fill_info when link down bpf: fix lockdep splat net: cdc_ncm: GetNtbFormat endian fix openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start netem: remove unnecessary 64 bit modulus netem: use 64 bit divide by rate tcp: Namespace-ify sysctl_tcp_default_congestion_control net: Protect iterations over net::fib_notifier_ops in fib_seq_sum() ipv6: set all.accept_dad to 0 by default uapi: fix linux/tls.h userspace compilation error usbnet: ipheth: prevent TX queue timeouts when device not ready vhost_net: conditionally enable tx polling uapi: fix linux/rxrpc.h userspace compilation errors net: stmmac: fix LPI transitioning for dwmac4 atm: horizon: Fix irq release error net-sysfs: trigger netlink notification on ifalias change via sysfs openvswitch: Using kfree_rcu() to simplify the code openvswitch: Make local function ovs_nsh_key_attr_size() static openvswitch: Fix return value check in ovs_meter_cmd_features() ...
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c9
-rw-r--r--net/8021q/vlan.h2
-rw-r--r--net/8021q/vlan_netlink.c3
-rw-r--r--net/atm/clip.c4
-rw-r--r--net/atm/lec.c19
-rw-r--r--net/atm/mpc.c11
-rw-r--r--net/ax25/af_ax25.c7
-rw-r--r--net/ax25/ax25_ds_timer.c9
-rw-r--r--net/ax25/ax25_timer.c41
-rw-r--r--net/batman-adv/bat_iv_ogm.c24
-rw-r--r--net/batman-adv/bat_v.c11
-rw-r--r--net/batman-adv/bat_v_elp.c6
-rw-r--r--net/batman-adv/bat_v_ogm.c12
-rw-r--r--net/batman-adv/distributed-arp-table.c4
-rw-r--r--net/batman-adv/gateway_client.c8
-rw-r--r--net/batman-adv/gateway_common.c18
-rw-r--r--net/batman-adv/hard-interface.c14
-rw-r--r--net/batman-adv/icmp_socket.c4
-rw-r--r--net/batman-adv/main.c12
-rw-r--r--net/batman-adv/main.h2
-rw-r--r--net/batman-adv/multicast.c2
-rw-r--r--net/batman-adv/originator.c26
-rw-r--r--net/batman-adv/routing.c6
-rw-r--r--net/batman-adv/send.c6
-rw-r--r--net/batman-adv/soft-interface.c10
-rw-r--r--net/batman-adv/sysfs.c4
-rw-r--r--net/batman-adv/tp_meter.c2
-rw-r--r--net/bluetooth/a2mp.c2
-rw-r--r--net/bluetooth/amp.c4
-rw-r--r--net/bluetooth/ecdh_helper.c228
-rw-r--r--net/bluetooth/ecdh_helper.h9
-rw-r--r--net/bluetooth/hci_conn.c6
-rw-r--r--net/bluetooth/hci_core.c35
-rw-r--r--net/bluetooth/hci_event.c46
-rw-r--r--net/bluetooth/hci_request.c21
-rw-r--r--net/bluetooth/hci_request.h1
-rw-r--r--net/bluetooth/hci_sock.c17
-rw-r--r--net/bluetooth/hci_sysfs.c2
-rw-r--r--net/bluetooth/mgmt.c57
-rw-r--r--net/bluetooth/selftest.c48
-rw-r--r--net/bluetooth/smp.c149
-rw-r--r--net/bpf/test_run.c3
-rw-r--r--net/bridge/Makefile2
-rw-r--r--net/bridge/br.c2
-rw-r--r--net/bridge/br_arp_nd_proxy.c469
-rw-r--r--net/bridge/br_device.c27
-rw-r--r--net/bridge/br_forward.c2
-rw-r--r--net/bridge/br_if.c24
-rw-r--r--net/bridge/br_input.c77
-rw-r--r--net/bridge/br_ioctl.c4
-rw-r--r--net/bridge/br_mdb.c54
-rw-r--r--net/bridge/br_multicast.c141
-rw-r--r--net/bridge/br_netlink.c129
-rw-r--r--net/bridge/br_netlink_tunnel.c14
-rw-r--r--net/bridge/br_private.h40
-rw-r--r--net/bridge/br_private_tunnel.h3
-rw-r--r--net/bridge/br_stp.c6
-rw-r--r--net/bridge/br_stp_if.c4
-rw-r--r--net/bridge/br_stp_timer.c50
-rw-r--r--net/bridge/br_sysfs_if.c22
-rw-r--r--net/bridge/br_vlan.c78
-rw-r--r--net/bridge/netfilter/ebtables.c3
-rw-r--r--net/can/af_can.c4
-rw-r--r--net/can/af_can.h2
-rw-r--r--net/can/proc.c8
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dev.c343
-rw-r--r--net/core/dst.c16
-rw-r--r--net/core/ethtool.c16
-rw-r--r--net/core/fib_notifier.c10
-rw-r--r--net/core/fib_rules.c15
-rw-r--r--net/core/filter.c336
-rw-r--r--net/core/flow_dissector.c130
-rw-r--r--net/core/lwt_bpf.c2
-rw-r--r--net/core/neighbour.c18
-rw-r--r--net/core/net-sysfs.c28
-rw-r--r--net/core/net-traces.c3
-rw-r--r--net/core/net_namespace.c1
-rw-r--r--net/core/pktgen.c16
-rw-r--r--net/core/rtnetlink.c448
-rw-r--r--net/core/skbuff.c57
-rw-r--r--net/core/sock.c35
-rw-r--r--net/dccp/ccids/ccid2.c10
-rw-r--r--net/dccp/ccids/ccid2.h1
-rw-r--r--net/dccp/ccids/ccid3.c11
-rw-r--r--net/dccp/ccids/ccid3.h1
-rw-r--r--net/dccp/ccids/lib/packet_history.c4
-rw-r--r--net/dccp/input.c1
-rw-r--r--net/dccp/options.c2
-rw-r--r--net/dccp/timer.c30
-rw-r--r--net/decnet/af_decnet.c7
-rw-r--r--net/decnet/dn_dev.c12
-rw-r--r--net/decnet/dn_nsp_in.c8
-rw-r--r--net/decnet/dn_nsp_out.c18
-rw-r--r--net/decnet/dn_route.c8
-rw-r--r--net/decnet/dn_table.c1
-rw-r--r--net/dsa/Kconfig4
-rw-r--r--net/dsa/Makefile3
-rw-r--r--net/dsa/dsa.c105
-rw-r--r--net/dsa/dsa2.c909
-rw-r--r--net/dsa/dsa_priv.h71
-rw-r--r--net/dsa/legacy.c85
-rw-r--r--net/dsa/master.c143
-rw-r--r--net/dsa/port.c105
-rw-r--r--net/dsa/slave.c601
-rw-r--r--net/dsa/switch.c2
-rw-r--r--net/dsa/tag_brcm.c90
-rw-r--r--net/dsa/tag_dsa.c28
-rw-r--r--net/dsa/tag_edsa.c28
-rw-r--r--net/dsa/tag_ksz.c13
-rw-r--r--net/dsa/tag_lan9303.c55
-rw-r--r--net/dsa/tag_mtk.c20
-rw-r--r--net/dsa/tag_qca.c22
-rw-r--r--net/dsa/tag_trailer.c13
-rw-r--r--net/hsr/hsr_device.c9
-rw-r--r--net/hsr/hsr_framereg.c6
-rw-r--r--net/hsr/hsr_framereg.h2
-rw-r--r--net/ieee802154/6lowpan/reassembly.c5
-rw-r--r--net/ieee802154/netlink.c6
-rw-r--r--net/ipv4/af_inet.c12
-rw-r--r--net/ipv4/arp.c1
-rw-r--r--net/ipv4/devinet.c43
-rw-r--r--net/ipv4/fib_frontend.c34
-rw-r--r--net/ipv4/fib_semantics.c19
-rw-r--r--net/ipv4/fib_trie.c42
-rw-r--r--net/ipv4/icmp.c20
-rw-r--r--net/ipv4/inet_connection_sock.c57
-rw-r--r--net/ipv4/inet_fragment.c4
-rw-r--r--net/ipv4/inet_timewait_sock.c7
-rw-r--r--net/ipv4/inetpeer.c11
-rw-r--r--net/ipv4/ip_fragment.c5
-rw-r--r--net/ipv4/ip_gre.c88
-rw-r--r--net/ipv4/ip_tunnel.c12
-rw-r--r--net/ipv4/ip_vti.c16
-rw-r--r--net/ipv4/ipip.c7
-rw-r--r--net/ipv4/ipmr.c262
-rw-r--r--net/ipv4/netfilter/arp_tables.c22
-rw-r--r--net/ipv4/netfilter/ip_tables.c23
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c2
-rw-r--r--net/ipv4/netfilter/nf_conntrack_proto_icmp.c28
-rw-r--r--net/ipv4/netfilter/nf_nat_l3proto_ipv4.c3
-rw-r--r--net/ipv4/proc.c1
-rw-r--r--net/ipv4/route.c5
-rw-r--r--net/ipv4/syncookies.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c520
-rw-r--r--net/ipv4/tcp.c167
-rw-r--r--net/ipv4/tcp_cdg.c2
-rw-r--r--net/ipv4/tcp_cong.c76
-rw-r--r--net/ipv4/tcp_fastopen.c160
-rw-r--r--net/ipv4/tcp_input.c597
-rw-r--r--net/ipv4/tcp_ipv4.c69
-rw-r--r--net/ipv4/tcp_metrics.c22
-rw-r--r--net/ipv4/tcp_minisocks.c41
-rw-r--r--net/ipv4/tcp_nv.c47
-rw-r--r--net/ipv4/tcp_output.c324
-rw-r--r--net/ipv4/tcp_recovery.c102
-rw-r--r--net/ipv4/tcp_timer.c77
-rw-r--r--net/ipv4/tcp_vegas.c2
-rw-r--r--net/ipv4/udp.c3
-rw-r--r--net/ipv6/addrconf.c381
-rw-r--r--net/ipv6/addrconf_core.c9
-rw-r--r--net/ipv6/addrlabel.c146
-rw-r--r--net/ipv6/af_inet6.c4
-rw-r--r--net/ipv6/ah6.c1
-rw-r--r--net/ipv6/esp6.c8
-rw-r--r--net/ipv6/exthdrs.c73
-rw-r--r--net/ipv6/exthdrs_core.c5
-rw-r--r--net/ipv6/icmp.c50
-rw-r--r--net/ipv6/ila/ila.h12
-rw-r--r--net/ipv6/ila/ila_common.c104
-rw-r--r--net/ipv6/ila/ila_lwt.c111
-rw-r--r--net/ipv6/ila/ila_xlat.c26
-rw-r--r--net/ipv6/ip6_fib.c667
-rw-r--r--net/ipv6/ip6_gre.c28
-rw-r--r--net/ipv6/ip6_tunnel.c89
-rw-r--r--net/ipv6/ip6_vti.c23
-rw-r--r--net/ipv6/ip6mr.c5
-rw-r--r--net/ipv6/ipv6_sockglue.c12
-rw-r--r--net/ipv6/ndisc.c18
-rw-r--r--net/ipv6/netfilter/ip6_tables.c22
-rw-r--r--net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c24
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c5
-rw-r--r--net/ipv6/netfilter/nf_nat_l3proto_ipv6.c3
-rw-r--r--net/ipv6/output_core.c31
-rw-r--r--net/ipv6/ping.c5
-rw-r--r--net/ipv6/raw.c4
-rw-r--r--net/ipv6/reassembly.c5
-rw-r--r--net/ipv6/route.c940
-rw-r--r--net/ipv6/sit.c40
-rw-r--r--net/ipv6/syncookies.c2
-rw-r--r--net/ipv6/sysctl_net_ipv6.c32
-rw-r--r--net/ipv6/tcp_ipv6.c17
-rw-r--r--net/ipv6/xfrm6_policy.c1
-rw-r--r--net/ipv6/xfrm6_tunnel.c8
-rw-r--r--net/ipx/af_ipx.c1
-rw-r--r--net/kcm/kcmsock.c2
-rw-r--r--net/key/af_key.c2
-rw-r--r--net/l2tp/l2tp_core.c83
-rw-r--r--net/l2tp/l2tp_core.h37
-rw-r--r--net/l2tp/l2tp_debugfs.c4
-rw-r--r--net/l2tp/l2tp_eth.c106
-rw-r--r--net/l2tp/l2tp_ip.c4
-rw-r--r--net/l2tp/l2tp_ip6.c4
-rw-r--r--net/l2tp/l2tp_netlink.c24
-rw-r--r--net/l2tp/l2tp_ppp.c320
-rw-r--r--net/lapb/lapb_iface.c4
-rw-r--r--net/lapb/lapb_timer.c18
-rw-r--r--net/llc/llc_c_ac.c27
-rw-r--r--net/llc/llc_conn.c12
-rw-r--r--net/mac80211/Makefile3
-rw-r--r--net/mac80211/aead_api.c (renamed from net/mac80211/aes_ccm.c)40
-rw-r--r--net/mac80211/aead_api.h27
-rw-r--r--net/mac80211/aes_ccm.h42
-rw-r--r--net/mac80211/aes_gcm.c109
-rw-r--r--net/mac80211/aes_gcm.h38
-rw-r--r--net/mac80211/agg-rx.c4
-rw-r--r--net/mac80211/ht.c12
-rw-r--r--net/mac80211/ieee80211_i.h2
-rw-r--r--net/mac80211/iface.c29
-rw-r--r--net/mac80211/mesh.c3
-rw-r--r--net/mac80211/mesh.h1
-rw-r--r--net/mac80211/mesh_hwmp.c8
-rw-r--r--net/mac80211/mesh_plink.c13
-rw-r--r--net/mac80211/mlme.c33
-rw-r--r--net/mac80211/scan.c37
-rw-r--r--net/mac80211/sta_info.c61
-rw-r--r--net/mac80211/sta_info.h4
-rw-r--r--net/mac80211/tx.c34
-rw-r--r--net/mac80211/util.c25
-rw-r--r--net/mac80211/vht.c10
-rw-r--r--net/mac80211/wpa.c4
-rw-r--r--net/mac802154/llsec.c14
-rw-r--r--net/mpls/Kconfig1
-rw-r--r--net/mpls/af_mpls.c36
-rw-r--r--net/ncsi/ncsi-aen.c15
-rw-r--r--net/ncsi/ncsi-manage.c78
-rw-r--r--net/ncsi/ncsi-rsp.c41
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_gen.h10
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_ip.c2
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_ipmac.c2
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_port.c2
-rw-r--r--net/netfilter/ipset/ip_set_hash_gen.h12
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportnet.c2
-rw-r--r--net/netfilter/ipset/ip_set_list_set.c17
-rw-r--r--net/netfilter/ipset/pfxlen.c395
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c8
-rw-r--r--net/netfilter/nf_conntrack_core.c15
-rw-r--r--net/netfilter/nf_conntrack_h323_asn1.c81
-rw-r--r--net/netfilter/nf_conntrack_netlink.c10
-rw-r--r--net/netfilter/nf_conntrack_proto.c86
-rw-r--r--net/netfilter/nf_conntrack_proto_dccp.c21
-rw-r--r--net/netfilter/nf_conntrack_proto_generic.c1
-rw-r--r--net/netfilter/nf_conntrack_proto_gre.c1
-rw-r--r--net/netfilter/nf_conntrack_proto_sctp.c4
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c62
-rw-r--r--net/netfilter/nf_conntrack_proto_udp.c41
-rw-r--r--net/netfilter/nf_nat_core.c9
-rw-r--r--net/netfilter/nf_tables_api.c195
-rw-r--r--net/netfilter/nft_ct.c39
-rw-r--r--net/netfilter/nft_set_bitmap.c18
-rw-r--r--net/netfilter/nft_set_hash.c41
-rw-r--r--net/netfilter/nft_set_rbtree.c73
-rw-r--r--net/netfilter/x_tables.c21
-rw-r--r--net/netfilter/xt_bpf.c2
-rw-r--r--net/netfilter/xt_connlimit.c55
-rw-r--r--net/netlink/af_netlink.c48
-rw-r--r--net/netlink/af_netlink.h1
-rw-r--r--net/netrom/af_netrom.c6
-rw-r--r--net/netrom/nr_in.c2
-rw-r--r--net/netrom/nr_route.c62
-rw-r--r--net/netrom/nr_timer.c48
-rw-r--r--net/nfc/core.c11
-rw-r--r--net/nfc/digital_core.c1
-rw-r--r--net/nfc/hci/core.c8
-rw-r--r--net/nfc/hci/llc_shdlc.c26
-rw-r--r--net/nfc/llcp_core.c16
-rw-r--r--net/nfc/netlink.c29
-rw-r--r--net/nsh/nsh.c60
-rw-r--r--net/openvswitch/Kconfig1
-rw-r--r--net/openvswitch/Makefile1
-rw-r--r--net/openvswitch/actions.c126
-rw-r--r--net/openvswitch/conntrack.c12
-rw-r--r--net/openvswitch/conntrack.h7
-rw-r--r--net/openvswitch/datapath.c90
-rw-r--r--net/openvswitch/datapath.h39
-rw-r--r--net/openvswitch/dp_notify.c4
-rw-r--r--net/openvswitch/flow.c51
-rw-r--r--net/openvswitch/flow.h7
-rw-r--r--net/openvswitch/flow_netlink.c405
-rw-r--r--net/openvswitch/flow_netlink.h5
-rw-r--r--net/openvswitch/meter.c597
-rw-r--r--net/openvswitch/meter.h54
-rw-r--r--net/openvswitch/vport-netdev.c3
-rw-r--r--net/packet/af_packet.c25
-rw-r--r--net/phonet/af_phonet.c17
-rw-r--r--net/phonet/datagram.c2
-rw-r--r--net/phonet/pep.c2
-rw-r--r--net/phonet/pn_dev.c3
-rw-r--r--net/qrtr/qrtr.c377
-rw-r--r--net/rds/ib.c11
-rw-r--r--net/rds/ib.h2
-rw-r--r--net/rds/ib_rdma.c4
-rw-r--r--net/rose/af_rose.c17
-rw-r--r--net/rose/rose_in.c1
-rw-r--r--net/rose/rose_link.c16
-rw-r--r--net/rose/rose_loopback.c9
-rw-r--r--net/rose/rose_route.c10
-rw-r--r--net/rose/rose_timer.c39
-rw-r--r--net/rxrpc/af_rxrpc.c42
-rw-r--r--net/rxrpc/ar-internal.h1
-rw-r--r--net/rxrpc/call_event.c2
-rw-r--r--net/rxrpc/call_object.c1
-rw-r--r--net/rxrpc/input.c3
-rw-r--r--net/rxrpc/output.c19
-rw-r--r--net/rxrpc/peer_object.c13
-rw-r--r--net/rxrpc/recvmsg.c7
-rw-r--r--net/rxrpc/sendmsg.c108
-rw-r--r--net/sched/Kconfig11
-rw-r--r--net/sched/Makefile1
-rw-r--r--net/sched/act_api.c221
-rw-r--r--net/sched/act_bpf.c4
-rw-r--r--net/sched/act_ife.c153
-rw-r--r--net/sched/act_meta_mark.c2
-rw-r--r--net/sched/act_meta_skbprio.c2
-rw-r--r--net/sched/act_meta_skbtcindex.c2
-rw-r--r--net/sched/act_mirred.c13
-rw-r--r--net/sched/act_vlan.c81
-rw-r--r--net/sched/cls_api.c318
-rw-r--r--net/sched/cls_basic.c38
-rw-r--r--net/sched/cls_bpf.c99
-rw-r--r--net/sched/cls_flow.c14
-rw-r--r--net/sched/cls_flower.c76
-rw-r--r--net/sched/cls_fw.c5
-rw-r--r--net/sched/cls_matchall.c58
-rw-r--r--net/sched/cls_tcindex.c5
-rw-r--r--net/sched/cls_u32.c187
-rw-r--r--net/sched/ematch.c2
-rw-r--r--net/sched/sch_api.c9
-rw-r--r--net/sched/sch_atm.c4
-rw-r--r--net/sched/sch_cbq.c3
-rw-r--r--net/sched/sch_cbs.c373
-rw-r--r--net/sched/sch_drr.c3
-rw-r--r--net/sched/sch_dsmark.c2
-rw-r--r--net/sched/sch_fq_codel.c3
-rw-r--r--net/sched/sch_generic.c70
-rw-r--r--net/sched/sch_hfsc.c5
-rw-r--r--net/sched/sch_htb.c10
-rw-r--r--net/sched/sch_ingress.c49
-rw-r--r--net/sched/sch_mq.c10
-rw-r--r--net/sched/sch_mqprio.c273
-rw-r--r--net/sched/sch_multiq.c3
-rw-r--r--net/sched/sch_netem.c167
-rw-r--r--net/sched/sch_pie.c10
-rw-r--r--net/sched/sch_prio.c3
-rw-r--r--net/sched/sch_qfq.c3
-rw-r--r--net/sched/sch_red.c93
-rw-r--r--net/sched/sch_sfb.c3
-rw-r--r--net/sched/sch_sfq.c13
-rw-r--r--net/sctp/Makefile3
-rw-r--r--net/sctp/associola.c3
-rw-r--r--net/sctp/chunk.c6
-rw-r--r--net/sctp/outqueue.c63
-rw-r--r--net/sctp/protocol.c7
-rw-r--r--net/sctp/sm_sideeffect.c88
-rw-r--r--net/sctp/socket.c179
-rw-r--r--net/sctp/stream.c202
-rw-r--r--net/sctp/stream_sched.c275
-rw-r--r--net/sctp/stream_sched_prio.c347
-rw-r--r--net/sctp/stream_sched_rr.c201
-rw-r--r--net/sctp/transport.c13
-rw-r--r--net/smc/af_smc.c42
-rw-r--r--net/smc/smc_cdc.c7
-rw-r--r--net/smc/smc_cdc.h3
-rw-r--r--net/smc/smc_close.c3
-rw-r--r--net/smc/smc_core.c12
-rw-r--r--net/smc/smc_ib.c26
-rw-r--r--net/smc/smc_tx.c6
-rw-r--r--net/sunrpc/sched.c8
-rw-r--r--net/sunrpc/svc.c2
-rw-r--r--net/sunrpc/svc_xprt.c9
-rw-r--r--net/sunrpc/xprt.c9
-rw-r--r--net/switchdev/switchdev.c2
-rw-r--r--net/tipc/Makefile2
-rw-r--r--net/tipc/bcast.c18
-rw-r--r--net/tipc/core.h5
-rw-r--r--net/tipc/discover.c6
-rw-r--r--net/tipc/group.c871
-rw-r--r--net/tipc/group.h73
-rw-r--r--net/tipc/link.c34
-rw-r--r--net/tipc/monitor.c17
-rw-r--r--net/tipc/msg.c7
-rw-r--r--net/tipc/msg.h128
-rw-r--r--net/tipc/name_table.c176
-rw-r--r--net/tipc/name_table.h28
-rw-r--r--net/tipc/node.c50
-rw-r--r--net/tipc/node.h5
-rw-r--r--net/tipc/server.c121
-rw-r--r--net/tipc/server.h5
-rw-r--r--net/tipc/socket.c845
-rw-r--r--net/tipc/subscr.c6
-rw-r--r--net/tls/tls_main.c96
-rw-r--r--net/tls/tls_sw.c24
-rw-r--r--net/unix/af_unix.c1
-rw-r--r--net/vmw_vsock/Kconfig10
-rw-r--r--net/vmw_vsock/Makefile3
-rw-r--r--net/vmw_vsock/af_vsock.c73
-rw-r--r--net/vmw_vsock/diag.c186
-rw-r--r--net/vmw_vsock/hyperv_transport.c13
-rw-r--r--net/vmw_vsock/virtio_transport.c2
-rw-r--r--net/vmw_vsock/virtio_transport_common.c22
-rw-r--r--net/vmw_vsock/vmci_transport.c35
-rw-r--r--net/vmw_vsock/vmci_transport_notify.c2
-rw-r--r--net/vmw_vsock/vmci_transport_notify_qstate.c2
-rw-r--r--net/wireless/.gitignore3
-rw-r--r--net/wireless/Kconfig58
-rw-r--r--net/wireless/Makefile24
-rw-r--r--net/wireless/certs/sforshee.x509bin0 -> 680 bytes
-rw-r--r--net/wireless/chan.c4
-rw-r--r--net/wireless/core.c2
-rw-r--r--net/wireless/core.h5
-rw-r--r--net/wireless/db.txt17
-rw-r--r--net/wireless/genregdb.awk158
-rw-r--r--net/wireless/nl80211.c199
-rw-r--r--net/wireless/nl80211.h2
-rw-r--r--net/wireless/reg.c452
-rw-r--r--net/wireless/reg.h14
-rw-r--r--net/wireless/regdb.h23
-rw-r--r--net/wireless/sme.c45
-rw-r--r--net/wireless/util.c202
-rw-r--r--net/x25/af_x25.c9
-rw-r--r--net/x25/x25_facilities.c2
-rw-r--r--net/x25/x25_in.c1
-rw-r--r--net/x25/x25_timer.c18
-rw-r--r--net/xfrm/xfrm_policy.c17
-rw-r--r--net/xfrm/xfrm_user.c105
437 files changed, 17158 insertions, 7867 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 4a72ee4e2ae9..8dfdd94e430f 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -138,7 +138,7 @@ int vlan_check_real_dev(struct net_device *real_dev,
return 0;
}
-int register_vlan_dev(struct net_device *dev)
+int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
@@ -174,7 +174,7 @@ int register_vlan_dev(struct net_device *dev)
if (err < 0)
goto out_uninit_mvrp;
- err = netdev_upper_dev_link(real_dev, dev);
+ err = netdev_upper_dev_link(real_dev, dev, extack);
if (err)
goto out_unregister_netdev;
@@ -270,7 +270,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
vlan->flags = VLAN_FLAG_REORDER_HDR;
new_dev->rtnl_link_ops = &vlan_link_ops;
- err = register_vlan_dev(new_dev);
+ err = register_vlan_dev(new_dev, NULL);
if (err < 0)
goto out_free_newdev;
@@ -328,6 +328,9 @@ static void vlan_transfer_features(struct net_device *dev,
vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid;
#endif
+ vlandev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+ vlandev->priv_flags |= (vlan->real_dev->priv_flags & IFF_XMIT_DST_RELEASE);
+
netdev_update_features(vlandev);
}
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 0e7afdf86127..a8ba51030b75 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -108,7 +108,7 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result);
int vlan_check_real_dev(struct net_device *real_dev,
__be16 protocol, u16 vlan_id);
void vlan_setup(struct net_device *dev);
-int register_vlan_dev(struct net_device *dev);
+int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack);
void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
bool vlan_dev_inherit_address(struct net_device *dev,
struct net_device *real_dev);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 5e831de3103e..6689c0b272a7 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -143,6 +143,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
vlan->vlan_proto = proto;
vlan->vlan_id = nla_get_u16(data[IFLA_VLAN_ID]);
vlan->real_dev = real_dev;
+ dev->priv_flags |= (real_dev->priv_flags & IFF_XMIT_DST_RELEASE);
vlan->flags = VLAN_FLAG_REORDER_HDR;
err = vlan_check_real_dev(real_dev, vlan->vlan_proto, vlan->vlan_id);
@@ -160,7 +161,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
if (err < 0)
return err;
- return register_vlan_dev(dev);
+ return register_vlan_dev(dev, extack);
}
static inline size_t vlan_qos_map_size(unsigned int n)
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 65f706e4344c..d4f6029d5109 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -153,7 +153,7 @@ static int neigh_check_cb(struct neighbour *n)
return 1;
}
-static void idle_timer_check(unsigned long dummy)
+static void idle_timer_check(struct timer_list *unused)
{
write_lock(&arp_tbl.lock);
__neigh_for_each_release(&arp_tbl, neigh_check_cb);
@@ -887,7 +887,7 @@ static int __init atm_clip_init(void)
register_netdevice_notifier(&clip_dev_notifier);
register_inetaddr_notifier(&clip_inet_notifier);
- setup_timer(&idle_timer, idle_timer_check, 0);
+ timer_setup(&idle_timer, idle_timer_check, 0);
#ifdef CONFIG_PROC_FS
{
diff --git a/net/atm/lec.c b/net/atm/lec.c
index a3d93a1bb133..c976196da3ea 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -1232,7 +1232,7 @@ static void lane2_associate_ind(struct net_device *dev, const u8 *mac_addr,
#define LEC_ARP_REFRESH_INTERVAL (3*HZ)
static void lec_arp_check_expire(struct work_struct *work);
-static void lec_arp_expire_arp(unsigned long data);
+static void lec_arp_expire_arp(struct timer_list *t);
/*
* Arp table funcs
@@ -1559,8 +1559,7 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv,
}
ether_addr_copy(to_return->mac_addr, mac_addr);
INIT_HLIST_NODE(&to_return->next);
- setup_timer(&to_return->timer, lec_arp_expire_arp,
- (unsigned long)to_return);
+ timer_setup(&to_return->timer, lec_arp_expire_arp, 0);
to_return->last_used = jiffies;
to_return->priv = priv;
skb_queue_head_init(&to_return->tx_wait);
@@ -1569,11 +1568,11 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv,
}
/* Arp sent timer expired */
-static void lec_arp_expire_arp(unsigned long data)
+static void lec_arp_expire_arp(struct timer_list *t)
{
struct lec_arp_table *entry;
- entry = (struct lec_arp_table *)data;
+ entry = from_timer(entry, t, timer);
pr_debug("\n");
if (entry->status == ESI_ARP_PENDING) {
@@ -1591,10 +1590,10 @@ static void lec_arp_expire_arp(unsigned long data)
}
/* Unknown/unused vcc expire, remove associated entry */
-static void lec_arp_expire_vcc(unsigned long data)
+static void lec_arp_expire_vcc(struct timer_list *t)
{
unsigned long flags;
- struct lec_arp_table *to_remove = (struct lec_arp_table *)data;
+ struct lec_arp_table *to_remove = from_timer(to_remove, t, timer);
struct lec_priv *priv = to_remove->priv;
del_timer(&to_remove->timer);
@@ -1799,7 +1798,7 @@ static struct atm_vcc *lec_arp_resolve(struct lec_priv *priv,
else
send_to_lecd(priv, l_arp_xmt, mac_to_find, NULL, NULL);
entry->timer.expires = jiffies + (1 * HZ);
- entry->timer.function = lec_arp_expire_arp;
+ entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_arp;
add_timer(&entry->timer);
found = priv->mcast_vcc;
}
@@ -1999,7 +1998,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
entry->old_recv_push = old_push;
entry->status = ESI_UNKNOWN;
entry->timer.expires = jiffies + priv->vcc_timeout_period;
- entry->timer.function = lec_arp_expire_vcc;
+ entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_vcc;
hlist_add_head(&entry->next, &priv->lec_no_forward);
add_timer(&entry->timer);
dump_arp_table(priv);
@@ -2083,7 +2082,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
entry->status = ESI_UNKNOWN;
hlist_add_head(&entry->next, &priv->lec_arp_empty_ones);
entry->timer.expires = jiffies + priv->vcc_timeout_period;
- entry->timer.function = lec_arp_expire_vcc;
+ entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_vcc;
add_timer(&entry->timer);
pr_debug("After vcc was added\n");
dump_arp_table(priv);
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 63138c8c2269..e882d8b5db05 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -95,7 +95,7 @@ static netdev_tx_t mpc_send_packet(struct sk_buff *skb,
static int mpoa_event_listener(struct notifier_block *mpoa_notifier,
unsigned long event, void *dev);
static void mpc_timer_refresh(void);
-static void mpc_cache_check(unsigned long checking_time);
+static void mpc_cache_check(struct timer_list *unused);
static struct llc_snap_hdr llc_snap_mpoa_ctrl = {
0xaa, 0xaa, 0x03,
@@ -799,7 +799,6 @@ static int atm_mpoa_mpoad_attach(struct atm_vcc *vcc, int arg)
int err;
if (mpcs == NULL) {
- init_timer(&mpc_timer);
mpc_timer_refresh();
/* This lets us now how our LECs are doing */
@@ -1408,15 +1407,17 @@ static void clean_up(struct k_message *msg, struct mpoa_client *mpc, int action)
msg_to_mpoad(msg, mpc);
}
+static unsigned long checking_time;
+
static void mpc_timer_refresh(void)
{
mpc_timer.expires = jiffies + (MPC_P2 * HZ);
- mpc_timer.data = mpc_timer.expires;
- mpc_timer.function = mpc_cache_check;
+ checking_time = mpc_timer.expires;
+ mpc_timer.function = (TIMER_FUNC_TYPE)mpc_cache_check;
add_timer(&mpc_timer);
}
-static void mpc_cache_check(unsigned long checking_time)
+static void mpc_cache_check(struct timer_list *unused)
{
struct mpoa_client *mpc = mpcs;
static unsigned long previous_resolving_check_time;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index f3f9d18891de..06eac1f50c5e 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -268,9 +268,9 @@ void ax25_destroy_socket(ax25_cb *);
/*
* Handler for deferred kills.
*/
-static void ax25_destroy_timer(unsigned long data)
+static void ax25_destroy_timer(struct timer_list *t)
{
- ax25_cb *ax25=(ax25_cb *)data;
+ ax25_cb *ax25 = from_timer(ax25, t, dtimer);
struct sock *sk;
sk=ax25->sk;
@@ -326,8 +326,7 @@ void ax25_destroy_socket(ax25_cb *ax25)
if (ax25->sk != NULL) {
if (sk_has_allocations(ax25->sk)) {
/* Defer: outstanding buffers */
- setup_timer(&ax25->dtimer, ax25_destroy_timer,
- (unsigned long)ax25);
+ timer_setup(&ax25->dtimer, ax25_destroy_timer, 0);
ax25->dtimer.expires = jiffies + 2 * HZ;
add_timer(&ax25->dtimer);
} else {
diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c
index 5fb2104b7304..e9d11313d45b 100644
--- a/net/ax25/ax25_ds_timer.c
+++ b/net/ax25/ax25_ds_timer.c
@@ -29,7 +29,7 @@
#include <linux/mm.h>
#include <linux/interrupt.h>
-static void ax25_ds_timeout(unsigned long);
+static void ax25_ds_timeout(struct timer_list *);
/*
* Add DAMA slave timeout timer to timer list.
@@ -41,8 +41,7 @@ static void ax25_ds_timeout(unsigned long);
void ax25_ds_setup_timer(ax25_dev *ax25_dev)
{
- setup_timer(&ax25_dev->dama.slave_timer, ax25_ds_timeout,
- (unsigned long)ax25_dev);
+ timer_setup(&ax25_dev->dama.slave_timer, ax25_ds_timeout, 0);
}
void ax25_ds_del_timer(ax25_dev *ax25_dev)
@@ -66,9 +65,9 @@ void ax25_ds_set_timer(ax25_dev *ax25_dev)
* Silently discard all (slave) connections in case our master forgot us...
*/
-static void ax25_ds_timeout(unsigned long arg)
+static void ax25_ds_timeout(struct timer_list *t)
{
- ax25_dev *ax25_dev = (struct ax25_dev *) arg;
+ ax25_dev *ax25_dev = from_timer(ax25_dev, t, dama.slave_timer);
ax25_cb *ax25;
if (ax25_dev == NULL || !ax25_dev->dama.slave)
diff --git a/net/ax25/ax25_timer.c b/net/ax25/ax25_timer.c
index 23a6f38a80bf..c47b7ee1e4da 100644
--- a/net/ax25/ax25_timer.c
+++ b/net/ax25/ax25_timer.c
@@ -33,20 +33,19 @@
#include <linux/mm.h>
#include <linux/interrupt.h>
-static void ax25_heartbeat_expiry(unsigned long);
-static void ax25_t1timer_expiry(unsigned long);
-static void ax25_t2timer_expiry(unsigned long);
-static void ax25_t3timer_expiry(unsigned long);
-static void ax25_idletimer_expiry(unsigned long);
+static void ax25_heartbeat_expiry(struct timer_list *);
+static void ax25_t1timer_expiry(struct timer_list *);
+static void ax25_t2timer_expiry(struct timer_list *);
+static void ax25_t3timer_expiry(struct timer_list *);
+static void ax25_idletimer_expiry(struct timer_list *);
void ax25_setup_timers(ax25_cb *ax25)
{
- setup_timer(&ax25->timer, ax25_heartbeat_expiry, (unsigned long)ax25);
- setup_timer(&ax25->t1timer, ax25_t1timer_expiry, (unsigned long)ax25);
- setup_timer(&ax25->t2timer, ax25_t2timer_expiry, (unsigned long)ax25);
- setup_timer(&ax25->t3timer, ax25_t3timer_expiry, (unsigned long)ax25);
- setup_timer(&ax25->idletimer, ax25_idletimer_expiry,
- (unsigned long)ax25);
+ timer_setup(&ax25->timer, ax25_heartbeat_expiry, 0);
+ timer_setup(&ax25->t1timer, ax25_t1timer_expiry, 0);
+ timer_setup(&ax25->t2timer, ax25_t2timer_expiry, 0);
+ timer_setup(&ax25->t3timer, ax25_t3timer_expiry, 0);
+ timer_setup(&ax25->idletimer, ax25_idletimer_expiry, 0);
}
void ax25_start_heartbeat(ax25_cb *ax25)
@@ -120,10 +119,10 @@ unsigned long ax25_display_timer(struct timer_list *timer)
EXPORT_SYMBOL(ax25_display_timer);
-static void ax25_heartbeat_expiry(unsigned long param)
+static void ax25_heartbeat_expiry(struct timer_list *t)
{
int proto = AX25_PROTO_STD_SIMPLEX;
- ax25_cb *ax25 = (ax25_cb *)param;
+ ax25_cb *ax25 = from_timer(ax25, t, timer);
if (ax25->ax25_dev)
proto = ax25->ax25_dev->values[AX25_VALUES_PROTOCOL];
@@ -145,9 +144,9 @@ static void ax25_heartbeat_expiry(unsigned long param)
}
}
-static void ax25_t1timer_expiry(unsigned long param)
+static void ax25_t1timer_expiry(struct timer_list *t)
{
- ax25_cb *ax25 = (ax25_cb *)param;
+ ax25_cb *ax25 = from_timer(ax25, t, t1timer);
switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) {
case AX25_PROTO_STD_SIMPLEX:
@@ -164,9 +163,9 @@ static void ax25_t1timer_expiry(unsigned long param)
}
}
-static void ax25_t2timer_expiry(unsigned long param)
+static void ax25_t2timer_expiry(struct timer_list *t)
{
- ax25_cb *ax25 = (ax25_cb *)param;
+ ax25_cb *ax25 = from_timer(ax25, t, t2timer);
switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) {
case AX25_PROTO_STD_SIMPLEX:
@@ -183,9 +182,9 @@ static void ax25_t2timer_expiry(unsigned long param)
}
}
-static void ax25_t3timer_expiry(unsigned long param)
+static void ax25_t3timer_expiry(struct timer_list *t)
{
- ax25_cb *ax25 = (ax25_cb *)param;
+ ax25_cb *ax25 = from_timer(ax25, t, t3timer);
switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) {
case AX25_PROTO_STD_SIMPLEX:
@@ -204,9 +203,9 @@ static void ax25_t3timer_expiry(unsigned long param)
}
}
-static void ax25_idletimer_expiry(unsigned long param)
+static void ax25_idletimer_expiry(struct timer_list *t)
{
- ax25_cb *ax25 = (ax25_cb *)param;
+ ax25_cb *ax25 = from_timer(ax25, t, idletimer);
switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) {
case AX25_PROTO_STD_SIMPLEX:
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 83ba5483455a..1b659ab652fb 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -916,8 +916,8 @@ 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))
+ if (hard_iface->if_status == BATADV_IF_NOT_IN_USE ||
+ hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)
return;
/* the interface gets activated here to avoid race conditions between
@@ -1264,7 +1264,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node,
* drops as they can't send and receive at the same time.
*/
tq_iface_penalty = BATADV_TQ_MAX_VALUE;
- if (if_outgoing && (if_incoming == if_outgoing) &&
+ if (if_outgoing && if_incoming == if_outgoing &&
batadv_is_wifi_hardif(if_outgoing))
tq_iface_penalty = batadv_hop_penalty(BATADV_TQ_MAX_VALUE,
bat_priv);
@@ -1369,7 +1369,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr,
ret = BATADV_NEIGH_DUP;
} else {
set_mark = 0;
- if (is_dup && (ret != BATADV_NEIGH_DUP))
+ if (is_dup && ret != BATADV_NEIGH_DUP)
ret = BATADV_ORIG_DUP;
}
@@ -1515,7 +1515,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
/* drop packet if sender is not a direct neighbor and if we
* don't route towards it
*/
- if (!is_single_hop_neigh && (!orig_neigh_router)) {
+ if (!is_single_hop_neigh && !orig_neigh_router) {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"Drop packet: OGM via unknown neighbor!\n");
goto out_neigh;
@@ -1535,7 +1535,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
sameseq = orig_ifinfo->last_real_seqno == ntohl(ogm_packet->seqno);
similar_ttl = (orig_ifinfo->last_ttl - 3) <= ogm_packet->ttl;
- if (is_bidirect && ((dup_status == BATADV_NO_DUP) ||
+ if (is_bidirect && (dup_status == BATADV_NO_DUP ||
(sameseq && similar_ttl))) {
batadv_iv_ogm_orig_update(bat_priv, orig_node,
orig_ifinfo, ethhdr,
@@ -1553,8 +1553,8 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
/* OGMs from secondary interfaces should only scheduled once
* per interface where it has been received, not multiple times
*/
- if ((ogm_packet->ttl <= 2) &&
- (if_incoming != if_outgoing)) {
+ if (ogm_packet->ttl <= 2 &&
+ if_incoming != if_outgoing) {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"Drop packet: OGM from secondary interface and wrong outgoing interface\n");
goto out_neigh;
@@ -1590,7 +1590,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
if_incoming, if_outgoing);
out_neigh:
- if ((orig_neigh_node) && (!is_single_hop_neigh))
+ if (orig_neigh_node && !is_single_hop_neigh)
batadv_orig_node_put(orig_neigh_node);
out:
if (router_ifinfo)
@@ -2523,9 +2523,9 @@ batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv)
tmp_gw_factor *= 100 * 100;
tmp_gw_factor >>= 18;
- if ((tmp_gw_factor > max_gw_factor) ||
- ((tmp_gw_factor == max_gw_factor) &&
- (tq_avg > max_tq))) {
+ if (tmp_gw_factor > max_gw_factor ||
+ (tmp_gw_factor == max_gw_factor &&
+ tq_avg > max_tq)) {
if (curr_gw)
batadv_gw_node_put(curr_gw);
curr_gw = gw_node;
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 4e2724c5b33d..341ceab8338d 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -19,7 +19,6 @@
#include "main.h"
#include <linux/atomic.h>
-#include <linux/bug.h>
#include <linux/cache.h>
#include <linux/errno.h>
#include <linux/if_ether.h>
@@ -623,11 +622,11 @@ static int batadv_v_neigh_cmp(struct batadv_neigh_node *neigh1,
int ret = 0;
ifinfo1 = batadv_neigh_ifinfo_get(neigh1, if_outgoing1);
- if (WARN_ON(!ifinfo1))
+ if (!ifinfo1)
goto err_ifinfo1;
ifinfo2 = batadv_neigh_ifinfo_get(neigh2, if_outgoing2);
- if (WARN_ON(!ifinfo2))
+ if (!ifinfo2)
goto err_ifinfo2;
ret = ifinfo1->bat_v.throughput - ifinfo2->bat_v.throughput;
@@ -649,11 +648,11 @@ static bool batadv_v_neigh_is_sob(struct batadv_neigh_node *neigh1,
bool ret = false;
ifinfo1 = batadv_neigh_ifinfo_get(neigh1, if_outgoing1);
- if (WARN_ON(!ifinfo1))
+ if (!ifinfo1)
goto err_ifinfo1;
ifinfo2 = batadv_neigh_ifinfo_get(neigh2, if_outgoing2);
- if (WARN_ON(!ifinfo2))
+ if (!ifinfo2)
goto err_ifinfo2;
threshold = ifinfo1->bat_v.throughput / 4;
@@ -767,7 +766,7 @@ batadv_v_gw_get_best_gw_node(struct batadv_priv *bat_priv)
if (batadv_v_gw_throughput_get(gw_node, &bw) < 0)
goto next;
- if (curr_gw && (bw <= max_bw))
+ if (curr_gw && bw <= max_bw)
goto next;
if (curr_gw)
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index bd1064d98e16..1de992c58b35 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -134,7 +134,7 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh)
hard_iface->bat_v.flags &= ~BATADV_FULL_DUPLEX;
throughput = link_settings.base.speed;
- if (throughput && (throughput != SPEED_UNKNOWN))
+ if (throughput && throughput != SPEED_UNKNOWN)
return throughput * 10;
}
@@ -263,8 +263,8 @@ static void batadv_v_elp_periodic_work(struct work_struct *work)
goto out;
/* we are in the process of shutting this interface down */
- if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) ||
- (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED))
+ if (hard_iface->if_status == BATADV_IF_NOT_IN_USE ||
+ hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)
goto out;
/* the interface was enabled but may not be ready yet */
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 8be61734fc43..c251445a42a0 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -304,8 +304,8 @@ static u32 batadv_v_forward_penalty(struct batadv_priv *bat_priv,
* due to the store & forward characteristics of WIFI.
* Very low throughput values are the exception.
*/
- if ((throughput > 10) &&
- (if_incoming == if_outgoing) &&
+ if (throughput > 10 &&
+ if_incoming == if_outgoing &&
!(if_incoming->bat_v.flags & BATADV_FULL_DUPLEX))
return throughput / 2;
@@ -455,7 +455,7 @@ static int batadv_v_ogm_metric_update(struct batadv_priv *bat_priv,
/* drop packets with old seqnos, however accept the first packet after
* a host has been rebooted.
*/
- if ((seq_diff < 0) && !protection_started)
+ if (seq_diff < 0 && !protection_started)
goto out;
neigh_node->last_seen = jiffies;
@@ -568,8 +568,8 @@ static bool batadv_v_ogm_route_update(struct batadv_priv *bat_priv,
router_throughput = router_ifinfo->bat_v.throughput;
neigh_throughput = neigh_ifinfo->bat_v.throughput;
- if ((neigh_seq_diff < BATADV_OGM_MAX_ORIGDIFF) &&
- (router_throughput >= neigh_throughput))
+ if (neigh_seq_diff < BATADV_OGM_MAX_ORIGDIFF &&
+ router_throughput >= neigh_throughput)
goto out;
}
@@ -621,7 +621,7 @@ batadv_v_ogm_process_per_outif(struct batadv_priv *bat_priv,
return;
/* only unknown & newer OGMs contain TVLVs we are interested in */
- if ((seqno_age > 0) && (if_outgoing == BATADV_IF_DEFAULT))
+ if (seqno_age > 0 && if_outgoing == BATADV_IF_DEFAULT)
batadv_tvlv_containers_process(bat_priv, true, orig_node,
NULL, NULL,
(unsigned char *)(ogm2 + 1),
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index b6cfa78e9381..760c0de72582 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -492,8 +492,8 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res,
/* this is an hash collision with the temporary selected node. Choose
* the one with the lowest address
*/
- if ((tmp_max == max) && max_orig_node &&
- (batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0))
+ if (tmp_max == max && max_orig_node &&
+ batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0)
goto out;
ret = true;
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index de9955d5224d..10d521f0b17f 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -248,12 +248,12 @@ void batadv_gw_election(struct batadv_priv *bat_priv)
}
}
- if ((curr_gw) && (!next_gw)) {
+ if (curr_gw && !next_gw) {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"Removing selected gateway - no gateway in range\n");
batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_DEL,
NULL);
- } else if ((!curr_gw) && (next_gw)) {
+ } else if (!curr_gw && next_gw) {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"Adding route to gateway %pM (bandwidth: %u.%u/%u.%u MBit, tq: %i)\n",
next_gw->orig_node->orig,
@@ -411,8 +411,8 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv,
goto out;
}
- if ((gw_node->bandwidth_down == ntohl(gateway->bandwidth_down)) &&
- (gw_node->bandwidth_up == ntohl(gateway->bandwidth_up)))
+ if (gw_node->bandwidth_down == ntohl(gateway->bandwidth_down) &&
+ gw_node->bandwidth_up == ntohl(gateway->bandwidth_up))
goto out;
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 33940c5c74a8..2c26039c23fc 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -56,8 +56,8 @@ bool batadv_parse_throughput(struct net_device *net_dev, char *buff,
if (strncasecmp(tmp_ptr, "mbit", 4) == 0)
bw_unit_type = BATADV_BW_UNIT_MBIT;
- if ((strncasecmp(tmp_ptr, "kbit", 4) == 0) ||
- (bw_unit_type == BATADV_BW_UNIT_MBIT))
+ if (strncasecmp(tmp_ptr, "kbit", 4) == 0 ||
+ bw_unit_type == BATADV_BW_UNIT_MBIT)
*tmp_ptr = '\0';
}
@@ -190,7 +190,7 @@ ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff,
if (!up_new)
up_new = 1;
- if ((down_curr == down_new) && (up_curr == up_new))
+ if (down_curr == down_new && up_curr == up_new)
return count;
batadv_gw_reselect(bat_priv);
@@ -224,16 +224,16 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
/* only fetch the tvlv value if the handler wasn't called via the
* CIFNOTFND flag and if there is data to fetch
*/
- if ((flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) ||
- (tvlv_value_len < sizeof(gateway))) {
+ if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND ||
+ tvlv_value_len < sizeof(gateway)) {
gateway.bandwidth_down = 0;
gateway.bandwidth_up = 0;
} else {
gateway_ptr = tvlv_value;
gateway.bandwidth_down = gateway_ptr->bandwidth_down;
gateway.bandwidth_up = gateway_ptr->bandwidth_up;
- if ((gateway.bandwidth_down == 0) ||
- (gateway.bandwidth_up == 0)) {
+ if (gateway.bandwidth_down == 0 ||
+ gateway.bandwidth_up == 0) {
gateway.bandwidth_down = 0;
gateway.bandwidth_up = 0;
}
@@ -242,8 +242,8 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
batadv_gw_node_update(bat_priv, orig, &gateway);
/* restart gateway selection */
- if ((gateway.bandwidth_down != 0) &&
- (atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT))
+ if (gateway.bandwidth_down != 0 &&
+ atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT)
batadv_gw_check_election(bat_priv, orig);
}
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index e348f76ea8c1..4e3d5340ad96 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -504,8 +504,8 @@ static void batadv_check_known_mac_addr(const struct net_device *net_dev)
rcu_read_lock();
list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
- if ((hard_iface->if_status != BATADV_IF_ACTIVE) &&
- (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED))
+ if (hard_iface->if_status != BATADV_IF_ACTIVE &&
+ hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)
continue;
if (hard_iface->net_dev == net_dev)
@@ -568,8 +568,8 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
rcu_read_lock();
list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
- if ((hard_iface->if_status != BATADV_IF_ACTIVE) &&
- (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED))
+ if (hard_iface->if_status != BATADV_IF_ACTIVE &&
+ hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)
continue;
if (hard_iface->soft_iface != soft_iface)
@@ -654,8 +654,8 @@ out:
static void
batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface)
{
- if ((hard_iface->if_status != BATADV_IF_ACTIVE) &&
- (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED))
+ if (hard_iface->if_status != BATADV_IF_ACTIVE &&
+ hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)
return;
hard_iface->if_status = BATADV_IF_INACTIVE;
@@ -738,7 +738,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
bat_priv = netdev_priv(hard_iface->soft_iface);
ret = netdev_master_upper_dev_link(hard_iface->net_dev,
- soft_iface, NULL, NULL);
+ soft_iface, NULL, NULL, NULL);
if (ret)
goto err_dev;
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 8ead292886d1..bded31121d12 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -132,10 +132,10 @@ static ssize_t batadv_socket_read(struct file *file, char __user *buf,
size_t packet_len;
int error;
- if ((file->f_flags & O_NONBLOCK) && (socket_client->queue_len == 0))
+ if ((file->f_flags & O_NONBLOCK) && socket_client->queue_len == 0)
return -EAGAIN;
- if ((!buf) || (count < sizeof(struct batadv_icmp_packet)))
+ if (!buf || count < sizeof(struct batadv_icmp_packet))
return -EINVAL;
if (!access_ok(VERIFY_WRITE, buf, count))
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index fb381fb26a66..4daed7ad46f2 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -73,8 +73,8 @@
* list traversals just rcu-locked
*/
struct list_head batadv_hardif_list;
-static int (*batadv_rx_handler[256])(struct sk_buff *,
- struct batadv_hard_iface *);
+static int (*batadv_rx_handler[256])(struct sk_buff *skb,
+ struct batadv_hard_iface *recv_if);
unsigned char batadv_broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
@@ -540,12 +540,12 @@ batadv_recv_handler_register(u8 packet_type,
int (*recv_handler)(struct sk_buff *,
struct batadv_hard_iface *))
{
- int (*curr)(struct sk_buff *,
- struct batadv_hard_iface *);
+ int (*curr)(struct sk_buff *skb,
+ struct batadv_hard_iface *recv_if);
curr = batadv_rx_handler[packet_type];
- if ((curr != batadv_recv_unhandled_packet) &&
- (curr != batadv_recv_unhandled_unicast_packet))
+ if (curr != batadv_recv_unhandled_packet &&
+ curr != batadv_recv_unhandled_unicast_packet)
return -EBUSY;
batadv_rx_handler[packet_type] = recv_handler;
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 05cc7637c064..edb2f239d04d 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -24,7 +24,7 @@
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2017.3"
+#define BATADV_SOURCE_VERSION "2017.4"
#endif
/* B.A.T.M.A.N. parameters */
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index d327670641ac..e553a8770a89 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -1126,7 +1126,7 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv,
bool orig_initialized;
if (orig_mcast_enabled && tvlv_value &&
- (tvlv_value_len >= sizeof(mcast_flags)))
+ tvlv_value_len >= sizeof(mcast_flags))
mcast_flags = *(u8 *)tvlv_value;
spin_lock_bh(&orig->mcast_handler_lock);
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 8e2a4b205257..2967b86c13da 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -1062,9 +1062,9 @@ batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv,
continue;
/* don't purge if the interface is not (going) down */
- if ((if_outgoing->if_status != BATADV_IF_INACTIVE) &&
- (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) &&
- (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED))
+ if (if_outgoing->if_status != BATADV_IF_INACTIVE &&
+ if_outgoing->if_status != BATADV_IF_NOT_IN_USE &&
+ if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)
continue;
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
@@ -1106,9 +1106,9 @@ batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv,
continue;
/* don't purge if the interface is not (going) down */
- if ((if_outgoing->if_status != BATADV_IF_INACTIVE) &&
- (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) &&
- (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED))
+ if (if_outgoing->if_status != BATADV_IF_INACTIVE &&
+ if_outgoing->if_status != BATADV_IF_NOT_IN_USE &&
+ if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)
continue;
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
@@ -1155,13 +1155,13 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
last_seen = neigh_node->last_seen;
if_incoming = neigh_node->if_incoming;
- if ((batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT)) ||
- (if_incoming->if_status == BATADV_IF_INACTIVE) ||
- (if_incoming->if_status == BATADV_IF_NOT_IN_USE) ||
- (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) {
- if ((if_incoming->if_status == BATADV_IF_INACTIVE) ||
- (if_incoming->if_status == BATADV_IF_NOT_IN_USE) ||
- (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED))
+ if (batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT) ||
+ if_incoming->if_status == BATADV_IF_INACTIVE ||
+ if_incoming->if_status == BATADV_IF_NOT_IN_USE ||
+ if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) {
+ if (if_incoming->if_status == BATADV_IF_INACTIVE ||
+ if_incoming->if_status == BATADV_IF_NOT_IN_USE ||
+ if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"neighbor purge: originator %pM, neighbor: %pM, iface: %s\n",
orig_node->orig, neigh_node->addr,
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index f10e3ff26f9d..40d9bf3e5bfe 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -93,14 +93,14 @@ static void _batadv_update_route(struct batadv_priv *bat_priv,
batadv_orig_ifinfo_put(orig_ifinfo);
/* route deleted */
- if ((curr_router) && (!neigh_node)) {
+ if (curr_router && !neigh_node) {
batadv_dbg(BATADV_DBG_ROUTES, bat_priv,
"Deleting route towards: %pM\n", orig_node->orig);
batadv_tt_global_del_orig(bat_priv, orig_node, -1,
"Deleted route towards originator");
/* route added */
- } else if ((!curr_router) && (neigh_node)) {
+ } else if (!curr_router && neigh_node) {
batadv_dbg(BATADV_DBG_ROUTES, bat_priv,
"Adding route towards: %pM (via %pM)\n",
orig_node->orig, neigh_node->addr);
@@ -381,7 +381,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
/* add record route information if not full */
if ((icmph->msg_type == BATADV_ECHO_REPLY ||
icmph->msg_type == BATADV_ECHO_REQUEST) &&
- (skb->len >= sizeof(struct batadv_icmp_packet_rr))) {
+ skb->len >= sizeof(struct batadv_icmp_packet_rr)) {
if (skb_linearize(skb) < 0)
goto free_skb;
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 054a65e6eb68..7895323fd2a7 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -142,7 +142,7 @@ int batadv_send_unicast_skb(struct sk_buff *skb,
#ifdef CONFIG_BATMAN_ADV_BATMAN_V
hardif_neigh = batadv_hardif_neigh_get(neigh->if_incoming, neigh->addr);
- if ((hardif_neigh) && (ret != NET_XMIT_DROP))
+ if (hardif_neigh && ret != NET_XMIT_DROP)
hardif_neigh->bat_v.last_unicast_tx = jiffies;
if (hardif_neigh)
@@ -615,8 +615,8 @@ batadv_forw_packet_list_steal(struct hlist_head *forw_list,
* we delete only packets belonging to the given interface
*/
if (hard_iface &&
- (forw_packet->if_incoming != hard_iface) &&
- (forw_packet->if_outgoing != hard_iface))
+ forw_packet->if_incoming != hard_iface &&
+ forw_packet->if_outgoing != hard_iface)
continue;
hlist_del(&forw_packet->list);
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 10f7edfb176e..9f673cdfecf8 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -69,8 +69,8 @@ int batadv_skb_head_push(struct sk_buff *skb, unsigned int len)
int result;
/* TODO: We must check if we can release all references to non-payload
- * data using skb_header_release in our skbs to allow skb_cow_header to
- * work optimally. This means that those skbs are not allowed to read
+ * data using __skb_header_release in our skbs to allow skb_cow_header
+ * to work optimally. This means that those skbs are not allowed to read
* or write any data which is before the current position of skb->data
* after that call and thus allow other skbs with the same data buffer
* to write freely in that area.
@@ -160,7 +160,7 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)
static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu)
{
/* check ranges */
- if ((new_mtu < 68) || (new_mtu > batadv_hardif_min_mtu(dev)))
+ if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev))
return -EINVAL;
dev->mtu = new_mtu;
@@ -863,11 +863,13 @@ free_bat_counters:
* batadv_softif_slave_add - Add a slave interface to a batadv_soft_interface
* @dev: batadv_soft_interface used as master interface
* @slave_dev: net_device which should become the slave interface
+ * @extack: extended ACK report struct
*
* Return: 0 if successful or error otherwise.
*/
static int batadv_softif_slave_add(struct net_device *dev,
- struct net_device *slave_dev)
+ struct net_device *slave_dev,
+ struct netlink_ext_ack *extack)
{
struct batadv_hard_iface *hard_iface;
struct net *net = dev_net(dev);
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 0ae8b30e4eaa..aa187fd42475 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -925,8 +925,8 @@ static int batadv_store_mesh_iface_finish(struct net_device *net_dev,
if (hard_iface->if_status == status_tmp)
goto out;
- if ((hard_iface->soft_iface) &&
- (strncmp(hard_iface->soft_iface->name, ifname, IFNAMSIZ) == 0))
+ if (hard_iface->soft_iface &&
+ strncmp(hard_iface->soft_iface->name, ifname, IFNAMSIZ) == 0)
goto out;
if (status_tmp == BATADV_IF_NOT_IN_USE) {
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index bfe8effe9238..4b90033f35a8 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -1206,7 +1206,7 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst,
/* send the ack */
r = batadv_send_skb_to_orig(skb, orig_node, NULL);
- if (unlikely(r < 0) || (r == NET_XMIT_DROP)) {
+ if (unlikely(r < 0) || r == NET_XMIT_DROP) {
ret = BATADV_TP_REASON_DST_UNREACHABLE;
goto out;
}
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index aad994edd3bb..51c2cf2d8923 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -573,7 +573,7 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK,
&mgr->l2cap_conn->hcon->dst);
if (!hcon) {
- BT_ERR("No phys link exist");
+ bt_dev_err(hdev, "no phys link exist");
rsp.status = A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS;
goto clean;
}
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index ebcab5bbadd7..78bec8df8525 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -187,7 +187,7 @@ int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type)
/* Legacy key */
if (conn->key_type < 3) {
- BT_ERR("Legacy key type %d", conn->key_type);
+ bt_dev_err(hdev, "legacy key type %d", conn->key_type);
return -EACCES;
}
@@ -207,7 +207,7 @@ int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type)
/* Derive Generic AMP Link Key (gamp) */
err = hmac_sha256(keybuf, HCI_AMP_LINK_KEY_SIZE, "gamp", 4, gamp_key);
if (err) {
- BT_ERR("Could not derive Generic AMP Key: err %d", err);
+ bt_dev_err(hdev, "could not derive Generic AMP Key: err %d", err);
return err;
}
diff --git a/net/bluetooth/ecdh_helper.c b/net/bluetooth/ecdh_helper.c
index c7b1a9aee579..2155ce802877 100644
--- a/net/bluetooth/ecdh_helper.c
+++ b/net/bluetooth/ecdh_helper.c
@@ -23,7 +23,6 @@
#include "ecdh_helper.h"
#include <linux/scatterlist.h>
-#include <crypto/kpp.h>
#include <crypto/ecdh.h>
struct ecdh_completion {
@@ -50,55 +49,35 @@ static inline void swap_digits(u64 *in, u64 *out, unsigned int ndigits)
out[i] = __swab64(in[ndigits - 1 - i]);
}
-bool compute_ecdh_secret(const u8 public_key[64], const u8 private_key[32],
- u8 secret[32])
+/* compute_ecdh_secret() - function assumes that the private key was
+ * already set.
+ * @tfm: KPP tfm handle allocated with crypto_alloc_kpp().
+ * @public_key: pair's ecc public key.
+ * secret: memory where the ecdh computed shared secret will be saved.
+ *
+ * Return: zero on success; error code in case of error.
+ */
+int compute_ecdh_secret(struct crypto_kpp *tfm, const u8 public_key[64],
+ u8 secret[32])
{
- struct crypto_kpp *tfm;
struct kpp_request *req;
- struct ecdh p;
+ u8 *tmp;
struct ecdh_completion result;
struct scatterlist src, dst;
- u8 *tmp, *buf;
- unsigned int buf_len;
- int err = -ENOMEM;
+ int err;
tmp = kmalloc(64, GFP_KERNEL);
if (!tmp)
- return false;
+ return -ENOMEM;
- tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
- if (IS_ERR(tfm)) {
- pr_err("alg: kpp: Failed to load tfm for kpp: %ld\n",
- PTR_ERR(tfm));
+ req = kpp_request_alloc(tfm, GFP_KERNEL);
+ if (!req) {
+ err = -ENOMEM;
goto free_tmp;
}
- req = kpp_request_alloc(tfm, GFP_KERNEL);
- if (!req)
- goto free_kpp;
-
init_completion(&result.completion);
- /* Security Manager Protocol holds digits in litte-endian order
- * while ECC API expect big-endian data
- */
- swap_digits((u64 *)private_key, (u64 *)tmp, 4);
- p.key = (char *)tmp;
- p.key_size = 32;
- /* Set curve_id */
- p.curve_id = ECC_CURVE_NIST_P256;
- buf_len = crypto_ecdh_key_len(&p);
- buf = kmalloc(buf_len, GFP_KERNEL);
- if (!buf)
- goto free_req;
-
- crypto_ecdh_encode_key(buf, buf_len, &p);
-
- /* Set A private Key */
- err = crypto_kpp_set_secret(tfm, (void *)buf, buf_len);
- if (err)
- goto free_all;
-
swap_digits((u64 *)public_key, (u64 *)tmp, 4); /* x */
swap_digits((u64 *)&public_key[32], (u64 *)&tmp[32], 4); /* y */
@@ -123,104 +102,129 @@ bool compute_ecdh_secret(const u8 public_key[64], const u8 private_key[32],
memcpy(secret, tmp, 32);
free_all:
- kzfree(buf);
-free_req:
kpp_request_free(req);
-free_kpp:
- crypto_free_kpp(tfm);
free_tmp:
- kfree(tmp);
- return (err == 0);
+ kzfree(tmp);
+ return err;
}
-bool generate_ecdh_keys(u8 public_key[64], u8 private_key[32])
+/* set_ecdh_privkey() - set or generate ecc private key.
+ *
+ * Function generates an ecc private key in the crypto subsystem when receiving
+ * a NULL private key or sets the received key when not NULL.
+ *
+ * @tfm: KPP tfm handle allocated with crypto_alloc_kpp().
+ * @private_key: user's ecc private key. When not NULL, the key is expected
+ * in little endian format.
+ *
+ * Return: zero on success; error code in case of error.
+ */
+int set_ecdh_privkey(struct crypto_kpp *tfm, const u8 private_key[32])
+{
+ u8 *buf, *tmp = NULL;
+ unsigned int buf_len;
+ int err;
+ struct ecdh p = {0};
+
+ p.curve_id = ECC_CURVE_NIST_P256;
+
+ if (private_key) {
+ tmp = kmalloc(32, GFP_KERNEL);
+ if (!tmp)
+ return -ENOMEM;
+ swap_digits((u64 *)private_key, (u64 *)tmp, 4);
+ p.key = tmp;
+ p.key_size = 32;
+ }
+
+ buf_len = crypto_ecdh_key_len(&p);
+ buf = kmalloc(buf_len, GFP_KERNEL);
+ if (!buf) {
+ err = -ENOMEM;
+ goto free_tmp;
+ }
+
+ err = crypto_ecdh_encode_key(buf, buf_len, &p);
+ if (err)
+ goto free_all;
+
+ err = crypto_kpp_set_secret(tfm, buf, buf_len);
+ /* fall through */
+free_all:
+ kzfree(buf);
+free_tmp:
+ kzfree(tmp);
+ return err;
+}
+
+/* generate_ecdh_public_key() - function assumes that the private key was
+ * already set.
+ *
+ * @tfm: KPP tfm handle allocated with crypto_alloc_kpp().
+ * @public_key: memory where the computed ecc public key will be saved.
+ *
+ * Return: zero on success; error code in case of error.
+ */
+int generate_ecdh_public_key(struct crypto_kpp *tfm, u8 public_key[64])
{
- struct crypto_kpp *tfm;
struct kpp_request *req;
- struct ecdh p;
+ u8 *tmp;
struct ecdh_completion result;
struct scatterlist dst;
- u8 *tmp, *buf;
- unsigned int buf_len;
- int err = -ENOMEM;
- const unsigned short max_tries = 16;
- unsigned short tries = 0;
+ int err;
tmp = kmalloc(64, GFP_KERNEL);
if (!tmp)
- return false;
+ return -ENOMEM;
- tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
- if (IS_ERR(tfm)) {
- pr_err("alg: kpp: Failed to load tfm for kpp: %ld\n",
- PTR_ERR(tfm));
+ req = kpp_request_alloc(tfm, GFP_KERNEL);
+ if (!req) {
+ err = -ENOMEM;
goto free_tmp;
}
- req = kpp_request_alloc(tfm, GFP_KERNEL);
- if (!req)
- goto free_kpp;
-
init_completion(&result.completion);
+ sg_init_one(&dst, tmp, 64);
+ kpp_request_set_input(req, NULL, 0);
+ kpp_request_set_output(req, &dst, 64);
+ kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+ ecdh_complete, &result);
- /* Set curve_id */
- p.curve_id = ECC_CURVE_NIST_P256;
- p.key_size = 32;
- buf_len = crypto_ecdh_key_len(&p);
- buf = kmalloc(buf_len, GFP_KERNEL);
- if (!buf)
- goto free_req;
-
- do {
- if (tries++ >= max_tries)
- goto free_all;
-
- /* Set private Key */
- p.key = (char *)private_key;
- crypto_ecdh_encode_key(buf, buf_len, &p);
- err = crypto_kpp_set_secret(tfm, buf, buf_len);
- if (err)
- goto free_all;
-
- sg_init_one(&dst, tmp, 64);
- kpp_request_set_input(req, NULL, 0);
- kpp_request_set_output(req, &dst, 64);
- kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
- ecdh_complete, &result);
-
- err = crypto_kpp_generate_public_key(req);
-
- if (err == -EINPROGRESS) {
- wait_for_completion(&result.completion);
- err = result.err;
- }
-
- /* Private key is not valid. Regenerate */
- if (err == -EINVAL)
- continue;
-
- if (err < 0)
- goto free_all;
- else
- break;
-
- } while (true);
-
- /* Keys are handed back in little endian as expected by Security
- * Manager Protocol
+ err = crypto_kpp_generate_public_key(req);
+ if (err == -EINPROGRESS) {
+ wait_for_completion(&result.completion);
+ err = result.err;
+ }
+ if (err < 0)
+ goto free_all;
+
+ /* The public key is handed back in little endian as expected by
+ * the Security Manager Protocol.
*/
swap_digits((u64 *)tmp, (u64 *)public_key, 4); /* x */
swap_digits((u64 *)&tmp[32], (u64 *)&public_key[32], 4); /* y */
- swap_digits((u64 *)private_key, (u64 *)tmp, 4);
- memcpy(private_key, tmp, 32);
free_all:
- kzfree(buf);
-free_req:
kpp_request_free(req);
-free_kpp:
- crypto_free_kpp(tfm);
free_tmp:
kfree(tmp);
- return (err == 0);
+ return err;
+}
+
+/* generate_ecdh_keys() - generate ecc key pair.
+ *
+ * @tfm: KPP tfm handle allocated with crypto_alloc_kpp().
+ * @public_key: memory where the computed ecc public key will be saved.
+ *
+ * Return: zero on success; error code in case of error.
+ */
+int generate_ecdh_keys(struct crypto_kpp *tfm, u8 public_key[64])
+{
+ int err;
+
+ err = set_ecdh_privkey(tfm, NULL);
+ if (err)
+ return err;
+
+ return generate_ecdh_public_key(tfm, public_key);
}
diff --git a/net/bluetooth/ecdh_helper.h b/net/bluetooth/ecdh_helper.h
index 7a423faf76e5..a6f8d03d4aaf 100644
--- a/net/bluetooth/ecdh_helper.h
+++ b/net/bluetooth/ecdh_helper.h
@@ -20,8 +20,11 @@
* COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
* SOFTWARE IS DISCLAIMED.
*/
+#include <crypto/kpp.h>
#include <linux/types.h>
-bool compute_ecdh_secret(const u8 pub_a[64], const u8 priv_b[32],
- u8 secret[32]);
-bool generate_ecdh_keys(u8 public_key[64], u8 private_key[32]);
+int compute_ecdh_secret(struct crypto_kpp *tfm, const u8 pair_public_key[64],
+ u8 secret[32]);
+int set_ecdh_privkey(struct crypto_kpp *tfm, const u8 *private_key);
+int generate_ecdh_public_key(struct crypto_kpp *tfm, u8 public_key[64]);
+int generate_ecdh_keys(struct crypto_kpp *tfm, u8 public_key[64]);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index dc59eae54717..a9682534c377 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -729,8 +729,8 @@ static void create_le_conn_complete(struct hci_dev *hdev, u8 status, u16 opcode)
goto done;
}
- BT_ERR("HCI request failed to create LE connection: status 0x%2.2x",
- status);
+ bt_dev_err(hdev, "request failed to create LE connection: "
+ "status 0x%2.2x", status);
if (!conn)
goto done;
@@ -907,7 +907,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
*/
if (hci_dev_test_flag(hdev, HCI_LE_SCAN) &&
hdev->le_scan_type == LE_SCAN_ACTIVE) {
- skb_queue_purge(&req.cmd_q);
+ hci_req_purge(&req);
hci_conn_del(conn);
return ERR_PTR(-EBUSY);
}
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 6bc679cd3481..40d260f2bea5 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -267,7 +267,7 @@ static int hci_init1_req(struct hci_request *req, unsigned long opt)
amp_init1(req);
break;
default:
- BT_ERR("Unknown device type %d", hdev->dev_type);
+ bt_dev_err(hdev, "Unknown device type %d", hdev->dev_type);
break;
}
@@ -2150,8 +2150,7 @@ static void hci_error_reset(struct work_struct *work)
if (hdev->hw_error)
hdev->hw_error(hdev, hdev->hw_error_code);
else
- BT_ERR("%s hardware error 0x%2.2x", hdev->name,
- hdev->hw_error_code);
+ bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code);
if (hci_dev_do_close(hdev))
return;
@@ -2524,9 +2523,9 @@ static void hci_cmd_timeout(struct work_struct *work)
struct hci_command_hdr *sent = (void *) hdev->sent_cmd->data;
u16 opcode = __le16_to_cpu(sent->opcode);
- BT_ERR("%s command 0x%4.4x tx timeout", hdev->name, opcode);
+ bt_dev_err(hdev, "command 0x%4.4x tx timeout", opcode);
} else {
- BT_ERR("%s command tx timeout", hdev->name);
+ bt_dev_err(hdev, "command tx timeout");
}
atomic_set(&hdev->cmd_cnt, 1);
@@ -2858,7 +2857,7 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev,
params = kzalloc(sizeof(*params), GFP_KERNEL);
if (!params) {
- BT_ERR("Out of memory");
+ bt_dev_err(hdev, "out of memory");
return NULL;
}
@@ -3393,7 +3392,7 @@ static void hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
err = hdev->send(hdev, skb);
if (err < 0) {
- BT_ERR("%s sending frame failed (%d)", hdev->name, err);
+ bt_dev_err(hdev, "sending frame failed (%d)", err);
kfree_skb(skb);
}
}
@@ -3408,7 +3407,7 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen,
skb = hci_prepare_cmd(hdev, opcode, plen, param);
if (!skb) {
- BT_ERR("%s no memory for command", hdev->name);
+ bt_dev_err(hdev, "no memory for command");
return -ENOMEM;
}
@@ -3493,7 +3492,7 @@ static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue,
hci_add_acl_hdr(skb, chan->handle, flags);
break;
default:
- BT_ERR("%s unknown dev_type %d", hdev->name, hdev->dev_type);
+ bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type);
return;
}
@@ -3618,7 +3617,7 @@ static struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type,
break;
default:
cnt = 0;
- BT_ERR("Unknown link type");
+ bt_dev_err(hdev, "unknown link type %d", conn->type);
}
q = cnt / num;
@@ -3635,15 +3634,15 @@ static void hci_link_tx_to(struct hci_dev *hdev, __u8 type)
struct hci_conn_hash *h = &hdev->conn_hash;
struct hci_conn *c;
- BT_ERR("%s link tx timeout", hdev->name);
+ bt_dev_err(hdev, "link tx timeout");
rcu_read_lock();
/* Kill stalled connections */
list_for_each_entry_rcu(c, &h->list, list) {
if (c->type == type && c->sent) {
- BT_ERR("%s killing stalled connection %pMR",
- hdev->name, &c->dst);
+ bt_dev_err(hdev, "killing stalled connection %pMR",
+ &c->dst);
hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM);
}
}
@@ -3724,7 +3723,7 @@ static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type,
break;
default:
cnt = 0;
- BT_ERR("Unknown link type");
+ bt_dev_err(hdev, "unknown link type %d", chan->conn->type);
}
q = cnt / num;
@@ -4066,8 +4065,8 @@ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb)
l2cap_recv_acldata(conn, skb, flags);
return;
} else {
- BT_ERR("%s ACL packet for unknown connection handle %d",
- hdev->name, handle);
+ bt_dev_err(hdev, "ACL packet for unknown connection handle %d",
+ handle);
}
kfree_skb(skb);
@@ -4097,8 +4096,8 @@ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb)
sco_recv_scodata(conn, skb);
return;
} else {
- BT_ERR("%s SCO packet for unknown connection handle %d",
- hdev->name, handle);
+ bt_dev_err(hdev, "SCO packet for unknown connection handle %d",
+ handle);
}
kfree_skb(skb);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0b4dba08a14e..cd3bbb766c24 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1188,7 +1188,8 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
break;
default:
- BT_ERR("Used reserved LE_Scan_Enable param %d", cp->enable);
+ bt_dev_err(hdev, "use of reserved LE_Scan_Enable param %d",
+ cp->enable);
break;
}
@@ -1485,7 +1486,7 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status)
conn = hci_conn_add(hdev, ACL_LINK, &cp->bdaddr,
HCI_ROLE_MASTER);
if (!conn)
- BT_ERR("No memory for new connection");
+ bt_dev_err(hdev, "no memory for new connection");
}
}
@@ -2269,7 +2270,7 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr,
HCI_ROLE_SLAVE);
if (!conn) {
- BT_ERR("No memory for new connection");
+ bt_dev_err(hdev, "no memory for new connection");
hci_dev_unlock(hdev);
return;
}
@@ -2431,7 +2432,7 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
if (!hci_conn_ssp_enabled(conn) &&
test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) {
- BT_INFO("re-auth of legacy device is not possible.");
+ bt_dev_info(hdev, "re-auth of legacy device is not possible.");
} else {
set_bit(HCI_CONN_AUTH, &conn->flags);
conn->sec_level = conn->pending_sec_level;
@@ -2535,8 +2536,7 @@ static void read_enc_key_size_complete(struct hci_dev *hdev, u8 status,
BT_DBG("%s status 0x%02x", hdev->name, status);
if (!skb || skb->len < sizeof(*rp)) {
- BT_ERR("%s invalid HCI Read Encryption Key Size response",
- hdev->name);
+ bt_dev_err(hdev, "invalid read key size response");
return;
}
@@ -2554,8 +2554,8 @@ static void read_enc_key_size_complete(struct hci_dev *hdev, u8 status,
* supported.
*/
if (rp->status) {
- BT_ERR("%s failed to read key size for handle %u", hdev->name,
- handle);
+ bt_dev_err(hdev, "failed to read key size for handle %u",
+ handle);
conn->enc_key_size = HCI_LINK_KEY_SIZE;
} else {
conn->enc_key_size = rp->key_size;
@@ -2664,7 +2664,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
hci_req_add(&req, HCI_OP_READ_ENC_KEY_SIZE, sizeof(cp), &cp);
if (hci_req_run_skb(&req, read_enc_key_size_complete)) {
- BT_ERR("Sending HCI Read Encryption Key Size failed");
+ bt_dev_err(hdev, "sending read key size failed");
conn->enc_key_size = HCI_LINK_KEY_SIZE;
goto notify;
}
@@ -3197,7 +3197,7 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *skb)
int i;
if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_PACKET_BASED) {
- BT_ERR("Wrong event for mode %d", hdev->flow_ctl_mode);
+ bt_dev_err(hdev, "wrong event for mode %d", hdev->flow_ctl_mode);
return;
}
@@ -3249,7 +3249,8 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *skb)
break;
default:
- BT_ERR("Unknown type %d conn %p", conn->type, conn);
+ bt_dev_err(hdev, "unknown type %d conn %p",
+ conn->type, conn);
break;
}
}
@@ -3271,7 +3272,7 @@ static struct hci_conn *__hci_conn_lookup_handle(struct hci_dev *hdev,
return chan->conn;
break;
default:
- BT_ERR("%s unknown dev_type %d", hdev->name, hdev->dev_type);
+ bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type);
break;
}
@@ -3284,7 +3285,7 @@ static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb)
int i;
if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_BLOCK_BASED) {
- BT_ERR("Wrong event for mode %d", hdev->flow_ctl_mode);
+ bt_dev_err(hdev, "wrong event for mode %d", hdev->flow_ctl_mode);
return;
}
@@ -3320,7 +3321,8 @@ static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb)
break;
default:
- BT_ERR("Unknown type %d conn %p", conn->type, conn);
+ bt_dev_err(hdev, "unknown type %d conn %p",
+ conn->type, conn);
break;
}
}
@@ -4479,7 +4481,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
if (!conn) {
conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr, ev->role);
if (!conn) {
- BT_ERR("No memory for new connection");
+ bt_dev_err(hdev, "no memory for new connection");
goto unlock;
}
@@ -4749,8 +4751,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
case LE_ADV_SCAN_RSP:
break;
default:
- BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x",
- type);
+ bt_dev_err_ratelimited(hdev, "unknown advertising packet "
+ "type: 0x%02x", type);
return;
}
@@ -4769,8 +4771,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
/* Adjust for actual length */
if (len != real_len) {
- BT_ERR_RATELIMITED("%s advertising data length corrected",
- hdev->name);
+ bt_dev_err_ratelimited(hdev, "advertising data len corrected");
len = real_len;
}
@@ -5192,7 +5193,7 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
return false;
if (skb->len < sizeof(*hdr)) {
- BT_ERR("Too short HCI event");
+ bt_dev_err(hdev, "too short HCI event");
return false;
}
@@ -5206,12 +5207,13 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
}
if (hdr->evt != HCI_EV_CMD_COMPLETE) {
- BT_DBG("Last event is not cmd complete (0x%2.2x)", hdr->evt);
+ bt_dev_err(hdev, "last event is not cmd complete (0x%2.2x)",
+ hdr->evt);
return false;
}
if (skb->len < sizeof(*ev)) {
- BT_ERR("Too short cmd_complete event");
+ bt_dev_err(hdev, "too short cmd_complete event");
return false;
}
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index b73ac149de34..abc0f3224dd1 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -41,6 +41,11 @@ void hci_req_init(struct hci_request *req, struct hci_dev *hdev)
req->err = 0;
}
+void hci_req_purge(struct hci_request *req)
+{
+ skb_queue_purge(&req->cmd_q);
+}
+
static int req_run(struct hci_request *req, hci_req_complete_t complete,
hci_req_complete_skb_t complete_skb)
{
@@ -331,8 +336,8 @@ void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen,
skb = hci_prepare_cmd(hdev, opcode, plen, param);
if (!skb) {
- BT_ERR("%s no memory for command (opcode 0x%4.4x)",
- hdev->name, opcode);
+ bt_dev_err(hdev, "no memory for command (opcode 0x%4.4x)",
+ opcode);
req->err = -ENOMEM;
return;
}
@@ -1421,7 +1426,7 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy,
err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa);
if (err < 0) {
- BT_ERR("%s failed to generate new RPA", hdev->name);
+ bt_dev_err(hdev, "failed to generate new RPA");
return err;
}
@@ -1783,7 +1788,7 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason)
err = hci_req_run(&req, abort_conn_complete);
if (err && err != -ENODATA) {
- BT_ERR("Failed to run HCI request: err %d", err);
+ bt_dev_err(conn->hdev, "failed to run HCI request: err %d", err);
return err;
}
@@ -1867,7 +1872,8 @@ static void le_scan_disable_work(struct work_struct *work)
hci_req_sync(hdev, le_scan_disable, 0, HCI_CMD_TIMEOUT, &status);
if (status) {
- BT_ERR("Failed to disable LE scan: status 0x%02x", status);
+ bt_dev_err(hdev, "failed to disable LE scan: status 0x%02x",
+ status);
return;
}
@@ -1898,7 +1904,7 @@ static void le_scan_disable_work(struct work_struct *work)
hci_req_sync(hdev, bredr_inquiry, DISCOV_INTERLEAVED_INQUIRY_LEN,
HCI_CMD_TIMEOUT, &status);
if (status) {
- BT_ERR("Inquiry failed: status 0x%02x", status);
+ bt_dev_err(hdev, "inquiry failed: status 0x%02x", status);
goto discov_stopped;
}
@@ -1940,7 +1946,8 @@ static void le_scan_restart_work(struct work_struct *work)
hci_req_sync(hdev, le_scan_restart, 0, HCI_CMD_TIMEOUT, &status);
if (status) {
- BT_ERR("Failed to restart LE scan: status %d", status);
+ bt_dev_err(hdev, "failed to restart LE scan: status %d",
+ status);
return;
}
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index dde77bd59f91..702beb140d9f 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -36,6 +36,7 @@ struct hci_request {
};
void hci_req_init(struct hci_request *req, struct hci_dev *hdev);
+void hci_req_purge(struct hci_request *req);
int hci_req_run(struct hci_request *req, hci_req_complete_t complete);
int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete);
void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 65d734c165bd..923e9a271872 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -251,15 +251,13 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
}
/* Send frame to sockets with specific channel */
-void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
- int flag, struct sock *skip_sk)
+static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
+ int flag, struct sock *skip_sk)
{
struct sock *sk;
BT_DBG("channel %u len %d", channel, skb->len);
- read_lock(&hci_sk_list.lock);
-
sk_for_each(sk, &hci_sk_list.head) {
struct sk_buff *nskb;
@@ -285,6 +283,13 @@ void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
kfree_skb(nskb);
}
+}
+
+void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
+ int flag, struct sock *skip_sk)
+{
+ read_lock(&hci_sk_list.lock);
+ __hci_send_to_channel(channel, skb, flag, skip_sk);
read_unlock(&hci_sk_list.lock);
}
@@ -388,8 +393,8 @@ void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event,
hdr->index = index;
hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE);
- hci_send_to_channel(HCI_CHANNEL_MONITOR, skb,
- HCI_SOCK_TRUSTED, NULL);
+ __hci_send_to_channel(HCI_CHANNEL_MONITOR, skb,
+ HCI_SOCK_TRUSTED, NULL);
kfree_skb(skb);
}
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index d5c7c89ec4d6..9874844a95a9 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -51,7 +51,7 @@ void hci_conn_add_sysfs(struct hci_conn *conn)
dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle);
if (device_add(&conn->dev) < 0) {
- BT_ERR("Failed to register connection device");
+ bt_dev_err(hdev, "failed to register connection device");
return;
}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 1fba2a03f8ae..6e9fc86d8daf 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2159,8 +2159,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
key_count = __le16_to_cpu(cp->key_count);
if (key_count > max_key_count) {
- BT_ERR("load_link_keys: too big key_count value %u",
- key_count);
+ bt_dev_err(hdev, "load_link_keys: too big key_count value %u",
+ key_count);
return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
MGMT_STATUS_INVALID_PARAMS);
}
@@ -2168,8 +2168,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
expected_len = sizeof(*cp) + key_count *
sizeof(struct mgmt_link_key_info);
if (expected_len != len) {
- BT_ERR("load_link_keys: expected %u bytes, got %u bytes",
- expected_len, len);
+ bt_dev_err(hdev, "load_link_keys: expected %u bytes, got %u bytes",
+ expected_len, len);
return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
MGMT_STATUS_INVALID_PARAMS);
}
@@ -2561,7 +2561,7 @@ static int pin_code_reply(struct sock *sk, struct hci_dev *hdev, void *data,
memcpy(&ncp.addr, &cp->addr, sizeof(ncp.addr));
- BT_ERR("PIN code is not 16 bytes long");
+ bt_dev_err(hdev, "PIN code is not 16 bytes long");
err = send_pin_code_neg_reply(sk, hdev, &ncp);
if (err >= 0)
@@ -3391,7 +3391,8 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
MGMT_OP_ADD_REMOTE_OOB_DATA,
status, &cp->addr, sizeof(cp->addr));
} else {
- BT_ERR("add_remote_oob_data: invalid length of %u bytes", len);
+ bt_dev_err(hdev, "add_remote_oob_data: invalid len of %u bytes",
+ len);
err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA,
MGMT_STATUS_INVALID_PARAMS);
}
@@ -3604,8 +3605,8 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev,
uuid_count = __le16_to_cpu(cp->uuid_count);
if (uuid_count > max_uuid_count) {
- BT_ERR("service_discovery: too big uuid_count value %u",
- uuid_count);
+ bt_dev_err(hdev, "service_discovery: too big uuid_count value %u",
+ uuid_count);
err = mgmt_cmd_complete(sk, hdev->id,
MGMT_OP_START_SERVICE_DISCOVERY,
MGMT_STATUS_INVALID_PARAMS, &cp->type,
@@ -3615,8 +3616,8 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev,
expected_len = sizeof(*cp) + uuid_count * 16;
if (expected_len != len) {
- BT_ERR("service_discovery: expected %u bytes, got %u bytes",
- expected_len, len);
+ bt_dev_err(hdev, "service_discovery: expected %u bytes, got %u bytes",
+ expected_len, len);
err = mgmt_cmd_complete(sk, hdev->id,
MGMT_OP_START_SERVICE_DISCOVERY,
MGMT_STATUS_INVALID_PARAMS, &cp->type,
@@ -3943,7 +3944,7 @@ static void set_advertising_complete(struct hci_dev *hdev, u8 status,
err = hci_req_run(&req, enable_advertising_instance);
if (err)
- BT_ERR("Failed to re-configure advertising");
+ bt_dev_err(hdev, "failed to re-configure advertising");
unlock:
hci_dev_unlock(hdev);
@@ -4664,15 +4665,16 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
irk_count = __le16_to_cpu(cp->irk_count);
if (irk_count > max_irk_count) {
- BT_ERR("load_irks: too big irk_count value %u", irk_count);
+ bt_dev_err(hdev, "load_irks: too big irk_count value %u",
+ irk_count);
return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS,
MGMT_STATUS_INVALID_PARAMS);
}
expected_len = sizeof(*cp) + irk_count * sizeof(struct mgmt_irk_info);
if (expected_len != len) {
- BT_ERR("load_irks: expected %u bytes, got %u bytes",
- expected_len, len);
+ bt_dev_err(hdev, "load_irks: expected %u bytes, got %u bytes",
+ expected_len, len);
return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS,
MGMT_STATUS_INVALID_PARAMS);
}
@@ -4745,7 +4747,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
key_count = __le16_to_cpu(cp->key_count);
if (key_count > max_key_count) {
- BT_ERR("load_ltks: too big key_count value %u", key_count);
+ bt_dev_err(hdev, "load_ltks: too big key_count value %u",
+ key_count);
return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
MGMT_STATUS_INVALID_PARAMS);
}
@@ -4753,8 +4756,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
expected_len = sizeof(*cp) + key_count *
sizeof(struct mgmt_ltk_info);
if (expected_len != len) {
- BT_ERR("load_keys: expected %u bytes, got %u bytes",
- expected_len, len);
+ bt_dev_err(hdev, "load_keys: expected %u bytes, got %u bytes",
+ expected_len, len);
return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
MGMT_STATUS_INVALID_PARAMS);
}
@@ -4873,14 +4876,15 @@ static void conn_info_refresh_complete(struct hci_dev *hdev, u8 hci_status,
}
if (!cp) {
- BT_ERR("invalid sent_cmd in conn_info response");
+ bt_dev_err(hdev, "invalid sent_cmd in conn_info response");
goto unlock;
}
handle = __le16_to_cpu(cp->handle);
conn = hci_conn_hash_lookup_handle(hdev, handle);
if (!conn) {
- BT_ERR("unknown handle (%d) in conn_info response", handle);
+ bt_dev_err(hdev, "unknown handle (%d) in conn_info response",
+ handle);
goto unlock;
}
@@ -5477,8 +5481,8 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
param_count = __le16_to_cpu(cp->param_count);
if (param_count > max_param_count) {
- BT_ERR("load_conn_param: too big param_count value %u",
- param_count);
+ bt_dev_err(hdev, "load_conn_param: too big param_count value %u",
+ param_count);
return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM,
MGMT_STATUS_INVALID_PARAMS);
}
@@ -5486,8 +5490,8 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
expected_len = sizeof(*cp) + param_count *
sizeof(struct mgmt_conn_param);
if (expected_len != len) {
- BT_ERR("load_conn_param: expected %u bytes, got %u bytes",
- expected_len, len);
+ bt_dev_err(hdev, "load_conn_param: expected %u bytes, got %u bytes",
+ expected_len, len);
return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM,
MGMT_STATUS_INVALID_PARAMS);
}
@@ -5512,7 +5516,7 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
} else if (param->addr.type == BDADDR_LE_RANDOM) {
addr_type = ADDR_LE_DEV_RANDOM;
} else {
- BT_ERR("Ignoring invalid connection parameters");
+ bt_dev_err(hdev, "ignoring invalid connection parameters");
continue;
}
@@ -5525,14 +5529,14 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
min, max, latency, timeout);
if (hci_check_conn_params(min, max, latency, timeout) < 0) {
- BT_ERR("Ignoring invalid connection parameters");
+ bt_dev_err(hdev, "ignoring invalid connection parameters");
continue;
}
hci_param = hci_conn_params_add(hdev, &param->addr.bdaddr,
addr_type);
if (!hci_param) {
- BT_ERR("Failed to add connection parameters");
+ bt_dev_err(hdev, "failed to add connection parameters");
continue;
}
@@ -6383,6 +6387,7 @@ static int remove_advertising(struct sock *sk, struct hci_dev *hdev,
if (skb_queue_empty(&req.cmd_q) ||
!hdev_is_powered(hdev) ||
hci_dev_test_flag(hdev, HCI_ADVERTISING)) {
+ hci_req_purge(&req);
rp.instance = cp->instance;
err = mgmt_cmd_complete(sk, hdev->id,
MGMT_OP_REMOVE_ADVERTISING,
diff --git a/net/bluetooth/selftest.c b/net/bluetooth/selftest.c
index 34a1227f4391..03e3c89c3046 100644
--- a/net/bluetooth/selftest.c
+++ b/net/bluetooth/selftest.c
@@ -138,12 +138,12 @@ static const u8 dhkey_3[32] __initconst = {
0x7c, 0x1c, 0xf9, 0x49, 0xe6, 0xd7, 0xaa, 0x70,
};
-static int __init test_ecdh_sample(const u8 priv_a[32], const u8 priv_b[32],
- const u8 pub_a[64], const u8 pub_b[64],
- const u8 dhkey[32])
+static int __init test_ecdh_sample(struct crypto_kpp *tfm, const u8 priv_a[32],
+ const u8 priv_b[32], const u8 pub_a[64],
+ const u8 pub_b[64], const u8 dhkey[32])
{
u8 *tmp, *dhkey_a, *dhkey_b;
- int ret = 0;
+ int ret;
tmp = kmalloc(64, GFP_KERNEL);
if (!tmp)
@@ -152,17 +152,30 @@ static int __init test_ecdh_sample(const u8 priv_a[32], const u8 priv_b[32],
dhkey_a = &tmp[0];
dhkey_b = &tmp[32];
- compute_ecdh_secret(pub_b, priv_a, dhkey_a);
- compute_ecdh_secret(pub_a, priv_b, dhkey_b);
+ ret = set_ecdh_privkey(tfm, priv_a);
+ if (ret)
+ goto out;
+
+ ret = compute_ecdh_secret(tfm, pub_b, dhkey_a);
+ if (ret)
+ goto out;
if (memcmp(dhkey_a, dhkey, 32)) {
ret = -EINVAL;
goto out;
}
+ ret = set_ecdh_privkey(tfm, priv_b);
+ if (ret)
+ goto out;
+
+ ret = compute_ecdh_secret(tfm, pub_a, dhkey_b);
+ if (ret)
+ goto out;
+
if (memcmp(dhkey_b, dhkey, 32))
ret = -EINVAL;
-
+ /* fall through*/
out:
kfree(tmp);
return ret;
@@ -185,30 +198,43 @@ static const struct file_operations test_ecdh_fops = {
static int __init test_ecdh(void)
{
+ struct crypto_kpp *tfm;
ktime_t calltime, delta, rettime;
- unsigned long long duration;
+ unsigned long long duration = 0;
int err;
calltime = ktime_get();
- err = test_ecdh_sample(priv_a_1, priv_b_1, pub_a_1, pub_b_1, dhkey_1);
+ tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
+ if (IS_ERR(tfm)) {
+ BT_ERR("Unable to create ECDH crypto context");
+ err = PTR_ERR(tfm);
+ goto done;
+ }
+
+ err = test_ecdh_sample(tfm, priv_a_1, priv_b_1, pub_a_1, pub_b_1,
+ dhkey_1);
if (err) {
BT_ERR("ECDH sample 1 failed");
goto done;
}
- err = test_ecdh_sample(priv_a_2, priv_b_2, pub_a_2, pub_b_2, dhkey_2);
+ err = test_ecdh_sample(tfm, priv_a_2, priv_b_2, pub_a_2, pub_b_2,
+ dhkey_2);
if (err) {
BT_ERR("ECDH sample 2 failed");
goto done;
}
- err = test_ecdh_sample(priv_a_3, priv_a_3, pub_a_3, pub_a_3, dhkey_3);
+ err = test_ecdh_sample(tfm, priv_a_3, priv_a_3, pub_a_3, pub_a_3,
+ dhkey_3);
if (err) {
BT_ERR("ECDH sample 3 failed");
goto done;
}
+ crypto_free_kpp(tfm);
+
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
duration = (unsigned long long) ktime_to_ns(delta) >> 10;
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index a0ef89772c36..01117ae84f1d 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -26,6 +26,7 @@
#include <crypto/algapi.h>
#include <crypto/b128ops.h>
#include <crypto/hash.h>
+#include <crypto/kpp.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
@@ -83,7 +84,6 @@ enum {
struct smp_dev {
/* Secure Connections OOB data */
u8 local_pk[64];
- u8 local_sk[32];
u8 local_rand[16];
bool debug_key;
@@ -92,6 +92,7 @@ struct smp_dev {
struct crypto_cipher *tfm_aes;
struct crypto_shash *tfm_cmac;
+ struct crypto_kpp *tfm_ecdh;
};
struct smp_chan {
@@ -124,13 +125,13 @@ struct smp_chan {
/* Secure Connections variables */
u8 local_pk[64];
- u8 local_sk[32];
u8 remote_pk[64];
u8 dhkey[32];
u8 mackey[16];
struct crypto_cipher *tfm_aes;
struct crypto_shash *tfm_cmac;
+ struct crypto_kpp *tfm_ecdh;
};
/* These debug key values are defined in the SMP section of the core
@@ -565,22 +566,22 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16])
if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) {
BT_DBG("Using debug keys");
+ err = set_ecdh_privkey(smp->tfm_ecdh, debug_sk);
+ if (err)
+ return err;
memcpy(smp->local_pk, debug_pk, 64);
- memcpy(smp->local_sk, debug_sk, 32);
smp->debug_key = true;
} else {
while (true) {
- /* Seed private key with random number */
- get_random_bytes(smp->local_sk, 32);
-
- /* Generate local key pair for Secure Connections */
- if (!generate_ecdh_keys(smp->local_pk, smp->local_sk))
- return -EIO;
+ /* Generate key pair for Secure Connections */
+ err = generate_ecdh_keys(smp->tfm_ecdh, smp->local_pk);
+ if (err)
+ return err;
/* This is unlikely, but we need to check that
* we didn't accidentially generate a debug key.
*/
- if (crypto_memneq(smp->local_sk, debug_sk, 32))
+ if (crypto_memneq(smp->local_pk, debug_pk, 64))
break;
}
smp->debug_key = false;
@@ -588,7 +589,6 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16])
SMP_DBG("OOB Public Key X: %32phN", smp->local_pk);
SMP_DBG("OOB Public Key Y: %32phN", smp->local_pk + 32);
- SMP_DBG("OOB Private Key: %32phN", smp->local_sk);
get_random_bytes(smp->local_rand, 16);
@@ -771,6 +771,7 @@ static void smp_chan_destroy(struct l2cap_conn *conn)
crypto_free_cipher(smp->tfm_aes);
crypto_free_shash(smp->tfm_cmac);
+ crypto_free_kpp(smp->tfm_ecdh);
/* Ensure that we don't leave any debug key around if debug key
* support hasn't been explicitly enabled.
@@ -995,7 +996,8 @@ static u8 smp_random(struct smp_chan *smp)
return SMP_UNSPECIFIED;
if (crypto_memneq(smp->pcnf, confirm, sizeof(smp->pcnf))) {
- BT_ERR("Pairing failed (confirmation values mismatch)");
+ bt_dev_err(hcon->hdev, "pairing failed "
+ "(confirmation values mismatch)");
return SMP_CONFIRM_FAILED;
}
@@ -1209,7 +1211,7 @@ static void sc_generate_ltk(struct smp_chan *smp)
key = hci_find_link_key(hdev, &hcon->dst);
if (!key) {
- BT_ERR("%s No Link Key found to generate LTK", hdev->name);
+ bt_dev_err(hdev, "no Link Key found to generate LTK");
return;
}
@@ -1391,16 +1393,19 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
smp->tfm_aes = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(smp->tfm_aes)) {
BT_ERR("Unable to create AES crypto context");
- kzfree(smp);
- return NULL;
+ goto zfree_smp;
}
smp->tfm_cmac = crypto_alloc_shash("cmac(aes)", 0, 0);
if (IS_ERR(smp->tfm_cmac)) {
BT_ERR("Unable to create CMAC crypto context");
- crypto_free_cipher(smp->tfm_aes);
- kzfree(smp);
- return NULL;
+ goto free_cipher;
+ }
+
+ smp->tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
+ if (IS_ERR(smp->tfm_ecdh)) {
+ BT_ERR("Unable to create ECDH crypto context");
+ goto free_shash;
}
smp->conn = conn;
@@ -1413,6 +1418,14 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
hci_conn_hold(conn->hcon);
return smp;
+
+free_shash:
+ crypto_free_shash(smp->tfm_cmac);
+free_cipher:
+ crypto_free_cipher(smp->tfm_aes);
+zfree_smp:
+ kzfree(smp);
+ return NULL;
}
static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16])
@@ -1883,7 +1896,6 @@ static u8 sc_send_public_key(struct smp_chan *smp)
smp_dev = chan->data;
memcpy(smp->local_pk, smp_dev->local_pk, 64);
- memcpy(smp->local_sk, smp_dev->local_sk, 32);
memcpy(smp->lr, smp_dev->local_rand, 16);
if (smp_dev->debug_key)
@@ -1894,22 +1906,20 @@ static u8 sc_send_public_key(struct smp_chan *smp)
if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) {
BT_DBG("Using debug keys");
+ if (set_ecdh_privkey(smp->tfm_ecdh, debug_sk))
+ return SMP_UNSPECIFIED;
memcpy(smp->local_pk, debug_pk, 64);
- memcpy(smp->local_sk, debug_sk, 32);
set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags);
} else {
while (true) {
- /* Seed private key with random number */
- get_random_bytes(smp->local_sk, 32);
-
- /* Generate local key pair for Secure Connections */
- if (!generate_ecdh_keys(smp->local_pk, smp->local_sk))
+ /* Generate key pair for Secure Connections */
+ if (generate_ecdh_keys(smp->tfm_ecdh, smp->local_pk))
return SMP_UNSPECIFIED;
/* This is unlikely, but we need to check that
* we didn't accidentially generate a debug key.
*/
- if (crypto_memneq(smp->local_sk, debug_sk, 32))
+ if (crypto_memneq(smp->local_pk, debug_pk, 64))
break;
}
}
@@ -1917,7 +1927,6 @@ static u8 sc_send_public_key(struct smp_chan *smp)
done:
SMP_DBG("Local Public Key X: %32phN", smp->local_pk);
SMP_DBG("Local Public Key Y: %32phN", smp->local_pk + 32);
- SMP_DBG("Local Private Key: %32phN", smp->local_sk);
smp_send_cmd(smp->conn, SMP_CMD_PUBLIC_KEY, 64, smp->local_pk);
@@ -2059,11 +2068,11 @@ static int fixup_sc_false_positive(struct smp_chan *smp)
return SMP_UNSPECIFIED;
if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) {
- BT_ERR("Refusing SMP SC -> legacy fallback in SC-only mode");
+ bt_dev_err(hdev, "refusing legacy fallback in SC-only mode");
return SMP_UNSPECIFIED;
}
- BT_ERR("Trying to fall back to legacy SMP");
+ bt_dev_err(hdev, "trying to fall back to legacy SMP");
req = (void *) &smp->preq[1];
rsp = (void *) &smp->prsp[1];
@@ -2074,7 +2083,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp)
auth = req->auth_req & AUTH_REQ_MASK(hdev);
if (tk_request(conn, 0, auth, rsp->io_capability, req->io_capability)) {
- BT_ERR("Failed to fall back to legacy SMP");
+ bt_dev_err(hdev, "failed to fall back to legacy SMP");
return SMP_UNSPECIFIED;
}
@@ -2347,7 +2356,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
chan = conn->smp;
if (!chan) {
- BT_ERR("SMP security requested but not available");
+ bt_dev_err(hcon->hdev, "security requested but not available");
return 1;
}
@@ -2540,7 +2549,7 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn,
*/
if (!bacmp(&info->bdaddr, BDADDR_ANY) ||
!hci_is_identity_address(&info->bdaddr, info->addr_type)) {
- BT_ERR("Ignoring IRK with no identity address");
+ bt_dev_err(hcon->hdev, "ignoring IRK with no identity address");
goto distribute;
}
@@ -2645,6 +2654,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
struct l2cap_chan *chan = conn->smp;
struct smp_chan *smp = chan->data;
struct hci_dev *hdev = hcon->hdev;
+ struct crypto_kpp *tfm_ecdh;
struct smp_cmd_pairing_confirm cfm;
int err;
@@ -2677,7 +2687,18 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
SMP_DBG("Remote Public Key X: %32phN", smp->remote_pk);
SMP_DBG("Remote Public Key Y: %32phN", smp->remote_pk + 32);
- if (!compute_ecdh_secret(smp->remote_pk, smp->local_sk, smp->dhkey))
+ /* Compute the shared secret on the same crypto tfm on which the private
+ * key was set/generated.
+ */
+ if (test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) {
+ struct smp_dev *smp_dev = chan->data;
+
+ tfm_ecdh = smp_dev->tfm_ecdh;
+ } else {
+ tfm_ecdh = smp->tfm_ecdh;
+ }
+
+ if (compute_ecdh_secret(tfm_ecdh, smp->remote_pk, smp->dhkey))
return SMP_UNSPECIFIED;
SMP_DBG("DHKey %32phN", smp->dhkey);
@@ -2933,8 +2954,8 @@ done:
return err;
drop:
- BT_ERR("%s unexpected SMP command 0x%02x from %pMR", hcon->hdev->name,
- code, &hcon->dst);
+ bt_dev_err(hcon->hdev, "unexpected SMP command 0x%02x from %pMR",
+ code, &hcon->dst);
kfree_skb(skb);
return 0;
}
@@ -3001,8 +3022,7 @@ static void bredr_pairing(struct l2cap_chan *chan)
smp = smp_chan_create(conn);
if (!smp) {
- BT_ERR("%s unable to create SMP context for BR/EDR",
- hdev->name);
+ bt_dev_err(hdev, "unable to create SMP context for BR/EDR");
return;
}
@@ -3169,6 +3189,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
struct smp_dev *smp;
struct crypto_cipher *tfm_aes;
struct crypto_shash *tfm_cmac;
+ struct crypto_kpp *tfm_ecdh;
if (cid == L2CAP_CID_SMP_BREDR) {
smp = NULL;
@@ -3194,8 +3215,18 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
return ERR_CAST(tfm_cmac);
}
+ tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
+ if (IS_ERR(tfm_ecdh)) {
+ BT_ERR("Unable to create ECDH crypto context");
+ crypto_free_shash(tfm_cmac);
+ crypto_free_cipher(tfm_aes);
+ kzfree(smp);
+ return ERR_CAST(tfm_ecdh);
+ }
+
smp->tfm_aes = tfm_aes;
smp->tfm_cmac = tfm_cmac;
+ smp->tfm_ecdh = tfm_ecdh;
smp->min_key_size = SMP_MIN_ENC_KEY_SIZE;
smp->max_key_size = SMP_MAX_ENC_KEY_SIZE;
@@ -3205,6 +3236,7 @@ create_chan:
if (smp) {
crypto_free_cipher(smp->tfm_aes);
crypto_free_shash(smp->tfm_cmac);
+ crypto_free_kpp(smp->tfm_ecdh);
kzfree(smp);
}
return ERR_PTR(-ENOMEM);
@@ -3252,6 +3284,7 @@ static void smp_del_chan(struct l2cap_chan *chan)
chan->data = NULL;
crypto_free_cipher(smp->tfm_aes);
crypto_free_shash(smp->tfm_cmac);
+ crypto_free_kpp(smp->tfm_ecdh);
kzfree(smp);
}
@@ -3490,25 +3523,18 @@ void smp_unregister(struct hci_dev *hdev)
#if IS_ENABLED(CONFIG_BT_SELFTEST_SMP)
-static inline void swap_digits(u64 *in, u64 *out, unsigned int ndigits)
+static int __init test_debug_key(struct crypto_kpp *tfm_ecdh)
{
- int i;
-
- for (i = 0; i < ndigits; i++)
- out[i] = __swab64(in[ndigits - 1 - i]);
-}
-
-static int __init test_debug_key(void)
-{
- u8 pk[64], sk[32];
-
- swap_digits((u64 *)debug_sk, (u64 *)sk, 4);
+ u8 pk[64];
+ int err;
- if (!generate_ecdh_keys(pk, sk))
- return -EINVAL;
+ err = set_ecdh_privkey(tfm_ecdh, debug_sk);
+ if (err)
+ return err;
- if (crypto_memneq(sk, debug_sk, 32))
- return -EINVAL;
+ err = generate_ecdh_public_key(tfm_ecdh, pk);
+ if (err)
+ return err;
if (crypto_memneq(pk, debug_pk, 64))
return -EINVAL;
@@ -3763,7 +3789,8 @@ static const struct file_operations test_smp_fops = {
};
static int __init run_selftests(struct crypto_cipher *tfm_aes,
- struct crypto_shash *tfm_cmac)
+ struct crypto_shash *tfm_cmac,
+ struct crypto_kpp *tfm_ecdh)
{
ktime_t calltime, delta, rettime;
unsigned long long duration;
@@ -3771,7 +3798,7 @@ static int __init run_selftests(struct crypto_cipher *tfm_aes,
calltime = ktime_get();
- err = test_debug_key();
+ err = test_debug_key(tfm_ecdh);
if (err) {
BT_ERR("debug_key test failed");
goto done;
@@ -3848,6 +3875,7 @@ int __init bt_selftest_smp(void)
{
struct crypto_cipher *tfm_aes;
struct crypto_shash *tfm_cmac;
+ struct crypto_kpp *tfm_ecdh;
int err;
tfm_aes = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
@@ -3863,10 +3891,19 @@ int __init bt_selftest_smp(void)
return PTR_ERR(tfm_cmac);
}
- err = run_selftests(tfm_aes, tfm_cmac);
+ tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
+ if (IS_ERR(tfm_ecdh)) {
+ BT_ERR("Unable to create ECDH crypto context");
+ crypto_free_shash(tfm_cmac);
+ crypto_free_cipher(tfm_aes);
+ return PTR_ERR(tfm_ecdh);
+ }
+
+ err = run_selftests(tfm_aes, tfm_cmac, tfm_ecdh);
crypto_free_shash(tfm_cmac);
crypto_free_cipher(tfm_aes);
+ crypto_free_kpp(tfm_ecdh);
return err;
}
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 6be41a44d688..a86e6687026e 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -133,7 +133,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
if (is_l2)
__skb_push(skb, ETH_HLEN);
if (is_direct_pkt_access)
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
retval = bpf_test_run(prog, skb, repeat, &duration);
if (!is_l2)
__skb_push(skb, ETH_HLEN);
@@ -162,6 +162,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
xdp.data_hard_start = data;
xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN;
+ xdp.data_meta = xdp.data;
xdp.data_end = xdp.data + size;
retval = bpf_test_run(prog, &xdp, repeat, &duration);
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index f760e62a672a..ac9ef337f0fa 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -8,7 +8,7 @@ obj-$(CONFIG_BRIDGE) += bridge.o
bridge-y := br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \
br_ioctl.o br_stp.o br_stp_bpdu.o \
br_stp_if.o br_stp_timer.o br_netlink.o \
- br_netlink_tunnel.o
+ br_netlink_tunnel.o br_arp_nd_proxy.o
bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 1407d1ba7577..6bf06e756df2 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -112,7 +112,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v
/* Events that may cause spanning tree to refresh */
if (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
event == NETDEV_CHANGE || event == NETDEV_DOWN)
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, NULL, p);
return NOTIFY_DONE;
}
diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
new file mode 100644
index 000000000000..2cf7716254be
--- /dev/null
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -0,0 +1,469 @@
+/*
+ * Handle bridge arp/nd proxy/suppress
+ *
+ * Copyright (C) 2017 Cumulus Networks
+ * Copyright (c) 2017 Roopa Prabhu <roopa@cumulusnetworks.com>
+ *
+ * Authors:
+ * Roopa Prabhu <roopa@cumulusnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/neighbour.h>
+#include <net/arp.h>
+#include <linux/if_vlan.h>
+#include <linux/inetdevice.h>
+#include <net/addrconf.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ip6_checksum.h>
+#endif
+
+#include "br_private.h"
+
+void br_recalculate_neigh_suppress_enabled(struct net_bridge *br)
+{
+ struct net_bridge_port *p;
+ bool neigh_suppress = false;
+
+ list_for_each_entry(p, &br->port_list, list) {
+ if (p->flags & BR_NEIGH_SUPPRESS) {
+ neigh_suppress = true;
+ break;
+ }
+ }
+
+ br->neigh_suppress_enabled = neigh_suppress;
+}
+
+#if IS_ENABLED(CONFIG_INET)
+static void br_arp_send(struct net_bridge *br, struct net_bridge_port *p,
+ struct net_device *dev, __be32 dest_ip, __be32 src_ip,
+ const unsigned char *dest_hw,
+ const unsigned char *src_hw,
+ const unsigned char *target_hw,
+ __be16 vlan_proto, u16 vlan_tci)
+{
+ struct net_bridge_vlan_group *vg;
+ struct sk_buff *skb;
+ u16 pvid;
+
+ netdev_dbg(dev, "arp send dev %s dst %pI4 dst_hw %pM src %pI4 src_hw %pM\n",
+ dev->name, &dest_ip, dest_hw, &src_ip, src_hw);
+
+ if (!vlan_tci) {
+ arp_send(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip,
+ dest_hw, src_hw, target_hw);
+ return;
+ }
+
+ skb = arp_create(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip,
+ dest_hw, src_hw, target_hw);
+ if (!skb)
+ return;
+
+ if (p)
+ vg = nbp_vlan_group_rcu(p);
+ else
+ vg = br_vlan_group_rcu(br);
+ pvid = br_get_pvid(vg);
+ if (pvid == (vlan_tci & VLAN_VID_MASK))
+ vlan_tci = 0;
+
+ if (vlan_tci)
+ __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+
+ if (p) {
+ arp_xmit(skb);
+ } else {
+ skb_reset_mac_header(skb);
+ __skb_pull(skb, skb_network_offset(skb));
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->pkt_type = PACKET_HOST;
+
+ netif_rx_ni(skb);
+ }
+}
+
+static int br_chk_addr_ip(struct net_device *dev, void *data)
+{
+ __be32 ip = *(__be32 *)data;
+ struct in_device *in_dev;
+ __be32 addr = 0;
+
+ in_dev = __in_dev_get_rcu(dev);
+ if (in_dev)
+ addr = inet_confirm_addr(dev_net(dev), in_dev, 0, ip,
+ RT_SCOPE_HOST);
+
+ if (addr == ip)
+ return 1;
+
+ return 0;
+}
+
+static bool br_is_local_ip(struct net_device *dev, __be32 ip)
+{
+ if (br_chk_addr_ip(dev, &ip))
+ return true;
+
+ /* check if ip is configured on upper dev */
+ if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &ip))
+ return true;
+
+ return false;
+}
+
+void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
+ u16 vid, struct net_bridge_port *p)
+{
+ struct net_device *dev = br->dev;
+ struct net_device *vlandev = dev;
+ struct neighbour *n;
+ struct arphdr *parp;
+ u8 *arpptr, *sha;
+ __be32 sip, tip;
+
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+
+ if ((dev->flags & IFF_NOARP) ||
+ !pskb_may_pull(skb, arp_hdr_len(dev)))
+ return;
+
+ parp = arp_hdr(skb);
+
+ if (parp->ar_pro != htons(ETH_P_IP) ||
+ parp->ar_hln != dev->addr_len ||
+ parp->ar_pln != 4)
+ return;
+
+ arpptr = (u8 *)parp + sizeof(struct arphdr);
+ sha = arpptr;
+ arpptr += dev->addr_len; /* sha */
+ memcpy(&sip, arpptr, sizeof(sip));
+ arpptr += sizeof(sip);
+ arpptr += dev->addr_len; /* tha */
+ memcpy(&tip, arpptr, sizeof(tip));
+
+ if (ipv4_is_loopback(tip) ||
+ ipv4_is_multicast(tip))
+ return;
+
+ if (br->neigh_suppress_enabled) {
+ if (p && (p->flags & BR_NEIGH_SUPPRESS))
+ return;
+ if (ipv4_is_zeronet(sip) || sip == tip) {
+ /* prevent flooding to neigh suppress ports */
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ return;
+ }
+ }
+
+ if (parp->ar_op != htons(ARPOP_REQUEST))
+ return;
+
+ if (vid != 0) {
+ vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto,
+ vid);
+ if (!vlandev)
+ return;
+ }
+
+ if (br->neigh_suppress_enabled && br_is_local_ip(vlandev, tip)) {
+ /* its our local ip, so don't proxy reply
+ * and don't forward to neigh suppress ports
+ */
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ return;
+ }
+
+ n = neigh_lookup(&arp_tbl, &tip, vlandev);
+ if (n) {
+ struct net_bridge_fdb_entry *f;
+
+ if (!(n->nud_state & NUD_VALID)) {
+ neigh_release(n);
+ return;
+ }
+
+ f = br_fdb_find_rcu(br, n->ha, vid);
+ if (f) {
+ bool replied = false;
+
+ if ((p && (p->flags & BR_PROXYARP)) ||
+ (f->dst && (f->dst->flags & (BR_PROXYARP_WIFI |
+ BR_NEIGH_SUPPRESS)))) {
+ if (!vid)
+ br_arp_send(br, p, skb->dev, sip, tip,
+ sha, n->ha, sha, 0, 0);
+ else
+ br_arp_send(br, p, skb->dev, sip, tip,
+ sha, n->ha, sha,
+ skb->vlan_proto,
+ skb_vlan_tag_get(skb));
+ replied = true;
+ }
+
+ /* If we have replied or as long as we know the
+ * mac, indicate to arp replied
+ */
+ if (replied || br->neigh_suppress_enabled)
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ }
+
+ neigh_release(n);
+ }
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *msg)
+{
+ struct nd_msg *m;
+
+ m = skb_header_pointer(skb, skb_network_offset(skb) +
+ sizeof(struct ipv6hdr), sizeof(*msg), msg);
+ if (!m)
+ return NULL;
+
+ if (m->icmph.icmp6_code != 0 ||
+ (m->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION &&
+ m->icmph.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT))
+ return NULL;
+
+ return m;
+}
+
+static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
+ struct sk_buff *request, struct neighbour *n,
+ __be16 vlan_proto, u16 vlan_tci, struct nd_msg *ns)
+{
+ struct net_device *dev = request->dev;
+ struct net_bridge_vlan_group *vg;
+ struct sk_buff *reply;
+ struct nd_msg *na;
+ struct ipv6hdr *pip6;
+ int na_olen = 8; /* opt hdr + ETH_ALEN for target */
+ int ns_olen;
+ int i, len;
+ u8 *daddr;
+ u16 pvid;
+
+ if (!dev)
+ return;
+
+ len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
+ sizeof(*na) + na_olen + dev->needed_tailroom;
+
+ reply = alloc_skb(len, GFP_ATOMIC);
+ if (!reply)
+ return;
+
+ reply->protocol = htons(ETH_P_IPV6);
+ reply->dev = dev;
+ skb_reserve(reply, LL_RESERVED_SPACE(dev));
+ skb_push(reply, sizeof(struct ethhdr));
+ skb_set_mac_header(reply, 0);
+
+ daddr = eth_hdr(request)->h_source;
+
+ /* Do we need option processing ? */
+ ns_olen = request->len - (skb_network_offset(request) +
+ sizeof(struct ipv6hdr)) - sizeof(*ns);
+ for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) {
+ if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
+ daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+ break;
+ }
+ }
+
+ /* Ethernet header */
+ ether_addr_copy(eth_hdr(reply)->h_dest, daddr);
+ ether_addr_copy(eth_hdr(reply)->h_source, n->ha);
+ eth_hdr(reply)->h_proto = htons(ETH_P_IPV6);
+ reply->protocol = htons(ETH_P_IPV6);
+
+ skb_pull(reply, sizeof(struct ethhdr));
+ skb_set_network_header(reply, 0);
+ skb_put(reply, sizeof(struct ipv6hdr));
+
+ /* IPv6 header */
+ pip6 = ipv6_hdr(reply);
+ memset(pip6, 0, sizeof(struct ipv6hdr));
+ pip6->version = 6;
+ pip6->priority = ipv6_hdr(request)->priority;
+ pip6->nexthdr = IPPROTO_ICMPV6;
+ pip6->hop_limit = 255;
+ pip6->daddr = ipv6_hdr(request)->saddr;
+ pip6->saddr = *(struct in6_addr *)n->primary_key;
+
+ skb_pull(reply, sizeof(struct ipv6hdr));
+ skb_set_transport_header(reply, 0);
+
+ na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen);
+
+ /* Neighbor Advertisement */
+ memset(na, 0, sizeof(*na) + na_olen);
+ na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
+ na->icmph.icmp6_router = 0; /* XXX: should be 1 ? */
+ na->icmph.icmp6_override = 1;
+ na->icmph.icmp6_solicited = 1;
+ na->target = ns->target;
+ ether_addr_copy(&na->opt[2], n->ha);
+ na->opt[0] = ND_OPT_TARGET_LL_ADDR;
+ na->opt[1] = na_olen >> 3;
+
+ na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr,
+ &pip6->daddr,
+ sizeof(*na) + na_olen,
+ IPPROTO_ICMPV6,
+ csum_partial(na, sizeof(*na) + na_olen, 0));
+
+ pip6->payload_len = htons(sizeof(*na) + na_olen);
+
+ skb_push(reply, sizeof(struct ipv6hdr));
+ skb_push(reply, sizeof(struct ethhdr));
+
+ reply->ip_summed = CHECKSUM_UNNECESSARY;
+
+ if (p)
+ vg = nbp_vlan_group_rcu(p);
+ else
+ vg = br_vlan_group_rcu(br);
+ pvid = br_get_pvid(vg);
+ if (pvid == (vlan_tci & VLAN_VID_MASK))
+ vlan_tci = 0;
+
+ if (vlan_tci)
+ __vlan_hwaccel_put_tag(reply, vlan_proto, vlan_tci);
+
+ netdev_dbg(dev, "nd send dev %s dst %pI6 dst_hw %pM src %pI6 src_hw %pM\n",
+ dev->name, &pip6->daddr, daddr, &pip6->saddr, n->ha);
+
+ if (p) {
+ dev_queue_xmit(reply);
+ } else {
+ skb_reset_mac_header(reply);
+ __skb_pull(reply, skb_network_offset(reply));
+ reply->ip_summed = CHECKSUM_UNNECESSARY;
+ reply->pkt_type = PACKET_HOST;
+
+ netif_rx_ni(reply);
+ }
+}
+
+static int br_chk_addr_ip6(struct net_device *dev, void *data)
+{
+ struct in6_addr *addr = (struct in6_addr *)data;
+
+ if (ipv6_chk_addr(dev_net(dev), addr, dev, 0))
+ return 1;
+
+ return 0;
+}
+
+static bool br_is_local_ip6(struct net_device *dev, struct in6_addr *addr)
+
+{
+ if (br_chk_addr_ip6(dev, addr))
+ return true;
+
+ /* check if ip is configured on upper dev */
+ if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, addr))
+ return true;
+
+ return false;
+}
+
+void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
+ u16 vid, struct net_bridge_port *p, struct nd_msg *msg)
+{
+ struct net_device *dev = br->dev;
+ struct net_device *vlandev = NULL;
+ struct in6_addr *saddr, *daddr;
+ struct ipv6hdr *iphdr;
+ struct neighbour *n;
+
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+
+ if (p && (p->flags & BR_NEIGH_SUPPRESS))
+ return;
+
+ if (msg->icmph.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT &&
+ !msg->icmph.icmp6_solicited) {
+ /* prevent flooding to neigh suppress ports */
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ return;
+ }
+
+ if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
+ return;
+
+ iphdr = ipv6_hdr(skb);
+ saddr = &iphdr->saddr;
+ daddr = &iphdr->daddr;
+
+ if (ipv6_addr_any(saddr) || !ipv6_addr_cmp(saddr, daddr)) {
+ /* prevent flooding to neigh suppress ports */
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ return;
+ }
+
+ if (vid != 0) {
+ /* build neigh table lookup on the vlan device */
+ vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto,
+ vid);
+ if (!vlandev)
+ return;
+ } else {
+ vlandev = dev;
+ }
+
+ if (br_is_local_ip6(vlandev, &msg->target)) {
+ /* its our own ip, so don't proxy reply
+ * and don't forward to arp suppress ports
+ */
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ return;
+ }
+
+ n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, vlandev);
+ if (n) {
+ struct net_bridge_fdb_entry *f;
+
+ if (!(n->nud_state & NUD_VALID)) {
+ neigh_release(n);
+ return;
+ }
+
+ f = br_fdb_find_rcu(br, n->ha, vid);
+ if (f) {
+ bool replied = false;
+
+ if (f->dst && (f->dst->flags & BR_NEIGH_SUPPRESS)) {
+ if (vid != 0)
+ br_nd_send(br, p, skb, n,
+ skb->vlan_proto,
+ skb_vlan_tag_get(skb), msg);
+ else
+ br_nd_send(br, p, skb, n, 0, 0, msg);
+ replied = true;
+ }
+
+ /* If we have replied or as long as we know the
+ * mac, indicate to NEIGH_SUPPRESS ports that we
+ * have replied
+ */
+ if (replied || br->neigh_suppress_enabled)
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ }
+ neigh_release(n);
+ }
+}
+#endif
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index f6b6a92f1c48..af5b8c87f590 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -39,6 +39,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
const struct nf_br_ops *nf_ops;
const unsigned char *dest;
+ struct ethhdr *eth;
u16 vid = 0;
rcu_read_lock();
@@ -57,11 +58,30 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
BR_INPUT_SKB_CB(skb)->brdev = dev;
skb_reset_mac_header(skb);
+ eth = eth_hdr(skb);
skb_pull(skb, ETH_HLEN);
if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid))
goto out;
+ if (IS_ENABLED(CONFIG_INET) &&
+ (eth->h_proto == htons(ETH_P_ARP) ||
+ eth->h_proto == htons(ETH_P_RARP)) &&
+ br->neigh_suppress_enabled) {
+ br_do_proxy_suppress_arp(skb, br, vid, NULL);
+ } else if (IS_ENABLED(CONFIG_IPV6) &&
+ skb->protocol == htons(ETH_P_IPV6) &&
+ br->neigh_suppress_enabled &&
+ pskb_may_pull(skb, sizeof(struct ipv6hdr) +
+ sizeof(struct nd_msg)) &&
+ ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
+ struct nd_msg *msg, _msg;
+
+ msg = br_is_nd_neigh_msg(skb, &_msg);
+ if (msg)
+ br_do_suppress_nd(skb, br, vid, NULL, msg);
+ }
+
dest = eth_hdr(skb)->h_dest;
if (is_broadcast_ether_addr(dest)) {
br_flood(br, skb, BR_PKT_BROADCAST, false, true);
@@ -320,12 +340,13 @@ void br_netpoll_disable(struct net_bridge_port *p)
#endif
-static int br_add_slave(struct net_device *dev, struct net_device *slave_dev)
+static int br_add_slave(struct net_device *dev, struct net_device *slave_dev,
+ struct netlink_ext_ack *extack)
{
struct net_bridge *br = netdev_priv(dev);
- return br_add_if(br, slave_dev);
+ return br_add_if(br, slave_dev, extack);
}
static int br_del_slave(struct net_device *dev, struct net_device *slave_dev)
@@ -400,7 +421,7 @@ void br_dev_setup(struct net_device *dev)
br->bridge_id.prio[0] = 0x80;
br->bridge_id.prio[1] = 0x00;
- ether_addr_copy(br->group_addr, eth_reserved_addr_base);
+ ether_addr_copy(br->group_addr, eth_stp_addr);
br->stp_enabled = BR_NO_STP;
br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 48fb17417fac..b4eed113d2ec 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -204,7 +204,7 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
/* Do not flood to ports that enable proxy ARP */
if (p->flags & BR_PROXYARP)
continue;
- if ((p->flags & BR_PROXYARP_WIFI) &&
+ if ((p->flags & (BR_PROXYARP_WIFI | BR_NEIGH_SUPPRESS)) &&
BR_INPUT_SKB_CB(skb)->proxyarp_replied)
continue;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index f3aef22931ab..9ba4ed65c52b 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -271,7 +271,7 @@ static void del_nbp(struct net_bridge_port *p)
br_stp_disable_port(p);
spin_unlock_bh(&br->lock);
- br_ifinfo_notify(RTM_DELLINK, p);
+ br_ifinfo_notify(RTM_DELLINK, NULL, p);
list_del_rcu(&p->list);
if (netdev_get_fwd_headroom(dev) == br->dev->needed_headroom)
@@ -310,6 +310,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head)
del_nbp(p);
}
+ br_recalculate_neigh_suppress_enabled(br);
+
br_fdb_delete_by_port(br, NULL, 0, 1);
cancel_delayed_work_sync(&br->gc_work);
@@ -480,7 +482,8 @@ netdev_features_t br_features_recompute(struct net_bridge *br,
}
/* called with RTNL */
-int br_add_if(struct net_bridge *br, struct net_device *dev)
+int br_add_if(struct net_bridge *br, struct net_device *dev,
+ struct netlink_ext_ack *extack)
{
struct net_bridge_port *p;
int err = 0;
@@ -500,16 +503,22 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
return -EINVAL;
/* No bridging of bridges */
- if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit)
+ if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) {
+ NL_SET_ERR_MSG(extack,
+ "Can not enslave a bridge to a bridge");
return -ELOOP;
+ }
/* Device is already being bridged */
if (br_port_exists(dev))
return -EBUSY;
/* No bridging devices that dislike that (e.g. wireless) */
- if (dev->priv_flags & IFF_DONT_BRIDGE)
+ if (dev->priv_flags & IFF_DONT_BRIDGE) {
+ NL_SET_ERR_MSG(extack,
+ "Device does not allow enslaving to a bridge");
return -EOPNOTSUPP;
+ }
p = new_nbp(br, dev);
if (IS_ERR(p))
@@ -540,7 +549,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
dev->priv_flags |= IFF_BRIDGE_PORT;
- err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL);
+ err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL, extack);
if (err)
goto err5;
@@ -580,7 +589,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
br_stp_enable_port(p);
spin_unlock_bh(&br->lock);
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, NULL, p);
if (changed_addr)
call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
@@ -653,4 +662,7 @@ void br_port_flags_change(struct net_bridge_port *p, unsigned long mask)
if (mask & BR_AUTO_MASK)
nbp_update_port_count(br);
+
+ if (mask & BR_NEIGH_SUPPRESS)
+ br_recalculate_neigh_suppress_enabled(br);
}
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 7637f58c1226..7f98a7d25866 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -71,62 +71,6 @@ static int br_pass_frame_up(struct sk_buff *skb)
br_netif_receive_skb);
}
-static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
- u16 vid, struct net_bridge_port *p)
-{
- struct net_device *dev = br->dev;
- struct neighbour *n;
- struct arphdr *parp;
- u8 *arpptr, *sha;
- __be32 sip, tip;
-
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
-
- if ((dev->flags & IFF_NOARP) ||
- !pskb_may_pull(skb, arp_hdr_len(dev)))
- return;
-
- parp = arp_hdr(skb);
-
- if (parp->ar_pro != htons(ETH_P_IP) ||
- parp->ar_op != htons(ARPOP_REQUEST) ||
- parp->ar_hln != dev->addr_len ||
- parp->ar_pln != 4)
- return;
-
- arpptr = (u8 *)parp + sizeof(struct arphdr);
- sha = arpptr;
- arpptr += dev->addr_len; /* sha */
- memcpy(&sip, arpptr, sizeof(sip));
- arpptr += sizeof(sip);
- arpptr += dev->addr_len; /* tha */
- memcpy(&tip, arpptr, sizeof(tip));
-
- if (ipv4_is_loopback(tip) ||
- ipv4_is_multicast(tip))
- return;
-
- n = neigh_lookup(&arp_tbl, &tip, dev);
- if (n) {
- struct net_bridge_fdb_entry *f;
-
- if (!(n->nud_state & NUD_VALID)) {
- neigh_release(n);
- return;
- }
-
- f = br_fdb_find_rcu(br, n->ha, vid);
- if (f && ((p->flags & BR_PROXYARP) ||
- (f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) {
- arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip,
- sha, n->ha, sha);
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
- }
-
- neigh_release(n);
- }
-}
-
/* note: already called with rcu_read_lock */
int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
@@ -171,15 +115,29 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
BR_INPUT_SKB_CB(skb)->brdev = br->dev;
- if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP))
- br_do_proxy_arp(skb, br, vid, p);
+ if (IS_ENABLED(CONFIG_INET) &&
+ (skb->protocol == htons(ETH_P_ARP) ||
+ skb->protocol == htons(ETH_P_RARP))) {
+ br_do_proxy_suppress_arp(skb, br, vid, p);
+ } else if (IS_ENABLED(CONFIG_IPV6) &&
+ skb->protocol == htons(ETH_P_IPV6) &&
+ br->neigh_suppress_enabled &&
+ pskb_may_pull(skb, sizeof(struct ipv6hdr) +
+ sizeof(struct nd_msg)) &&
+ ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
+ struct nd_msg *msg, _msg;
+
+ msg = br_is_nd_neigh_msg(skb, &_msg);
+ if (msg)
+ br_do_suppress_nd(skb, br, vid, p, msg);
+ }
switch (pkt_type) {
case BR_PKT_MULTICAST:
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
br_multicast_querier_exists(br, eth_hdr(skb))) {
- if ((mdst && mdst->mglist) ||
+ if ((mdst && mdst->host_joined) ||
br_multicast_is_router(br)) {
local_rcv = true;
br->dev->stats.multicast++;
@@ -289,6 +247,7 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
*
* Others reserved for future standardization
*/
+ fwd_mask |= p->group_fwd_mask;
switch (dest[5]) {
case 0x00: /* Bridge Group Address */
/* If STP is turned off,
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 7970f8540cbb..73b957fd639d 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -98,7 +98,7 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd)
return -EINVAL;
if (isadd)
- ret = br_add_if(br, dev);
+ ret = br_add_if(br, dev, NULL);
else
ret = br_del_if(br, dev);
@@ -293,7 +293,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
if (!ret) {
if (p)
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, NULL, p);
else
netdev_state_change(br->dev);
}
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 31ddff22563e..b0f4c734900b 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -292,6 +292,46 @@ err:
kfree(priv);
}
+static void br_mdb_switchdev_host_port(struct net_device *dev,
+ struct net_device *lower_dev,
+ struct br_mdb_entry *entry, int type)
+{
+ struct switchdev_obj_port_mdb mdb = {
+ .obj = {
+ .id = SWITCHDEV_OBJ_ID_HOST_MDB,
+ .flags = SWITCHDEV_F_DEFER,
+ },
+ .vid = entry->vid,
+ };
+
+ if (entry->addr.proto == htons(ETH_P_IP))
+ ip_eth_mc_map(entry->addr.u.ip4, mdb.addr);
+#if IS_ENABLED(CONFIG_IPV6)
+ else
+ ipv6_eth_mc_map(&entry->addr.u.ip6, mdb.addr);
+#endif
+
+ mdb.obj.orig_dev = dev;
+ switch (type) {
+ case RTM_NEWMDB:
+ switchdev_port_obj_add(lower_dev, &mdb.obj);
+ break;
+ case RTM_DELMDB:
+ switchdev_port_obj_del(lower_dev, &mdb.obj);
+ break;
+ }
+}
+
+static void br_mdb_switchdev_host(struct net_device *dev,
+ struct br_mdb_entry *entry, int type)
+{
+ struct net_device *lower_dev;
+ struct list_head *iter;
+
+ netdev_for_each_lower_dev(dev, lower_dev, iter)
+ br_mdb_switchdev_host_port(dev, lower_dev, entry, type);
+}
+
static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p,
struct br_mdb_entry *entry, int type)
{
@@ -317,7 +357,7 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p,
#endif
mdb.obj.orig_dev = port_dev;
- if (port_dev && type == RTM_NEWMDB) {
+ if (p && port_dev && type == RTM_NEWMDB) {
complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC);
if (complete_info) {
complete_info->port = p;
@@ -327,10 +367,13 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p,
if (switchdev_port_obj_add(port_dev, &mdb.obj))
kfree(complete_info);
}
- } else if (port_dev && type == RTM_DELMDB) {
+ } else if (p && port_dev && type == RTM_DELMDB) {
switchdev_port_obj_del(port_dev, &mdb.obj);
}
+ if (!p)
+ br_mdb_switchdev_host(dev, entry, type);
+
skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC);
if (!skb)
goto errout;
@@ -353,7 +396,10 @@ void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
struct br_mdb_entry entry;
memset(&entry, 0, sizeof(entry));
- entry.ifindex = port->dev->ifindex;
+ if (port)
+ entry.ifindex = port->dev->ifindex;
+ else
+ entry.ifindex = dev->ifindex;
entry.addr.proto = group->proto;
entry.addr.u.ip4 = group->u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
@@ -655,7 +701,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
call_rcu_bh(&p->rcu, br_multicast_free_pg);
err = 0;
- if (!mp->ports && !mp->mglist &&
+ if (!mp->ports && !mp->host_joined &&
netif_running(br->dev))
mod_timer(&mp->timer, jiffies);
break;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 8dc5c8d69bcd..cb4729539b82 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -239,9 +239,9 @@ static void br_multicast_free_group(struct rcu_head *head)
kfree(mp);
}
-static void br_multicast_group_expired(unsigned long data)
+static void br_multicast_group_expired(struct timer_list *t)
{
- struct net_bridge_mdb_entry *mp = (void *)data;
+ struct net_bridge_mdb_entry *mp = from_timer(mp, t, timer);
struct net_bridge *br = mp->br;
struct net_bridge_mdb_htable *mdb;
@@ -249,7 +249,8 @@ static void br_multicast_group_expired(unsigned long data)
if (!netif_running(br->dev) || timer_pending(&mp->timer))
goto out;
- mp->mglist = false;
+ mp->host_joined = false;
+ br_mdb_notify(br->dev, NULL, &mp->addr, RTM_DELMDB, 0);
if (mp->ports)
goto out;
@@ -292,7 +293,7 @@ static void br_multicast_del_pg(struct net_bridge *br,
p->flags);
call_rcu_bh(&p->rcu, br_multicast_free_pg);
- if (!mp->ports && !mp->mglist &&
+ if (!mp->ports && !mp->host_joined &&
netif_running(br->dev))
mod_timer(&mp->timer, jiffies);
@@ -302,9 +303,9 @@ static void br_multicast_del_pg(struct net_bridge *br,
WARN_ON(1);
}
-static void br_multicast_port_group_expired(unsigned long data)
+static void br_multicast_port_group_expired(struct timer_list *t)
{
- struct net_bridge_port_group *pg = (void *)data;
+ struct net_bridge_port_group *pg = from_timer(pg, t, timer);
struct net_bridge *br = pg->port->br;
spin_lock(&br->multicast_lock);
@@ -701,8 +702,7 @@ rehash:
mp->br = br;
mp->addr = *group;
- setup_timer(&mp->timer, br_multicast_group_expired,
- (unsigned long)mp);
+ timer_setup(&mp->timer, br_multicast_group_expired, 0);
hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]);
mdb->size++;
@@ -729,8 +729,7 @@ struct net_bridge_port_group *br_multicast_new_port_group(
p->flags = flags;
rcu_assign_pointer(p->next, next);
hlist_add_head(&p->mglist, &port->mglist);
- setup_timer(&p->timer, br_multicast_port_group_expired,
- (unsigned long)p);
+ timer_setup(&p->timer, br_multicast_port_group_expired, 0);
if (src)
memcpy(p->eth_addr, src, ETH_ALEN);
@@ -775,7 +774,10 @@ static int br_multicast_add_group(struct net_bridge *br,
goto err;
if (!port) {
- mp->mglist = true;
+ if (!mp->host_joined) {
+ mp->host_joined = true;
+ br_mdb_notify(br->dev, NULL, &mp->addr, RTM_NEWMDB, 0);
+ }
mod_timer(&mp->timer, now + br->multicast_membership_interval);
goto out;
}
@@ -843,9 +845,10 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
}
#endif
-static void br_multicast_router_expired(unsigned long data)
+static void br_multicast_router_expired(struct timer_list *t)
{
- struct net_bridge_port *port = (void *)data;
+ struct net_bridge_port *port =
+ from_timer(port, t, multicast_router_timer);
struct net_bridge *br = port->br;
spin_lock(&br->multicast_lock);
@@ -859,8 +862,32 @@ out:
spin_unlock(&br->multicast_lock);
}
-static void br_multicast_local_router_expired(unsigned long data)
+static void br_mc_router_state_change(struct net_bridge *p,
+ bool is_mc_router)
+{
+ struct switchdev_attr attr = {
+ .orig_dev = p->dev,
+ .id = SWITCHDEV_ATTR_ID_BRIDGE_MROUTER,
+ .flags = SWITCHDEV_F_DEFER,
+ .u.mrouter = is_mc_router,
+ };
+
+ switchdev_port_attr_set(p->dev, &attr);
+}
+
+static void br_multicast_local_router_expired(struct timer_list *t)
{
+ struct net_bridge *br = from_timer(br, t, multicast_router_timer);
+
+ spin_lock(&br->multicast_lock);
+ if (br->multicast_router == MDB_RTR_TYPE_DISABLED ||
+ br->multicast_router == MDB_RTR_TYPE_PERM ||
+ timer_pending(&br->multicast_router_timer))
+ goto out;
+
+ br_mc_router_state_change(br, false);
+out:
+ spin_unlock(&br->multicast_lock);
}
static void br_multicast_querier_expired(struct net_bridge *br,
@@ -876,17 +903,17 @@ out:
spin_unlock(&br->multicast_lock);
}
-static void br_ip4_multicast_querier_expired(unsigned long data)
+static void br_ip4_multicast_querier_expired(struct timer_list *t)
{
- struct net_bridge *br = (void *)data;
+ struct net_bridge *br = from_timer(br, t, ip4_other_query.timer);
br_multicast_querier_expired(br, &br->ip4_own_query);
}
#if IS_ENABLED(CONFIG_IPV6)
-static void br_ip6_multicast_querier_expired(unsigned long data)
+static void br_ip6_multicast_querier_expired(struct timer_list *t)
{
- struct net_bridge *br = (void *)data;
+ struct net_bridge *br = from_timer(br, t, ip6_other_query.timer);
br_multicast_querier_expired(br, &br->ip6_own_query);
}
@@ -987,17 +1014,17 @@ out:
spin_unlock(&br->multicast_lock);
}
-static void br_ip4_multicast_port_query_expired(unsigned long data)
+static void br_ip4_multicast_port_query_expired(struct timer_list *t)
{
- struct net_bridge_port *port = (void *)data;
+ struct net_bridge_port *port = from_timer(port, t, ip4_own_query.timer);
br_multicast_port_query_expired(port, &port->ip4_own_query);
}
#if IS_ENABLED(CONFIG_IPV6)
-static void br_ip6_multicast_port_query_expired(unsigned long data)
+static void br_ip6_multicast_port_query_expired(struct timer_list *t)
{
- struct net_bridge_port *port = (void *)data;
+ struct net_bridge_port *port = from_timer(port, t, ip6_own_query.timer);
br_multicast_port_query_expired(port, &port->ip6_own_query);
}
@@ -1019,13 +1046,13 @@ int br_multicast_add_port(struct net_bridge_port *port)
{
port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY;
- setup_timer(&port->multicast_router_timer, br_multicast_router_expired,
- (unsigned long)port);
- setup_timer(&port->ip4_own_query.timer,
- br_ip4_multicast_port_query_expired, (unsigned long)port);
+ timer_setup(&port->multicast_router_timer,
+ br_multicast_router_expired, 0);
+ timer_setup(&port->ip4_own_query.timer,
+ br_ip4_multicast_port_query_expired, 0);
#if IS_ENABLED(CONFIG_IPV6)
- setup_timer(&port->ip6_own_query.timer,
- br_ip6_multicast_port_query_expired, (unsigned long)port);
+ timer_setup(&port->ip6_own_query.timer,
+ br_ip6_multicast_port_query_expired, 0);
#endif
br_mc_disabled_update(port->dev, port->br->multicast_disabled);
@@ -1364,9 +1391,12 @@ static void br_multicast_mark_router(struct net_bridge *br,
unsigned long now = jiffies;
if (!port) {
- if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY)
+ if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) {
+ if (!timer_pending(&br->multicast_router_timer))
+ br_mc_router_state_change(br, true);
mod_timer(&br->multicast_router_timer,
now + br->multicast_querier_interval);
+ }
return;
}
@@ -1451,7 +1481,7 @@ static int br_ip4_multicast_query(struct net_bridge *br,
max_delay *= br->multicast_last_member_count;
- if (mp->mglist &&
+ if (mp->host_joined &&
(timer_pending(&mp->timer) ?
time_after(mp->timer.expires, now + max_delay) :
try_to_del_timer_sync(&mp->timer) >= 0))
@@ -1535,7 +1565,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
goto out;
max_delay *= br->multicast_last_member_count;
- if (mp->mglist &&
+ if (mp->host_joined &&
(timer_pending(&mp->timer) ?
time_after(mp->timer.expires, now + max_delay) :
try_to_del_timer_sync(&mp->timer) >= 0))
@@ -1596,7 +1626,7 @@ br_multicast_leave_group(struct net_bridge *br,
br_mdb_notify(br->dev, port, group, RTM_DELMDB,
p->flags);
- if (!mp->ports && !mp->mglist &&
+ if (!mp->ports && !mp->host_joined &&
netif_running(br->dev))
mod_timer(&mp->timer, jiffies);
}
@@ -1636,7 +1666,7 @@ br_multicast_leave_group(struct net_bridge *br,
br->multicast_last_member_interval;
if (!port) {
- if (mp->mglist &&
+ if (mp->host_joined &&
(timer_pending(&mp->timer) ?
time_after(mp->timer.expires, time) :
try_to_del_timer_sync(&mp->timer) >= 0)) {
@@ -1906,17 +1936,17 @@ static void br_multicast_query_expired(struct net_bridge *br,
spin_unlock(&br->multicast_lock);
}
-static void br_ip4_multicast_query_expired(unsigned long data)
+static void br_ip4_multicast_query_expired(struct timer_list *t)
{
- struct net_bridge *br = (void *)data;
+ struct net_bridge *br = from_timer(br, t, ip4_own_query.timer);
br_multicast_query_expired(br, &br->ip4_own_query, &br->ip4_querier);
}
#if IS_ENABLED(CONFIG_IPV6)
-static void br_ip6_multicast_query_expired(unsigned long data)
+static void br_ip6_multicast_query_expired(struct timer_list *t)
{
- struct net_bridge *br = (void *)data;
+ struct net_bridge *br = from_timer(br, t, ip6_own_query.timer);
br_multicast_query_expired(br, &br->ip6_own_query, &br->ip6_querier);
}
@@ -1951,17 +1981,17 @@ void br_multicast_init(struct net_bridge *br)
br->has_ipv6_addr = 1;
spin_lock_init(&br->multicast_lock);
- setup_timer(&br->multicast_router_timer,
+ timer_setup(&br->multicast_router_timer,
br_multicast_local_router_expired, 0);
- setup_timer(&br->ip4_other_query.timer,
- br_ip4_multicast_querier_expired, (unsigned long)br);
- setup_timer(&br->ip4_own_query.timer, br_ip4_multicast_query_expired,
- (unsigned long)br);
+ timer_setup(&br->ip4_other_query.timer,
+ br_ip4_multicast_querier_expired, 0);
+ timer_setup(&br->ip4_own_query.timer,
+ br_ip4_multicast_query_expired, 0);
#if IS_ENABLED(CONFIG_IPV6)
- setup_timer(&br->ip6_other_query.timer,
- br_ip6_multicast_querier_expired, (unsigned long)br);
- setup_timer(&br->ip6_own_query.timer, br_ip6_multicast_query_expired,
- (unsigned long)br);
+ timer_setup(&br->ip6_other_query.timer,
+ br_ip6_multicast_querier_expired, 0);
+ timer_setup(&br->ip6_own_query.timer,
+ br_ip6_multicast_query_expired, 0);
#endif
}
@@ -2042,9 +2072,14 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val)
switch (val) {
case MDB_RTR_TYPE_DISABLED:
case MDB_RTR_TYPE_PERM:
+ br_mc_router_state_change(br, val == MDB_RTR_TYPE_PERM);
del_timer(&br->multicast_router_timer);
- /* fall through */
+ br->multicast_router = val;
+ err = 0;
+ break;
case MDB_RTR_TYPE_TEMP_QUERY:
+ if (br->multicast_router != MDB_RTR_TYPE_TEMP_QUERY)
+ br_mc_router_state_change(br, false);
br->multicast_router = val;
err = 0;
break;
@@ -2184,6 +2219,18 @@ bool br_multicast_enabled(const struct net_device *dev)
}
EXPORT_SYMBOL_GPL(br_multicast_enabled);
+bool br_multicast_router(const struct net_device *dev)
+{
+ struct net_bridge *br = netdev_priv(dev);
+ bool is_router;
+
+ spin_lock_bh(&br->multicast_lock);
+ is_router = br_multicast_is_router(br);
+ spin_unlock_bh(&br->multicast_lock);
+ return is_router;
+}
+EXPORT_SYMBOL_GPL(br_multicast_router);
+
int br_multicast_set_querier(struct net_bridge *br, unsigned long val)
{
unsigned long max_delay;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index de2152730809..d0ef0a8e8831 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -138,6 +138,7 @@ static inline size_t br_port_info_size(void)
+ nla_total_size(1) /* IFLA_BRPORT_PROXYARP */
+ nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */
+ nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */
+ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */
+ nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */
+ nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */
+ nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */
@@ -152,6 +153,7 @@ static inline size_t br_port_info_size(void)
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */
#endif
+ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */
+ 0;
}
@@ -208,7 +210,10 @@ static int br_port_fill_attrs(struct sk_buff *skb,
p->topology_change_ack) ||
nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) ||
nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags &
- BR_VLAN_TUNNEL)))
+ BR_VLAN_TUNNEL)) ||
+ nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) ||
+ nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS,
+ !!(p->flags & BR_NEIGH_SUPPRESS)))
return -EMSGSIZE;
timerval = br_timer_value(&p->message_age_timer);
@@ -356,14 +361,14 @@ nla_put_failure:
* Contains port and master info as well as carrier and bridge state.
*/
static int br_fill_ifinfo(struct sk_buff *skb,
- struct net_bridge_port *port,
+ const struct net_bridge_port *port,
u32 pid, u32 seq, int event, unsigned int flags,
u32 filter_mask, const struct net_device *dev)
{
+ u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
struct net_bridge *br;
struct ifinfomsg *hdr;
struct nlmsghdr *nlh;
- u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
if (port)
br = port->br;
@@ -449,28 +454,36 @@ nla_put_failure:
return -EMSGSIZE;
}
-/*
- * Notify listeners of a change in port information
- */
-void br_ifinfo_notify(int event, struct net_bridge_port *port)
+/* Notify listeners of a change in bridge or port information */
+void br_ifinfo_notify(int event, const struct net_bridge *br,
+ const struct net_bridge_port *port)
{
- struct net *net;
+ u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
+ struct net_device *dev;
struct sk_buff *skb;
int err = -ENOBUFS;
- u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
+ struct net *net;
+ u16 port_no = 0;
- if (!port)
+ if (WARN_ON(!port && !br))
return;
- net = dev_net(port->dev);
- br_debug(port->br, "port %u(%s) event %d\n",
- (unsigned int)port->port_no, port->dev->name, event);
+ if (port) {
+ dev = port->dev;
+ br = port->br;
+ port_no = port->port_no;
+ } else {
+ dev = br->dev;
+ }
+
+ net = dev_net(dev);
+ br_debug(br, "port %u(%s) event %d\n", port_no, dev->name, event);
- skb = nlmsg_new(br_nlmsg_size(port->dev, filter), GFP_ATOMIC);
+ skb = nlmsg_new(br_nlmsg_size(dev, filter), GFP_ATOMIC);
if (skb == NULL)
goto errout;
- err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, port->dev);
+ err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev);
if (err < 0) {
/* -EMSGSIZE implies BUG in br_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -483,7 +496,6 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
}
-
/*
* Dump information about all ports, in response to GETLINK
*/
@@ -501,8 +513,9 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
}
static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
- int cmd, struct bridge_vlan_info *vinfo)
+ int cmd, struct bridge_vlan_info *vinfo, bool *changed)
{
+ bool curr_change;
int err = 0;
switch (cmd) {
@@ -511,22 +524,27 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
/* if the MASTER flag is set this will act on the global
* per-VLAN entry as well
*/
- err = nbp_vlan_add(p, vinfo->vid, vinfo->flags);
- if (err)
- break;
+ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags,
+ &curr_change);
} else {
vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY;
- err = br_vlan_add(br, vinfo->vid, vinfo->flags);
+ err = br_vlan_add(br, vinfo->vid, vinfo->flags,
+ &curr_change);
}
+ if (curr_change)
+ *changed = true;
break;
case RTM_DELLINK:
if (p) {
- nbp_vlan_delete(p, vinfo->vid);
- if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
- br_vlan_delete(p->br, vinfo->vid);
- } else {
- br_vlan_delete(br, vinfo->vid);
+ if (!nbp_vlan_delete(p, vinfo->vid))
+ *changed = true;
+
+ if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) &&
+ !br_vlan_delete(p->br, vinfo->vid))
+ *changed = true;
+ } else if (!br_vlan_delete(br, vinfo->vid)) {
+ *changed = true;
}
break;
}
@@ -537,7 +555,8 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
static int br_process_vlan_info(struct net_bridge *br,
struct net_bridge_port *p, int cmd,
struct bridge_vlan_info *vinfo_curr,
- struct bridge_vlan_info **vinfo_last)
+ struct bridge_vlan_info **vinfo_last,
+ bool *changed)
{
if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK)
return -EINVAL;
@@ -567,7 +586,7 @@ static int br_process_vlan_info(struct net_bridge *br,
sizeof(struct bridge_vlan_info));
for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) {
tmp_vinfo.vid = v;
- err = br_vlan_info(br, p, cmd, &tmp_vinfo);
+ err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed);
if (err)
break;
}
@@ -576,13 +595,13 @@ static int br_process_vlan_info(struct net_bridge *br,
return err;
}
- return br_vlan_info(br, p, cmd, vinfo_curr);
+ return br_vlan_info(br, p, cmd, vinfo_curr, changed);
}
static int br_afspec(struct net_bridge *br,
struct net_bridge_port *p,
struct nlattr *af_spec,
- int cmd)
+ int cmd, bool *changed)
{
struct bridge_vlan_info *vinfo_curr = NULL;
struct bridge_vlan_info *vinfo_last = NULL;
@@ -602,7 +621,8 @@ static int br_afspec(struct net_bridge *br,
return err;
err = br_process_vlan_tunnel_info(br, p, cmd,
&tinfo_curr,
- &tinfo_last);
+ &tinfo_last,
+ changed);
if (err)
return err;
break;
@@ -611,7 +631,7 @@ static int br_afspec(struct net_bridge *br,
return -EINVAL;
vinfo_curr = nla_data(attr);
err = br_process_vlan_info(br, p, cmd, vinfo_curr,
- &vinfo_last);
+ &vinfo_last, changed);
if (err)
return err;
break;
@@ -637,6 +657,9 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
[IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 },
[IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 },
[IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 },
+ [IFLA_BRPORT_VLAN_TUNNEL] = { .type = NLA_U8 },
+ [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 },
+ [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 },
};
/* Change the state of the port and notify spanning tree */
@@ -773,6 +796,20 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
return err;
}
#endif
+
+ if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) {
+ u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]);
+
+ if (fwd_mask & BR_GROUPFWD_MACPAUSE)
+ return -EINVAL;
+ p->group_fwd_mask = fwd_mask;
+ }
+
+ err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS,
+ BR_NEIGH_SUPPRESS);
+ if (err)
+ return err;
+
br_port_flags_change(p, old_flags ^ p->flags);
return 0;
}
@@ -780,10 +817,12 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
/* Change state and parameters on port. */
int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
{
+ struct net_bridge *br = (struct net_bridge *)netdev_priv(dev);
+ struct nlattr *tb[IFLA_BRPORT_MAX + 1];
+ struct net_bridge_port *p;
struct nlattr *protinfo;
struct nlattr *afspec;
- struct net_bridge_port *p;
- struct nlattr *tb[IFLA_BRPORT_MAX + 1];
+ bool changed = false;
int err = 0;
protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO);
@@ -819,15 +858,14 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
}
if (err)
goto out;
+ changed = true;
}
- if (afspec) {
- err = br_afspec((struct net_bridge *)netdev_priv(dev), p,
- afspec, RTM_SETLINK);
- }
+ if (afspec)
+ err = br_afspec(br, p, afspec, RTM_SETLINK, &changed);
- if (err == 0)
- br_ifinfo_notify(RTM_NEWLINK, p);
+ if (changed)
+ br_ifinfo_notify(RTM_NEWLINK, br, p);
out:
return err;
}
@@ -835,8 +873,10 @@ out:
/* Delete port information */
int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
{
- struct nlattr *afspec;
+ struct net_bridge *br = (struct net_bridge *)netdev_priv(dev);
struct net_bridge_port *p;
+ struct nlattr *afspec;
+ bool changed = false;
int err = 0;
afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
@@ -848,13 +888,12 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
if (!p && !(dev->priv_flags & IFF_EBRIDGE))
return -EINVAL;
- err = br_afspec((struct net_bridge *)netdev_priv(dev), p,
- afspec, RTM_DELLINK);
- if (err == 0)
+ err = br_afspec(br, p, afspec, RTM_DELLINK, &changed);
+ if (changed)
/* Send RTM_NEWLINK because userspace
* expects RTM_NEWLINK for vlan dels
*/
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, br, p);
return err;
}
diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c
index 3712c7f0e00c..da8cb99fd259 100644
--- a/net/bridge/br_netlink_tunnel.c
+++ b/net/bridge/br_netlink_tunnel.c
@@ -198,7 +198,7 @@ static const struct nla_policy vlan_tunnel_policy[IFLA_BRIDGE_VLAN_TUNNEL_MAX +
};
static int br_vlan_tunnel_info(struct net_bridge_port *p, int cmd,
- u16 vid, u32 tun_id)
+ u16 vid, u32 tun_id, bool *changed)
{
int err = 0;
@@ -208,9 +208,12 @@ static int br_vlan_tunnel_info(struct net_bridge_port *p, int cmd,
switch (cmd) {
case RTM_SETLINK:
err = nbp_vlan_tunnel_info_add(p, vid, tun_id);
+ if (!err)
+ *changed = true;
break;
case RTM_DELLINK:
- nbp_vlan_tunnel_info_delete(p, vid);
+ if (!nbp_vlan_tunnel_info_delete(p, vid))
+ *changed = true;
break;
}
@@ -254,7 +257,8 @@ int br_parse_vlan_tunnel_info(struct nlattr *attr,
int br_process_vlan_tunnel_info(struct net_bridge *br,
struct net_bridge_port *p, int cmd,
struct vtunnel_info *tinfo_curr,
- struct vtunnel_info *tinfo_last)
+ struct vtunnel_info *tinfo_last,
+ bool *changed)
{
int err;
@@ -272,7 +276,7 @@ int br_process_vlan_tunnel_info(struct net_bridge *br,
return -EINVAL;
t = tinfo_last->tunid;
for (v = tinfo_last->vid; v <= tinfo_curr->vid; v++) {
- err = br_vlan_tunnel_info(p, cmd, v, t);
+ err = br_vlan_tunnel_info(p, cmd, v, t, changed);
if (err)
return err;
t++;
@@ -283,7 +287,7 @@ int br_process_vlan_tunnel_info(struct net_bridge *br,
if (tinfo_last->flags)
return -EINVAL;
err = br_vlan_tunnel_info(p, cmd, tinfo_curr->vid,
- tinfo_curr->tunid);
+ tinfo_curr->tunid, changed);
if (err)
return err;
memset(tinfo_last, 0, sizeof(struct vtunnel_info));
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e870cfc85b14..1312b8d20ec3 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -36,7 +36,14 @@
/* Control of forwarding link local multicast */
#define BR_GROUPFWD_DEFAULT 0
/* Don't allow forwarding of control protocols like STP, MAC PAUSE and LACP */
-#define BR_GROUPFWD_RESTRICTED 0x0007u
+enum {
+ BR_GROUPFWD_STP = BIT(0),
+ BR_GROUPFWD_MACPAUSE = BIT(1),
+ BR_GROUPFWD_LACP = BIT(2),
+};
+
+#define BR_GROUPFWD_RESTRICTED (BR_GROUPFWD_STP | BR_GROUPFWD_MACPAUSE | \
+ BR_GROUPFWD_LACP)
/* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */
#define BR_GROUPFWD_8021AD 0xB801u
@@ -202,7 +209,7 @@ struct net_bridge_mdb_entry
struct rcu_head rcu;
struct timer_list timer;
struct br_ip addr;
- bool mglist;
+ bool host_joined;
};
struct net_bridge_mdb_htable
@@ -268,6 +275,7 @@ struct net_bridge_port {
#ifdef CONFIG_NET_SWITCHDEV
int offload_fwd_mark;
#endif
+ u16 group_fwd_mask;
};
#define br_auto_port(p) ((p)->flags & BR_AUTO_MASK)
@@ -396,6 +404,7 @@ struct net_bridge {
#ifdef CONFIG_NET_SWITCHDEV
int offload_fwd_mark;
#endif
+ bool neigh_suppress_enabled;
};
struct br_input_skb_cb {
@@ -558,7 +567,8 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
void br_port_carrier_check(struct net_bridge_port *p);
int br_add_bridge(struct net *net, const char *name);
int br_del_bridge(struct net *net, const char *name);
-int br_add_if(struct net_bridge *br, struct net_device *dev);
+int br_add_if(struct net_bridge *br, struct net_device *dev,
+ struct netlink_ext_ack *extack);
int br_del_if(struct net_bridge *br, struct net_device *dev);
int br_min_mtu(const struct net_bridge *br);
netdev_features_t br_features_recompute(struct net_bridge *br,
@@ -793,7 +803,8 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
const struct net_bridge_port *port,
struct net_bridge_vlan_group *vg,
struct sk_buff *skb);
-int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
+int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags,
+ bool *changed);
int br_vlan_delete(struct net_bridge *br, u16 vid);
void br_vlan_flush(struct net_bridge *br);
struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid);
@@ -806,7 +817,8 @@ int br_vlan_set_stats(struct net_bridge *br, unsigned long val);
int br_vlan_init(struct net_bridge *br);
int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val);
int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid);
-int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
+int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
+ bool *changed);
int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
void nbp_vlan_flush(struct net_bridge_port *port);
int nbp_vlan_init(struct net_bridge_port *port);
@@ -893,8 +905,10 @@ static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
return skb;
}
-static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
+static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags,
+ bool *changed)
{
+ *changed = false;
return -EOPNOTSUPP;
}
@@ -916,8 +930,10 @@ static inline int br_vlan_init(struct net_bridge *br)
return 0;
}
-static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
+static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
+ bool *changed)
{
+ *changed = false;
return -EOPNOTSUPP;
}
@@ -1055,7 +1071,8 @@ extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr)
extern struct rtnl_link_ops br_link_ops;
int br_netlink_init(void);
void br_netlink_fini(void);
-void br_ifinfo_notify(int event, struct net_bridge_port *port);
+void br_ifinfo_notify(int event, const struct net_bridge *br,
+ const struct net_bridge_port *port);
int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev,
@@ -1130,4 +1147,11 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb)
}
#endif /* CONFIG_NET_SWITCHDEV */
+/* br_arp_nd_proxy.c */
+void br_recalculate_neigh_suppress_enabled(struct net_bridge *br);
+void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
+ u16 vid, struct net_bridge_port *p);
+void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
+ u16 vid, struct net_bridge_port *p, struct nd_msg *msg);
+struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *m);
#endif
diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h
index 4a447a378ab3..a259471bfd78 100644
--- a/net/bridge/br_private_tunnel.h
+++ b/net/bridge/br_private_tunnel.h
@@ -26,7 +26,8 @@ int br_process_vlan_tunnel_info(struct net_bridge *br,
struct net_bridge_port *p,
int cmd,
struct vtunnel_info *tinfo_curr,
- struct vtunnel_info *tinfo_last);
+ struct vtunnel_info *tinfo_last,
+ bool *changed);
int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg);
int br_fill_vlan_tunnel_info(struct sk_buff *skb,
struct net_bridge_vlan_group *vg);
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 8f56c2d1f1a7..b6941961a876 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -123,7 +123,7 @@ static void br_root_port_block(const struct net_bridge *br,
(unsigned int) p->port_no, p->dev->name);
br_set_state(p, BR_STATE_LISTENING);
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, NULL, p);
if (br->forward_delay > 0)
mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay);
@@ -403,7 +403,7 @@ static void br_make_blocking(struct net_bridge_port *p)
br_topology_change_detection(p->br);
br_set_state(p, BR_STATE_BLOCKING);
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, NULL, p);
del_timer(&p->forward_delay_timer);
}
@@ -426,7 +426,7 @@ static void br_make_forwarding(struct net_bridge_port *p)
else
br_set_state(p, BR_STATE_LEARNING);
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, NULL, p);
if (br->forward_delay != 0)
mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay);
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 89110319ef0f..808e2b914015 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -96,7 +96,7 @@ void br_stp_enable_port(struct net_bridge_port *p)
{
br_init_port(p);
br_port_state_selection(p->br);
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, NULL, p);
}
/* called under bridge lock */
@@ -111,7 +111,7 @@ void br_stp_disable_port(struct net_bridge_port *p)
p->topology_change_ack = 0;
p->config_pending = 0;
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, NULL, p);
del_timer(&p->message_age_timer);
del_timer(&p->forward_delay_timer);
diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index 60b6fe277a8b..e7739de5f0e1 100644
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -31,9 +31,9 @@ static int br_is_designated_for_some_port(const struct net_bridge *br)
return 0;
}
-static void br_hello_timer_expired(unsigned long arg)
+static void br_hello_timer_expired(struct timer_list *t)
{
- struct net_bridge *br = (struct net_bridge *)arg;
+ struct net_bridge *br = from_timer(br, t, hello_timer);
br_debug(br, "hello timer expired\n");
spin_lock(&br->lock);
@@ -47,9 +47,9 @@ static void br_hello_timer_expired(unsigned long arg)
spin_unlock(&br->lock);
}
-static void br_message_age_timer_expired(unsigned long arg)
+static void br_message_age_timer_expired(struct timer_list *t)
{
- struct net_bridge_port *p = (struct net_bridge_port *) arg;
+ struct net_bridge_port *p = from_timer(p, t, message_age_timer);
struct net_bridge *br = p->br;
const bridge_id *id = &p->designated_bridge;
int was_root;
@@ -80,9 +80,9 @@ static void br_message_age_timer_expired(unsigned long arg)
spin_unlock(&br->lock);
}
-static void br_forward_delay_timer_expired(unsigned long arg)
+static void br_forward_delay_timer_expired(struct timer_list *t)
{
- struct net_bridge_port *p = (struct net_bridge_port *) arg;
+ struct net_bridge_port *p = from_timer(p, t, forward_delay_timer);
struct net_bridge *br = p->br;
br_debug(br, "port %u(%s) forward delay timer\n",
@@ -99,14 +99,14 @@ static void br_forward_delay_timer_expired(unsigned long arg)
netif_carrier_on(br->dev);
}
rcu_read_lock();
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, NULL, p);
rcu_read_unlock();
spin_unlock(&br->lock);
}
-static void br_tcn_timer_expired(unsigned long arg)
+static void br_tcn_timer_expired(struct timer_list *t)
{
- struct net_bridge *br = (struct net_bridge *) arg;
+ struct net_bridge *br = from_timer(br, t, tcn_timer);
br_debug(br, "tcn timer expired\n");
spin_lock(&br->lock);
@@ -118,9 +118,9 @@ static void br_tcn_timer_expired(unsigned long arg)
spin_unlock(&br->lock);
}
-static void br_topology_change_timer_expired(unsigned long arg)
+static void br_topology_change_timer_expired(struct timer_list *t)
{
- struct net_bridge *br = (struct net_bridge *) arg;
+ struct net_bridge *br = from_timer(br, t, topology_change_timer);
br_debug(br, "topo change timer expired\n");
spin_lock(&br->lock);
@@ -129,9 +129,9 @@ static void br_topology_change_timer_expired(unsigned long arg)
spin_unlock(&br->lock);
}
-static void br_hold_timer_expired(unsigned long arg)
+static void br_hold_timer_expired(struct timer_list *t)
{
- struct net_bridge_port *p = (struct net_bridge_port *) arg;
+ struct net_bridge_port *p = from_timer(p, t, hold_timer);
br_debug(p->br, "port %u(%s) hold timer expired\n",
(unsigned int) p->port_no, p->dev->name);
@@ -144,27 +144,17 @@ static void br_hold_timer_expired(unsigned long arg)
void br_stp_timer_init(struct net_bridge *br)
{
- setup_timer(&br->hello_timer, br_hello_timer_expired,
- (unsigned long) br);
-
- setup_timer(&br->tcn_timer, br_tcn_timer_expired,
- (unsigned long) br);
-
- setup_timer(&br->topology_change_timer,
- br_topology_change_timer_expired,
- (unsigned long) br);
+ timer_setup(&br->hello_timer, br_hello_timer_expired, 0);
+ timer_setup(&br->tcn_timer, br_tcn_timer_expired, 0);
+ timer_setup(&br->topology_change_timer,
+ br_topology_change_timer_expired, 0);
}
void br_stp_port_timer_init(struct net_bridge_port *p)
{
- setup_timer(&p->message_age_timer, br_message_age_timer_expired,
- (unsigned long) p);
-
- setup_timer(&p->forward_delay_timer, br_forward_delay_timer_expired,
- (unsigned long) p);
-
- setup_timer(&p->hold_timer, br_hold_timer_expired,
- (unsigned long) p);
+ timer_setup(&p->message_age_timer, br_message_age_timer_expired, 0);
+ timer_setup(&p->forward_delay_timer, br_forward_delay_timer_expired, 0);
+ timer_setup(&p->hold_timer, br_hold_timer_expired, 0);
}
/* Report ticks left (in USER_HZ) used for API */
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 5d5d413a6cf8..0254c35b2bf0 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -165,6 +165,23 @@ static int store_flush(struct net_bridge_port *p, unsigned long v)
}
static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush);
+static ssize_t show_group_fwd_mask(struct net_bridge_port *p, char *buf)
+{
+ return sprintf(buf, "%#x\n", p->group_fwd_mask);
+}
+
+static int store_group_fwd_mask(struct net_bridge_port *p,
+ unsigned long v)
+{
+ if (v & BR_GROUPFWD_MACPAUSE)
+ return -EINVAL;
+ p->group_fwd_mask = v;
+
+ return 0;
+}
+static BRPORT_ATTR(group_fwd_mask, S_IRUGO | S_IWUSR, show_group_fwd_mask,
+ store_group_fwd_mask);
+
BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE);
BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK);
@@ -174,6 +191,7 @@ BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP);
BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI);
BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD);
BRPORT_ATTR_FLAG(broadcast_flood, BR_BCAST_FLOOD);
+BRPORT_ATTR_FLAG(neigh_suppress, BR_NEIGH_SUPPRESS);
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -223,6 +241,8 @@ static const struct brport_attribute *brport_attrs[] = {
&brport_attr_proxyarp_wifi,
&brport_attr_multicast_flood,
&brport_attr_broadcast_flood,
+ &brport_attr_group_fwd_mask,
+ &brport_attr_neigh_suppress,
NULL
};
@@ -260,7 +280,7 @@ static ssize_t brport_store(struct kobject *kobj,
ret = brport_attr->store(p, val);
spin_unlock_bh(&p->br->lock);
if (!ret) {
- br_ifinfo_notify(RTM_NEWLINK, p);
+ br_ifinfo_notify(RTM_NEWLINK, NULL, p);
ret = count;
}
}
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 233a30040c91..51935270c651 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -32,27 +32,34 @@ static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid)
return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params);
}
-static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid)
+static bool __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid)
{
if (vg->pvid == vid)
- return;
+ return false;
smp_wmb();
vg->pvid = vid;
+
+ return true;
}
-static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid)
+static bool __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid)
{
if (vg->pvid != vid)
- return;
+ return false;
smp_wmb();
vg->pvid = 0;
+
+ return true;
}
-static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
+/* return true if anything changed, false otherwise */
+static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
{
struct net_bridge_vlan_group *vg;
+ u16 old_flags = v->flags;
+ bool ret;
if (br_vlan_is_master(v))
vg = br_vlan_group(v->br);
@@ -60,14 +67,16 @@ static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
vg = nbp_vlan_group(v->port);
if (flags & BRIDGE_VLAN_INFO_PVID)
- __vlan_add_pvid(vg, v->vid);
+ ret = __vlan_add_pvid(vg, v->vid);
else
- __vlan_delete_pvid(vg, v->vid);
+ ret = __vlan_delete_pvid(vg, v->vid);
if (flags & BRIDGE_VLAN_INFO_UNTAGGED)
v->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
else
v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED;
+
+ return ret || !!(old_flags ^ v->flags);
}
static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br,
@@ -151,8 +160,10 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid
vg = br_vlan_group(br);
masterv = br_vlan_find(vg, vid);
if (!masterv) {
+ bool changed;
+
/* missing global ctx, create it now */
- if (br_vlan_add(br, vid, 0))
+ if (br_vlan_add(br, vid, 0, &changed))
return NULL;
masterv = br_vlan_find(vg, vid);
if (WARN_ON(!masterv))
@@ -232,8 +243,11 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
/* need to work on the master vlan too */
if (flags & BRIDGE_VLAN_INFO_MASTER) {
- err = br_vlan_add(br, v->vid, flags |
- BRIDGE_VLAN_INFO_BRENTRY);
+ bool changed;
+
+ err = br_vlan_add(br, v->vid,
+ flags | BRIDGE_VLAN_INFO_BRENTRY,
+ &changed);
if (err)
goto out_filt;
}
@@ -550,8 +564,9 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
+ * changed must be true only if the vlan was created or updated
*/
-int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
+int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed)
{
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *vlan;
@@ -559,6 +574,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
ASSERT_RTNL();
+ *changed = false;
vg = br_vlan_group(br);
vlan = br_vlan_find(vg, vid);
if (vlan) {
@@ -576,8 +592,11 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
refcount_inc(&vlan->refcnt);
vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY;
vg->num_vlans++;
+ *changed = true;
}
- __vlan_add_flags(vlan, flags);
+ if (__vlan_add_flags(vlan, flags))
+ *changed = true;
+
return 0;
}
@@ -600,6 +619,8 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
if (ret) {
free_percpu(vlan->stats);
kfree(vlan);
+ } else {
+ *changed = true;
}
return ret;
@@ -824,9 +845,10 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
const struct net_bridge_vlan *pvent;
struct net_bridge_vlan_group *vg;
struct net_bridge_port *p;
+ unsigned long *changed;
+ bool vlchange;
u16 old_pvid;
int err = 0;
- unsigned long *changed;
if (!pvid) {
br_vlan_disable_default_pvid(br);
@@ -850,7 +872,8 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
err = br_vlan_add(br, pvid,
BRIDGE_VLAN_INFO_PVID |
BRIDGE_VLAN_INFO_UNTAGGED |
- BRIDGE_VLAN_INFO_BRENTRY);
+ BRIDGE_VLAN_INFO_BRENTRY,
+ &vlchange);
if (err)
goto out;
br_vlan_delete(br, old_pvid);
@@ -869,7 +892,8 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
err = nbp_vlan_add(p, pvid,
BRIDGE_VLAN_INFO_PVID |
- BRIDGE_VLAN_INFO_UNTAGGED);
+ BRIDGE_VLAN_INFO_UNTAGGED,
+ &vlchange);
if (err)
goto err_port;
nbp_vlan_delete(p, old_pvid);
@@ -890,7 +914,8 @@ err_port:
if (old_pvid)
nbp_vlan_add(p, old_pvid,
BRIDGE_VLAN_INFO_PVID |
- BRIDGE_VLAN_INFO_UNTAGGED);
+ BRIDGE_VLAN_INFO_UNTAGGED,
+ &vlchange);
nbp_vlan_delete(p, pvid);
}
@@ -899,7 +924,8 @@ err_port:
br_vlan_add(br, old_pvid,
BRIDGE_VLAN_INFO_PVID |
BRIDGE_VLAN_INFO_UNTAGGED |
- BRIDGE_VLAN_INFO_BRENTRY);
+ BRIDGE_VLAN_INFO_BRENTRY,
+ &vlchange);
br_vlan_delete(br, pvid);
}
goto out;
@@ -931,6 +957,7 @@ int br_vlan_init(struct net_bridge *br)
{
struct net_bridge_vlan_group *vg;
int ret = -ENOMEM;
+ bool changed;
vg = kzalloc(sizeof(*vg), GFP_KERNEL);
if (!vg)
@@ -947,7 +974,7 @@ int br_vlan_init(struct net_bridge *br)
rcu_assign_pointer(br->vlgrp, vg);
ret = br_vlan_add(br, 1,
BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED |
- BRIDGE_VLAN_INFO_BRENTRY);
+ BRIDGE_VLAN_INFO_BRENTRY, &changed);
if (ret)
goto err_vlan_add;
@@ -992,9 +1019,12 @@ int nbp_vlan_init(struct net_bridge_port *p)
INIT_LIST_HEAD(&vg->vlan_list);
rcu_assign_pointer(p->vlgrp, vg);
if (p->br->default_pvid) {
+ bool changed;
+
ret = nbp_vlan_add(p, p->br->default_pvid,
BRIDGE_VLAN_INFO_PVID |
- BRIDGE_VLAN_INFO_UNTAGGED);
+ BRIDGE_VLAN_INFO_UNTAGGED,
+ &changed);
if (ret)
goto err_vlan_add;
}
@@ -1016,8 +1046,10 @@ err_vlan_enabled:
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
+ * changed must be true only if the vlan was created or updated
*/
-int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
+int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
+ bool *changed)
{
struct switchdev_obj_port_vlan v = {
.obj.orig_dev = port->dev,
@@ -1031,13 +1063,15 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
ASSERT_RTNL();
+ *changed = false;
vlan = br_vlan_find(nbp_vlan_group(port), vid);
if (vlan) {
/* Pass the flags to the hardware bridge */
ret = switchdev_port_obj_add(port->dev, &v.obj);
if (ret && ret != -EOPNOTSUPP)
return ret;
- __vlan_add_flags(vlan, flags);
+ *changed = __vlan_add_flags(vlan, flags);
+
return 0;
}
@@ -1050,6 +1084,8 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
ret = __vlan_add(vlan, flags);
if (ret)
kfree(vlan);
+ else
+ *changed = true;
return ret;
}
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 3b3dcf719e07..37817d25b63d 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -2112,9 +2112,8 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base,
for (i = 0, j = 1 ; j < 4 ; j++, i++) {
struct compat_ebt_entry_mwt *match32;
unsigned int size;
- char *buf = buf_start;
+ char *buf = buf_start + offsets[i];
- buf = buf_start + offsets[i];
if (offsets[i] > offsets[j])
return -EINVAL;
diff --git a/net/can/af_can.c b/net/can/af_can.c
index ecd5c703d11e..003b2d6d655f 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -887,8 +887,8 @@ static int can_pernet_init(struct net *net)
if (IS_ENABLED(CONFIG_PROC_FS)) {
/* the statistics are updated every second (timer triggered) */
if (stats_timer) {
- setup_timer(&net->can.can_stattimer, can_stat_update,
- (unsigned long)net);
+ timer_setup(&net->can.can_stattimer, can_stat_update,
+ 0);
mod_timer(&net->can.can_stattimer,
round_jiffies(jiffies + HZ));
}
diff --git a/net/can/af_can.h b/net/can/af_can.h
index d0ef45bb2a72..eca6463c6213 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -113,6 +113,6 @@ struct s_pstats {
/* function prototypes for the CAN networklayer procfs (proc.c) */
void can_init_proc(struct net *net);
void can_remove_proc(struct net *net);
-void can_stat_update(unsigned long data);
+void can_stat_update(struct timer_list *t);
#endif /* AF_CAN_H */
diff --git a/net/can/proc.c b/net/can/proc.c
index 83045f00c63c..d979b3dc49a6 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -115,9 +115,9 @@ static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif,
return rate;
}
-void can_stat_update(unsigned long data)
+void can_stat_update(struct timer_list *t)
{
- struct net *net = (struct net *)data;
+ struct net *net = from_timer(net, t, can.can_stattimer);
struct s_stats *can_stats = net->can.can_stats;
unsigned long j = jiffies; /* snapshot */
@@ -221,7 +221,7 @@ static int can_stats_proc_show(struct seq_file *m, void *v)
seq_putc(m, '\n');
- if (net->can.can_stattimer.function == can_stat_update) {
+ if (net->can.can_stattimer.function == (TIMER_FUNC_TYPE)can_stat_update) {
seq_printf(m, " %8ld %% total match ratio (RXMR)\n",
can_stats->total_rx_match_ratio);
@@ -291,7 +291,7 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v)
user_reset = 1;
- if (net->can.can_stattimer.function == can_stat_update) {
+ if (net->can.can_stattimer.function == (TIMER_FUNC_TYPE)can_stat_update) {
seq_printf(m, "Scheduled statistic reset #%ld.\n",
can_pstats->stats_reset + 1);
} else {
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 3964c108b169..522873ed120b 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -189,7 +189,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
}
if (!skb->len) {
skb = skb_set_peeked(skb);
- if (unlikely(IS_ERR(skb))) {
+ if (IS_ERR(skb)) {
*err = PTR_ERR(skb);
return NULL;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 61559ca3980b..8ee29f4f5fa9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -145,6 +145,7 @@
#include <linux/crash_dump.h>
#include <linux/sctp.h>
#include <net/udp_tunnel.h>
+#include <linux/net_namespace.h>
#include "net-sysfs.h"
@@ -162,7 +163,6 @@ static struct list_head offload_base __read_mostly;
static int netif_rx_internal(struct sk_buff *skb);
static int call_netdevice_notifiers_info(unsigned long val,
- struct net_device *dev,
struct netdev_notifier_info *info);
static struct napi_struct *napi_by_id(unsigned int napi_id);
@@ -188,6 +188,8 @@ static struct napi_struct *napi_by_id(unsigned int napi_id);
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base_lock);
+static DEFINE_MUTEX(ifalias_mutex);
+
/* protects napi_hash addition/deletion and napi_gen_id */
static DEFINE_SPINLOCK(napi_hash_lock);
@@ -1062,7 +1064,10 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
unsigned long *inuse;
struct net_device *d;
- p = strnchr(name, IFNAMSIZ-1, '%');
+ if (!dev_valid_name(name))
+ return -EINVAL;
+
+ p = strchr(name, '%');
if (p) {
/*
* Verify the string as this thing may have come from
@@ -1093,8 +1098,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
free_page((unsigned long) inuse);
}
- if (buf != name)
- snprintf(buf, IFNAMSIZ, name, i);
+ snprintf(buf, IFNAMSIZ, name, i);
if (!__dev_get_by_name(net, buf))
return i;
@@ -1102,7 +1106,21 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
* when the name is long and there isn't enough space left
* for the digits, or if all bits are used.
*/
- return -ENFILE;
+ return p ? -ENFILE : -EEXIST;
+}
+
+static int dev_alloc_name_ns(struct net *net,
+ struct net_device *dev,
+ const char *name)
+{
+ char buf[IFNAMSIZ];
+ int ret;
+
+ BUG_ON(!net);
+ ret = __dev_alloc_name(net, name, buf);
+ if (ret >= 0)
+ strlcpy(dev->name, buf, IFNAMSIZ);
+ return ret;
}
/**
@@ -1121,48 +1139,14 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
int dev_alloc_name(struct net_device *dev, const char *name)
{
- char buf[IFNAMSIZ];
- struct net *net;
- int ret;
-
- BUG_ON(!dev_net(dev));
- net = dev_net(dev);
- ret = __dev_alloc_name(net, name, buf);
- if (ret >= 0)
- strlcpy(dev->name, buf, IFNAMSIZ);
- return ret;
+ return dev_alloc_name_ns(dev_net(dev), dev, name);
}
EXPORT_SYMBOL(dev_alloc_name);
-static int dev_alloc_name_ns(struct net *net,
- struct net_device *dev,
- const char *name)
-{
- char buf[IFNAMSIZ];
- int ret;
-
- ret = __dev_alloc_name(net, name, buf);
- if (ret >= 0)
- strlcpy(dev->name, buf, IFNAMSIZ);
- return ret;
-}
-
int dev_get_valid_name(struct net *net, struct net_device *dev,
const char *name)
{
- BUG_ON(!net);
-
- if (!dev_valid_name(name))
- return -EINVAL;
-
- if (strchr(name, '%'))
- return dev_alloc_name_ns(net, dev, name);
- else if (__dev_get_by_name(net, name))
- return -EEXIST;
- else if (dev->name != name)
- strlcpy(dev->name, name, IFNAMSIZ);
-
- return 0;
+ return dev_alloc_name_ns(net, dev, name);
}
EXPORT_SYMBOL(dev_get_valid_name);
@@ -1265,29 +1249,53 @@ rollback:
*/
int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
{
- char *new_ifalias;
-
- ASSERT_RTNL();
+ struct dev_ifalias *new_alias = NULL;
if (len >= IFALIASZ)
return -EINVAL;
- if (!len) {
- kfree(dev->ifalias);
- dev->ifalias = NULL;
- return 0;
+ if (len) {
+ new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL);
+ if (!new_alias)
+ return -ENOMEM;
+
+ memcpy(new_alias->ifalias, alias, len);
+ new_alias->ifalias[len] = 0;
}
- new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
- if (!new_ifalias)
- return -ENOMEM;
- dev->ifalias = new_ifalias;
- memcpy(dev->ifalias, alias, len);
- dev->ifalias[len] = 0;
+ mutex_lock(&ifalias_mutex);
+ rcu_swap_protected(dev->ifalias, new_alias,
+ mutex_is_locked(&ifalias_mutex));
+ mutex_unlock(&ifalias_mutex);
+
+ if (new_alias)
+ kfree_rcu(new_alias, rcuhead);
return len;
}
+/**
+ * dev_get_alias - get ifalias of a device
+ * @dev: device
+ * @name: buffer to store name of ifalias
+ * @len: size of buffer
+ *
+ * get ifalias for a device. Caller must make sure dev cannot go
+ * away, e.g. rcu read lock or own a reference count to device.
+ */
+int dev_get_alias(const struct net_device *dev, char *name, size_t len)
+{
+ const struct dev_ifalias *alias;
+ int ret = 0;
+
+ rcu_read_lock();
+ alias = rcu_dereference(dev->ifalias);
+ if (alias)
+ ret = snprintf(name, len, "%s", alias->ifalias);
+ rcu_read_unlock();
+
+ return ret;
+}
/**
* netdev_features_change - device changes features
@@ -1312,10 +1320,11 @@ EXPORT_SYMBOL(netdev_features_change);
void netdev_state_change(struct net_device *dev)
{
if (dev->flags & IFF_UP) {
- struct netdev_notifier_change_info change_info;
+ struct netdev_notifier_change_info change_info = {
+ .info.dev = dev,
+ };
- change_info.flags_changed = 0;
- call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+ call_netdevice_notifiers_info(NETDEV_CHANGE,
&change_info.info);
rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
}
@@ -1536,9 +1545,10 @@ EXPORT_SYMBOL(dev_disable_lro);
static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
struct net_device *dev)
{
- struct netdev_notifier_info info;
+ struct netdev_notifier_info info = {
+ .dev = dev,
+ };
- netdev_notifier_info_init(&info, dev);
return nb->notifier_call(nb, val, &info);
}
@@ -1663,11 +1673,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
*/
static int call_netdevice_notifiers_info(unsigned long val,
- struct net_device *dev,
struct netdev_notifier_info *info)
{
ASSERT_RTNL();
- netdev_notifier_info_init(info, dev);
return raw_notifier_call_chain(&netdev_chain, val, info);
}
@@ -1682,9 +1690,11 @@ static int call_netdevice_notifiers_info(unsigned long val,
int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
- struct netdev_notifier_info info;
+ struct netdev_notifier_info info = {
+ .dev = dev,
+ };
- return call_netdevice_notifiers_info(val, dev, &info);
+ return call_netdevice_notifiers_info(val, &info);
}
EXPORT_SYMBOL(call_netdevice_notifiers);
@@ -2012,6 +2022,7 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
return 0;
}
+EXPORT_SYMBOL(netdev_txq_to_tc);
#ifdef CONFIG_XPS
static DEFINE_MUTEX(xps_map_mutex);
@@ -3245,22 +3256,22 @@ EXPORT_SYMBOL(dev_loopback_xmit);
static struct sk_buff *
sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
{
- struct tcf_proto *cl = rcu_dereference_bh(dev->egress_cl_list);
+ struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress);
struct tcf_result cl_res;
- if (!cl)
+ if (!miniq)
return skb;
/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
- qdisc_bstats_cpu_update(cl->q, skb);
+ mini_qdisc_bstats_cpu_update(miniq, skb);
- switch (tcf_classify(skb, cl, &cl_res, false)) {
+ switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
case TC_ACT_OK:
case TC_ACT_RECLASSIFY:
skb->tc_index = TC_H_MIN(cl_res.classid);
break;
case TC_ACT_SHOT:
- qdisc_qstats_cpu_drop(cl->q);
+ mini_qdisc_qstats_cpu_drop(miniq);
*ret = NET_XMIT_DROP;
kfree_skb(skb);
return NULL;
@@ -3864,8 +3875,8 @@ drop:
static u32 netif_receive_generic_xdp(struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
+ u32 metalen, act = XDP_DROP;
struct xdp_buff xdp;
- u32 act = XDP_DROP;
void *orig_data;
int hlen, off;
u32 mac_len;
@@ -3876,8 +3887,25 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
if (skb_cloned(skb))
return XDP_PASS;
- if (skb_linearize(skb))
- goto do_drop;
+ /* XDP packets must be linear and must have sufficient headroom
+ * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
+ * native XDP provides, thus we need to do it here as well.
+ */
+ if (skb_is_nonlinear(skb) ||
+ skb_headroom(skb) < XDP_PACKET_HEADROOM) {
+ int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
+ int troom = skb->tail + skb->data_len - skb->end;
+
+ /* In case we have to go down the path and also linearize,
+ * then lets do the pskb_expand_head() work just once here.
+ */
+ if (pskb_expand_head(skb,
+ hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
+ troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
+ goto do_drop;
+ if (troom > 0 && __skb_linearize(skb))
+ goto do_drop;
+ }
/* The XDP program wants to see the packet starting at the MAC
* header.
@@ -3885,6 +3913,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
mac_len = skb->data - skb_mac_header(skb);
hlen = skb_headlen(skb) + mac_len;
xdp.data = skb->data - mac_len;
+ xdp.data_meta = xdp.data;
xdp.data_end = xdp.data + hlen;
xdp.data_hard_start = skb->data - skb_headroom(skb);
orig_data = xdp.data;
@@ -3902,10 +3931,12 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
case XDP_REDIRECT:
case XDP_TX:
__skb_push(skb, mac_len);
- /* fall through */
+ break;
case XDP_PASS:
+ metalen = xdp.data - xdp.data_meta;
+ if (metalen)
+ skb_metadata_set(skb, metalen);
break;
-
default:
bpf_warn_invalid_xdp_action(act);
/* fall through */
@@ -4140,7 +4171,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
struct net_device *orig_dev)
{
#ifdef CONFIG_NET_CLS_ACT
- struct tcf_proto *cl = rcu_dereference_bh(skb->dev->ingress_cl_list);
+ struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
struct tcf_result cl_res;
/* If there's at least one ingress present somewhere (so
@@ -4148,8 +4179,9 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
* that are not configured with an ingress qdisc will bail
* out here.
*/
- if (!cl)
+ if (!miniq)
return skb;
+
if (*pt_prev) {
*ret = deliver_skb(skb, *pt_prev, orig_dev);
*pt_prev = NULL;
@@ -4157,15 +4189,15 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
qdisc_skb_cb(skb)->pkt_len = skb->len;
skb->tc_at_ingress = 1;
- qdisc_bstats_cpu_update(cl->q, skb);
+ mini_qdisc_bstats_cpu_update(miniq, skb);
- switch (tcf_classify(skb, cl, &cl_res, false)) {
+ switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
case TC_ACT_OK:
case TC_ACT_RECLASSIFY:
skb->tc_index = TC_H_MIN(cl_res.classid);
break;
case TC_ACT_SHOT:
- qdisc_qstats_cpu_drop(cl->q);
+ mini_qdisc_qstats_cpu_drop(miniq);
kfree_skb(skb);
return NULL;
case TC_ACT_STOLEN:
@@ -4443,6 +4475,33 @@ out:
return ret;
}
+/**
+ * netif_receive_skb_core - special purpose version of netif_receive_skb
+ * @skb: buffer to process
+ *
+ * More direct receive version of netif_receive_skb(). It should
+ * only be used by callers that have a need to skip RPS and Generic XDP.
+ * Caller must also take care of handling if (page_is_)pfmemalloc.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ *
+ * Return values (usually ignored):
+ * NET_RX_SUCCESS: no congestion
+ * NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb_core(struct sk_buff *skb)
+{
+ int ret;
+
+ rcu_read_lock();
+ ret = __netif_receive_skb_core(skb, false);
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(netif_receive_skb_core);
+
static int __netif_receive_skb(struct sk_buff *skb)
{
int ret;
@@ -4468,7 +4527,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
return ret;
}
-static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp)
+static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
{
struct bpf_prog *old = rtnl_dereference(dev->xdp_prog);
struct bpf_prog *new = xdp->prog;
@@ -4695,6 +4754,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
diffs |= p->vlan_tci ^ skb->vlan_tci;
diffs |= skb_metadata_dst_cmp(p, skb);
+ diffs |= skb_metadata_differs(p, skb);
if (maclen == ETH_HLEN)
diffs |= compare_ether_header(skb_mac_header(p),
skb_mac_header(skb));
@@ -6228,9 +6288,19 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
static int __netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev, bool master,
- void *upper_priv, void *upper_info)
-{
- struct netdev_notifier_changeupper_info changeupper_info;
+ void *upper_priv, void *upper_info,
+ struct netlink_ext_ack *extack)
+{
+ struct netdev_notifier_changeupper_info changeupper_info = {
+ .info = {
+ .dev = dev,
+ .extack = extack,
+ },
+ .upper_dev = upper_dev,
+ .master = master,
+ .linking = true,
+ .upper_info = upper_info,
+ };
int ret = 0;
ASSERT_RTNL();
@@ -6248,12 +6318,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
if (master && netdev_master_upper_dev_get(dev))
return -EBUSY;
- changeupper_info.upper_dev = upper_dev;
- changeupper_info.master = master;
- changeupper_info.linking = true;
- changeupper_info.upper_info = upper_info;
-
- ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+ ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER,
&changeupper_info.info);
ret = notifier_to_errno(ret);
if (ret)
@@ -6264,7 +6329,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
if (ret)
return ret;
- ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+ ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
ret = notifier_to_errno(ret);
if (ret)
@@ -6289,9 +6354,11 @@ rollback:
* returns zero.
*/
int netdev_upper_dev_link(struct net_device *dev,
- struct net_device *upper_dev)
+ struct net_device *upper_dev,
+ struct netlink_ext_ack *extack)
{
- return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL);
+ return __netdev_upper_dev_link(dev, upper_dev, false,
+ NULL, NULL, extack);
}
EXPORT_SYMBOL(netdev_upper_dev_link);
@@ -6310,10 +6377,11 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
*/
int netdev_master_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev,
- void *upper_priv, void *upper_info)
+ void *upper_priv, void *upper_info,
+ struct netlink_ext_ack *extack)
{
return __netdev_upper_dev_link(dev, upper_dev, true,
- upper_priv, upper_info);
+ upper_priv, upper_info, extack);
}
EXPORT_SYMBOL(netdev_master_upper_dev_link);
@@ -6328,20 +6396,24 @@ EXPORT_SYMBOL(netdev_master_upper_dev_link);
void netdev_upper_dev_unlink(struct net_device *dev,
struct net_device *upper_dev)
{
- struct netdev_notifier_changeupper_info changeupper_info;
+ struct netdev_notifier_changeupper_info changeupper_info = {
+ .info = {
+ .dev = dev,
+ },
+ .upper_dev = upper_dev,
+ .linking = false,
+ };
ASSERT_RTNL();
- changeupper_info.upper_dev = upper_dev;
changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev;
- changeupper_info.linking = false;
- call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+ call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER,
&changeupper_info.info);
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
- call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+ call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
@@ -6357,11 +6429,13 @@ EXPORT_SYMBOL(netdev_upper_dev_unlink);
void netdev_bonding_info_change(struct net_device *dev,
struct netdev_bonding_info *bonding_info)
{
- struct netdev_notifier_bonding_info info;
+ struct netdev_notifier_bonding_info info = {
+ .info.dev = dev,
+ };
memcpy(&info.bonding_info, bonding_info,
sizeof(struct netdev_bonding_info));
- call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev,
+ call_netdevice_notifiers_info(NETDEV_BONDING_INFO,
&info.info);
}
EXPORT_SYMBOL(netdev_bonding_info_change);
@@ -6487,11 +6561,13 @@ EXPORT_SYMBOL(dev_get_nest_level);
void netdev_lower_state_changed(struct net_device *lower_dev,
void *lower_state_info)
{
- struct netdev_notifier_changelowerstate_info changelowerstate_info;
+ struct netdev_notifier_changelowerstate_info changelowerstate_info = {
+ .info.dev = lower_dev,
+ };
ASSERT_RTNL();
changelowerstate_info.lower_state_info = lower_state_info;
- call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, lower_dev,
+ call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE,
&changelowerstate_info.info);
}
EXPORT_SYMBOL(netdev_lower_state_changed);
@@ -6782,11 +6858,14 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
if (dev->flags & IFF_UP &&
(changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) {
- struct netdev_notifier_change_info change_info;
+ struct netdev_notifier_change_info change_info = {
+ .info = {
+ .dev = dev,
+ },
+ .flags_changed = changes,
+ };
- change_info.flags_changed = changes;
- call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
- &change_info.info);
+ call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info);
}
}
@@ -6993,26 +7072,26 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
}
EXPORT_SYMBOL(dev_change_proto_down);
-u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id)
+u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op, u32 *prog_id)
{
- struct netdev_xdp xdp;
+ struct netdev_bpf xdp;
memset(&xdp, 0, sizeof(xdp));
xdp.command = XDP_QUERY_PROG;
/* Query must always succeed. */
- WARN_ON(xdp_op(dev, &xdp) < 0);
+ WARN_ON(bpf_op(dev, &xdp) < 0);
if (prog_id)
*prog_id = xdp.prog_id;
return xdp.prog_attached;
}
-static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op,
+static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
struct netlink_ext_ack *extack, u32 flags,
struct bpf_prog *prog)
{
- struct netdev_xdp xdp;
+ struct netdev_bpf xdp;
memset(&xdp, 0, sizeof(xdp));
if (flags & XDP_FLAGS_HW_MODE)
@@ -7023,7 +7102,7 @@ static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op,
xdp.flags = flags;
xdp.prog = prog;
- return xdp_op(dev, &xdp);
+ return bpf_op(dev, &xdp);
}
/**
@@ -7040,32 +7119,36 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
{
const struct net_device_ops *ops = dev->netdev_ops;
struct bpf_prog *prog = NULL;
- xdp_op_t xdp_op, xdp_chk;
+ bpf_op_t bpf_op, bpf_chk;
int err;
ASSERT_RTNL();
- xdp_op = xdp_chk = ops->ndo_xdp;
- if (!xdp_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE)))
+ bpf_op = bpf_chk = ops->ndo_bpf;
+ if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE)))
return -EOPNOTSUPP;
- if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE))
- xdp_op = generic_xdp_install;
- if (xdp_op == xdp_chk)
- xdp_chk = generic_xdp_install;
+ if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE))
+ bpf_op = generic_xdp_install;
+ if (bpf_op == bpf_chk)
+ bpf_chk = generic_xdp_install;
if (fd >= 0) {
- if (xdp_chk && __dev_xdp_attached(dev, xdp_chk, NULL))
+ if (bpf_chk && __dev_xdp_attached(dev, bpf_chk, NULL))
return -EEXIST;
if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
- __dev_xdp_attached(dev, xdp_op, NULL))
+ __dev_xdp_attached(dev, bpf_op, NULL))
return -EBUSY;
- prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
+ if (bpf_op == ops->ndo_bpf)
+ prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
+ dev);
+ else
+ prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
if (IS_ERR(prog))
return PTR_ERR(prog);
}
- err = dev_xdp_install(dev, xdp_op, extack, flags, prog);
+ err = dev_xdp_install(dev, bpf_op, extack, flags, prog);
if (err < 0 && prog)
bpf_prog_put(prog);
@@ -7157,7 +7240,7 @@ static void rollback_registered_many(struct list_head *head)
if (!dev->rtnl_link_ops ||
dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
- GFP_KERNEL);
+ GFP_KERNEL, NULL);
/*
* Flush the unicast and multicast chains
@@ -7994,7 +8077,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
unsigned int txqs, unsigned int rxqs)
{
struct net_device *dev;
- size_t alloc_size;
+ unsigned int alloc_size;
struct net_device *p;
BUG_ON(strlen(name) >= sizeof(dev->name));
@@ -8244,7 +8327,7 @@ EXPORT_SYMBOL(unregister_netdev);
int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
{
- int err;
+ int err, new_nsid;
ASSERT_RTNL();
@@ -8300,7 +8383,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
rcu_barrier();
call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
- rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
+ if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net)
+ new_nsid = peernet2id_alloc(dev_net(dev), net);
+ else
+ new_nsid = peernet2id(dev_net(dev), net);
+ rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid);
/*
* Flush the unicast and multicast chains
@@ -8562,6 +8649,8 @@ static void __net_exit netdev_exit(struct net *net)
{
kfree(net->dev_name_head);
kfree(net->dev_index_head);
+ if (net != &init_net)
+ WARN_ON_ONCE(!list_empty(&net->dev_base_head));
}
static struct pernet_operations __net_initdata netdev_net_ops = {
diff --git a/net/core/dst.c b/net/core/dst.c
index a6c47da7d0f8..662a2d4a3d19 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -322,3 +322,19 @@ metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags)
return md_dst;
}
EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu);
+
+void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst)
+{
+#ifdef CONFIG_DST_CACHE
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu);
+
+ if (one_md_dst->type == METADATA_IP_TUNNEL)
+ dst_cache_destroy(&one_md_dst->u.tun_info.dst_cache);
+ }
+#endif
+ free_percpu(md_dst);
+}
+EXPORT_SYMBOL_GPL(metadata_dst_free_percpu);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 9a9a3d77e327..f8fcf450a36e 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -403,6 +403,22 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data)
return 0;
}
+/* Given two link masks, AND them together and save the result in dst. */
+void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst,
+ struct ethtool_link_ksettings *src)
+{
+ unsigned int size = BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS);
+ unsigned int idx = 0;
+
+ for (; idx < size; idx++) {
+ dst->link_modes.supported[idx] &=
+ src->link_modes.supported[idx];
+ dst->link_modes.advertising[idx] &=
+ src->link_modes.advertising[idx];
+ }
+}
+EXPORT_SYMBOL(ethtool_intersect_link_masks);
+
void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst,
u32 legacy_u32)
{
diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c
index 4fc202dbdfb6..0c048bdeb016 100644
--- a/net/core/fib_notifier.c
+++ b/net/core/fib_notifier.c
@@ -34,12 +34,14 @@ static unsigned int fib_seq_sum(void)
rtnl_lock();
for_each_net(net) {
- list_for_each_entry(ops, &net->fib_notifier_ops, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(ops, &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();
}
rtnl_unlock();
@@ -161,8 +163,14 @@ static int __net_init fib_notifier_net_init(struct net *net)
return 0;
}
+static void __net_exit fib_notifier_net_exit(struct net *net)
+{
+ WARN_ON_ONCE(!list_empty(&net->fib_notifier_ops));
+}
+
static struct pernet_operations fib_notifier_net_ops = {
.init = fib_notifier_net_init,
+ .exit = fib_notifier_net_exit,
};
static int __init fib_notifier_init(void)
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 9a6d97c1d810..98e1066c3d55 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -314,10 +314,12 @@ static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net,
static int call_fib_rule_notifiers(struct net *net,
enum fib_event_type event_type,
struct fib_rule *rule,
- struct fib_rules_ops *ops)
+ struct fib_rules_ops *ops,
+ struct netlink_ext_ack *extack)
{
struct fib_rule_notifier_info info = {
.info.family = ops->family,
+ .info.extack = extack,
.rule = rule,
};
@@ -609,7 +611,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
if (rule->tun_id)
ip_tunnel_need_metadata();
- call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops);
+ call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops, extack);
notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid);
flush_route_cache(ops);
rules_ops_put(ops);
@@ -749,7 +751,8 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
}
}
- call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops);
+ call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops,
+ NULL);
notify_rule_change(RTM_DELRULE, rule, ops, nlh,
NETLINK_CB(skb).portid);
fib_rule_put(rule);
@@ -1019,8 +1022,14 @@ static int __net_init fib_rules_net_init(struct net *net)
return 0;
}
+static void __net_exit fib_rules_net_exit(struct net *net)
+{
+ WARN_ON_ONCE(!list_empty(&net->rules_ops));
+}
+
static struct pernet_operations fib_rules_net_ops = {
.init = fib_rules_net_init,
+ .exit = fib_rules_net_exit,
};
static int __init fib_rules_init(void)
diff --git a/net/core/filter.c b/net/core/filter.c
index 6ae94f825f72..1afa17935954 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -43,6 +43,7 @@
#include <linux/timer.h>
#include <linux/uaccess.h>
#include <asm/unaligned.h>
+#include <asm/cmpxchg.h>
#include <linux/filter.h>
#include <linux/ratelimit.h>
#include <linux/seccomp.h>
@@ -1406,7 +1407,7 @@ static inline int bpf_try_make_writable(struct sk_buff *skb,
{
int err = __bpf_try_make_writable(skb, write_len);
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return err;
}
@@ -1968,7 +1969,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto,
ret = skb_vlan_push(skb, vlan_proto, vlan_tci);
bpf_pull_mac_rcsum(skb);
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return ret;
}
@@ -1990,7 +1991,7 @@ BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb)
ret = skb_vlan_pop(skb);
bpf_pull_mac_rcsum(skb);
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return ret;
}
@@ -2184,7 +2185,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto,
* need to be verified first.
*/
ret = bpf_skb_proto_xlat(skb, proto);
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return ret;
}
@@ -2309,7 +2310,7 @@ static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
ret = shrink ? bpf_skb_net_shrink(skb, len_diff_abs) :
bpf_skb_net_grow(skb, len_diff_abs);
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return ret;
}
@@ -2400,7 +2401,7 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
skb_gso_reset(skb);
}
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return ret;
}
@@ -2440,7 +2441,7 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
skb_reset_mac_header(skb);
}
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return 0;
}
@@ -2453,14 +2454,26 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
.arg3_type = ARG_ANYTHING,
};
+static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
+{
+ return xdp_data_meta_unsupported(xdp) ? 0 :
+ xdp->data - xdp->data_meta;
+}
+
BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset)
{
+ unsigned long metalen = xdp_get_metalen(xdp);
+ void *data_start = xdp->data_hard_start + metalen;
void *data = xdp->data + offset;
- if (unlikely(data < xdp->data_hard_start ||
+ if (unlikely(data < data_start ||
data > xdp->data_end - ETH_HLEN))
return -EINVAL;
+ if (metalen)
+ memmove(xdp->data_meta + offset,
+ xdp->data_meta, metalen);
+ xdp->data_meta += offset;
xdp->data = data;
return 0;
@@ -2474,6 +2487,33 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
.arg2_type = ARG_ANYTHING,
};
+BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset)
+{
+ void *meta = xdp->data_meta + offset;
+ unsigned long metalen = xdp->data - meta;
+
+ if (xdp_data_meta_unsupported(xdp))
+ return -ENOTSUPP;
+ if (unlikely(meta < xdp->data_hard_start ||
+ meta > xdp->data))
+ return -EINVAL;
+ if (unlikely((metalen & (sizeof(__u32) - 1)) ||
+ (metalen > 32)))
+ return -EACCES;
+
+ xdp->data_meta = meta;
+
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
+ .func = bpf_xdp_adjust_meta,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+};
+
static int __bpf_tx_xdp(struct net_device *dev,
struct bpf_map *map,
struct xdp_buff *xdp,
@@ -2488,10 +2528,36 @@ static int __bpf_tx_xdp(struct net_device *dev,
err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
if (err)
return err;
- if (map)
+ dev->netdev_ops->ndo_xdp_flush(dev);
+ return 0;
+}
+
+static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
+ struct bpf_map *map,
+ struct xdp_buff *xdp,
+ u32 index)
+{
+ int err;
+
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ struct net_device *dev = fwd;
+
+ if (!dev->netdev_ops->ndo_xdp_xmit)
+ return -EOPNOTSUPP;
+
+ err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
+ if (err)
+ return err;
__dev_map_insert_ctx(map, index);
- else
- dev->netdev_ops->ndo_xdp_flush(dev);
+
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ struct bpf_cpu_map_entry *rcpu = fwd;
+
+ err = cpu_map_enqueue(rcpu, xdp, dev_rx);
+ if (err)
+ return err;
+ __cpu_map_insert_ctx(map, index);
+ }
return 0;
}
@@ -2501,11 +2567,33 @@ void xdp_do_flush_map(void)
struct bpf_map *map = ri->map_to_flush;
ri->map_to_flush = NULL;
- if (map)
- __dev_map_flush(map);
+ if (map) {
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ __dev_map_flush(map);
+ break;
+ case BPF_MAP_TYPE_CPUMAP:
+ __cpu_map_flush(map);
+ break;
+ default:
+ break;
+ }
+ }
}
EXPORT_SYMBOL_GPL(xdp_do_flush_map);
+static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
+{
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ return __dev_map_lookup_elem(map, index);
+ case BPF_MAP_TYPE_CPUMAP:
+ return __cpu_map_lookup_elem(map, index);
+ default:
+ return NULL;
+ }
+}
+
static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
unsigned long aux)
{
@@ -2518,8 +2606,8 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
- struct net_device *fwd = NULL;
u32 index = ri->ifindex;
+ void *fwd = NULL;
int err;
ri->ifindex = 0;
@@ -2532,7 +2620,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
goto err;
}
- fwd = __dev_map_lookup_elem(map, index);
+ fwd = __xdp_map_lookup_elem(map, index);
if (!fwd) {
err = -EINVAL;
goto err;
@@ -2540,7 +2628,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
if (ri->map_to_flush && ri->map_to_flush != map)
xdp_do_flush_map();
- err = __bpf_tx_xdp(fwd, map, xdp, index);
+ err = __bpf_tx_xdp_map(dev, fwd, map, xdp, index);
if (unlikely(err))
goto err;
@@ -2582,54 +2670,88 @@ err:
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
-int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
- struct bpf_prog *xdp_prog)
+static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
+{
+ unsigned int len;
+
+ if (unlikely(!(fwd->flags & IFF_UP)))
+ return -ENETDOWN;
+
+ len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
+ if (skb->len > len)
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
struct net_device *fwd = NULL;
u32 index = ri->ifindex;
- unsigned int len;
int err = 0;
ri->ifindex = 0;
ri->map = NULL;
ri->map_owner = 0;
- if (map) {
- if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
- err = -EFAULT;
- map = NULL;
- goto err;
- }
- fwd = __dev_map_lookup_elem(map, index);
- } else {
- fwd = dev_get_by_index_rcu(dev_net(dev), index);
+ if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
+ err = -EFAULT;
+ map = NULL;
+ goto err;
}
+ fwd = __xdp_map_lookup_elem(map, index);
if (unlikely(!fwd)) {
err = -EINVAL;
goto err;
}
- if (unlikely(!(fwd->flags & IFF_UP))) {
- err = -ENETDOWN;
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ goto err;
+ skb->dev = fwd;
+ } else {
+ /* TODO: Handle BPF_MAP_TYPE_CPUMAP */
+ err = -EBADRQC;
goto err;
}
- len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
- if (skb->len > len) {
- err = -EMSGSIZE;
+ _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+ return 0;
+err:
+ _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+ return err;
+}
+
+int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+ u32 index = ri->ifindex;
+ struct net_device *fwd;
+ int err = 0;
+
+ if (ri->map)
+ return xdp_do_generic_redirect_map(dev, skb, xdp_prog);
+
+ ri->ifindex = 0;
+ fwd = dev_get_by_index_rcu(dev_net(dev), index);
+ if (unlikely(!fwd)) {
+ err = -EINVAL;
goto err;
}
+ if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ goto err;
+
skb->dev = fwd;
- map ? _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index)
- : _trace_xdp_redirect(dev, xdp_prog, index);
+ _trace_xdp_redirect(dev, xdp_prog, index);
return 0;
err:
- map ? _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err)
- : _trace_xdp_redirect_err(dev, xdp_prog, index, err);
+ _trace_xdp_redirect_err(dev, xdp_prog, index, err);
return err;
}
EXPORT_SYMBOL_GPL(xdp_do_generic_redirect);
@@ -2698,7 +2820,8 @@ bool bpf_helper_changes_pkt_data(void *func)
func == bpf_clone_redirect ||
func == bpf_l3_csum_replace ||
func == bpf_l4_csum_replace ||
- func == bpf_xdp_adjust_head)
+ func == bpf_xdp_adjust_head ||
+ func == bpf_xdp_adjust_meta)
return true;
return false;
@@ -2949,14 +3072,15 @@ static const struct bpf_func_proto *
bpf_get_skb_set_tunnel_proto(enum bpf_func_id which)
{
if (!md_dst) {
- /* Race is not possible, since it's called from verifier
- * that is holding verifier mutex.
- */
- md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX,
- METADATA_IP_TUNNEL,
- GFP_KERNEL);
- if (!md_dst)
+ struct metadata_dst __percpu *tmp;
+
+ tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX,
+ METADATA_IP_TUNNEL,
+ GFP_KERNEL);
+ if (!tmp)
return NULL;
+ if (cmpxchg(&md_dst, NULL, tmp))
+ metadata_dst_free_percpu(tmp);
}
switch (which) {
@@ -3151,7 +3275,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
static const struct bpf_func_proto bpf_setsockopt_proto = {
.func = bpf_setsockopt,
- .gpl_only = true,
+ .gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
@@ -3160,6 +3284,47 @@ static const struct bpf_func_proto bpf_setsockopt_proto = {
.arg5_type = ARG_CONST_SIZE,
};
+BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
+ int, level, int, optname, char *, optval, int, optlen)
+{
+ struct sock *sk = bpf_sock->sk;
+
+ if (!sk_fullsock(sk))
+ goto err_clear;
+
+#ifdef CONFIG_INET
+ if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) {
+ if (optname == TCP_CONGESTION) {
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (!icsk->icsk_ca_ops || optlen <= 1)
+ goto err_clear;
+ strncpy(optval, icsk->icsk_ca_ops->name, optlen);
+ optval[optlen - 1] = 0;
+ } else {
+ goto err_clear;
+ }
+ } else {
+ goto err_clear;
+ }
+ return 0;
+#endif
+err_clear:
+ memset(optval, 0, optlen);
+ return -EINVAL;
+}
+
+static const struct bpf_func_proto bpf_getsockopt_proto = {
+ .func = bpf_getsockopt,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg5_type = ARG_CONST_SIZE,
+};
+
static const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
@@ -3294,6 +3459,8 @@ xdp_func_proto(enum bpf_func_id func_id)
return &bpf_get_smp_processor_id_proto;
case BPF_FUNC_xdp_adjust_head:
return &bpf_xdp_adjust_head_proto;
+ case BPF_FUNC_xdp_adjust_meta:
+ return &bpf_xdp_adjust_meta_proto;
case BPF_FUNC_redirect:
return &bpf_xdp_redirect_proto;
case BPF_FUNC_redirect_map:
@@ -3336,6 +3503,8 @@ static const struct bpf_func_proto *
switch (func_id) {
case BPF_FUNC_setsockopt:
return &bpf_setsockopt_proto;
+ case BPF_FUNC_getsockopt:
+ return &bpf_getsockopt_proto;
case BPF_FUNC_sock_map_update:
return &bpf_sock_map_update_proto;
default:
@@ -3424,6 +3593,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4):
case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4):
case bpf_ctx_range(struct __sk_buff, data):
+ case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range(struct __sk_buff, data_end):
if (size != size_default)
return false;
@@ -3450,6 +3620,7 @@ static bool sk_filter_is_valid_access(int off, int size,
switch (off) {
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range(struct __sk_buff, data):
+ case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range(struct __sk_buff, data_end):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
return false;
@@ -3474,6 +3645,7 @@ static bool lwt_is_valid_access(int off, int size,
switch (off) {
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
+ case bpf_ctx_range(struct __sk_buff, data_meta):
return false;
}
@@ -3592,6 +3764,9 @@ static bool tc_cls_act_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data):
info->reg_type = PTR_TO_PACKET;
break;
+ case bpf_ctx_range(struct __sk_buff, data_meta):
+ info->reg_type = PTR_TO_PACKET_META;
+ break;
case bpf_ctx_range(struct __sk_buff, data_end):
info->reg_type = PTR_TO_PACKET_END;
break;
@@ -3625,6 +3800,9 @@ static bool xdp_is_valid_access(int off, int size,
case offsetof(struct xdp_md, data):
info->reg_type = PTR_TO_PACKET;
break;
+ case offsetof(struct xdp_md, data_meta):
+ info->reg_type = PTR_TO_PACKET_META;
+ break;
case offsetof(struct xdp_md, data_end):
info->reg_type = PTR_TO_PACKET_END;
break;
@@ -3683,6 +3861,12 @@ static bool sk_skb_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
+ switch (off) {
+ case bpf_ctx_range(struct __sk_buff, tc_classid):
+ case bpf_ctx_range(struct __sk_buff, data_meta):
+ return false;
+ }
+
if (type == BPF_WRITE) {
switch (off) {
case bpf_ctx_range(struct __sk_buff, tc_index):
@@ -3695,7 +3879,6 @@ static bool sk_skb_is_valid_access(int off, int size,
switch (off) {
case bpf_ctx_range(struct __sk_buff, mark):
- case bpf_ctx_range(struct __sk_buff, tc_classid):
return false;
case bpf_ctx_range(struct __sk_buff, data):
info->reg_type = PTR_TO_PACKET;
@@ -3853,6 +4036,15 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
offsetof(struct sk_buff, data));
break;
+ case offsetof(struct __sk_buff, data_meta):
+ off = si->off;
+ off -= offsetof(struct __sk_buff, data_meta);
+ off += offsetof(struct sk_buff, cb);
+ off += offsetof(struct bpf_skb_data_end, data_meta);
+ *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
+ si->src_reg, off);
+ break;
+
case offsetof(struct __sk_buff, data_end):
off = si->off;
off -= offsetof(struct __sk_buff, data_end);
@@ -4101,6 +4293,11 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
si->dst_reg, si->src_reg,
offsetof(struct xdp_buff, data));
break;
+ case offsetof(struct xdp_md, data_meta):
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta),
+ si->dst_reg, si->src_reg,
+ offsetof(struct xdp_buff, data_meta));
+ break;
case offsetof(struct xdp_md, data_end):
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end),
si->dst_reg, si->src_reg,
@@ -4269,68 +4466,95 @@ static u32 sk_skb_convert_ctx_access(enum bpf_access_type type,
return insn - insn_buf;
}
-const struct bpf_verifier_ops sk_filter_prog_ops = {
+const struct bpf_verifier_ops sk_filter_verifier_ops = {
.get_func_proto = sk_filter_func_proto,
.is_valid_access = sk_filter_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
};
-const struct bpf_verifier_ops tc_cls_act_prog_ops = {
+const struct bpf_prog_ops sk_filter_prog_ops = {
+};
+
+const struct bpf_verifier_ops tc_cls_act_verifier_ops = {
.get_func_proto = tc_cls_act_func_proto,
.is_valid_access = tc_cls_act_is_valid_access,
.convert_ctx_access = tc_cls_act_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
+};
+
+const struct bpf_prog_ops tc_cls_act_prog_ops = {
.test_run = bpf_prog_test_run_skb,
};
-const struct bpf_verifier_ops xdp_prog_ops = {
+const struct bpf_verifier_ops xdp_verifier_ops = {
.get_func_proto = xdp_func_proto,
.is_valid_access = xdp_is_valid_access,
.convert_ctx_access = xdp_convert_ctx_access,
+};
+
+const struct bpf_prog_ops xdp_prog_ops = {
.test_run = bpf_prog_test_run_xdp,
};
-const struct bpf_verifier_ops cg_skb_prog_ops = {
+const struct bpf_verifier_ops cg_skb_verifier_ops = {
.get_func_proto = sk_filter_func_proto,
.is_valid_access = sk_filter_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
+};
+
+const struct bpf_prog_ops cg_skb_prog_ops = {
.test_run = bpf_prog_test_run_skb,
};
-const struct bpf_verifier_ops lwt_inout_prog_ops = {
+const struct bpf_verifier_ops lwt_inout_verifier_ops = {
.get_func_proto = lwt_inout_func_proto,
.is_valid_access = lwt_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
+};
+
+const struct bpf_prog_ops lwt_inout_prog_ops = {
.test_run = bpf_prog_test_run_skb,
};
-const struct bpf_verifier_ops lwt_xmit_prog_ops = {
+const struct bpf_verifier_ops lwt_xmit_verifier_ops = {
.get_func_proto = lwt_xmit_func_proto,
.is_valid_access = lwt_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
+};
+
+const struct bpf_prog_ops lwt_xmit_prog_ops = {
.test_run = bpf_prog_test_run_skb,
};
-const struct bpf_verifier_ops cg_sock_prog_ops = {
+const struct bpf_verifier_ops cg_sock_verifier_ops = {
.get_func_proto = sock_filter_func_proto,
.is_valid_access = sock_filter_is_valid_access,
.convert_ctx_access = sock_filter_convert_ctx_access,
};
-const struct bpf_verifier_ops sock_ops_prog_ops = {
+const struct bpf_prog_ops cg_sock_prog_ops = {
+};
+
+const struct bpf_verifier_ops sock_ops_verifier_ops = {
.get_func_proto = sock_ops_func_proto,
.is_valid_access = sock_ops_is_valid_access,
.convert_ctx_access = sock_ops_convert_ctx_access,
};
-const struct bpf_verifier_ops sk_skb_prog_ops = {
+const struct bpf_prog_ops sock_ops_prog_ops = {
+};
+
+const struct bpf_verifier_ops sk_skb_verifier_ops = {
.get_func_proto = sk_skb_func_proto,
.is_valid_access = sk_skb_is_valid_access,
.convert_ctx_access = sk_skb_convert_ctx_access,
.gen_prologue = sk_skb_prologue,
};
+const struct bpf_prog_ops sk_skb_prog_ops = {
+};
+
int sk_detach_filter(struct sock *sk)
{
int ret = -ENOENT;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 0a977373d003..15ce30063765 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -5,10 +5,12 @@
#include <linux/ipv6.h>
#include <linux/if_vlan.h>
#include <net/dsa.h>
+#include <net/dst_metadata.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/gre.h>
#include <net/pptp.h>
+#include <net/tipc.h>
#include <linux/igmp.h>
#include <linux/icmp.h>
#include <linux/sctp.h>
@@ -115,6 +117,102 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
}
EXPORT_SYMBOL(__skb_flow_get_ports);
+static void
+skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type,
+ struct flow_dissector *flow_dissector,
+ void *target_container)
+{
+ struct flow_dissector_key_control *ctrl;
+
+ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL))
+ return;
+
+ ctrl = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_CONTROL,
+ target_container);
+ ctrl->addr_type = type;
+}
+
+static void
+__skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container)
+{
+ struct ip_tunnel_info *info;
+ struct ip_tunnel_key *key;
+
+ /* A quick check to see if there might be something to do. */
+ if (!dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID) &&
+ !dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) &&
+ !dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) &&
+ !dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_CONTROL) &&
+ !dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_PORTS))
+ return;
+
+ info = skb_tunnel_info(skb);
+ if (!info)
+ return;
+
+ key = &info->key;
+
+ switch (ip_tunnel_info_af(info)) {
+ case AF_INET:
+ skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+ flow_dissector,
+ target_container);
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+ struct flow_dissector_key_ipv4_addrs *ipv4;
+
+ ipv4 = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+ target_container);
+ ipv4->src = key->u.ipv4.src;
+ ipv4->dst = key->u.ipv4.dst;
+ }
+ break;
+ case AF_INET6:
+ skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+ flow_dissector,
+ target_container);
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
+ struct flow_dissector_key_ipv6_addrs *ipv6;
+
+ ipv6 = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS,
+ target_container);
+ ipv6->src = key->u.ipv6.src;
+ ipv6->dst = key->u.ipv6.dst;
+ }
+ break;
+ }
+
+ if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+ struct flow_dissector_key_keyid *keyid;
+
+ keyid = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ target_container);
+ keyid->keyid = tunnel_id_to_key32(key->tun_id);
+ }
+
+ if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+ struct flow_dissector_key_ports *tp;
+
+ tp = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_PORTS,
+ target_container);
+ tp->src = key->tp_src;
+ tp->dst = key->tp_dst;
+ }
+}
+
static enum flow_dissect_ret
__skb_flow_dissect_mpls(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
@@ -478,6 +576,9 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
FLOW_DISSECTOR_KEY_BASIC,
target_container);
+ __skb_flow_dissect_tunnel_info(skb, flow_dissector,
+ target_container);
+
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
struct ethhdr *eth = eth_hdr(skb);
@@ -672,23 +773,22 @@ proto_again:
break;
}
case htons(ETH_P_TIPC): {
- struct {
- __be32 pre[3];
- __be32 srcnode;
- } *hdr, _hdr;
- hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
+ struct tipc_basic_hdr *hdr, _hdr;
+
+ hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr),
+ data, hlen, &_hdr);
if (!hdr) {
fdret = FLOW_DISSECT_RET_OUT_BAD;
break;
}
if (dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_TIPC_ADDRS)) {
+ FLOW_DISSECTOR_KEY_TIPC)) {
key_addrs = skb_flow_dissector_target(flow_dissector,
- FLOW_DISSECTOR_KEY_TIPC_ADDRS,
+ FLOW_DISSECTOR_KEY_TIPC,
target_container);
- key_addrs->tipcaddrs.srcnode = hdr->srcnode;
- key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC_ADDRS;
+ key_addrs->tipckey.key = tipc_hdr_rps_key(hdr);
+ key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC;
}
fdret = FLOW_DISSECT_RET_OUT_GOOD;
break;
@@ -924,8 +1024,8 @@ static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
diff -= sizeof(flow->addrs.v6addrs);
break;
- case FLOW_DISSECTOR_KEY_TIPC_ADDRS:
- diff -= sizeof(flow->addrs.tipcaddrs);
+ case FLOW_DISSECTOR_KEY_TIPC:
+ diff -= sizeof(flow->addrs.tipckey);
break;
}
return (sizeof(*flow) - diff) / sizeof(u32);
@@ -939,8 +1039,8 @@ __be32 flow_get_u32_src(const struct flow_keys *flow)
case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
return (__force __be32)ipv6_addr_hash(
&flow->addrs.v6addrs.src);
- case FLOW_DISSECTOR_KEY_TIPC_ADDRS:
- return flow->addrs.tipcaddrs.srcnode;
+ case FLOW_DISSECTOR_KEY_TIPC:
+ return flow->addrs.tipckey.key;
default:
return 0;
}
@@ -1221,8 +1321,8 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = {
.offset = offsetof(struct flow_keys, addrs.v6addrs),
},
{
- .key_id = FLOW_DISSECTOR_KEY_TIPC_ADDRS,
- .offset = offsetof(struct flow_keys, addrs.tipcaddrs),
+ .key_id = FLOW_DISSECTOR_KEY_TIPC,
+ .offset = offsetof(struct flow_keys, addrs.tipckey),
},
{
.key_id = FLOW_DISSECTOR_KEY_PORTS,
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 1307731ddfe4..e7e626fb87bb 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -51,7 +51,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
*/
preempt_disable();
rcu_read_lock();
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
ret = bpf_prog_run_save_cb(lwt->prog, skb);
rcu_read_unlock();
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 16a1a4c4eb57..6ea3a1a7f36a 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -457,7 +457,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
const void *pkey)
{
struct neighbour *n;
- int key_len = tbl->key_len;
+ unsigned int key_len = tbl->key_len;
u32 hash_val;
struct neigh_hash_table *nht;
@@ -488,7 +488,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
struct net_device *dev, bool want_ref)
{
u32 hash_val;
- int key_len = tbl->key_len;
+ unsigned int key_len = tbl->key_len;
int error;
struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev);
struct neigh_hash_table *nht;
@@ -572,7 +572,7 @@ out_neigh_release:
}
EXPORT_SYMBOL(__neigh_create);
-static u32 pneigh_hash(const void *pkey, int key_len)
+static u32 pneigh_hash(const void *pkey, unsigned int key_len)
{
u32 hash_val = *(u32 *)(pkey + key_len - 4);
hash_val ^= (hash_val >> 16);
@@ -585,7 +585,7 @@ static u32 pneigh_hash(const void *pkey, int key_len)
static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n,
struct net *net,
const void *pkey,
- int key_len,
+ unsigned int key_len,
struct net_device *dev)
{
while (n) {
@@ -601,7 +601,7 @@ static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n,
struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl,
struct net *net, const void *pkey, struct net_device *dev)
{
- int key_len = tbl->key_len;
+ unsigned int key_len = tbl->key_len;
u32 hash_val = pneigh_hash(pkey, key_len);
return __pneigh_lookup_1(tbl->phash_buckets[hash_val],
@@ -614,7 +614,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
struct net_device *dev, int creat)
{
struct pneigh_entry *n;
- int key_len = tbl->key_len;
+ unsigned int key_len = tbl->key_len;
u32 hash_val = pneigh_hash(pkey, key_len);
read_lock_bh(&tbl->lock);
@@ -659,7 +659,7 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
struct net_device *dev)
{
struct pneigh_entry *n, **np;
- int key_len = tbl->key_len;
+ unsigned int key_len = tbl->key_len;
u32 hash_val = pneigh_hash(pkey, key_len);
write_lock_bh(&tbl->lock);
@@ -1662,7 +1662,7 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tbl == NULL)
return -EAFNOSUPPORT;
- if (nla_len(dst_attr) < tbl->key_len)
+ if (nla_len(dst_attr) < (int)tbl->key_len)
goto out;
if (ndm->ndm_flags & NTF_PROXY) {
@@ -1730,7 +1730,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tbl == NULL)
return -EAFNOSUPPORT;
- if (nla_len(tb[NDA_DST]) < tbl->key_len)
+ if (nla_len(tb[NDA_DST]) < (int)tbl->key_len)
goto out;
dst = nla_data(tb[NDA_DST]);
lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 927a6dcbad96..799b75268291 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -382,7 +382,7 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
struct net_device *netdev = to_net_dev(dev);
struct net *net = dev_net(netdev);
size_t count = len;
- ssize_t ret;
+ ssize_t ret = 0;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
@@ -393,23 +393,30 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
if (!rtnl_trylock())
return restart_syscall();
- ret = dev_set_alias(netdev, buf, count);
+
+ if (dev_isalive(netdev)) {
+ ret = dev_set_alias(netdev, buf, count);
+ if (ret < 0)
+ goto err;
+ ret = len;
+ netdev_state_change(netdev);
+ }
+err:
rtnl_unlock();
- return ret < 0 ? ret : len;
+ return ret;
}
static ssize_t ifalias_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
const struct net_device *netdev = to_net_dev(dev);
+ char tmp[IFALIASZ];
ssize_t ret = 0;
- if (!rtnl_trylock())
- return restart_syscall();
- if (netdev->ifalias)
- ret = sprintf(buf, "%s\n", netdev->ifalias);
- rtnl_unlock();
+ ret = dev_get_alias(netdev, tmp, sizeof(tmp));
+ if (ret > 0)
+ ret = sprintf(buf, "%s\n", tmp);
return ret;
}
static DEVICE_ATTR_RW(ifalias);
@@ -1488,7 +1495,10 @@ static void netdev_release(struct device *d)
BUG_ON(dev->reg_state != NETREG_RELEASED);
- kfree(dev->ifalias);
+ /* no need to wait for rcu grace period:
+ * device is dead and about to be freed.
+ */
+ kfree(rcu_access_pointer(dev->ifalias));
netdev_freemem(dev);
}
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index 71f209542364..380934580fa1 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -32,6 +32,7 @@
#include <trace/events/napi.h>
#include <trace/events/sock.h>
#include <trace/events/udp.h>
+#include <trace/events/tcp.h>
#include <trace/events/fib.h>
#include <trace/events/qdisc.h>
#if IS_ENABLED(CONFIG_IPV6)
@@ -49,3 +50,5 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update);
EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6cfdc7c84c48..b797832565d3 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -234,6 +234,7 @@ int peernet2id_alloc(struct net *net, struct net *peer)
rtnl_net_notifyid(net, RTM_NEWNSID, id);
return id;
}
+EXPORT_SYMBOL_GPL(peernet2id_alloc);
/* This function returns, if assigned, the id of a peer netns. */
int peernet2id(struct net *net, struct net *peer)
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 3b2034f6d49d..f95a15086225 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2165,7 +2165,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
+ pkt_dev->pkt_overhead;
}
- for (i = 0; i < IN6_ADDR_HSIZE; i++)
+ for (i = 0; i < sizeof(struct in6_addr); i++)
if (pkt_dev->cur_in6_saddr.s6_addr[i]) {
set = 1;
break;
@@ -2711,7 +2711,7 @@ static inline __be16 build_tci(unsigned int id, unsigned int cfi,
static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb,
int datalen)
{
- struct timeval timestamp;
+ struct timespec64 timestamp;
struct pktgen_hdr *pgh;
pgh = skb_put(skb, sizeof(*pgh));
@@ -2773,9 +2773,17 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb,
pgh->tv_sec = 0;
pgh->tv_usec = 0;
} else {
- do_gettimeofday(&timestamp);
+ /*
+ * pgh->tv_sec wraps in y2106 when interpreted as unsigned
+ * as done by wireshark, or y2038 when interpreted as signed.
+ * This is probably harmless, but if anyone wants to improve
+ * it, we could introduce a variant that puts 64-bit nanoseconds
+ * into the respective header bytes.
+ * This would also be slightly faster to read.
+ */
+ ktime_get_real_ts64(&timestamp);
pgh->tv_sec = htonl(timestamp.tv_sec);
- pgh->tv_usec = htonl(timestamp.tv_usec);
+ pgh->tv_usec = htonl(timestamp.tv_nsec / NSEC_PER_USEC);
}
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5ace48926b19..dabba2a91fc8 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -453,7 +453,7 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
{
const struct rtnl_af_ops *ops;
- list_for_each_entry(ops, &rtnl_af_ops, list) {
+ list_for_each_entry_rcu(ops, &rtnl_af_ops, list) {
if (ops->family == family)
return ops;
}
@@ -470,32 +470,22 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
void rtnl_af_register(struct rtnl_af_ops *ops)
{
rtnl_lock();
- list_add_tail(&ops->list, &rtnl_af_ops);
+ list_add_tail_rcu(&ops->list, &rtnl_af_ops);
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(rtnl_af_register);
/**
- * __rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink.
- * @ops: struct rtnl_af_ops * to unregister
- *
- * The caller must hold the rtnl_mutex.
- */
-void __rtnl_af_unregister(struct rtnl_af_ops *ops)
-{
- list_del(&ops->list);
-}
-EXPORT_SYMBOL_GPL(__rtnl_af_unregister);
-
-/**
* rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink.
* @ops: struct rtnl_af_ops * to unregister
*/
void rtnl_af_unregister(struct rtnl_af_ops *ops)
{
rtnl_lock();
- __rtnl_af_unregister(ops);
+ list_del_rcu(&ops->list);
rtnl_unlock();
+
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(rtnl_af_unregister);
@@ -508,13 +498,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev,
/* IFLA_AF_SPEC */
size = nla_total_size(sizeof(struct nlattr));
- list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
if (af_ops->get_link_af_size) {
/* AF_* + nested data */
size += nla_total_size(sizeof(struct nlattr)) +
af_ops->get_link_af_size(dev, ext_filter_mask);
}
}
+ rcu_read_unlock();
return size;
}
@@ -522,11 +514,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev,
static bool rtnl_have_link_slave_info(const struct net_device *dev)
{
struct net_device *master_dev;
+ bool ret = false;
- master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
+ rcu_read_lock();
+
+ master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev);
if (master_dev && master_dev->rtnl_link_ops)
- return true;
- return false;
+ ret = true;
+ rcu_read_unlock();
+ return ret;
}
static int rtnl_link_slave_info_fill(struct sk_buff *skb,
@@ -923,8 +919,10 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
+ rtnl_xdp_size() /* IFLA_XDP */
+ nla_total_size(4) /* IFLA_EVENT */
- + nla_total_size(1); /* IFLA_PROTO_DOWN */
-
+ + nla_total_size(4) /* IFLA_NEW_NETNSID */
+ + nla_total_size(1) /* IFLA_PROTO_DOWN */
+ + nla_total_size(4) /* IFLA_IF_NETNSID */
+ + 0;
}
static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -1211,6 +1209,36 @@ nla_put_vfinfo_failure:
return -EMSGSIZE;
}
+static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb,
+ struct net_device *dev,
+ u32 ext_filter_mask)
+{
+ struct nlattr *vfinfo;
+ int i, num_vfs;
+
+ if (!dev->dev.parent || ((ext_filter_mask & RTEXT_FILTER_VF) == 0))
+ return 0;
+
+ num_vfs = dev_num_vf(dev->dev.parent);
+ if (nla_put_u32(skb, IFLA_NUM_VF, num_vfs))
+ return -EMSGSIZE;
+
+ if (!dev->netdev_ops->ndo_get_vf_config)
+ return 0;
+
+ vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST);
+ if (!vfinfo)
+ return -EMSGSIZE;
+
+ for (i = 0; i < num_vfs; i++) {
+ if (rtnl_fill_vfinfo(skb, dev, i, vfinfo))
+ return -EMSGSIZE;
+ }
+
+ nla_nest_end(skb, vfinfo);
+ return 0;
+}
+
static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
{
struct rtnl_link_ifmap map;
@@ -1242,10 +1270,10 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
*prog_id = generic_xdp_prog->aux->id;
return XDP_ATTACHED_SKB;
}
- if (!ops->ndo_xdp)
+ if (!ops->ndo_bpf)
return XDP_ATTACHED_NONE;
- return __dev_xdp_attached(dev, ops->ndo_xdp, prog_id);
+ return __dev_xdp_attached(dev, ops->ndo_bpf, prog_id);
}
static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
@@ -1307,16 +1335,108 @@ static u32 rtnl_get_event(unsigned long event)
return rtnl_event_type;
}
-static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
+static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev)
+{
+ const struct net_device *upper_dev;
+ int ret = 0;
+
+ rcu_read_lock();
+
+ upper_dev = netdev_master_upper_dev_get_rcu(dev);
+ if (upper_dev)
+ ret = nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex);
+
+ rcu_read_unlock();
+ return ret;
+}
+
+static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev)
+{
+ int ifindex = dev_get_iflink(dev);
+
+ if (dev->ifindex == ifindex)
+ return 0;
+
+ return nla_put_u32(skb, IFLA_LINK, ifindex);
+}
+
+static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ char buf[IFALIASZ];
+ int ret;
+
+ ret = dev_get_alias(dev, buf, sizeof(buf));
+ return ret > 0 ? nla_put_string(skb, IFLA_IFALIAS, buf) : 0;
+}
+
+static int rtnl_fill_link_netnsid(struct sk_buff *skb,
+ const struct net_device *dev,
+ struct net *src_net)
+{
+ if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) {
+ 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);
+
+ if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
+ return -EMSGSIZE;
+ }
+ }
+
+ return 0;
+}
+
+static int rtnl_fill_link_af(struct sk_buff *skb,
+ const struct net_device *dev,
+ u32 ext_filter_mask)
+{
+ const struct rtnl_af_ops *af_ops;
+ struct nlattr *af_spec;
+
+ af_spec = nla_nest_start(skb, IFLA_AF_SPEC);
+ if (!af_spec)
+ return -EMSGSIZE;
+
+ list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
+ struct nlattr *af;
+ int err;
+
+ if (!af_ops->fill_link_af)
+ continue;
+
+ af = nla_nest_start(skb, af_ops->family);
+ if (!af)
+ return -EMSGSIZE;
+
+ err = af_ops->fill_link_af(skb, dev, ext_filter_mask);
+ /*
+ * Caller may return ENODATA to indicate that there
+ * was no data to be dumped. This is not an error, it
+ * means we should trim the attribute header and
+ * continue.
+ */
+ if (err == -ENODATA)
+ nla_nest_cancel(skb, af);
+ else if (err < 0)
+ return -EMSGSIZE;
+
+ nla_nest_end(skb, af);
+ }
+
+ nla_nest_end(skb, af_spec);
+ return 0;
+}
+
+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)
+ u32 event, int *new_nsid, int tgt_netnsid)
{
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
- struct nlattr *af_spec;
- struct rtnl_af_ops *af_ops;
- struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
ASSERT_RTNL();
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
@@ -1331,6 +1451,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
ifm->ifi_flags = dev_get_flags(dev);
ifm->ifi_change = change;
+ if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_IF_NETNSID, tgt_netnsid))
+ goto nla_put_failure;
+
if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) ||
nla_put_u8(skb, IFLA_OPERSTATE,
@@ -1345,15 +1468,12 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
#ifdef CONFIG_RPS
nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
#endif
- (dev->ifindex != dev_get_iflink(dev) &&
- nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) ||
- (upper_dev &&
- nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) ||
+ nla_put_iflink(skb, dev) ||
+ put_master_ifindex(skb, dev) ||
nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
(dev->qdisc &&
nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
- (dev->ifalias &&
- nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) ||
+ nla_put_ifalias(skb, dev) ||
nla_put_u32(skb, IFLA_CARRIER_CHANGES,
atomic_read(&dev->carrier_changes)) ||
nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
@@ -1385,27 +1505,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
if (rtnl_fill_stats(skb, dev))
goto nla_put_failure;
- if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) &&
- nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)))
+ if (rtnl_fill_vf(skb, dev, ext_filter_mask))
goto nla_put_failure;
- if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent &&
- ext_filter_mask & RTEXT_FILTER_VF) {
- int i;
- struct nlattr *vfinfo;
- int num_vfs = dev_num_vf(dev->dev.parent);
-
- vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST);
- if (!vfinfo)
- goto nla_put_failure;
- for (i = 0; i < num_vfs; i++) {
- if (rtnl_fill_vfinfo(skb, dev, i, vfinfo))
- goto nla_put_failure;
- }
-
- nla_nest_end(skb, vfinfo);
- }
-
if (rtnl_port_fill(skb, dev, ext_filter_mask))
goto nla_put_failure;
@@ -1417,51 +1519,23 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
goto nla_put_failure;
}
- if (dev->rtnl_link_ops &&
- dev->rtnl_link_ops->get_link_net) {
- struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
-
- if (!net_eq(dev_net(dev), link_net)) {
- int id = peernet2id_alloc(dev_net(dev), link_net);
-
- if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
- goto nla_put_failure;
- }
- }
-
- if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC)))
+ if (rtnl_fill_link_netnsid(skb, dev, src_net))
goto nla_put_failure;
- list_for_each_entry(af_ops, &rtnl_af_ops, list) {
- if (af_ops->fill_link_af) {
- struct nlattr *af;
- int err;
-
- if (!(af = nla_nest_start(skb, af_ops->family)))
- goto nla_put_failure;
-
- err = af_ops->fill_link_af(skb, dev, ext_filter_mask);
-
- /*
- * Caller may return ENODATA to indicate that there
- * was no data to be dumped. This is not an error, it
- * means we should trim the attribute header and
- * continue.
- */
- if (err == -ENODATA)
- nla_nest_cancel(skb, af);
- else if (err < 0)
- goto nla_put_failure;
-
- nla_nest_end(skb, af);
- }
- }
+ if (new_nsid &&
+ nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0)
+ goto nla_put_failure;
- nla_nest_end(skb, af_spec);
+ rcu_read_lock();
+ if (rtnl_fill_link_af(skb, dev, ext_filter_mask))
+ goto nla_put_failure_rcu;
+ rcu_read_unlock();
nlmsg_end(skb, nlh);
return 0;
+nla_put_failure_rcu:
+ rcu_read_unlock();
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
@@ -1503,6 +1577,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_XDP] = { .type = NLA_NESTED },
[IFLA_EVENT] = { .type = NLA_U32 },
[IFLA_GROUP] = { .type = NLA_U32 },
+ [IFLA_IF_NETNSID] = { .type = NLA_S32 },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -1606,9 +1681,28 @@ static bool link_dump_filtered(struct net_device *dev,
return false;
}
+static struct net *get_target_net(struct sk_buff *skb, int netnsid)
+{
+ struct net *net;
+
+ net = get_net_ns_by_id(sock_net(skb->sk), netnsid);
+ if (!net)
+ return ERR_PTR(-EINVAL);
+
+ /* For now, the caller is required to have CAP_NET_ADMIN in
+ * the user namespace owning the target net ns.
+ */
+ if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+ put_net(net);
+ return ERR_PTR(-EACCES);
+ }
+ return net;
+}
+
static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
+ struct net *tgt_net = net;
int h, s_h;
int idx = 0, s_idx;
struct net_device *dev;
@@ -1618,6 +1712,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
const struct rtnl_link_ops *kind_ops = NULL;
unsigned int flags = NLM_F_MULTI;
int master_idx = 0;
+ int netnsid = -1;
int err;
int hdrlen;
@@ -1636,6 +1731,15 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX,
ifla_policy, NULL) >= 0) {
+ if (tb[IFLA_IF_NETNSID]) {
+ netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
+ tgt_net = get_target_net(skb, netnsid);
+ if (IS_ERR(tgt_net)) {
+ tgt_net = net;
+ netnsid = -1;
+ }
+ }
+
if (tb[IFLA_EXT_MASK])
ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
@@ -1651,17 +1755,19 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
- head = &net->dev_index_head[h];
+ head = &tgt_net->dev_index_head[h];
hlist_for_each_entry(dev, head, index_hlist) {
if (link_dump_filtered(dev, master_idx, kind_ops))
goto cont;
if (idx < s_idx)
goto cont;
- err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+ err = rtnl_fill_ifinfo(skb, dev, net,
+ RTM_NEWLINK,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, 0,
flags,
- ext_filter_mask, 0);
+ ext_filter_mask, 0, NULL,
+ netnsid);
if (err < 0) {
if (likely(skb->len))
@@ -1680,6 +1786,8 @@ out_err:
cb->args[0] = h;
cb->seq = net->dev_base_seq;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+ if (netnsid >= 0)
+ put_net(tgt_net);
return err;
}
@@ -1726,17 +1834,27 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
const struct rtnl_af_ops *af_ops;
- if (!(af_ops = rtnl_af_lookup(nla_type(af))))
+ rcu_read_lock();
+ af_ops = rtnl_af_lookup(nla_type(af));
+ if (!af_ops) {
+ rcu_read_unlock();
return -EAFNOSUPPORT;
+ }
- if (!af_ops->set_link_af)
+ if (!af_ops->set_link_af) {
+ rcu_read_unlock();
return -EOPNOTSUPP;
+ }
if (af_ops->validate_link_af) {
err = af_ops->validate_link_af(dev, af);
- if (err < 0)
+ if (err < 0) {
+ rcu_read_unlock();
return err;
+ }
}
+
+ rcu_read_unlock();
}
}
@@ -1912,7 +2030,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
return err;
}
-static int do_set_master(struct net_device *dev, int ifindex)
+static int do_set_master(struct net_device *dev, int ifindex,
+ struct netlink_ext_ack *extack)
{
struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
const struct net_device_ops *ops;
@@ -1937,7 +2056,7 @@ static int do_set_master(struct net_device *dev, int ifindex)
return -EINVAL;
ops = upper_dev->netdev_ops;
if (ops->ndo_add_slave) {
- err = ops->ndo_add_slave(upper_dev, dev);
+ err = ops->ndo_add_slave(upper_dev, dev, extack);
if (err)
return err;
} else {
@@ -2070,7 +2189,7 @@ static int do_setlink(const struct sk_buff *skb,
}
if (tb[IFLA_MASTER]) {
- err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
+ err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
if (err)
goto errout;
status |= DO_SETLINK_MODIFIED;
@@ -2193,13 +2312,17 @@ static int do_setlink(const struct sk_buff *skb,
nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
const struct rtnl_af_ops *af_ops;
- if (!(af_ops = rtnl_af_lookup(nla_type(af))))
- BUG();
+ rcu_read_lock();
+
+ BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af))));
err = af_ops->set_link_af(dev, af);
- if (err < 0)
+ if (err < 0) {
+ rcu_read_unlock();
goto errout;
+ }
+ rcu_read_unlock();
status |= DO_SETLINK_NOTIFY;
}
}
@@ -2277,6 +2400,9 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
goto errout;
+ if (tb[IFLA_IF_NETNSID])
+ return -EOPNOTSUPP;
+
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
@@ -2371,6 +2497,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
+ if (tb[IFLA_IF_NETNSID])
+ return -EOPNOTSUPP;
+
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
@@ -2502,6 +2631,9 @@ replay:
if (err < 0)
return err;
+ if (tb[IFLA_IF_NETNSID])
+ return -EOPNOTSUPP;
+
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
@@ -2579,12 +2711,6 @@ replay:
return err;
slave_data = slave_attr;
}
- if (m_ops->slave_validate) {
- err = m_ops->slave_validate(tb, slave_data,
- extack);
- if (err < 0)
- return err;
- }
}
if (dev) {
@@ -2714,7 +2840,8 @@ replay:
goto out_unregister;
}
if (tb[IFLA_MASTER]) {
- err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
+ err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]),
+ extack);
if (err)
goto out_unregister;
}
@@ -2740,11 +2867,13 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
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;
+ int netnsid = -1;
int err;
u32 ext_filter_mask = 0;
@@ -2752,35 +2881,50 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
+ if (tb[IFLA_IF_NETNSID]) {
+ netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
+ tgt_net = get_target_net(skb, netnsid);
+ if (IS_ERR(tgt_net))
+ 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]);
+ err = -EINVAL;
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
- dev = __dev_get_by_index(net, ifm->ifi_index);
+ dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
else if (tb[IFLA_IFNAME])
- dev = __dev_get_by_name(net, ifname);
+ dev = __dev_get_by_name(tgt_net, ifname);
else
- return -EINVAL;
+ goto out;
+ err = -ENODEV;
if (dev == NULL)
- return -ENODEV;
+ goto out;
+ err = -ENOBUFS;
nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL);
if (nskb == NULL)
- return -ENOBUFS;
+ goto out;
- err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid,
- nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0);
+ err = rtnl_fill_ifinfo(nskb, dev, net,
+ RTM_NEWLINK, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq, 0, 0, ext_filter_mask,
+ 0, NULL, netnsid);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size */
WARN_ON(err == -EMSGSIZE);
kfree_skb(nskb);
} else
err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid);
+out:
+ if (netnsid >= 0)
+ put_net(tgt_net);
return err;
}
@@ -2859,7 +3003,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
unsigned int change,
- u32 event, gfp_t flags)
+ u32 event, gfp_t flags, int *new_nsid)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
@@ -2870,7 +3014,9 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
if (skb == NULL)
goto errout;
- err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event);
+ err = rtnl_fill_ifinfo(skb, dev, dev_net(dev),
+ type, 0, 0, change, 0, 0, event,
+ new_nsid, -1);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -2893,14 +3039,14 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
static void rtmsg_ifinfo_event(int type, struct net_device *dev,
unsigned int change, u32 event,
- gfp_t flags)
+ gfp_t flags, int *new_nsid)
{
struct sk_buff *skb;
if (dev->reg_state != NETREG_REGISTERED)
return;
- skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags);
+ skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid);
if (skb)
rtmsg_ifinfo_send(skb, dev, flags);
}
@@ -2908,9 +3054,15 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev,
void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
gfp_t flags)
{
- rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags);
+ rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, NULL);
+}
+
+void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change,
+ gfp_t flags, int *new_nsid)
+{
+ rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags,
+ new_nsid);
}
-EXPORT_SYMBOL(rtmsg_ifinfo);
static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
struct net_device *dev,
@@ -3017,21 +3169,21 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm,
}
EXPORT_SYMBOL(ndo_dflt_fdb_add);
-static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid)
+static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid,
+ struct netlink_ext_ack *extack)
{
u16 vid = 0;
if (vlan_attr) {
if (nla_len(vlan_attr) != sizeof(u16)) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n");
+ NL_SET_ERR_MSG(extack, "invalid vlan attribute size");
return -EINVAL;
}
vid = nla_get_u16(vlan_attr);
if (!vid || vid >= VLAN_VID_MASK) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n",
- vid);
+ NL_SET_ERR_MSG(extack, "invalid vlan id");
return -EINVAL;
}
}
@@ -3056,24 +3208,24 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
ndm = nlmsg_data(nlh);
if (ndm->ndm_ifindex == 0) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n");
+ NL_SET_ERR_MSG(extack, "invalid ifindex");
return -EINVAL;
}
dev = __dev_get_by_index(net, ndm->ndm_ifindex);
if (dev == NULL) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n");
+ NL_SET_ERR_MSG(extack, "unknown ifindex");
return -ENODEV;
}
if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n");
+ NL_SET_ERR_MSG(extack, "invalid address");
return -EINVAL;
}
addr = nla_data(tb[NDA_LLADDR]);
- err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+ err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
if (err)
return err;
@@ -3160,24 +3312,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
ndm = nlmsg_data(nlh);
if (ndm->ndm_ifindex == 0) {
- pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n");
+ NL_SET_ERR_MSG(extack, "invalid ifindex");
return -EINVAL;
}
dev = __dev_get_by_index(net, ndm->ndm_ifindex);
if (dev == NULL) {
- pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n");
+ NL_SET_ERR_MSG(extack, "unknown ifindex");
return -ENODEV;
}
if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
- pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n");
+ NL_SET_ERR_MSG(extack, "invalid address");
return -EINVAL;
}
addr = nla_data(tb[NDA_LLADDR]);
- err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+ err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
if (err)
return err;
@@ -3617,7 +3769,7 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
dev = __dev_get_by_index(net, ifm->ifi_index);
if (!dev) {
- pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
+ NL_SET_ERR_MSG(extack, "unknown ifindex");
return -ENODEV;
}
@@ -3692,7 +3844,7 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
dev = __dev_get_by_index(net, ifm->ifi_index);
if (!dev) {
- pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
+ NL_SET_ERR_MSG(extack, "unknown ifindex");
return -ENODEV;
}
@@ -3943,25 +4095,30 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
if (!attr)
goto nla_put_failure;
- list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
if (af_ops->fill_stats_af) {
struct nlattr *af;
int err;
af = nla_nest_start(skb, af_ops->family);
- if (!af)
+ if (!af) {
+ rcu_read_unlock();
goto nla_put_failure;
-
+ }
err = af_ops->fill_stats_af(skb, dev);
- if (err == -ENODATA)
+ if (err == -ENODATA) {
nla_nest_cancel(skb, af);
- else if (err < 0)
+ } else if (err < 0) {
+ rcu_read_unlock();
goto nla_put_failure;
+ }
nla_nest_end(skb, af);
}
}
+ rcu_read_unlock();
nla_nest_end(skb, attr);
@@ -4030,7 +4187,8 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
/* for IFLA_STATS_AF_SPEC */
size += nla_total_size(0);
- list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
if (af_ops->get_stats_af_size) {
size += nla_total_size(
af_ops->get_stats_af_size(dev));
@@ -4039,6 +4197,7 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
size += nla_total_size(0);
}
}
+ rcu_read_unlock();
}
return size;
@@ -4292,9 +4451,10 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
case NETDEV_CHANGEUPPER:
case NETDEV_RESEND_IGMP:
case NETDEV_CHANGEINFODATA:
+ case NETDEV_CHANGELOWERSTATE:
case NETDEV_CHANGE_TX_QUEUE_LEN:
rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event),
- GFP_KERNEL);
+ GFP_KERNEL, NULL);
break;
default:
break;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e140ba49b30a..8134c00df6c2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1354,8 +1354,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
/* Set the tail pointer and length */
skb_put(n, skb->len);
- if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len))
- BUG();
+ BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
copy_skb_header(n, skb);
return n;
@@ -1453,8 +1452,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
BUG_ON(nhead < 0);
- if (skb_shared(skb))
- BUG();
+ BUG_ON(skb_shared(skb));
size = SKB_DATA_ALIGN(size);
@@ -1513,6 +1511,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
skb->nohdr = 0;
atomic_set(&skb_shinfo(skb)->dataref, 1);
+ skb_metadata_clear(skb);
+
/* It is not generally safe to change skb->truesize.
* For the moment, we really care of rx path, or
* when skb is orphaned (not attached to a socket).
@@ -1597,9 +1597,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
head_copy_off = newheadroom - head_copy_len;
/* Copy the linear header and data. */
- if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
- skb->len + head_copy_len))
- BUG();
+ BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
+ skb->len + head_copy_len));
copy_skb_header(n, skb);
@@ -1880,8 +1879,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
return NULL;
}
- if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta))
- BUG();
+ BUG_ON(skb_copy_bits(skb, skb_headlen(skb),
+ skb_tail_pointer(skb), delta));
/* Optimization: no fragments, no reasons to preestimate
* size of pulled pages. Superb.
@@ -2852,12 +2851,15 @@ EXPORT_SYMBOL(skb_queue_purge);
*/
void skb_rbtree_purge(struct rb_root *root)
{
- struct sk_buff *skb, *next;
+ struct rb_node *p = rb_first(root);
- rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode)
- kfree_skb(skb);
+ while (p) {
+ struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
- *root = RB_ROOT;
+ p = rb_next(p);
+ rb_erase(&skb->rbnode, root);
+ kfree_skb(skb);
+ }
}
/**
@@ -4766,6 +4768,7 @@ EXPORT_SYMBOL(kfree_skb_partial);
bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
bool *fragstolen, int *delta_truesize)
{
+ struct skb_shared_info *to_shinfo, *from_shinfo;
int i, delta, len = from->len;
*fragstolen = false;
@@ -4780,7 +4783,9 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
return true;
}
- if (skb_has_frag_list(to) || skb_has_frag_list(from))
+ to_shinfo = skb_shinfo(to);
+ from_shinfo = skb_shinfo(from);
+ if (to_shinfo->frag_list || from_shinfo->frag_list)
return false;
if (skb_zcopy(to) || skb_zcopy(from))
return false;
@@ -4789,8 +4794,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
struct page *page;
unsigned int offset;
- if (skb_shinfo(to)->nr_frags +
- skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+ if (to_shinfo->nr_frags +
+ from_shinfo->nr_frags >= MAX_SKB_FRAGS)
return false;
if (skb_head_is_locked(from))
@@ -4801,12 +4806,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
page = virt_to_head_page(from->head);
offset = from->data - (unsigned char *)page_address(page);
- skb_fill_page_desc(to, skb_shinfo(to)->nr_frags,
+ skb_fill_page_desc(to, to_shinfo->nr_frags,
page, offset, skb_headlen(from));
*fragstolen = true;
} else {
- if (skb_shinfo(to)->nr_frags +
- skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS)
+ if (to_shinfo->nr_frags +
+ from_shinfo->nr_frags > MAX_SKB_FRAGS)
return false;
delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from));
@@ -4814,19 +4819,19 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
WARN_ON_ONCE(delta < len);
- memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags,
- skb_shinfo(from)->frags,
- skb_shinfo(from)->nr_frags * sizeof(skb_frag_t));
- skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags;
+ memcpy(to_shinfo->frags + to_shinfo->nr_frags,
+ from_shinfo->frags,
+ from_shinfo->nr_frags * sizeof(skb_frag_t));
+ to_shinfo->nr_frags += from_shinfo->nr_frags;
if (!skb_cloned(from))
- skb_shinfo(from)->nr_frags = 0;
+ from_shinfo->nr_frags = 0;
/* if the skb is not cloned this does nothing
* since we set nr_frags to 0.
*/
- for (i = 0; i < skb_shinfo(from)->nr_frags; i++)
- skb_frag_ref(from, i);
+ for (i = 0; i < from_shinfo->nr_frags; i++)
+ __skb_frag_ref(&from_shinfo->frags[i]);
to->truesize += delta;
to->len += len;
diff --git a/net/core/sock.c b/net/core/sock.c
index 415f441c63b9..13719af7b4e3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2346,16 +2346,18 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
/* guarantee minimum buffer size under pressure */
if (kind == SK_MEM_RECV) {
- if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
+ if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot))
return 1;
} else { /* SK_MEM_SEND */
+ int wmem0 = sk_get_wmem0(sk, prot);
+
if (sk->sk_type == SOCK_STREAM) {
- if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
+ if (sk->sk_wmem_queued < wmem0)
return 1;
- } else if (refcount_read(&sk->sk_wmem_alloc) <
- prot->sysctl_wmem[0])
+ } else if (refcount_read(&sk->sk_wmem_alloc) < wmem0) {
return 1;
+ }
}
if (sk_has_memory_pressure(sk)) {
@@ -2685,7 +2687,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk_init_common(sk);
sk->sk_send_head = NULL;
- init_timer(&sk->sk_timer);
+ timer_setup(&sk->sk_timer, NULL, 0);
sk->sk_allocation = GFP_KERNEL;
sk->sk_rcvbuf = sysctl_rmem_default;
@@ -2744,6 +2746,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_max_pacing_rate = ~0U;
sk->sk_pacing_rate = ~0U;
+ sk->sk_pacing_shift = 10;
sk->sk_incoming_cpu = -1;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
@@ -3042,7 +3045,6 @@ struct prot_inuse {
static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR);
-#ifdef CONFIG_NET_NS
void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
{
__this_cpu_add(net->core.inuse->val[prot->inuse_idx], val);
@@ -3086,27 +3088,6 @@ static __init int net_inuse_init(void)
}
core_initcall(net_inuse_init);
-#else
-static DEFINE_PER_CPU(struct prot_inuse, prot_inuse);
-
-void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
-{
- __this_cpu_add(prot_inuse.val[prot->inuse_idx], val);
-}
-EXPORT_SYMBOL_GPL(sock_prot_inuse_add);
-
-int sock_prot_inuse_get(struct net *net, struct proto *prot)
-{
- int cpu, idx = prot->inuse_idx;
- int res = 0;
-
- for_each_possible_cpu(cpu)
- res += per_cpu(prot_inuse, cpu).val[idx];
-
- return res >= 0 ? res : 0;
-}
-EXPORT_SYMBOL_GPL(sock_prot_inuse_get);
-#endif
static void assign_proto_idx(struct proto *prot)
{
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index e1295d5f2c56..1c75cd1255f6 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -126,10 +126,10 @@ static void ccid2_change_l_seq_window(struct sock *sk, u64 val)
DCCPF_SEQ_WMAX));
}
-static void ccid2_hc_tx_rto_expire(unsigned long data)
+static void ccid2_hc_tx_rto_expire(struct timer_list *t)
{
- struct sock *sk = (struct sock *)data;
- struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+ struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer);
+ struct sock *sk = hc->sk;
const bool sender_was_blocked = ccid2_cwnd_network_limited(hc);
bh_lock_sock(sk);
@@ -733,8 +733,8 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
hc->tx_rpdupack = -1;
hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_jiffies32;
hc->tx_cwnd_used = 0;
- setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire,
- (unsigned long)sk);
+ hc->sk = sk;
+ timer_setup(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, 0);
INIT_LIST_HEAD(&hc->tx_av_chunks);
return 0;
}
diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h
index 6e50ef2898fb..1af0116dc6ce 100644
--- a/net/dccp/ccids/ccid2.h
+++ b/net/dccp/ccids/ccid2.h
@@ -85,6 +85,7 @@ struct ccid2_hc_tx_sock {
tx_rto;
u64 tx_rtt_seq:48;
struct timer_list tx_rtotimer;
+ struct sock *sk;
/* Congestion Window validation (optional, RFC 2861) */
u32 tx_cwnd_used,
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 119c04317d48..8b5ba6dffac7 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -195,10 +195,10 @@ static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hc,
}
}
-static void ccid3_hc_tx_no_feedback_timer(unsigned long data)
+static void ccid3_hc_tx_no_feedback_timer(struct timer_list *t)
{
- struct sock *sk = (struct sock *)data;
- struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
+ struct ccid3_hc_tx_sock *hc = from_timer(hc, t, tx_no_feedback_timer);
+ struct sock *sk = hc->sk;
unsigned long t_nfb = USEC_PER_SEC / 5;
bh_lock_sock(sk);
@@ -505,8 +505,9 @@ static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk)
hc->tx_state = TFRC_SSTATE_NO_SENT;
hc->tx_hist = NULL;
- setup_timer(&hc->tx_no_feedback_timer,
- ccid3_hc_tx_no_feedback_timer, (unsigned long)sk);
+ hc->sk = sk;
+ timer_setup(&hc->tx_no_feedback_timer,
+ ccid3_hc_tx_no_feedback_timer, 0);
return 0;
}
diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h
index 1a9933c29672..813d91c6e1e2 100644
--- a/net/dccp/ccids/ccid3.h
+++ b/net/dccp/ccids/ccid3.h
@@ -106,6 +106,7 @@ struct ccid3_hc_tx_sock {
u8 tx_last_win_count;
ktime_t tx_t_last_win_count;
struct timer_list tx_no_feedback_timer;
+ struct sock *sk;
ktime_t tx_t_ld;
ktime_t tx_t_nom;
struct tfrc_tx_hist_entry *tx_hist;
diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c
index 08df7a3acb3d..876e18592d71 100644
--- a/net/dccp/ccids/lib/packet_history.c
+++ b/net/dccp/ccids/lib/packet_history.c
@@ -149,10 +149,8 @@ static void tfrc_rx_hist_swap(struct tfrc_rx_hist *h, const u8 a, const u8 b)
{
const u8 idx_a = tfrc_rx_hist_index(h, a),
idx_b = tfrc_rx_hist_index(h, b);
- struct tfrc_rx_hist_entry *tmp = h->ring[idx_a];
- h->ring[idx_a] = h->ring[idx_b];
- h->ring[idx_b] = tmp;
+ swap(h->ring[idx_a], h->ring[idx_b]);
}
/*
diff --git a/net/dccp/input.c b/net/dccp/input.c
index fa6be9750bb4..d28d46bff6ab 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -534,6 +534,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk,
case DCCP_PKT_DATA:
if (sk->sk_state == DCCP_RESPOND)
break;
+ /* fall through */
case DCCP_PKT_DATAACK:
case DCCP_PKT_ACK:
/*
diff --git a/net/dccp/options.c b/net/dccp/options.c
index 51cdfc3bd8ca..4e40db017e19 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -227,8 +227,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
* Ack vectors are processed by the TX CCID if it is
* interested. The RX CCID need not parse Ack Vectors,
* since it is only interested in clearing old state.
- * Fall through.
*/
+ /* fall through */
case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC:
if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk,
pkt_type, opt, value, len))
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 3a2c34027758..b50a8732ff43 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -125,10 +125,11 @@ static void dccp_retransmit_timer(struct sock *sk)
__sk_dst_reset(sk);
}
-static void dccp_write_timer(unsigned long data)
+static void dccp_write_timer(struct timer_list *t)
{
- struct sock *sk = (struct sock *)data;
- struct inet_connection_sock *icsk = inet_csk(sk);
+ struct inet_connection_sock *icsk =
+ from_timer(icsk, t, icsk_retransmit_timer);
+ struct sock *sk = &icsk->icsk_inet.sk;
int event = 0;
bh_lock_sock(sk);
@@ -161,19 +162,20 @@ out:
sock_put(sk);
}
-static void dccp_keepalive_timer(unsigned long data)
+static void dccp_keepalive_timer(struct timer_list *t)
{
- struct sock *sk = (struct sock *)data;
+ struct sock *sk = from_timer(sk, t, sk_timer);
pr_err("dccp should not use a keepalive timer !\n");
sock_put(sk);
}
/* This is the same as tcp_delack_timer, sans prequeue & mem_reclaim stuff */
-static void dccp_delack_timer(unsigned long data)
+static void dccp_delack_timer(struct timer_list *t)
{
- struct sock *sk = (struct sock *)data;
- struct inet_connection_sock *icsk = inet_csk(sk);
+ struct inet_connection_sock *icsk =
+ from_timer(icsk, t, icsk_delack_timer);
+ struct sock *sk = &icsk->icsk_inet.sk;
bh_lock_sock(sk);
if (sock_owned_by_user(sk)) {
@@ -232,10 +234,13 @@ static void dccp_write_xmitlet(unsigned long data)
bh_unlock_sock(sk);
}
-static void dccp_write_xmit_timer(unsigned long data)
+static void dccp_write_xmit_timer(struct timer_list *t)
{
- dccp_write_xmitlet(data);
- sock_put((struct sock *)data);
+ struct dccp_sock *dp = from_timer(dp, t, dccps_xmit_timer);
+ struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
+
+ dccp_write_xmitlet((unsigned long)sk);
+ sock_put(sk);
}
void dccp_init_xmit_timers(struct sock *sk)
@@ -243,8 +248,7 @@ void dccp_init_xmit_timers(struct sock *sk)
struct dccp_sock *dp = dccp_sk(sk);
tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk);
- setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer,
- (unsigned long)sk);
+ timer_setup(&dp->dccps_xmit_timer, dccp_write_xmit_timer, 0);
inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer,
&dccp_keepalive_timer);
}
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 73a0399dc7a2..518cea17b811 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -533,10 +533,6 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf
scp->keepalive = 10 * HZ;
scp->keepalive_fxn = dn_keepalive;
- init_timer(&scp->delack_timer);
- scp->delack_pending = 0;
- scp->delack_fxn = dn_nsp_delayed_ack;
-
dn_start_slow_timer(sk);
out:
return sk;
@@ -634,10 +630,12 @@ static void dn_destroy_sock(struct sock *sk)
goto disc_reject;
case DN_RUN:
scp->state = DN_DI;
+ /* fall through */
case DN_DI:
case DN_DR:
disc_reject:
dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation);
+ /* fall through */
case DN_NC:
case DN_NR:
case DN_RJ:
@@ -651,6 +649,7 @@ disc_reject:
break;
default:
printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n");
+ /* fall through */
case DN_O:
dn_stop_slow_timer(sk);
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index df042b6d80b8..9153247dad28 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -1039,14 +1039,14 @@ static void dn_eth_down(struct net_device *dev)
static void dn_dev_set_timer(struct net_device *dev);
-static void dn_dev_timer_func(unsigned long arg)
+static void dn_dev_timer_func(struct timer_list *t)
{
- struct net_device *dev = (struct net_device *)arg;
- struct dn_dev *dn_db;
+ struct dn_dev *dn_db = from_timer(dn_db, t, timer);
+ struct net_device *dev;
struct dn_ifaddr *ifa;
rcu_read_lock();
- dn_db = rcu_dereference(dev->dn_ptr);
+ dev = dn_db->dev;
if (dn_db->t3 <= dn_db->parms.t2) {
if (dn_db->parms.timer3) {
for (ifa = rcu_dereference(dn_db->ifa_list);
@@ -1071,8 +1071,6 @@ static void dn_dev_set_timer(struct net_device *dev)
if (dn_db->parms.t2 > dn_db->parms.t3)
dn_db->parms.t2 = dn_db->parms.t3;
- dn_db->timer.data = (unsigned long)dev;
- dn_db->timer.function = dn_dev_timer_func;
dn_db->timer.expires = jiffies + (dn_db->parms.t2 * HZ);
add_timer(&dn_db->timer);
@@ -1101,7 +1099,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err)
rcu_assign_pointer(dev->dn_ptr, dn_db);
dn_db->dev = dev;
- init_timer(&dn_db->timer);
+ timer_setup(&dn_db->timer, dn_dev_timer_func, 0);
dn_db->uptime = jiffies;
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index 7ac086d5c0c0..1b2120645730 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -776,12 +776,8 @@ static int dn_nsp_rx_packet(struct net *net, struct sock *sk2,
* Swap src & dst and look up in the normal way.
*/
if (unlikely(cb->rt_flags & DN_RT_F_RTS)) {
- __le16 tmp = cb->dst_port;
- cb->dst_port = cb->src_port;
- cb->src_port = tmp;
- tmp = cb->dst;
- cb->dst = cb->src;
- cb->src = tmp;
+ swap(cb->dst_port, cb->src_port);
+ swap(cb->dst, cb->src);
}
/*
diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c
index 66f035e476ea..56a52a004c56 100644
--- a/net/decnet/dn_nsp_out.c
+++ b/net/decnet/dn_nsp_out.c
@@ -313,11 +313,8 @@ static __le16 *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, unsigned c
ackcrs |= 0x8000;
/* If this is an "other data/ack" message, swap acknum and ackcrs */
- if (other) {
- unsigned short tmp = acknum;
- acknum = ackcrs;
- ackcrs = tmp;
- }
+ if (other)
+ swap(acknum, ackcrs);
/* Set "cross subchannel" bit in ackcrs */
ackcrs |= 0x2000;
@@ -491,17 +488,6 @@ void dn_send_conn_ack (struct sock *sk)
dn_nsp_send(skb);
}
-void dn_nsp_delayed_ack(struct sock *sk)
-{
- struct dn_scp *scp = DN_SK(sk);
-
- if (scp->ackxmt_oth != scp->numoth_rcv)
- dn_nsp_send_oth_ack(sk);
-
- if (scp->ackxmt_dat != scp->numdat_rcv)
- dn_nsp_send_data_ack(sk);
-}
-
static int dn_nsp_retrans_conn_conf(struct sock *sk)
{
struct dn_scp *scp = DN_SK(sk);
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 6538632fbd03..b36dceab0dc1 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -338,7 +338,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou
dn_rt_hash_table[hash].chain);
rcu_assign_pointer(dn_rt_hash_table[hash].chain, rth);
- dst_use(&rth->dst, now);
+ dst_hold_and_use(&rth->dst, now);
spin_unlock_bh(&dn_rt_hash_table[hash].lock);
dst_release_immediate(&rt->dst);
@@ -351,7 +351,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou
rcu_assign_pointer(rt->dst.dn_next, dn_rt_hash_table[hash].chain);
rcu_assign_pointer(dn_rt_hash_table[hash].chain, rt);
- dst_use(&rt->dst, now);
+ dst_hold_and_use(&rt->dst, now);
spin_unlock_bh(&dn_rt_hash_table[hash].lock);
*rp = rt;
return 0;
@@ -1258,7 +1258,7 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowidn *
(flp->flowidn_mark == rt->fld.flowidn_mark) &&
dn_is_output_route(rt) &&
(rt->fld.flowidn_oif == flp->flowidn_oif)) {
- dst_use(&rt->dst, jiffies);
+ dst_hold_and_use(&rt->dst, jiffies);
rcu_read_unlock_bh();
*pprt = &rt->dst;
return 0;
@@ -1535,7 +1535,7 @@ static int dn_route_input(struct sk_buff *skb)
(rt->fld.flowidn_oif == 0) &&
(rt->fld.flowidn_mark == skb->mark) &&
(rt->fld.flowidn_iif == cb->iif)) {
- dst_use(&rt->dst, jiffies);
+ dst_hold_and_use(&rt->dst, jiffies);
rcu_read_unlock();
skb_dst_set(skb, (struct dst_entry *)rt);
return 0;
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index 08667f68e601..f0710b5d037d 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -156,6 +156,7 @@ static void dn_rehash_zone(struct dn_zone *dz)
default:
printk(KERN_DEBUG "DECnet: dn_rehash_zone: BUG! %d\n",
old_divisor);
+ /* fall through */
case 256:
new_divisor = 1024;
new_hashmask = 0x3FF;
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index cc5f8f971689..03c3bdf25468 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -7,6 +7,7 @@ config HAVE_NET_DSA
config NET_DSA
tristate "Distributed Switch Architecture"
depends on HAVE_NET_DSA && MAY_USE_DEVLINK
+ depends on BRIDGE || BRIDGE=n
select NET_SWITCHDEV
select PHYLIB
---help---
@@ -19,6 +20,9 @@ if NET_DSA
config NET_DSA_TAG_BRCM
bool
+config NET_DSA_TAG_BRCM_PREPEND
+ bool
+
config NET_DSA_TAG_DSA
bool
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 3d3c74193d06..0e13c1f95d13 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -1,10 +1,11 @@
# SPDX-License-Identifier: GPL-2.0
# the core
obj-$(CONFIG_NET_DSA) += dsa_core.o
-dsa_core-y += dsa.o dsa2.o legacy.o port.o slave.o switch.o
+dsa_core-y += dsa.o dsa2.o legacy.o master.o port.o slave.o switch.o
# tagging formats
dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o
+dsa_core-$(CONFIG_NET_DSA_TAG_BRCM_PREPEND) += tag_brcm.o
dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
dsa_core-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 03c58b0eb082..6a9d0f50fbee 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -14,6 +14,7 @@
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/module.h>
+#include <linux/notifier.h>
#include <linux/of.h>
#include <linux/of_mdio.h>
#include <linux/of_platform.h>
@@ -43,6 +44,9 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
#ifdef CONFIG_NET_DSA_TAG_BRCM
[DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops,
#endif
+#ifdef CONFIG_NET_DSA_TAG_BRCM_PREPEND
+ [DSA_TAG_PROTO_BRCM_PREPEND] = &brcm_prepend_netdev_ops,
+#endif
#ifdef CONFIG_NET_DSA_TAG_DSA
[DSA_TAG_PROTO_DSA] = &dsa_netdev_ops,
#endif
@@ -67,37 +71,6 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
[DSA_TAG_PROTO_NONE] = &none_ops,
};
-int dsa_cpu_dsa_setup(struct dsa_port *port)
-{
- struct device_node *port_dn = port->dn;
- struct dsa_switch *ds = port->ds;
- struct phy_device *phydev;
- int ret, mode;
-
- if (of_phy_is_fixed_link(port_dn)) {
- ret = of_phy_register_fixed_link(port_dn);
- if (ret) {
- dev_err(ds->dev, "failed to register fixed PHY\n");
- return ret;
- }
- phydev = of_phy_find_device(port_dn);
-
- mode = of_get_phy_mode(port_dn);
- if (mode < 0)
- mode = PHY_INTERFACE_MODE_NA;
- phydev->interface = mode;
-
- genphy_config_init(phydev);
- genphy_read_status(phydev);
- if (ds->ops->adjust_link)
- ds->ops->adjust_link(ds, port->index, phydev);
-
- put_device(&phydev->mdio.dev);
- }
-
- return 0;
-}
-
const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol)
{
const struct dsa_device_ops *ops;
@@ -112,42 +85,6 @@ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol)
return ops;
}
-int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp)
-{
- struct dsa_switch *ds = cpu_dp->ds;
- struct net_device *master;
- struct ethtool_ops *cpu_ops;
-
- master = cpu_dp->netdev;
-
- cpu_ops = devm_kzalloc(ds->dev, sizeof(*cpu_ops), GFP_KERNEL);
- if (!cpu_ops)
- return -ENOMEM;
-
- memcpy(&cpu_dp->ethtool_ops, master->ethtool_ops,
- sizeof(struct ethtool_ops));
- cpu_dp->orig_ethtool_ops = master->ethtool_ops;
- memcpy(cpu_ops, &cpu_dp->ethtool_ops,
- sizeof(struct ethtool_ops));
- dsa_cpu_port_ethtool_init(cpu_ops);
- master->ethtool_ops = cpu_ops;
-
- return 0;
-}
-
-void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp)
-{
- cpu_dp->netdev->ethtool_ops = cpu_dp->orig_ethtool_ops;
-}
-
-void dsa_cpu_dsa_destroy(struct dsa_port *port)
-{
- struct device_node *port_dn = port->dn;
-
- if (of_phy_is_fixed_link(port_dn))
- of_phy_deregister_fixed_link(port_dn);
-}
-
static int dev_is_class(struct device *dev, void *class)
{
if (dev->class != NULL && !strcmp(dev->class->name, class))
@@ -188,12 +125,12 @@ EXPORT_SYMBOL_GPL(dsa_dev_to_net_device);
static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *unused)
{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
+ struct dsa_port *cpu_dp = dev->dsa_ptr;
struct sk_buff *nskb = NULL;
struct pcpu_sw_netstats *s;
struct dsa_slave_priv *p;
- if (unlikely(dst == NULL)) {
+ if (unlikely(!cpu_dp)) {
kfree_skb(skb);
return 0;
}
@@ -202,7 +139,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
if (!skb)
return 0;
- nskb = dst->rcv(skb, dev, pt);
+ nskb = cpu_dp->rcv(skb, dev, pt);
if (!nskb) {
kfree_skb(skb);
return 0;
@@ -228,7 +165,7 @@ 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 ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev;
+ return dsa_is_user_port(ds, p) && ds->ports[p].slave;
}
int dsa_switch_suspend(struct dsa_switch *ds)
@@ -240,7 +177,7 @@ int dsa_switch_suspend(struct dsa_switch *ds)
if (!dsa_is_port_initialized(ds, i))
continue;
- ret = dsa_slave_suspend(ds->ports[i].netdev);
+ ret = dsa_slave_suspend(ds->ports[i].slave);
if (ret)
return ret;
}
@@ -267,7 +204,7 @@ int dsa_switch_resume(struct dsa_switch *ds)
if (!dsa_is_port_initialized(ds, i))
continue;
- ret = dsa_slave_resume(ds->ports[i].netdev);
+ ret = dsa_slave_resume(ds->ports[i].slave);
if (ret)
return ret;
}
@@ -289,6 +226,28 @@ bool dsa_schedule_work(struct work_struct *work)
return queue_work(dsa_owq, work);
}
+static ATOMIC_NOTIFIER_HEAD(dsa_notif_chain);
+
+int register_dsa_notifier(struct notifier_block *nb)
+{
+ return atomic_notifier_chain_register(&dsa_notif_chain, nb);
+}
+EXPORT_SYMBOL_GPL(register_dsa_notifier);
+
+int unregister_dsa_notifier(struct notifier_block *nb)
+{
+ return atomic_notifier_chain_unregister(&dsa_notif_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_dsa_notifier);
+
+int call_dsa_notifiers(unsigned long val, struct net_device *dev,
+ struct dsa_notifier_info *info)
+{
+ info->dev = dev;
+ return atomic_notifier_call_chain(&dsa_notif_chain, val, info);
+}
+EXPORT_SYMBOL_GPL(call_dsa_notifiers);
+
static int __init dsa_init_module(void)
{
int rc;
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 045d8a176279..44e3fb7dec8c 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -21,293 +21,297 @@
#include "dsa_priv.h"
-static LIST_HEAD(dsa_switch_trees);
+static LIST_HEAD(dsa_tree_list);
static DEFINE_MUTEX(dsa2_mutex);
static const struct devlink_ops dsa_devlink_ops = {
};
-static struct dsa_switch_tree *dsa_get_dst(u32 tree)
+static struct dsa_switch_tree *dsa_tree_find(int index)
{
struct dsa_switch_tree *dst;
- list_for_each_entry(dst, &dsa_switch_trees, list)
- if (dst->tree == tree) {
- kref_get(&dst->refcount);
+ list_for_each_entry(dst, &dsa_tree_list, list)
+ if (dst->index == index)
return dst;
- }
+
return NULL;
}
-static void dsa_free_dst(struct kref *ref)
+static struct dsa_switch_tree *dsa_tree_alloc(int index)
{
- struct dsa_switch_tree *dst = container_of(ref, struct dsa_switch_tree,
- refcount);
+ struct dsa_switch_tree *dst;
- list_del(&dst->list);
- kfree(dst);
+ dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ if (!dst)
+ return NULL;
+
+ dst->index = index;
+
+ INIT_LIST_HEAD(&dst->list);
+ list_add_tail(&dsa_tree_list, &dst->list);
+
+ /* Initialize the reference counter to the number of switches, not 1 */
+ kref_init(&dst->refcount);
+ refcount_set(&dst->refcount.refcount, 0);
+
+ return dst;
}
-static void dsa_put_dst(struct dsa_switch_tree *dst)
+static void dsa_tree_free(struct dsa_switch_tree *dst)
{
- kref_put(&dst->refcount, dsa_free_dst);
+ list_del(&dst->list);
+ kfree(dst);
}
-static struct dsa_switch_tree *dsa_add_dst(u32 tree)
+static struct dsa_switch_tree *dsa_tree_touch(int index)
{
struct dsa_switch_tree *dst;
- dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ dst = dsa_tree_find(index);
if (!dst)
- return NULL;
- dst->tree = tree;
- INIT_LIST_HEAD(&dst->list);
- list_add_tail(&dsa_switch_trees, &dst->list);
- kref_init(&dst->refcount);
+ dst = dsa_tree_alloc(index);
return dst;
}
-static void dsa_dst_add_ds(struct dsa_switch_tree *dst,
- struct dsa_switch *ds, u32 index)
+static void dsa_tree_get(struct dsa_switch_tree *dst)
{
kref_get(&dst->refcount);
- dst->ds[index] = ds;
}
-static void dsa_dst_del_ds(struct dsa_switch_tree *dst,
- struct dsa_switch *ds, u32 index)
+static void dsa_tree_release(struct kref *ref)
{
- dst->ds[index] = NULL;
- kref_put(&dst->refcount, dsa_free_dst);
+ struct dsa_switch_tree *dst;
+
+ dst = container_of(ref, struct dsa_switch_tree, refcount);
+
+ dsa_tree_free(dst);
}
-/* For platform data configurations, we need to have a valid name argument to
- * differentiate a disabled port from an enabled one
- */
-static bool dsa_port_is_valid(struct dsa_port *port)
+static void dsa_tree_put(struct dsa_switch_tree *dst)
{
- return !!(port->dn || port->name);
+ kref_put(&dst->refcount, dsa_tree_release);
}
static bool dsa_port_is_dsa(struct dsa_port *port)
{
- if (port->name && !strcmp(port->name, "dsa"))
- return true;
- else
- return !!of_parse_phandle(port->dn, "link", 0);
+ return port->type == DSA_PORT_TYPE_DSA;
}
static bool dsa_port_is_cpu(struct dsa_port *port)
{
- if (port->name && !strcmp(port->name, "cpu"))
- return true;
- else
- return !!of_parse_phandle(port->dn, "ethernet", 0);
+ return port->type == DSA_PORT_TYPE_CPU;
}
-static bool dsa_ds_find_port_dn(struct dsa_switch *ds,
- struct device_node *port)
+static bool dsa_port_is_user(struct dsa_port *dp)
{
- u32 index;
-
- for (index = 0; index < ds->num_ports; index++)
- if (ds->ports[index].dn == port)
- return true;
- return false;
+ return dp->type == DSA_PORT_TYPE_USER;
}
-static struct dsa_switch *dsa_dst_find_port_dn(struct dsa_switch_tree *dst,
- struct device_node *port)
+static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst,
+ struct device_node *dn)
{
struct dsa_switch *ds;
- u32 index;
+ struct dsa_port *dp;
+ int device, port;
- for (index = 0; index < DSA_MAX_SWITCHES; index++) {
- ds = dst->ds[index];
+ for (device = 0; device < DSA_MAX_SWITCHES; device++) {
+ ds = dst->ds[device];
if (!ds)
continue;
- if (dsa_ds_find_port_dn(ds, port))
- return ds;
+ for (port = 0; port < ds->num_ports; port++) {
+ dp = &ds->ports[port];
+
+ if (dp->dn == dn)
+ return dp;
+ }
}
return NULL;
}
-static int dsa_port_complete(struct dsa_switch_tree *dst,
- struct dsa_switch *src_ds,
- struct dsa_port *port,
- u32 src_port)
+static bool dsa_port_setup_routing_table(struct dsa_port *dp)
{
- struct device_node *link;
- int index;
- struct dsa_switch *dst_ds;
-
- for (index = 0;; index++) {
- link = of_parse_phandle(port->dn, "link", index);
- if (!link)
- break;
-
- dst_ds = dsa_dst_find_port_dn(dst, link);
- of_node_put(link);
+ struct dsa_switch *ds = dp->ds;
+ struct dsa_switch_tree *dst = ds->dst;
+ struct device_node *dn = dp->dn;
+ struct of_phandle_iterator it;
+ struct dsa_port *link_dp;
+ int err;
- if (!dst_ds)
- return 1;
+ of_for_each_phandle(&it, err, dn, "link", NULL, 0) {
+ link_dp = dsa_tree_find_port_by_node(dst, it.node);
+ if (!link_dp) {
+ of_node_put(it.node);
+ return false;
+ }
- src_ds->rtable[dst_ds->index] = src_port;
+ ds->rtable[link_dp->ds->index] = dp->index;
}
- return 0;
+ return true;
}
-/* A switch is complete if all the DSA ports phandles point to ports
- * known in the tree. A return value of 1 means the tree is not
- * complete. This is not an error condition. A value of 0 is
- * success.
- */
-static int dsa_ds_complete(struct dsa_switch_tree *dst, struct dsa_switch *ds)
+static bool dsa_switch_setup_routing_table(struct dsa_switch *ds)
{
- struct dsa_port *port;
- u32 index;
- int err;
-
- for (index = 0; index < ds->num_ports; index++) {
- port = &ds->ports[index];
- if (!dsa_port_is_valid(port))
- continue;
+ bool complete = true;
+ struct dsa_port *dp;
+ int i;
- if (!dsa_port_is_dsa(port))
- continue;
+ for (i = 0; i < DSA_MAX_SWITCHES; i++)
+ ds->rtable[i] = DSA_RTABLE_NONE;
- err = dsa_port_complete(dst, ds, port, index);
- if (err != 0)
- return err;
+ for (i = 0; i < ds->num_ports; i++) {
+ dp = &ds->ports[i];
- ds->dsa_port_mask |= BIT(index);
+ if (dsa_port_is_dsa(dp)) {
+ complete = dsa_port_setup_routing_table(dp);
+ if (!complete)
+ break;
+ }
}
- return 0;
+ return complete;
}
-/* A tree is complete if all the DSA ports phandles point to ports
- * known in the tree. A return value of 1 means the tree is not
- * complete. This is not an error condition. A value of 0 is
- * success.
- */
-static int dsa_dst_complete(struct dsa_switch_tree *dst)
+static bool dsa_tree_setup_routing_table(struct dsa_switch_tree *dst)
{
struct dsa_switch *ds;
- u32 index;
- int err;
+ bool complete = true;
+ int device;
- for (index = 0; index < DSA_MAX_SWITCHES; index++) {
- ds = dst->ds[index];
+ for (device = 0; device < DSA_MAX_SWITCHES; device++) {
+ ds = dst->ds[device];
if (!ds)
continue;
- err = dsa_ds_complete(dst, ds);
- if (err != 0)
- return err;
+ complete = dsa_switch_setup_routing_table(ds);
+ if (!complete)
+ break;
}
- return 0;
+ return complete;
}
-static int dsa_dsa_port_apply(struct dsa_port *port)
+static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst)
{
- struct dsa_switch *ds = port->ds;
- int err;
+ struct dsa_switch *ds;
+ struct dsa_port *dp;
+ int device, port;
- err = dsa_cpu_dsa_setup(port);
- if (err) {
- dev_warn(ds->dev, "Failed to setup dsa port %d: %d\n",
- port->index, err);
- return err;
- }
+ for (device = 0; device < DSA_MAX_SWITCHES; device++) {
+ ds = dst->ds[device];
+ if (!ds)
+ continue;
- memset(&port->devlink_port, 0, sizeof(port->devlink_port));
+ for (port = 0; port < ds->num_ports; port++) {
+ dp = &ds->ports[port];
- return devlink_port_register(ds->devlink, &port->devlink_port,
- port->index);
-}
+ if (dsa_port_is_cpu(dp))
+ return dp;
+ }
+ }
-static void dsa_dsa_port_unapply(struct dsa_port *port)
-{
- devlink_port_unregister(&port->devlink_port);
- dsa_cpu_dsa_destroy(port);
+ return NULL;
}
-static int dsa_cpu_port_apply(struct dsa_port *port)
+static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst)
{
- struct dsa_switch *ds = port->ds;
- int err;
+ struct dsa_switch *ds;
+ struct dsa_port *dp;
+ int device, port;
- err = dsa_cpu_dsa_setup(port);
- if (err) {
- dev_warn(ds->dev, "Failed to setup cpu port %d: %d\n",
- port->index, err);
- return err;
+ /* 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");
+ return -EINVAL;
}
- memset(&port->devlink_port, 0, sizeof(port->devlink_port));
- err = devlink_port_register(ds->devlink, &port->devlink_port,
- port->index);
- return err;
+ /* 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))
+ dp->cpu_dp = dst->cpu_dp;
+ }
+ }
+
+ return 0;
}
-static void dsa_cpu_port_unapply(struct dsa_port *port)
+static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst)
{
- devlink_port_unregister(&port->devlink_port);
- dsa_cpu_dsa_destroy(port);
- port->ds->cpu_port_mask &= ~BIT(port->index);
-
+ /* DSA currently only supports a single CPU port */
+ dst->cpu_dp = NULL;
}
-static int dsa_user_port_apply(struct dsa_port *port)
+static int dsa_port_setup(struct dsa_port *dp)
{
- struct dsa_switch *ds = port->ds;
- const char *name = port->name;
+ struct dsa_switch *ds = dp->ds;
int err;
- if (port->dn)
- name = of_get_property(port->dn, "label", NULL);
- if (!name)
- name = "eth%d";
+ memset(&dp->devlink_port, 0, sizeof(dp->devlink_port));
- err = dsa_slave_create(port, name);
- if (err) {
- dev_warn(ds->dev, "Failed to create slave %d: %d\n",
- port->index, err);
- port->netdev = NULL;
- return err;
- }
-
- memset(&port->devlink_port, 0, sizeof(port->devlink_port));
- err = devlink_port_register(ds->devlink, &port->devlink_port,
- port->index);
+ err = devlink_port_register(ds->devlink, &dp->devlink_port, dp->index);
if (err)
return err;
- devlink_port_type_eth_set(&port->devlink_port, port->netdev);
+ switch (dp->type) {
+ case DSA_PORT_TYPE_UNUSED:
+ break;
+ case DSA_PORT_TYPE_CPU:
+ case DSA_PORT_TYPE_DSA:
+ err = dsa_port_fixed_link_register_of(dp);
+ if (err) {
+ dev_err(ds->dev, "failed to register fixed link for port %d.%d\n",
+ ds->index, dp->index);
+ return err;
+ }
+
+ break;
+ case DSA_PORT_TYPE_USER:
+ err = dsa_slave_create(dp);
+ if (err)
+ dev_err(ds->dev, "failed to create slave for port %d.%d\n",
+ ds->index, dp->index);
+ else
+ devlink_port_type_eth_set(&dp->devlink_port, dp->slave);
+ break;
+ }
return 0;
}
-static void dsa_user_port_unapply(struct dsa_port *port)
+static void dsa_port_teardown(struct dsa_port *dp)
{
- devlink_port_unregister(&port->devlink_port);
- if (port->netdev) {
- dsa_slave_destroy(port->netdev);
- port->netdev = NULL;
- port->ds->enabled_port_mask &= ~(1 << port->index);
+ devlink_port_unregister(&dp->devlink_port);
+
+ switch (dp->type) {
+ case DSA_PORT_TYPE_UNUSED:
+ break;
+ case DSA_PORT_TYPE_CPU:
+ case DSA_PORT_TYPE_DSA:
+ dsa_port_fixed_link_unregister_of(dp);
+ break;
+ case DSA_PORT_TYPE_USER:
+ if (dp->slave) {
+ dsa_slave_destroy(dp->slave);
+ dp->slave = NULL;
+ }
+ break;
}
}
-static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
+static int dsa_switch_setup(struct dsa_switch *ds)
{
- struct dsa_port *port;
- u32 index;
int err;
/* Initialize ds->phys_mii_mask before registering the slave MDIO bus
@@ -315,7 +319,7 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
* the slave MDIO bus driver rely on these values for probing PHY
* devices or not
*/
- ds->phys_mii_mask = ds->enabled_port_mask;
+ ds->phys_mii_mask |= dsa_user_ports(ds);
/* Add the switch to devlink before calling setup, so that setup can
* add dpipe tables
@@ -336,12 +340,6 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
if (err)
return err;
- if (ds->ops->set_addr) {
- err = ds->ops->set_addr(ds, dst->cpu_dp->netdev->dev_addr);
- if (err < 0)
- return err;
- }
-
if (!ds->slave_mii_bus && ds->ops->phy_read) {
ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
if (!ds->slave_mii_bus)
@@ -354,56 +352,11 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
return err;
}
- for (index = 0; index < ds->num_ports; index++) {
- port = &ds->ports[index];
- if (!dsa_port_is_valid(port))
- continue;
-
- if (dsa_port_is_dsa(port)) {
- err = dsa_dsa_port_apply(port);
- if (err)
- return err;
- continue;
- }
-
- if (dsa_port_is_cpu(port)) {
- err = dsa_cpu_port_apply(port);
- if (err)
- return err;
- continue;
- }
-
- err = dsa_user_port_apply(port);
- if (err)
- continue;
- }
-
return 0;
}
-static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
+static void dsa_switch_teardown(struct dsa_switch *ds)
{
- struct dsa_port *port;
- u32 index;
-
- for (index = 0; index < ds->num_ports; index++) {
- port = &ds->ports[index];
- if (!dsa_port_is_valid(port))
- continue;
-
- if (dsa_port_is_dsa(port)) {
- dsa_dsa_port_unapply(port);
- continue;
- }
-
- if (dsa_port_is_cpu(port)) {
- dsa_cpu_port_unapply(port);
- continue;
- }
-
- dsa_user_port_unapply(port);
- }
-
if (ds->slave_mii_bus && ds->ops->phy_read)
mdiobus_unregister(ds->slave_mii_bus);
@@ -417,199 +370,228 @@ static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
}
-static int dsa_dst_apply(struct dsa_switch_tree *dst)
+static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
{
struct dsa_switch *ds;
- u32 index;
+ struct dsa_port *dp;
+ int device, port;
int err;
- for (index = 0; index < DSA_MAX_SWITCHES; index++) {
- ds = dst->ds[index];
+ for (device = 0; device < DSA_MAX_SWITCHES; device++) {
+ ds = dst->ds[device];
if (!ds)
continue;
- err = dsa_ds_apply(dst, ds);
+ err = dsa_switch_setup(ds);
if (err)
return err;
- }
- if (dst->cpu_dp) {
- err = dsa_cpu_port_ethtool_setup(dst->cpu_dp);
- if (err)
- return err;
- }
+ for (port = 0; port < ds->num_ports; port++) {
+ dp = &ds->ports[port];
- /* If we use a tagging format that doesn't have an ethertype
- * field, make sure that all packets from this point on get
- * sent to the tag format's receive function.
- */
- wmb();
- dst->cpu_dp->netdev->dsa_ptr = dst;
- dst->applied = true;
+ err = dsa_port_setup(dp);
+ if (err)
+ return err;
+ }
+ }
return 0;
}
-static void dsa_dst_unapply(struct dsa_switch_tree *dst)
+static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst)
{
struct dsa_switch *ds;
- u32 index;
-
- if (!dst->applied)
- return;
-
- dst->cpu_dp->netdev->dsa_ptr = NULL;
-
- /* If we used a tagging format that doesn't have an ethertype
- * field, make sure that all packets from this point get sent
- * without the tag and go through the regular receive path.
- */
- wmb();
+ struct dsa_port *dp;
+ int device, port;
- for (index = 0; index < DSA_MAX_SWITCHES; index++) {
- ds = dst->ds[index];
+ for (device = 0; device < DSA_MAX_SWITCHES; device++) {
+ ds = dst->ds[device];
if (!ds)
continue;
- dsa_ds_unapply(dst, ds);
- }
+ for (port = 0; port < ds->num_ports; port++) {
+ dp = &ds->ports[port];
- if (dst->cpu_dp) {
- dsa_cpu_port_ethtool_restore(dst->cpu_dp);
- dst->cpu_dp = NULL;
+ dsa_port_teardown(dp);
+ }
+
+ dsa_switch_teardown(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;
- pr_info("DSA: tree %d unapplied\n", dst->tree);
- dst->applied = false;
+ /* DSA currently supports a single pair of CPU port and master device */
+ return dsa_master_setup(master, cpu_dp);
}
-static int dsa_cpu_parse(struct dsa_port *port, u32 index,
- struct dsa_switch_tree *dst,
- struct dsa_switch *ds)
+static void dsa_tree_teardown_master(struct dsa_switch_tree *dst)
{
- enum dsa_tag_protocol tag_protocol;
- struct net_device *ethernet_dev;
- struct device_node *ethernet;
+ struct dsa_port *cpu_dp = dst->cpu_dp;
+ struct net_device *master = cpu_dp->master;
- if (port->dn) {
- ethernet = of_parse_phandle(port->dn, "ethernet", 0);
- if (!ethernet)
- return -EINVAL;
- ethernet_dev = of_find_net_device_by_node(ethernet);
- if (!ethernet_dev)
- return -EPROBE_DEFER;
- } else {
- ethernet_dev = dsa_dev_to_net_device(ds->cd->netdev[index]);
- if (!ethernet_dev)
- return -EPROBE_DEFER;
- dev_put(ethernet_dev);
- }
+ return dsa_master_teardown(master);
+}
- if (!dst->cpu_dp) {
- dst->cpu_dp = port;
- dst->cpu_dp->netdev = ethernet_dev;
+static int dsa_tree_setup(struct dsa_switch_tree *dst)
+{
+ bool complete;
+ int err;
+
+ if (dst->setup) {
+ pr_err("DSA: tree %d already setup! Disjoint trees?\n",
+ dst->index);
+ return -EEXIST;
}
- /* Initialize cpu_port_mask now for drv->setup()
- * to have access to a correct value, just like what
- * net/dsa/dsa.c::dsa_switch_setup_one does.
- */
- ds->cpu_port_mask |= BIT(index);
+ complete = dsa_tree_setup_routing_table(dst);
+ if (!complete)
+ return 0;
- tag_protocol = ds->ops->get_tag_protocol(ds);
- dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol);
- if (IS_ERR(dst->tag_ops)) {
- dev_warn(ds->dev, "No tagger for this switch\n");
- ds->cpu_port_mask &= ~BIT(index);
- return PTR_ERR(dst->tag_ops);
- }
+ err = dsa_tree_setup_default_cpu(dst);
+ if (err)
+ return err;
- dst->rcv = dst->tag_ops->rcv;
+ err = dsa_tree_setup_switches(dst);
+ if (err)
+ return err;
+
+ err = dsa_tree_setup_master(dst);
+ if (err)
+ return err;
+
+ dst->setup = true;
+
+ pr_info("DSA: tree %d setup\n", dst->index);
return 0;
}
-static int dsa_ds_parse(struct dsa_switch_tree *dst, struct dsa_switch *ds)
+static void dsa_tree_teardown(struct dsa_switch_tree *dst)
+{
+ if (!dst->setup)
+ return;
+
+ dsa_tree_teardown_master(dst);
+
+ dsa_tree_teardown_switches(dst);
+
+ dsa_tree_teardown_default_cpu(dst);
+
+ 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)
{
- struct dsa_port *port;
- u32 index;
+ dsa_tree_teardown(dst);
+
+ dst->ds[index] = NULL;
+ dsa_tree_put(dst);
+}
+
+static int dsa_tree_add_switch(struct dsa_switch_tree *dst,
+ struct dsa_switch *ds)
+{
+ unsigned int index = ds->index;
int err;
- for (index = 0; index < ds->num_ports; index++) {
- port = &ds->ports[index];
- if (!dsa_port_is_valid(port) ||
- dsa_port_is_dsa(port))
- continue;
+ if (dst->ds[index])
+ return -EBUSY;
- if (dsa_port_is_cpu(port)) {
- err = dsa_cpu_parse(port, index, dst, ds);
- if (err)
- return err;
- } else {
- /* Initialize enabled_port_mask now for drv->setup()
- * to have access to a correct value, just like what
- * net/dsa/dsa.c::dsa_switch_setup_one does.
- */
- ds->enabled_port_mask |= BIT(index);
- }
+ dsa_tree_get(dst);
+ dst->ds[index] = ds;
- }
+ err = dsa_tree_setup(dst);
+ if (err)
+ dsa_tree_remove_switch(dst, index);
- pr_info("DSA: switch %d %d parsed\n", dst->tree, ds->index);
+ return err;
+}
+
+static int dsa_port_parse_user(struct dsa_port *dp, const char *name)
+{
+ if (!name)
+ name = "eth%d";
+
+ dp->type = DSA_PORT_TYPE_USER;
+ dp->name = name;
return 0;
}
-static int dsa_dst_parse(struct dsa_switch_tree *dst)
+static int dsa_port_parse_dsa(struct dsa_port *dp)
{
- struct dsa_switch *ds;
- struct dsa_port *dp;
- u32 index;
- int port;
- int err;
+ dp->type = DSA_PORT_TYPE_DSA;
- for (index = 0; index < DSA_MAX_SWITCHES; index++) {
- ds = dst->ds[index];
- if (!ds)
- continue;
+ return 0;
+}
- err = dsa_ds_parse(dst, ds);
- if (err)
- return err;
- }
+static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master)
+{
+ struct dsa_switch *ds = dp->ds;
+ struct dsa_switch_tree *dst = ds->dst;
+ const struct dsa_device_ops *tag_ops;
+ enum dsa_tag_protocol tag_protocol;
- if (!dst->cpu_dp) {
- pr_warn("Tree has no master device\n");
- return -EINVAL;
+ tag_protocol = ds->ops->get_tag_protocol(ds, dp->index);
+ tag_ops = dsa_resolve_tag_protocol(tag_protocol);
+ if (IS_ERR(tag_ops)) {
+ dev_warn(ds->dev, "No tagger for this switch\n");
+ return PTR_ERR(tag_ops);
}
- /* Assign the default CPU port to all ports of the fabric */
- for (index = 0; index < DSA_MAX_SWITCHES; index++) {
- ds = dst->ds[index];
- if (!ds)
- continue;
+ dp->type = DSA_PORT_TYPE_CPU;
+ dp->rcv = tag_ops->rcv;
+ dp->tag_ops = tag_ops;
+ dp->master = master;
+ dp->dst = dst;
- for (port = 0; port < ds->num_ports; port++) {
- dp = &ds->ports[port];
- if (!dsa_port_is_valid(dp) ||
- dsa_port_is_dsa(dp) ||
- dsa_port_is_cpu(dp))
- continue;
+ return 0;
+}
- dp->cpu_dp = dst->cpu_dp;
- }
+static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn)
+{
+ struct device_node *ethernet = of_parse_phandle(dn, "ethernet", 0);
+ const char *name = of_get_property(dn, "label", NULL);
+ bool link = of_property_read_bool(dn, "link");
+
+ dp->dn = dn;
+
+ if (ethernet) {
+ struct net_device *master;
+
+ master = of_find_net_device_by_node(ethernet);
+ if (!master)
+ return -EPROBE_DEFER;
+
+ return dsa_port_parse_cpu(dp, master);
}
- pr_info("DSA: tree %d parsed\n", dst->tree);
+ if (link)
+ return dsa_port_parse_dsa(dp);
- return 0;
+ return dsa_port_parse_user(dp, name);
}
-static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds)
+static int dsa_switch_parse_ports_of(struct dsa_switch *ds,
+ struct device_node *dn)
{
- struct device_node *port;
- int err;
+ struct device_node *ports, *port;
+ struct dsa_port *dp;
u32 reg;
+ int err;
+
+ ports = of_get_child_by_name(dn, "ports");
+ if (!ports) {
+ dev_err(ds->dev, "no ports child node found\n");
+ return -EINVAL;
+ }
for_each_available_child_of_node(ports, port) {
err = of_property_read_u32(port, "reg", &reg);
@@ -619,174 +601,140 @@ static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds)
if (reg >= ds->num_ports)
return -EINVAL;
- ds->ports[reg].dn = port;
+ dp = &ds->ports[reg];
+
+ err = dsa_port_parse_of(dp, port);
+ if (err)
+ return err;
}
return 0;
}
-static int dsa_parse_ports(struct dsa_chip_data *cd, struct dsa_switch *ds)
+static int dsa_switch_parse_member_of(struct dsa_switch *ds,
+ struct device_node *dn)
{
- bool valid_name_found = false;
- unsigned int i;
+ u32 m[2] = { 0, 0 };
+ int sz;
- for (i = 0; i < DSA_MAX_PORTS; i++) {
- if (!cd->port_names[i])
- continue;
+ /* Don't error out if this optional property isn't found */
+ sz = of_property_read_variable_u32_array(dn, "dsa,member", m, 2, 2);
+ if (sz < 0 && sz != -EINVAL)
+ return sz;
- ds->ports[i].name = cd->port_names[i];
- valid_name_found = true;
- }
-
- if (!valid_name_found && i == DSA_MAX_PORTS)
+ ds->index = m[1];
+ if (ds->index >= DSA_MAX_SWITCHES)
return -EINVAL;
+ ds->dst = dsa_tree_touch(m[0]);
+ if (!ds->dst)
+ return -ENOMEM;
+
return 0;
}
-static int dsa_parse_member_dn(struct device_node *np, u32 *tree, u32 *index)
+static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn)
{
int err;
- *tree = *index = 0;
-
- err = of_property_read_u32_index(np, "dsa,member", 0, tree);
- if (err) {
- /* Does not exist, but it is optional */
- if (err == -EINVAL)
- return 0;
- return err;
- }
-
- err = of_property_read_u32_index(np, "dsa,member", 1, index);
+ err = dsa_switch_parse_member_of(ds, dn);
if (err)
return err;
- if (*index >= DSA_MAX_SWITCHES)
- return -EINVAL;
-
- return 0;
+ return dsa_switch_parse_ports_of(ds, dn);
}
-static int dsa_parse_member(struct dsa_chip_data *pd, u32 *tree, u32 *index)
+static int dsa_port_parse(struct dsa_port *dp, const char *name,
+ struct device *dev)
{
- if (!pd)
- return -ENODEV;
-
- /* We do not support complex trees with dsa_chip_data */
- *tree = 0;
- *index = 0;
+ if (!strcmp(name, "cpu")) {
+ struct net_device *master;
- return 0;
-}
+ master = dsa_dev_to_net_device(dev);
+ if (!master)
+ return -EPROBE_DEFER;
-static struct device_node *dsa_get_ports(struct dsa_switch *ds,
- struct device_node *np)
-{
- struct device_node *ports;
+ dev_put(master);
- ports = of_get_child_by_name(np, "ports");
- if (!ports) {
- dev_err(ds->dev, "no ports child node found\n");
- return ERR_PTR(-EINVAL);
+ return dsa_port_parse_cpu(dp, master);
}
- return ports;
+ if (!strcmp(name, "dsa"))
+ return dsa_port_parse_dsa(dp);
+
+ return dsa_port_parse_user(dp, name);
}
-static int _dsa_register_switch(struct dsa_switch *ds)
+static int dsa_switch_parse_ports(struct dsa_switch *ds,
+ struct dsa_chip_data *cd)
{
- struct dsa_chip_data *pdata = ds->dev->platform_data;
- struct device_node *np = ds->dev->of_node;
- struct dsa_switch_tree *dst;
- struct device_node *ports;
- u32 tree, index;
- int i, err;
-
- if (np) {
- err = dsa_parse_member_dn(np, &tree, &index);
- if (err)
- return err;
+ bool valid_name_found = false;
+ struct dsa_port *dp;
+ struct device *dev;
+ const char *name;
+ unsigned int i;
+ int err;
- ports = dsa_get_ports(ds, np);
- if (IS_ERR(ports))
- return PTR_ERR(ports);
+ for (i = 0; i < DSA_MAX_PORTS; i++) {
+ name = cd->port_names[i];
+ dev = cd->netdev[i];
+ dp = &ds->ports[i];
- err = dsa_parse_ports_dn(ports, ds);
- if (err)
- return err;
- } else {
- err = dsa_parse_member(pdata, &tree, &index);
- if (err)
- return err;
+ if (!name)
+ continue;
- err = dsa_parse_ports(pdata, ds);
+ err = dsa_port_parse(dp, name, dev);
if (err)
return err;
- }
- dst = dsa_get_dst(tree);
- if (!dst) {
- dst = dsa_add_dst(tree);
- if (!dst)
- return -ENOMEM;
- }
-
- if (dst->ds[index]) {
- err = -EBUSY;
- goto out;
+ valid_name_found = true;
}
- ds->dst = dst;
- ds->index = index;
- ds->cd = pdata;
-
- /* Initialize the routing table */
- for (i = 0; i < DSA_MAX_SWITCHES; ++i)
- ds->rtable[i] = DSA_RTABLE_NONE;
+ if (!valid_name_found && i == DSA_MAX_PORTS)
+ return -EINVAL;
- dsa_dst_add_ds(dst, ds, index);
+ return 0;
+}
- err = dsa_dst_complete(dst);
- if (err < 0)
- goto out_del_dst;
+static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd)
+{
+ ds->cd = cd;
- if (err == 1) {
- /* Not all switches registered yet */
- err = 0;
- goto out;
- }
+ /* We don't support interconnected switches nor multiple trees via
+ * platform data, so this is the unique switch of the tree.
+ */
+ ds->index = 0;
+ ds->dst = dsa_tree_touch(0);
+ if (!ds->dst)
+ return -ENOMEM;
- if (dst->applied) {
- pr_info("DSA: Disjoint trees?\n");
- return -EINVAL;
- }
+ return dsa_switch_parse_ports(ds, cd);
+}
- err = dsa_dst_parse(dst);
- if (err) {
- if (err == -EPROBE_DEFER) {
- dsa_dst_del_ds(dst, ds, ds->index);
- return err;
- }
+static int dsa_switch_add(struct dsa_switch *ds)
+{
+ struct dsa_switch_tree *dst = ds->dst;
- goto out_del_dst;
- }
+ return dsa_tree_add_switch(dst, ds);
+}
- err = dsa_dst_apply(dst);
- if (err) {
- dsa_dst_unapply(dst);
- goto out_del_dst;
- }
+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;
+ int err;
- dsa_put_dst(dst);
- return 0;
+ if (np)
+ err = dsa_switch_parse_of(ds, np);
+ else if (pdata)
+ err = dsa_switch_parse(ds, pdata);
+ else
+ err = -ENODEV;
-out_del_dst:
- dsa_dst_del_ds(dst, ds, ds->index);
-out:
- dsa_put_dst(dst);
+ if (err)
+ return err;
- return err;
+ return dsa_switch_add(ds);
}
struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n)
@@ -816,26 +764,25 @@ int dsa_register_switch(struct dsa_switch *ds)
int err;
mutex_lock(&dsa2_mutex);
- err = _dsa_register_switch(ds);
+ err = dsa_switch_probe(ds);
mutex_unlock(&dsa2_mutex);
return err;
}
EXPORT_SYMBOL_GPL(dsa_register_switch);
-static void _dsa_unregister_switch(struct dsa_switch *ds)
+static void dsa_switch_remove(struct dsa_switch *ds)
{
struct dsa_switch_tree *dst = ds->dst;
+ unsigned int index = ds->index;
- dsa_dst_unapply(dst);
-
- dsa_dst_del_ds(dst, ds, ds->index);
+ dsa_tree_remove_switch(dst, index);
}
void dsa_unregister_switch(struct dsa_switch *ds)
{
mutex_lock(&dsa2_mutex);
- _dsa_unregister_switch(ds);
+ dsa_switch_remove(ds);
mutex_unlock(&dsa2_mutex);
}
EXPORT_SYMBOL_GPL(dsa_unregister_switch);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 9c3eeb72462d..7d036696e8c4 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -66,7 +66,7 @@ struct dsa_notifier_vlan_info {
};
struct dsa_slave_priv {
- /* Copy of dp->ds->dst->tag_ops->xmit for faster access in hot path */
+ /* Copy of CPU port xmit for faster access in slave transmit hot path */
struct sk_buff * (*xmit)(struct sk_buff *skb,
struct net_device *dev);
@@ -79,7 +79,6 @@ struct dsa_slave_priv {
* The phylib phy_device pointer for the PHY connected
* to this port.
*/
- struct phy_device *phy;
phy_interface_t phy_interface;
int old_link;
int old_pause;
@@ -94,11 +93,7 @@ struct dsa_slave_priv {
};
/* dsa.c */
-int dsa_cpu_dsa_setup(struct dsa_port *port);
-void dsa_cpu_dsa_destroy(struct dsa_port *dport);
const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol);
-int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp);
-void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp);
bool dsa_schedule_work(struct work_struct *work);
/* legacy.c */
@@ -112,10 +107,35 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid);
+/* master.c */
+int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp);
+void dsa_master_teardown(struct net_device *dev);
+
+static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
+ int device, int port)
+{
+ struct dsa_port *cpu_dp = dev->dsa_ptr;
+ struct dsa_switch_tree *dst = cpu_dp->dst;
+ struct dsa_switch *ds;
+
+ if (device < 0 || device >= DSA_MAX_SWITCHES)
+ return NULL;
+
+ ds = dst->ds[device];
+ if (!ds)
+ return NULL;
+
+ if (port < 0 || port >= ds->num_ports)
+ return NULL;
+
+ return ds->ports[port].slave;
+}
+
/* port.c */
int dsa_port_set_state(struct dsa_port *dp, u8 state,
struct switchdev_trans *trans);
-void dsa_port_set_state_now(struct dsa_port *dp, u8 state);
+int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy);
+void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy);
int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br);
void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br);
int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
@@ -126,33 +146,52 @@ int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr,
u16 vid);
int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr,
u16 vid);
-int dsa_port_mdb_add(struct dsa_port *dp,
+int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data);
+int dsa_port_mdb_add(const struct dsa_port *dp,
const struct switchdev_obj_port_mdb *mdb,
struct switchdev_trans *trans);
-int dsa_port_mdb_del(struct dsa_port *dp,
+int dsa_port_mdb_del(const struct dsa_port *dp,
const struct switchdev_obj_port_mdb *mdb);
int dsa_port_vlan_add(struct dsa_port *dp,
const struct switchdev_obj_port_vlan *vlan,
struct switchdev_trans *trans);
int dsa_port_vlan_del(struct dsa_port *dp,
const struct switchdev_obj_port_vlan *vlan);
+int dsa_port_fixed_link_register_of(struct dsa_port *dp);
+void dsa_port_fixed_link_unregister_of(struct dsa_port *dp);
+
/* slave.c */
extern const struct dsa_device_ops notag_netdev_ops;
void dsa_slave_mii_bus_init(struct dsa_switch *ds);
-void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops);
-int dsa_slave_create(struct dsa_port *port, const char *name);
+int dsa_slave_create(struct dsa_port *dp);
void dsa_slave_destroy(struct net_device *slave_dev);
int dsa_slave_suspend(struct net_device *slave_dev);
int dsa_slave_resume(struct net_device *slave_dev);
int dsa_slave_register_notifier(void);
void dsa_slave_unregister_notifier(void);
+static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+
+ return p->dp;
+}
+
+static inline struct net_device *
+dsa_slave_to_master(const struct net_device *dev)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+
+ return dp->cpu_dp->master;
+}
+
/* switch.c */
int dsa_switch_register_notifier(struct dsa_switch *ds);
void dsa_switch_unregister_notifier(struct dsa_switch *ds);
/* tag_brcm.c */
extern const struct dsa_device_ops brcm_netdev_ops;
+extern const struct dsa_device_ops brcm_prepend_netdev_ops;
/* tag_dsa.c */
extern const struct dsa_device_ops dsa_netdev_ops;
@@ -175,14 +214,4 @@ extern const struct dsa_device_ops qca_netdev_ops;
/* tag_trailer.c */
extern const struct dsa_device_ops trailer_netdev_ops;
-static inline struct net_device *dsa_master_netdev(struct dsa_slave_priv *p)
-{
- return p->dp->cpu_dp->netdev;
-}
-
-static inline struct dsa_port *dsa_get_cpu_port(struct dsa_switch_tree *dst)
-{
- return dst->cpu_dp;
-}
-
#endif
diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c
index 91e6f7981d39..84611d7fcfa2 100644
--- a/net/dsa/legacy.c
+++ b/net/dsa/legacy.c
@@ -86,7 +86,7 @@ static int dsa_cpu_dsa_setups(struct dsa_switch *ds)
if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
continue;
- ret = dsa_cpu_dsa_setup(&ds->ports[port]);
+ ret = dsa_port_fixed_link_register_of(&ds->ports[port]);
if (ret)
return ret;
}
@@ -101,6 +101,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
struct dsa_chip_data *cd = ds->cd;
bool valid_name_found = false;
int index = ds->index;
+ struct dsa_port *dp;
int i, ret;
/*
@@ -109,9 +110,12 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
for (i = 0; i < ds->num_ports; i++) {
char *name;
+ dp = &ds->ports[i];
+
name = cd->port_names[i];
if (name == NULL)
continue;
+ dp->name = name;
if (!strcmp(name, "cpu")) {
if (dst->cpu_dp) {
@@ -120,12 +124,12 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
return -EINVAL;
}
dst->cpu_dp = &ds->ports[i];
- dst->cpu_dp->netdev = master;
- ds->cpu_port_mask |= 1 << i;
+ dst->cpu_dp->master = master;
+ dp->type = DSA_PORT_TYPE_CPU;
} else if (!strcmp(name, "dsa")) {
- ds->dsa_port_mask |= 1 << i;
+ dp->type = DSA_PORT_TYPE_DSA;
} else {
- ds->enabled_port_mask |= 1 << i;
+ dp->type = DSA_PORT_TYPE_USER;
}
valid_name_found = true;
}
@@ -136,7 +140,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
/* Make the built-in MII bus mask match the number of ports,
* switch drivers can override this later
*/
- ds->phys_mii_mask = ds->enabled_port_mask;
+ ds->phys_mii_mask |= dsa_user_ports(ds);
/*
* If the CPU connects to this switch, set the switch tree
@@ -144,14 +148,19 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
* switch.
*/
if (dst->cpu_dp->ds == ds) {
+ const struct dsa_device_ops *tag_ops;
enum dsa_tag_protocol tag_protocol;
- tag_protocol = ops->get_tag_protocol(ds);
- dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol);
- if (IS_ERR(dst->tag_ops))
- return PTR_ERR(dst->tag_ops);
+ tag_protocol = ops->get_tag_protocol(ds, dst->cpu_dp->index);
+ tag_ops = dsa_resolve_tag_protocol(tag_protocol);
+ if (IS_ERR(tag_ops))
+ return PTR_ERR(tag_ops);
+
+ dst->cpu_dp->tag_ops = tag_ops;
- dst->rcv = dst->tag_ops->rcv;
+ /* Few copies for faster access in master receive hot path */
+ dst->cpu_dp->rcv = dst->cpu_dp->tag_ops->rcv;
+ dst->cpu_dp->dst = dst;
}
memcpy(ds->rtable, cd->rtable, sizeof(ds->rtable));
@@ -167,12 +176,6 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
if (ret)
return ret;
- if (ops->set_addr) {
- ret = ops->set_addr(ds, master->dev_addr);
- if (ret < 0)
- return ret;
- }
-
if (!ds->slave_mii_bus && ops->phy_read) {
ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
if (!ds->slave_mii_bus)
@@ -191,10 +194,10 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
ds->ports[i].dn = cd->port_dn[i];
ds->ports[i].cpu_dp = dst->cpu_dp;
- if (!(ds->enabled_port_mask & (1 << i)))
+ if (dsa_is_user_port(ds, i))
continue;
- ret = dsa_slave_create(&ds->ports[i], cd->port_names[i]);
+ ret = dsa_slave_create(&ds->ports[i]);
if (ret < 0)
netdev_err(master, "[%d]: can't create dsa slave device for port %d(%s): %d\n",
index, i, cd->port_names[i], ret);
@@ -206,10 +209,6 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
netdev_err(master, "[%d] : can't configure CPU and DSA ports\n",
index);
- ret = dsa_cpu_port_ethtool_setup(ds->dst->cpu_dp);
- if (ret)
- return ret;
-
return 0;
}
@@ -263,24 +262,20 @@ static void dsa_switch_destroy(struct dsa_switch *ds)
/* Destroy network devices for physical switch ports. */
for (port = 0; port < ds->num_ports; port++) {
- if (!(ds->enabled_port_mask & (1 << port)))
+ if (!dsa_is_user_port(ds, port))
continue;
- if (!ds->ports[port].netdev)
+ if (!ds->ports[port].slave)
continue;
- dsa_slave_destroy(ds->ports[port].netdev);
+ dsa_slave_destroy(ds->ports[port].slave);
}
/* Disable configuration of the CPU and DSA ports */
for (port = 0; port < ds->num_ports; port++) {
if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
continue;
- dsa_cpu_dsa_destroy(&ds->ports[port]);
-
- /* Clearing a bit which is not set does no harm */
- ds->cpu_port_mask |= ~(1 << port);
- ds->dsa_port_mask |= ~(1 << port);
+ dsa_port_fixed_link_unregister_of(&ds->ports[port]);
}
if (ds->slave_mii_bus && ds->ops->phy_read)
@@ -598,15 +593,7 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev,
if (!configured)
return -EPROBE_DEFER;
- /*
- * If we use a tagging format that doesn't have an ethertype
- * field, make sure that all packets from this point on get
- * sent to the tag format's receive function.
- */
- wmb();
- dev->dsa_ptr = dst;
-
- return 0;
+ return dsa_master_setup(dst->cpu_dp->master, dst->cpu_dp);
}
static int dsa_probe(struct platform_device *pdev)
@@ -671,13 +658,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst)
{
int i;
- dst->cpu_dp->netdev->dsa_ptr = NULL;
-
- /* If we used a tagging format that doesn't have an ethertype
- * field, make sure that all packets from this point get sent
- * without the tag and go through the regular receive path.
- */
- wmb();
+ dsa_master_teardown(dst->cpu_dp->master);
for (i = 0; i < dst->pd->nr_chips; i++) {
struct dsa_switch *ds = dst->ds[i];
@@ -686,9 +667,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst)
dsa_switch_destroy(ds);
}
- dsa_cpu_port_ethtool_restore(dst->cpu_dp);
-
- dev_put(dst->cpu_dp->netdev);
+ dev_put(dst->cpu_dp->master);
}
static int dsa_remove(struct platform_device *pdev)
@@ -745,8 +724,7 @@ int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
const unsigned char *addr, u16 vid,
u16 flags)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_port *dp = p->dp;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
return dsa_port_fdb_add(dp, addr, vid);
}
@@ -755,8 +733,7 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_port *dp = p->dp;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
return dsa_port_fdb_del(dp, addr, vid);
}
diff --git a/net/dsa/master.c b/net/dsa/master.c
new file mode 100644
index 000000000000..00589147f042
--- /dev/null
+++ b/net/dsa/master.c
@@ -0,0 +1,143 @@
+/*
+ * Handling of a master device, switching frames via its switch fabric CPU port
+ *
+ * Copyright (c) 2017 Savoir-faire Linux Inc.
+ * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "dsa_priv.h"
+
+static void dsa_master_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *stats,
+ uint64_t *data)
+{
+ struct dsa_port *cpu_dp = dev->dsa_ptr;
+ const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
+ struct dsa_switch *ds = cpu_dp->ds;
+ int port = cpu_dp->index;
+ int count = 0;
+
+ if (ops && ops->get_sset_count && ops->get_ethtool_stats) {
+ count = ops->get_sset_count(dev, ETH_SS_STATS);
+ ops->get_ethtool_stats(dev, stats, data);
+ }
+
+ if (ds->ops->get_ethtool_stats)
+ ds->ops->get_ethtool_stats(ds, port, data + count);
+}
+
+static int dsa_master_get_sset_count(struct net_device *dev, int sset)
+{
+ struct dsa_port *cpu_dp = dev->dsa_ptr;
+ const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
+ struct dsa_switch *ds = cpu_dp->ds;
+ int count = 0;
+
+ if (ops && ops->get_sset_count)
+ count += ops->get_sset_count(dev, sset);
+
+ if (sset == ETH_SS_STATS && ds->ops->get_sset_count)
+ count += ds->ops->get_sset_count(ds);
+
+ return count;
+}
+
+static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset,
+ uint8_t *data)
+{
+ struct dsa_port *cpu_dp = dev->dsa_ptr;
+ const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
+ struct dsa_switch *ds = cpu_dp->ds;
+ int port = cpu_dp->index;
+ int len = ETH_GSTRING_LEN;
+ int mcount = 0, count;
+ unsigned int i;
+ uint8_t pfx[4];
+ uint8_t *ndata;
+
+ snprintf(pfx, sizeof(pfx), "p%.2d", port);
+ /* We do not want to be NULL-terminated, since this is a prefix */
+ pfx[sizeof(pfx) - 1] = '_';
+
+ if (ops && ops->get_sset_count && ops->get_strings) {
+ mcount = ops->get_sset_count(dev, ETH_SS_STATS);
+ ops->get_strings(dev, stringset, data);
+ }
+
+ if (stringset == ETH_SS_STATS && ds->ops->get_strings) {
+ ndata = data + mcount * len;
+ /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle
+ * the output after to prepend our CPU port prefix we
+ * constructed earlier
+ */
+ ds->ops->get_strings(ds, port, ndata);
+ count = ds->ops->get_sset_count(ds);
+ for (i = 0; i < count; i++) {
+ memmove(ndata + (i * len + sizeof(pfx)),
+ ndata + i * len, len - sizeof(pfx));
+ memcpy(ndata + i * len, pfx, sizeof(pfx));
+ }
+ }
+}
+
+static int dsa_master_ethtool_setup(struct net_device *dev)
+{
+ struct dsa_port *cpu_dp = dev->dsa_ptr;
+ struct dsa_switch *ds = cpu_dp->ds;
+ struct ethtool_ops *ops;
+
+ ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL);
+ if (!ops)
+ return -ENOMEM;
+
+ cpu_dp->orig_ethtool_ops = dev->ethtool_ops;
+ if (cpu_dp->orig_ethtool_ops)
+ memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops));
+
+ ops->get_sset_count = dsa_master_get_sset_count;
+ ops->get_ethtool_stats = dsa_master_get_ethtool_stats;
+ ops->get_strings = dsa_master_get_strings;
+
+ dev->ethtool_ops = ops;
+
+ return 0;
+}
+
+static void dsa_master_ethtool_teardown(struct net_device *dev)
+{
+ struct dsa_port *cpu_dp = dev->dsa_ptr;
+
+ dev->ethtool_ops = cpu_dp->orig_ethtool_ops;
+ cpu_dp->orig_ethtool_ops = NULL;
+}
+
+int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
+{
+ /* If we use a tagging format that doesn't have an ethertype
+ * field, make sure that all packets from this point on get
+ * sent to the tag format's receive function.
+ */
+ wmb();
+
+ dev->dsa_ptr = cpu_dp;
+
+ return dsa_master_ethtool_setup(dev);
+}
+
+void dsa_master_teardown(struct net_device *dev)
+{
+ dsa_master_ethtool_teardown(dev);
+
+ dev->dsa_ptr = NULL;
+
+ /* If we used a tagging format that doesn't have an ethertype
+ * field, make sure that all packets from this point get sent
+ * without the tag and go through the regular receive path.
+ */
+ wmb();
+}
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 659676ba3f8b..bb4be2679904 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -12,10 +12,12 @@
#include <linux/if_bridge.h>
#include <linux/notifier.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
#include "dsa_priv.h"
-static int dsa_port_notify(struct dsa_port *dp, unsigned long e, void *v)
+static int dsa_port_notify(const struct dsa_port *dp, unsigned long e, void *v)
{
struct raw_notifier_head *nh = &dp->ds->dst->nh;
int err;
@@ -56,7 +58,7 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state,
return 0;
}
-void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
+static void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
{
int err;
@@ -65,6 +67,35 @@ void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
pr_err("DSA: failed to set STP state %u (%d)\n", state, err);
}
+int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
+{
+ u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING;
+ struct dsa_switch *ds = dp->ds;
+ int port = dp->index;
+ int err;
+
+ if (ds->ops->port_enable) {
+ err = ds->ops->port_enable(ds, port, phy);
+ if (err)
+ return err;
+ }
+
+ dsa_port_set_state_now(dp, stp_state);
+
+ return 0;
+}
+
+void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy)
+{
+ struct dsa_switch *ds = dp->ds;
+ int port = dp->index;
+
+ dsa_port_set_state_now(dp, BR_STATE_DISABLED);
+
+ if (ds->ops->port_disable)
+ ds->ops->port_disable(ds, port, phy);
+}
+
int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br)
{
struct dsa_notifier_bridge_info info = {
@@ -173,7 +204,18 @@ int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr,
return dsa_port_notify(dp, DSA_NOTIFIER_FDB_DEL, &info);
}
-int dsa_port_mdb_add(struct dsa_port *dp,
+int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data)
+{
+ struct dsa_switch *ds = dp->ds;
+ int port = dp->index;
+
+ if (!ds->ops->port_fdb_dump)
+ return -EOPNOTSUPP;
+
+ return ds->ops->port_fdb_dump(ds, port, cb, data);
+}
+
+int dsa_port_mdb_add(const struct dsa_port *dp,
const struct switchdev_obj_port_mdb *mdb,
struct switchdev_trans *trans)
{
@@ -187,7 +229,7 @@ int dsa_port_mdb_add(struct dsa_port *dp,
return dsa_port_notify(dp, DSA_NOTIFIER_MDB_ADD, &info);
}
-int dsa_port_mdb_del(struct dsa_port *dp,
+int dsa_port_mdb_del(const struct dsa_port *dp,
const struct switchdev_obj_port_mdb *mdb)
{
struct dsa_notifier_mdb_info info = {
@@ -210,7 +252,10 @@ int dsa_port_vlan_add(struct dsa_port *dp,
.vlan = vlan,
};
- return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info);
+ if (br_vlan_enabled(dp->bridge_dev))
+ return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info);
+
+ return 0;
}
int dsa_port_vlan_del(struct dsa_port *dp,
@@ -222,5 +267,53 @@ int dsa_port_vlan_del(struct dsa_port *dp,
.vlan = vlan,
};
- return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info);
+ if (br_vlan_enabled(dp->bridge_dev))
+ return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info);
+
+ return 0;
+}
+
+int dsa_port_fixed_link_register_of(struct dsa_port *dp)
+{
+ struct device_node *dn = dp->dn;
+ struct dsa_switch *ds = dp->ds;
+ struct phy_device *phydev;
+ int port = dp->index;
+ int mode;
+ int err;
+
+ if (of_phy_is_fixed_link(dn)) {
+ err = of_phy_register_fixed_link(dn);
+ if (err) {
+ dev_err(ds->dev,
+ "failed to register the fixed PHY of port %d\n",
+ port);
+ return err;
+ }
+
+ phydev = of_phy_find_device(dn);
+
+ mode = of_get_phy_mode(dn);
+ if (mode < 0)
+ mode = PHY_INTERFACE_MODE_NA;
+ phydev->interface = mode;
+
+ genphy_config_init(phydev);
+ genphy_read_status(phydev);
+
+ if (ds->ops->adjust_link)
+ ds->ops->adjust_link(ds, port, phydev);
+
+ put_device(&phydev->mdio.dev);
+ }
+
+ return 0;
+}
+
+void dsa_port_fixed_link_unregister_of(struct dsa_port *dp)
+{
+ struct device_node *dn = dp->dn;
+
+ if (of_phy_is_fixed_link(dn))
+ of_phy_deregister_fixed_link(dn);
}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 865e29e62bad..d6e7a642493b 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -55,7 +55,7 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds)
ds->slave_mii_bus->read = dsa_slave_phy_read;
ds->slave_mii_bus->write = dsa_slave_phy_write;
snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d",
- ds->dst->tree, ds->index);
+ ds->dst->index, ds->index);
ds->slave_mii_bus->parent = ds->dev;
ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask;
}
@@ -64,18 +64,13 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds)
/* slave device handling ****************************************************/
static int dsa_slave_get_iflink(const struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
-
- return dsa_master_netdev(p)->ifindex;
+ return dsa_slave_to_master(dev)->ifindex;
}
static int dsa_slave_open(struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_port *dp = p->dp;
- struct dsa_switch *ds = dp->ds;
- struct net_device *master = dsa_master_netdev(p);
- u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING;
+ struct net_device *master = dsa_slave_to_master(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
int err;
if (!(master->flags & IFF_UP))
@@ -98,16 +93,12 @@ static int dsa_slave_open(struct net_device *dev)
goto clear_allmulti;
}
- if (ds->ops->port_enable) {
- err = ds->ops->port_enable(ds, p->dp->index, p->phy);
- if (err)
- goto clear_promisc;
- }
-
- dsa_port_set_state_now(p->dp, stp_state);
+ err = dsa_port_enable(dp, dev->phydev);
+ if (err)
+ goto clear_promisc;
- if (p->phy)
- phy_start(p->phy);
+ if (dev->phydev)
+ phy_start(dev->phydev);
return 0;
@@ -126,12 +117,13 @@ out:
static int dsa_slave_close(struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct net_device *master = dsa_master_netdev(p);
- struct dsa_switch *ds = p->dp->ds;
+ struct net_device *master = dsa_slave_to_master(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+
+ if (dev->phydev)
+ phy_stop(dev->phydev);
- if (p->phy)
- phy_stop(p->phy);
+ dsa_port_disable(dp, dev->phydev);
dev_mc_unsync(master, dev);
dev_uc_unsync(master, dev);
@@ -143,18 +135,12 @@ static int dsa_slave_close(struct net_device *dev)
if (!ether_addr_equal(dev->dev_addr, master->dev_addr))
dev_uc_del(master, dev->dev_addr);
- if (ds->ops->port_disable)
- ds->ops->port_disable(ds, p->dp->index, p->phy);
-
- dsa_port_set_state_now(p->dp, BR_STATE_DISABLED);
-
return 0;
}
static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct net_device *master = dsa_master_netdev(p);
+ struct net_device *master = dsa_slave_to_master(dev);
if (change & IFF_ALLMULTI)
dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1);
@@ -164,8 +150,7 @@ static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
static void dsa_slave_set_rx_mode(struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct net_device *master = dsa_master_netdev(p);
+ struct net_device *master = dsa_slave_to_master(dev);
dev_mc_sync(master, dev);
dev_uc_sync(master, dev);
@@ -173,8 +158,7 @@ static void dsa_slave_set_rx_mode(struct net_device *dev)
static int dsa_slave_set_mac_address(struct net_device *dev, void *a)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct net_device *master = dsa_master_netdev(p);
+ struct net_device *master = dsa_slave_to_master(dev);
struct sockaddr *addr = a;
int err;
@@ -255,43 +239,34 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
struct net_device *dev, struct net_device *filter_dev,
int *idx)
{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
struct dsa_slave_dump_ctx dump = {
.dev = dev,
.skb = skb,
.cb = cb,
.idx = *idx,
};
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_port *dp = p->dp;
- struct dsa_switch *ds = dp->ds;
int err;
- if (!ds->ops->port_fdb_dump)
- return -EOPNOTSUPP;
-
- err = ds->ops->port_fdb_dump(ds, dp->index,
- dsa_slave_port_fdb_do_dump,
- &dump);
+ err = dsa_port_fdb_dump(dp, dsa_slave_port_fdb_do_dump, &dump);
*idx = dump.idx;
+
return err;
}
static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
-
- if (p->phy != NULL)
- return phy_mii_ioctl(p->phy, ifr, cmd);
+ if (!dev->phydev)
+ return -ENODEV;
- return -EOPNOTSUPP;
+ return phy_mii_ioctl(dev->phydev, ifr, cmd);
}
static int dsa_slave_port_attr_set(struct net_device *dev,
const struct switchdev_attr *attr,
struct switchdev_trans *trans)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_port *dp = p->dp;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
int ret;
switch (attr->id) {
@@ -317,8 +292,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev,
const struct switchdev_obj *obj,
struct switchdev_trans *trans)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_port *dp = p->dp;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
int err;
/* For the prepare phase, ensure the full set of changes is feasable in
@@ -330,6 +304,13 @@ static int dsa_slave_port_obj_add(struct net_device *dev,
case SWITCHDEV_OBJ_ID_PORT_MDB:
err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj), trans);
break;
+ case SWITCHDEV_OBJ_ID_HOST_MDB:
+ /* DSA can directly translate this to a normal MDB add,
+ * but on the CPU port.
+ */
+ err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj),
+ trans);
+ break;
case SWITCHDEV_OBJ_ID_PORT_VLAN:
err = dsa_port_vlan_add(dp, SWITCHDEV_OBJ_PORT_VLAN(obj),
trans);
@@ -345,14 +326,19 @@ static int dsa_slave_port_obj_add(struct net_device *dev,
static int dsa_slave_port_obj_del(struct net_device *dev,
const struct switchdev_obj *obj)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_port *dp = p->dp;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
int err;
switch (obj->id) {
case SWITCHDEV_OBJ_ID_PORT_MDB:
err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj));
break;
+ case SWITCHDEV_OBJ_ID_HOST_MDB:
+ /* DSA can directly translate this to a normal MDB add,
+ * but on the CPU port.
+ */
+ err = dsa_port_mdb_del(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj));
+ break;
case SWITCHDEV_OBJ_ID_PORT_VLAN:
err = dsa_port_vlan_del(dp, SWITCHDEV_OBJ_PORT_VLAN(obj));
break;
@@ -367,13 +353,14 @@ static int dsa_slave_port_obj_del(struct net_device *dev,
static int dsa_slave_port_attr_get(struct net_device *dev,
struct switchdev_attr *attr)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
+ struct dsa_switch_tree *dst = ds->dst;
switch (attr->id) {
case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
- attr->u.ppid.id_len = sizeof(ds->index);
- memcpy(&attr->u.ppid.id, &ds->index, attr->u.ppid.id_len);
+ attr->u.ppid.id_len = sizeof(dst->index);
+ memcpy(&attr->u.ppid.id, &dst->index, attr->u.ppid.id_len);
break;
case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
attr->u.brport_flags_support = 0;
@@ -385,10 +372,12 @@ static int dsa_slave_port_attr_get(struct net_device *dev,
return 0;
}
-static inline netdev_tx_t dsa_netpoll_send_skb(struct dsa_slave_priv *p,
- struct sk_buff *skb)
+static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev,
+ struct sk_buff *skb)
{
#ifdef CONFIG_NET_POLL_CONTROLLER
+ struct dsa_slave_priv *p = netdev_priv(dev);
+
if (p->netpoll)
netpoll_send_skb(p->netpoll, skb);
#else
@@ -422,43 +411,18 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
* tag to be successfully transmitted
*/
if (unlikely(netpoll_tx_running(dev)))
- return dsa_netpoll_send_skb(p, nskb);
+ return dsa_slave_netpoll_send_skb(dev, nskb);
/* Queue the SKB for transmission on the parent interface, but
* do not modify its EtherType
*/
- nskb->dev = dsa_master_netdev(p);
+ nskb->dev = dsa_slave_to_master(dev);
dev_queue_xmit(nskb);
return NETDEV_TX_OK;
}
/* ethtool operations *******************************************************/
-static int
-dsa_slave_get_link_ksettings(struct net_device *dev,
- struct ethtool_link_ksettings *cmd)
-{
- struct dsa_slave_priv *p = netdev_priv(dev);
-
- if (!p->phy)
- return -EOPNOTSUPP;
-
- phy_ethtool_ksettings_get(p->phy, cmd);
-
- return 0;
-}
-
-static int
-dsa_slave_set_link_ksettings(struct net_device *dev,
- const struct ethtool_link_ksettings *cmd)
-{
- struct dsa_slave_priv *p = netdev_priv(dev);
-
- if (p->phy != NULL)
- return phy_ethtool_ksettings_set(p->phy, cmd);
-
- return -EOPNOTSUPP;
-}
static void dsa_slave_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *drvinfo)
@@ -470,11 +434,11 @@ static void dsa_slave_get_drvinfo(struct net_device *dev,
static int dsa_slave_get_regs_len(struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
if (ds->ops->get_regs_len)
- return ds->ops->get_regs_len(ds, p->dp->index);
+ return ds->ops->get_regs_len(ds, dp->index);
return -EOPNOTSUPP;
}
@@ -482,39 +446,27 @@ static int dsa_slave_get_regs_len(struct net_device *dev)
static void
dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
if (ds->ops->get_regs)
- ds->ops->get_regs(ds, p->dp->index, regs, _p);
-}
-
-static int dsa_slave_nway_reset(struct net_device *dev)
-{
- struct dsa_slave_priv *p = netdev_priv(dev);
-
- if (p->phy != NULL)
- return genphy_restart_aneg(p->phy);
-
- return -EOPNOTSUPP;
+ ds->ops->get_regs(ds, dp->index, regs, _p);
}
static u32 dsa_slave_get_link(struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ if (!dev->phydev)
+ return -ENODEV;
- if (p->phy != NULL) {
- genphy_update_link(p->phy);
- return p->phy->link;
- }
+ genphy_update_link(dev->phydev);
- return -EOPNOTSUPP;
+ return dev->phydev->link;
}
static int dsa_slave_get_eeprom_len(struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
if (ds->cd && ds->cd->eeprom_len)
return ds->cd->eeprom_len;
@@ -528,8 +480,8 @@ static int dsa_slave_get_eeprom_len(struct net_device *dev)
static int dsa_slave_get_eeprom(struct net_device *dev,
struct ethtool_eeprom *eeprom, u8 *data)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
if (ds->ops->get_eeprom)
return ds->ops->get_eeprom(ds, eeprom, data);
@@ -540,8 +492,8 @@ static int dsa_slave_get_eeprom(struct net_device *dev,
static int dsa_slave_set_eeprom(struct net_device *dev,
struct ethtool_eeprom *eeprom, u8 *data)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
if (ds->ops->set_eeprom)
return ds->ops->set_eeprom(ds, eeprom, data);
@@ -552,8 +504,8 @@ static int dsa_slave_set_eeprom(struct net_device *dev,
static void dsa_slave_get_strings(struct net_device *dev,
uint32_t stringset, uint8_t *data)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
if (stringset == ETH_SS_STATS) {
int len = ETH_GSTRING_LEN;
@@ -563,80 +515,7 @@ static void dsa_slave_get_strings(struct net_device *dev,
strncpy(data + 2 * len, "rx_packets", len);
strncpy(data + 3 * len, "rx_bytes", len);
if (ds->ops->get_strings)
- ds->ops->get_strings(ds, p->dp->index, data + 4 * len);
- }
-}
-
-static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev,
- struct ethtool_stats *stats,
- uint64_t *data)
-{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
- struct dsa_switch *ds = cpu_dp->ds;
- s8 cpu_port = cpu_dp->index;
- int count = 0;
-
- if (cpu_dp->ethtool_ops.get_sset_count) {
- count = cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS);
- cpu_dp->ethtool_ops.get_ethtool_stats(dev, stats, data);
- }
-
- if (ds->ops->get_ethtool_stats)
- ds->ops->get_ethtool_stats(ds, cpu_port, data + count);
-}
-
-static int dsa_cpu_port_get_sset_count(struct net_device *dev, int sset)
-{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
- struct dsa_switch *ds = cpu_dp->ds;
- int count = 0;
-
- if (cpu_dp->ethtool_ops.get_sset_count)
- count += cpu_dp->ethtool_ops.get_sset_count(dev, sset);
-
- if (sset == ETH_SS_STATS && ds->ops->get_sset_count)
- count += ds->ops->get_sset_count(ds);
-
- return count;
-}
-
-static void dsa_cpu_port_get_strings(struct net_device *dev,
- uint32_t stringset, uint8_t *data)
-{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
- struct dsa_switch *ds = cpu_dp->ds;
- s8 cpu_port = cpu_dp->index;
- int len = ETH_GSTRING_LEN;
- int mcount = 0, count;
- unsigned int i;
- uint8_t pfx[4];
- uint8_t *ndata;
-
- snprintf(pfx, sizeof(pfx), "p%.2d", cpu_port);
- /* We do not want to be NULL-terminated, since this is a prefix */
- pfx[sizeof(pfx) - 1] = '_';
-
- if (cpu_dp->ethtool_ops.get_sset_count) {
- mcount = cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS);
- cpu_dp->ethtool_ops.get_strings(dev, stringset, data);
- }
-
- if (stringset == ETH_SS_STATS && ds->ops->get_strings) {
- ndata = data + mcount * len;
- /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle
- * the output after to prepend our CPU port prefix we
- * constructed earlier
- */
- ds->ops->get_strings(ds, cpu_port, ndata);
- count = ds->ops->get_sset_count(ds);
- for (i = 0; i < count; i++) {
- memmove(ndata + (i * len + sizeof(pfx)),
- ndata + i * len, len - sizeof(pfx));
- memcpy(ndata + i * len, pfx, sizeof(pfx));
- }
+ ds->ops->get_strings(ds, dp->index, data + 4 * len);
}
}
@@ -644,8 +523,9 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats,
uint64_t *data)
{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_switch *ds = dp->ds;
struct pcpu_sw_netstats *s;
unsigned int start;
int i;
@@ -667,13 +547,13 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev,
data[3] += rx_bytes;
}
if (ds->ops->get_ethtool_stats)
- ds->ops->get_ethtool_stats(ds, p->dp->index, data + 4);
+ ds->ops->get_ethtool_stats(ds, dp->index, data + 4);
}
static int dsa_slave_get_sset_count(struct net_device *dev, int sset)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
if (sset == ETH_SS_STATS) {
int count;
@@ -690,77 +570,77 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset)
static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
if (ds->ops->get_wol)
- ds->ops->get_wol(ds, p->dp->index, w);
+ ds->ops->get_wol(ds, dp->index, w);
}
static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
int ret = -EOPNOTSUPP;
if (ds->ops->set_wol)
- ret = ds->ops->set_wol(ds, p->dp->index, w);
+ ret = ds->ops->set_wol(ds, dp->index, w);
return ret;
}
static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
int ret;
/* Port's PHY and MAC both need to be EEE capable */
- if (!p->phy)
+ if (!dev->phydev)
return -ENODEV;
if (!ds->ops->set_mac_eee)
return -EOPNOTSUPP;
- ret = ds->ops->set_mac_eee(ds, p->dp->index, e);
+ ret = ds->ops->set_mac_eee(ds, dp->index, e);
if (ret)
return ret;
if (e->eee_enabled) {
- ret = phy_init_eee(p->phy, 0);
+ ret = phy_init_eee(dev->phydev, 0);
if (ret)
return ret;
}
- return phy_ethtool_set_eee(p->phy, e);
+ return phy_ethtool_set_eee(dev->phydev, e);
}
static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
int ret;
/* Port's PHY and MAC both need to be EEE capable */
- if (!p->phy)
+ if (!dev->phydev)
return -ENODEV;
if (!ds->ops->get_mac_eee)
return -EOPNOTSUPP;
- ret = ds->ops->get_mac_eee(ds, p->dp->index, e);
+ ret = ds->ops->get_mac_eee(ds, dp->index, e);
if (ret)
return ret;
- return phy_ethtool_get_eee(p->phy, e);
+ return phy_ethtool_get_eee(dev->phydev, e);
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static int dsa_slave_netpoll_setup(struct net_device *dev,
struct netpoll_info *ni)
{
+ struct net_device *master = dsa_slave_to_master(dev);
struct dsa_slave_priv *p = netdev_priv(dev);
- struct net_device *master = dsa_master_netdev(p);
struct netpoll *netpoll;
int err = 0;
@@ -800,18 +680,18 @@ static void dsa_slave_poll_controller(struct net_device *dev)
static int dsa_slave_get_phys_port_name(struct net_device *dev,
char *name, size_t len)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
- if (snprintf(name, len, "p%d", p->dp->index) >= len)
+ if (snprintf(name, len, "p%d", dp->index) >= len)
return -EINVAL;
return 0;
}
static struct dsa_mall_tc_entry *
-dsa_slave_mall_tc_entry_find(struct dsa_slave_priv *p,
- unsigned long cookie)
+dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie)
{
+ struct dsa_slave_priv *p = netdev_priv(dev);
struct dsa_mall_tc_entry *mall_tc_entry;
list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list)
@@ -825,14 +705,15 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev,
struct tc_cls_matchall_offload *cls,
bool ingress)
{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
struct dsa_slave_priv *p = netdev_priv(dev);
struct dsa_mall_tc_entry *mall_tc_entry;
__be16 protocol = cls->common.protocol;
- struct dsa_switch *ds = p->dp->ds;
struct net *net = dev_net(dev);
- struct dsa_slave_priv *to_p;
+ struct dsa_switch *ds = dp->ds;
struct net_device *to_dev;
const struct tc_action *a;
+ struct dsa_port *to_dp;
int err = -EOPNOTSUPP;
LIST_HEAD(actions);
int ifindex;
@@ -865,13 +746,12 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev,
mall_tc_entry->type = DSA_PORT_MALL_MIRROR;
mirror = &mall_tc_entry->mirror;
- to_p = netdev_priv(to_dev);
+ to_dp = dsa_slave_to_port(to_dev);
- mirror->to_local_port = to_p->dp->index;
+ mirror->to_local_port = to_dp->index;
mirror->ingress = ingress;
- err = ds->ops->port_mirror_add(ds, p->dp->index, mirror,
- ingress);
+ err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress);
if (err) {
kfree(mall_tc_entry);
return err;
@@ -886,14 +766,14 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev,
static void dsa_slave_del_cls_matchall(struct net_device *dev,
struct tc_cls_matchall_offload *cls)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
struct dsa_mall_tc_entry *mall_tc_entry;
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_switch *ds = dp->ds;
if (!ds->ops->port_mirror_del)
return;
- mall_tc_entry = dsa_slave_mall_tc_entry_find(p, cls->cookie);
+ mall_tc_entry = dsa_slave_mall_tc_entry_find(dev, cls->cookie);
if (!mall_tc_entry)
return;
@@ -901,8 +781,7 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev,
switch (mall_tc_entry->type) {
case DSA_PORT_MALL_MIRROR:
- ds->ops->port_mirror_del(ds, p->dp->index,
- &mall_tc_entry->mirror);
+ ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror);
break;
default:
WARN_ON(1);
@@ -912,17 +791,9 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev,
}
static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev,
- struct tc_cls_matchall_offload *cls)
+ struct tc_cls_matchall_offload *cls,
+ bool ingress)
{
- bool ingress;
-
- if (is_classid_clsact_ingress(cls->common.classid))
- ingress = true;
- else if (is_classid_clsact_egress(cls->common.classid))
- ingress = false;
- else
- return -EOPNOTSUPP;
-
if (cls->common.chain_index)
return -EOPNOTSUPP;
@@ -937,12 +808,63 @@ static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev,
}
}
+static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+ void *cb_priv, bool ingress)
+{
+ struct net_device *dev = cb_priv;
+
+ if (!tc_can_offload(dev))
+ return -EOPNOTSUPP;
+
+ switch (type) {
+ case TC_SETUP_CLSMATCHALL:
+ return dsa_slave_setup_tc_cls_matchall(dev, type_data, ingress);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static int dsa_slave_setup_tc_block_cb_ig(enum tc_setup_type type,
+ void *type_data, void *cb_priv)
+{
+ return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, true);
+}
+
+static int dsa_slave_setup_tc_block_cb_eg(enum tc_setup_type type,
+ void *type_data, void *cb_priv)
+{
+ return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, false);
+}
+
+static int dsa_slave_setup_tc_block(struct net_device *dev,
+ struct tc_block_offload *f)
+{
+ tc_setup_cb_t *cb;
+
+ if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+ cb = dsa_slave_setup_tc_block_cb_ig;
+ else if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+ cb = dsa_slave_setup_tc_block_cb_eg;
+ else
+ return -EOPNOTSUPP;
+
+ switch (f->command) {
+ case TC_BLOCK_BIND:
+ return tcf_block_cb_register(f->block, cb, dev, dev);
+ case TC_BLOCK_UNBIND:
+ tcf_block_cb_unregister(f->block, cb, dev);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
switch (type) {
- case TC_SETUP_CLSMATCHALL:
- return dsa_slave_setup_tc_cls_matchall(dev, type_data);
+ case TC_SETUP_BLOCK:
+ return dsa_slave_setup_tc_block(dev, type_data);
default:
return -EOPNOTSUPP;
}
@@ -976,42 +898,35 @@ static void dsa_slave_get_stats64(struct net_device *dev,
}
}
-void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops)
-{
- ops->get_sset_count = dsa_cpu_port_get_sset_count;
- ops->get_ethtool_stats = dsa_cpu_port_get_ethtool_stats;
- ops->get_strings = dsa_cpu_port_get_strings;
-}
-
static int dsa_slave_get_rxnfc(struct net_device *dev,
struct ethtool_rxnfc *nfc, u32 *rule_locs)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
if (!ds->ops->get_rxnfc)
return -EOPNOTSUPP;
- return ds->ops->get_rxnfc(ds, p->dp->index, nfc, rule_locs);
+ return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs);
}
static int dsa_slave_set_rxnfc(struct net_device *dev,
struct ethtool_rxnfc *nfc)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
if (!ds->ops->set_rxnfc)
return -EOPNOTSUPP;
- return ds->ops->set_rxnfc(ds, p->dp->index, nfc);
+ return ds->ops->set_rxnfc(ds, dp->index, nfc);
}
static const struct ethtool_ops dsa_slave_ethtool_ops = {
.get_drvinfo = dsa_slave_get_drvinfo,
.get_regs_len = dsa_slave_get_regs_len,
.get_regs = dsa_slave_get_regs,
- .nway_reset = dsa_slave_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = dsa_slave_get_link,
.get_eeprom_len = dsa_slave_get_eeprom_len,
.get_eeprom = dsa_slave_get_eeprom,
@@ -1023,8 +938,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
.get_wol = dsa_slave_get_wol,
.set_eee = dsa_slave_set_eee,
.get_eee = dsa_slave_get_eee,
- .get_link_ksettings = dsa_slave_get_link_ksettings,
- .set_link_ksettings = dsa_slave_set_link_ksettings,
+ .get_link_ksettings = phy_ethtool_get_link_ksettings,
+ .set_link_ksettings = phy_ethtool_set_link_ksettings,
.get_rxnfc = dsa_slave_get_rxnfc,
.set_rxnfc = dsa_slave_set_rxnfc,
};
@@ -1064,78 +979,81 @@ static struct device_type dsa_type = {
static void dsa_slave_adjust_link(struct net_device *dev)
{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_switch *ds = dp->ds;
unsigned int status_changed = 0;
- if (p->old_link != p->phy->link) {
+ if (p->old_link != dev->phydev->link) {
status_changed = 1;
- p->old_link = p->phy->link;
+ p->old_link = dev->phydev->link;
}
- if (p->old_duplex != p->phy->duplex) {
+ if (p->old_duplex != dev->phydev->duplex) {
status_changed = 1;
- p->old_duplex = p->phy->duplex;
+ p->old_duplex = dev->phydev->duplex;
}
- if (p->old_pause != p->phy->pause) {
+ if (p->old_pause != dev->phydev->pause) {
status_changed = 1;
- p->old_pause = p->phy->pause;
+ p->old_pause = dev->phydev->pause;
}
if (ds->ops->adjust_link && status_changed)
- ds->ops->adjust_link(ds, p->dp->index, p->phy);
+ ds->ops->adjust_link(ds, dp->index, dev->phydev);
if (status_changed)
- phy_print_status(p->phy);
+ phy_print_status(dev->phydev);
}
static int dsa_slave_fixed_link_update(struct net_device *dev,
struct fixed_phy_status *status)
{
- struct dsa_slave_priv *p;
struct dsa_switch *ds;
+ struct dsa_port *dp;
if (dev) {
- p = netdev_priv(dev);
- ds = p->dp->ds;
+ dp = dsa_slave_to_port(dev);
+ ds = dp->ds;
if (ds->ops->fixed_link_update)
- ds->ops->fixed_link_update(ds, p->dp->index, status);
+ ds->ops->fixed_link_update(ds, dp->index, status);
}
return 0;
}
/* slave device setup *******************************************************/
-static int dsa_slave_phy_connect(struct dsa_slave_priv *p,
- struct net_device *slave_dev,
- int addr)
+static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr)
{
- struct dsa_switch *ds = p->dp->ds;
+ struct dsa_port *dp = dsa_slave_to_port(slave_dev);
+ struct dsa_slave_priv *p = netdev_priv(slave_dev);
+ struct dsa_switch *ds = dp->ds;
- p->phy = mdiobus_get_phy(ds->slave_mii_bus, addr);
- if (!p->phy) {
+ slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr);
+ if (!slave_dev->phydev) {
netdev_err(slave_dev, "no phy at %d\n", addr);
return -ENODEV;
}
/* Use already configured phy mode */
if (p->phy_interface == PHY_INTERFACE_MODE_NA)
- p->phy_interface = p->phy->interface;
- return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
- p->phy_interface);
+ p->phy_interface = slave_dev->phydev->interface;
+
+ return phy_connect_direct(slave_dev, slave_dev->phydev,
+ dsa_slave_adjust_link, p->phy_interface);
}
-static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
- struct net_device *slave_dev)
+static int dsa_slave_phy_setup(struct net_device *slave_dev)
{
- struct dsa_switch *ds = p->dp->ds;
- struct device_node *phy_dn, *port_dn;
+ struct dsa_port *dp = dsa_slave_to_port(slave_dev);
+ struct dsa_slave_priv *p = netdev_priv(slave_dev);
+ struct device_node *port_dn = dp->dn;
+ struct dsa_switch *ds = dp->ds;
+ struct device_node *phy_dn;
bool phy_is_fixed = false;
u32 phy_flags = 0;
int mode, ret;
- port_dn = p->dp->dn;
mode = of_get_phy_mode(port_dn);
if (mode < 0)
mode = PHY_INTERFACE_MODE_NA;
@@ -1156,52 +1074,35 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
}
if (ds->ops->get_phy_flags)
- phy_flags = ds->ops->get_phy_flags(ds, p->dp->index);
+ phy_flags = ds->ops->get_phy_flags(ds, dp->index);
if (phy_dn) {
- int phy_id = of_mdio_parse_addr(&slave_dev->dev, phy_dn);
-
- /* If this PHY address is part of phys_mii_mask, which means
- * that we need to divert reads and writes to/from it, then we
- * want to bind this device using the slave MII bus created by
- * DSA to make that happen.
- */
- if (!phy_is_fixed && phy_id >= 0 &&
- (ds->phys_mii_mask & (1 << phy_id))) {
- ret = dsa_slave_phy_connect(p, slave_dev, phy_id);
- if (ret) {
- netdev_err(slave_dev, "failed to connect to phy%d: %d\n", phy_id, ret);
- of_node_put(phy_dn);
- return ret;
- }
- } else {
- p->phy = of_phy_connect(slave_dev, phy_dn,
- dsa_slave_adjust_link,
- phy_flags,
- p->phy_interface);
- }
-
+ slave_dev->phydev = of_phy_connect(slave_dev, phy_dn,
+ dsa_slave_adjust_link,
+ phy_flags,
+ p->phy_interface);
of_node_put(phy_dn);
}
- if (p->phy && phy_is_fixed)
- fixed_phy_set_link_update(p->phy, dsa_slave_fixed_link_update);
+ if (slave_dev->phydev && phy_is_fixed)
+ fixed_phy_set_link_update(slave_dev->phydev,
+ dsa_slave_fixed_link_update);
/* We could not connect to a designated PHY, so use the switch internal
* MDIO bus instead
*/
- if (!p->phy) {
- ret = dsa_slave_phy_connect(p, slave_dev, p->dp->index);
+ if (!slave_dev->phydev) {
+ ret = dsa_slave_phy_connect(slave_dev, dp->index);
if (ret) {
netdev_err(slave_dev, "failed to connect to port %d: %d\n",
- p->dp->index, ret);
+ dp->index, ret);
if (phy_is_fixed)
of_phy_deregister_fixed_link(port_dn);
return ret;
}
}
- phy_attached_info(p->phy);
+ phy_attached_info(slave_dev->phydev);
return 0;
}
@@ -1221,12 +1122,12 @@ int dsa_slave_suspend(struct net_device *slave_dev)
netif_device_detach(slave_dev);
- if (p->phy) {
- phy_stop(p->phy);
+ if (slave_dev->phydev) {
+ phy_stop(slave_dev->phydev);
p->old_pause = -1;
p->old_link = -1;
p->old_duplex = -1;
- phy_suspend(p->phy);
+ phy_suspend(slave_dev->phydev);
}
return 0;
@@ -1234,31 +1135,40 @@ int dsa_slave_suspend(struct net_device *slave_dev)
int dsa_slave_resume(struct net_device *slave_dev)
{
- struct dsa_slave_priv *p = netdev_priv(slave_dev);
-
netif_device_attach(slave_dev);
- if (p->phy) {
- phy_resume(p->phy);
- phy_start(p->phy);
+ if (slave_dev->phydev) {
+ phy_resume(slave_dev->phydev);
+ phy_start(slave_dev->phydev);
}
return 0;
}
-int dsa_slave_create(struct dsa_port *port, const char *name)
+static void dsa_slave_notify(struct net_device *dev, unsigned long val)
+{
+ struct net_device *master = dsa_slave_to_master(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_notifier_register_info rinfo = {
+ .switch_number = dp->ds->index,
+ .port_number = dp->index,
+ .master = master,
+ .info.dev = dev,
+ };
+
+ call_dsa_notifiers(val, dev, &rinfo.info);
+}
+
+int dsa_slave_create(struct dsa_port *port)
{
+ const struct dsa_port *cpu_dp = port->cpu_dp;
+ struct net_device *master = cpu_dp->master;
struct dsa_switch *ds = port->ds;
- struct dsa_switch_tree *dst = ds->dst;
- struct net_device *master;
+ const char *name = port->name;
struct net_device *slave_dev;
struct dsa_slave_priv *p;
- struct dsa_port *cpu_dp;
int ret;
- cpu_dp = ds->dst->cpu_dp;
- master = cpu_dp->netdev;
-
if (!ds->num_tx_queues)
ds->num_tx_queues = 1;
@@ -1294,22 +1204,24 @@ int dsa_slave_create(struct dsa_port *port, const char *name)
}
p->dp = port;
INIT_LIST_HEAD(&p->mall_tc_list);
- p->xmit = dst->tag_ops->xmit;
+ p->xmit = cpu_dp->tag_ops->xmit;
p->old_pause = -1;
p->old_link = -1;
p->old_duplex = -1;
- port->netdev = slave_dev;
+ port->slave = slave_dev;
netif_carrier_off(slave_dev);
- ret = dsa_slave_phy_setup(p, slave_dev);
+ ret = dsa_slave_phy_setup(slave_dev);
if (ret) {
netdev_err(master, "error %d setting up slave phy\n", ret);
goto out_free;
}
+ dsa_slave_notify(slave_dev, DSA_PORT_REGISTER);
+
ret = register_netdev(slave_dev);
if (ret) {
netdev_err(master, "error %d registering interface %s\n",
@@ -1320,30 +1232,30 @@ int dsa_slave_create(struct dsa_port *port, const char *name)
return 0;
out_phy:
- phy_disconnect(p->phy);
- if (of_phy_is_fixed_link(p->dp->dn))
- of_phy_deregister_fixed_link(p->dp->dn);
+ phy_disconnect(slave_dev->phydev);
+ if (of_phy_is_fixed_link(port->dn))
+ of_phy_deregister_fixed_link(port->dn);
out_free:
free_percpu(p->stats64);
free_netdev(slave_dev);
- port->netdev = NULL;
+ port->slave = NULL;
return ret;
}
void dsa_slave_destroy(struct net_device *slave_dev)
{
+ struct dsa_port *dp = dsa_slave_to_port(slave_dev);
struct dsa_slave_priv *p = netdev_priv(slave_dev);
- struct device_node *port_dn;
-
- port_dn = p->dp->dn;
+ struct device_node *port_dn = dp->dn;
netif_carrier_off(slave_dev);
- if (p->phy) {
- phy_disconnect(p->phy);
+ if (slave_dev->phydev) {
+ phy_disconnect(slave_dev->phydev);
if (of_phy_is_fixed_link(port_dn))
of_phy_deregister_fixed_link(port_dn);
}
+ dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER);
unregister_netdev(slave_dev);
free_percpu(p->stats64);
free_netdev(slave_dev);
@@ -1357,8 +1269,7 @@ static bool dsa_slave_dev_check(struct net_device *dev)
static int dsa_slave_changeupper(struct net_device *dev,
struct netdev_notifier_changeupper_info *info)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
- struct dsa_port *dp = p->dp;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
int err = NOTIFY_DONE;
if (netif_is_bridge_master(info->upper_dev)) {
@@ -1379,7 +1290,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb,
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- if (dev->netdev_ops != &dsa_slave_netdev_ops)
+ if (!dsa_slave_dev_check(dev))
return NOTIFY_DONE;
if (event == NETDEV_CHANGEUPPER)
@@ -1401,14 +1312,14 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work)
container_of(work, struct dsa_switchdev_event_work, work);
struct net_device *dev = switchdev_work->dev;
struct switchdev_notifier_fdb_info *fdb_info;
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
int err;
rtnl_lock();
switch (switchdev_work->event) {
case SWITCHDEV_FDB_ADD_TO_DEVICE:
fdb_info = &switchdev_work->fdb_info;
- err = dsa_port_fdb_add(p->dp, fdb_info->addr, fdb_info->vid);
+ err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid);
if (err) {
netdev_dbg(dev, "fdb add failed err=%d\n", err);
break;
@@ -1419,7 +1330,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work)
case SWITCHDEV_FDB_DEL_TO_DEVICE:
fdb_info = &switchdev_work->fdb_info;
- err = dsa_port_fdb_del(p->dp, fdb_info->addr, fdb_info->vid);
+ err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid);
if (err) {
netdev_dbg(dev, "fdb del failed err=%d\n", err);
dev_close(dev);
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 1e2929f4290a..29608d087a7c 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -121,7 +121,7 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds,
if (ds->index == info->sw_index)
set_bit(info->port, group);
for (port = 0; port < ds->num_ports; port++)
- if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
+ if (dsa_is_dsa_port(ds, port))
set_bit(port, group);
if (switchdev_trans_ph_prepare(trans)) {
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index dbb016434ace..e6e0b7b6025c 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -59,9 +59,11 @@
#define BRCM_EG_TC_MASK 0x7
#define BRCM_EG_PID_MASK 0x1f
-static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev)
+static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb,
+ struct net_device *dev,
+ unsigned int offset)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
u16 queue = skb_get_queue_mapping(skb);
u8 *brcm_tag;
@@ -70,10 +72,10 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev
skb_push(skb, BRCM_TAG_LEN);
- memmove(skb->data, skb->data + BRCM_TAG_LEN, 2 * ETH_ALEN);
+ if (offset)
+ memmove(skb->data, skb->data + BRCM_TAG_LEN, offset);
- /* Build the tag after the MAC Source Address */
- brcm_tag = skb->data + 2 * ETH_ALEN;
+ brcm_tag = skb->data + offset;
/* Set the ingress opcode, traffic class, tag enforcment is
* deprecated
@@ -82,27 +84,30 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev
((queue & BRCM_IG_TC_MASK) << BRCM_IG_TC_SHIFT);
brcm_tag[1] = 0;
brcm_tag[2] = 0;
- if (p->dp->index == 8)
+ if (dp->index == 8)
brcm_tag[2] = BRCM_IG_DSTMAP2_MASK;
- brcm_tag[3] = (1 << p->dp->index) & BRCM_IG_DSTMAP1_MASK;
+ brcm_tag[3] = (1 << dp->index) & BRCM_IG_DSTMAP1_MASK;
+
+ /* Now tell the master network device about the desired output queue
+ * as well
+ */
+ skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(dp->index, queue));
return skb;
}
-static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt)
+static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb,
+ struct net_device *dev,
+ struct packet_type *pt,
+ unsigned int offset)
{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
- struct dsa_switch *ds = cpu_dp->ds;
int source_port;
u8 *brcm_tag;
if (unlikely(!pskb_may_pull(skb, BRCM_TAG_LEN)))
return NULL;
- /* skb->data points to the EtherType, the tag is right before it */
- brcm_tag = skb->data - 2;
+ brcm_tag = skb->data - offset;
/* The opcode should never be different than 0b000 */
if (unlikely((brcm_tag[0] >> BRCM_OPCODE_SHIFT) & BRCM_OPCODE_MASK))
@@ -117,24 +122,67 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
/* Locate which port this is coming from */
source_port = brcm_tag[3] & BRCM_EG_PID_MASK;
- /* Validate port against switch setup, either the port is totally */
- if (source_port >= ds->num_ports || !ds->ports[source_port].netdev)
+ skb->dev = dsa_master_find_slave(dev, 0, source_port);
+ if (!skb->dev)
return NULL;
/* Remove Broadcom tag and update checksum */
skb_pull_rcsum(skb, BRCM_TAG_LEN);
+ return skb;
+}
+
+#ifdef CONFIG_NET_DSA_TAG_BRCM
+static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ /* Build the tag after the MAC Source Address */
+ return brcm_tag_xmit_ll(skb, dev, 2 * ETH_ALEN);
+}
+
+
+static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt)
+{
+ struct sk_buff *nskb;
+
+ /* skb->data points to the EtherType, the tag is right before it */
+ nskb = brcm_tag_rcv_ll(skb, dev, pt, 2);
+ if (!nskb)
+ return nskb;
+
/* Move the Ethernet DA and SA */
- memmove(skb->data - ETH_HLEN,
- skb->data - ETH_HLEN - BRCM_TAG_LEN,
+ memmove(nskb->data - ETH_HLEN,
+ nskb->data - ETH_HLEN - BRCM_TAG_LEN,
2 * ETH_ALEN);
- skb->dev = ds->ports[source_port].netdev;
-
- return skb;
+ return nskb;
}
const struct dsa_device_ops brcm_netdev_ops = {
.xmit = brcm_tag_xmit,
.rcv = brcm_tag_rcv,
};
+#endif
+
+#ifdef CONFIG_NET_DSA_TAG_BRCM_PREPEND
+static struct sk_buff *brcm_tag_xmit_prepend(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ /* tag is prepended to the packet */
+ return brcm_tag_xmit_ll(skb, dev, 0);
+}
+
+static struct sk_buff *brcm_tag_rcv_prepend(struct sk_buff *skb,
+ struct net_device *dev,
+ struct packet_type *pt)
+{
+ /* tag is prepended to the packet */
+ return brcm_tag_rcv_ll(skb, dev, pt, ETH_HLEN);
+}
+
+const struct dsa_device_ops brcm_prepend_netdev_ops = {
+ .xmit = brcm_tag_xmit_prepend,
+ .rcv = brcm_tag_rcv_prepend,
+};
+#endif
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index fbf9ca954773..cd13cfc542ce 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -18,7 +18,7 @@
static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
u8 *dsa_header;
/*
@@ -34,8 +34,8 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
* Construct tagged FROM_CPU DSA tag from 802.1q tag.
*/
dsa_header = skb->data + 2 * ETH_ALEN;
- dsa_header[0] = 0x60 | p->dp->ds->index;
- dsa_header[1] = p->dp->index << 3;
+ dsa_header[0] = 0x60 | dp->ds->index;
+ dsa_header[1] = dp->index << 3;
/*
* Move CFI field from byte 2 to byte 1.
@@ -55,8 +55,8 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
* Construct untagged FROM_CPU DSA tag.
*/
dsa_header = skb->data + 2 * ETH_ALEN;
- dsa_header[0] = 0x40 | p->dp->ds->index;
- dsa_header[1] = p->dp->index << 3;
+ dsa_header[0] = 0x40 | dp->ds->index;
+ dsa_header[1] = dp->index << 3;
dsa_header[2] = 0x00;
dsa_header[3] = 0x00;
}
@@ -67,8 +67,6 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt)
{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_switch *ds;
u8 *dsa_header;
int source_device;
int source_port;
@@ -93,18 +91,8 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
source_device = dsa_header[0] & 0x1f;
source_port = (dsa_header[1] >> 3) & 0x1f;
- /*
- * Check that the source device exists and that the source
- * port is a registered DSA port.
- */
- if (source_device >= DSA_MAX_SWITCHES)
- return NULL;
-
- ds = dst->ds[source_device];
- if (!ds)
- return NULL;
-
- if (source_port >= ds->num_ports || !ds->ports[source_port].netdev)
+ skb->dev = dsa_master_find_slave(dev, source_device, source_port);
+ if (!skb->dev)
return NULL;
/*
@@ -153,7 +141,7 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
2 * ETH_ALEN);
}
- skb->dev = ds->ports[source_port].netdev;
+ skb->offload_fwd_mark = 1;
return skb;
}
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 76367ba1b2e2..4083326b806e 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -19,7 +19,7 @@
static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
u8 *edsa_header;
/*
@@ -43,8 +43,8 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
edsa_header[1] = ETH_P_EDSA & 0xff;
edsa_header[2] = 0x00;
edsa_header[3] = 0x00;
- edsa_header[4] = 0x60 | p->dp->ds->index;
- edsa_header[5] = p->dp->index << 3;
+ edsa_header[4] = 0x60 | dp->ds->index;
+ edsa_header[5] = dp->index << 3;
/*
* Move CFI field from byte 6 to byte 5.
@@ -68,8 +68,8 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
edsa_header[1] = ETH_P_EDSA & 0xff;
edsa_header[2] = 0x00;
edsa_header[3] = 0x00;
- edsa_header[4] = 0x40 | p->dp->ds->index;
- edsa_header[5] = p->dp->index << 3;
+ edsa_header[4] = 0x40 | dp->ds->index;
+ edsa_header[5] = dp->index << 3;
edsa_header[6] = 0x00;
edsa_header[7] = 0x00;
}
@@ -80,8 +80,6 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt)
{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_switch *ds;
u8 *edsa_header;
int source_device;
int source_port;
@@ -106,18 +104,8 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
source_device = edsa_header[0] & 0x1f;
source_port = (edsa_header[1] >> 3) & 0x1f;
- /*
- * Check that the source device exists and that the source
- * port is a registered DSA port.
- */
- if (source_device >= DSA_MAX_SWITCHES)
- return NULL;
-
- ds = dst->ds[source_device];
- if (!ds)
- return NULL;
-
- if (source_port >= ds->num_ports || !ds->ports[source_port].netdev)
+ skb->dev = dsa_master_find_slave(dev, source_device, source_port);
+ if (!skb->dev)
return NULL;
/*
@@ -172,7 +160,7 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
2 * ETH_ALEN);
}
- skb->dev = ds->ports[source_port].netdev;
+ skb->offload_fwd_mark = 1;
return skb;
}
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 010ca0a336c4..0f62effad88f 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -34,7 +34,7 @@
static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
struct sk_buff *nskb;
int padlen;
u8 *tag;
@@ -72,7 +72,7 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN);
tag[0] = 0;
- tag[1] = 1 << p->dp->index; /* destination port */
+ tag[1] = 1 << dp->index; /* destination port */
return nskb;
}
@@ -80,22 +80,19 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt)
{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
- struct dsa_switch *ds = cpu_dp->ds;
u8 *tag;
int source_port;
tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
source_port = tag[0] & 7;
- if (source_port >= ds->num_ports || !ds->ports[source_port].netdev)
+
+ skb->dev = dsa_master_find_slave(dev, 0, source_port);
+ if (!skb->dev)
return NULL;
pskb_trim_rcsum(skb, skb->len - KSZ_EGRESS_TAG_LEN);
- skb->dev = ds->ports[source_port].netdev;
-
return skb;
}
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index 0b9826105e42..548c00254c07 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -11,6 +11,7 @@
* GNU General Public License for more details.
*
*/
+#include <linux/dsa/lan9303.h>
#include <linux/etherdevice.h>
#include <linux/list.h>
#include <linux/slab.h>
@@ -39,10 +40,30 @@
*/
#define LAN9303_TAG_LEN 4
+# define LAN9303_TAG_TX_USE_ALR BIT(3)
+# define LAN9303_TAG_TX_STP_OVERRIDE BIT(4)
+# define LAN9303_TAG_RX_IGMP BIT(3)
+# define LAN9303_TAG_RX_STP BIT(4)
+# define LAN9303_TAG_RX_TRAPPED_TO_CPU (LAN9303_TAG_RX_IGMP | \
+ LAN9303_TAG_RX_STP)
+
+/* Decide whether to transmit using ALR lookup, or transmit directly to
+ * port using tag. ALR learning is performed only when using ALR lookup.
+ * If the two external ports are bridged and the frame is unicast,
+ * then use ALR lookup to allow ALR learning on CPU port.
+ * Otherwise transmit directly to port with STP state override.
+ * See also: lan9303_separate_ports() and lan9303.pdf 6.4.10.1
+ */
+static int lan9303_xmit_use_arl(struct dsa_port *dp, u8 *dest_addr)
+{
+ struct lan9303 *chip = dp->ds->priv;
+
+ return chip->is_bridged && !is_multicast_ether_addr(dest_addr);
+}
static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
u16 *lan9303_tag;
/* insert a special VLAN tag between the MAC addresses
@@ -62,26 +83,21 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev)
lan9303_tag = (u16 *)(skb->data + 2 * ETH_ALEN);
lan9303_tag[0] = htons(ETH_P_8021Q);
- lan9303_tag[1] = htons(p->dp->index | BIT(4));
+ lan9303_tag[1] = lan9303_xmit_use_arl(dp, skb->data) ?
+ LAN9303_TAG_TX_USE_ALR :
+ dp->index | LAN9303_TAG_TX_STP_OVERRIDE;
+ lan9303_tag[1] = htons(lan9303_tag[1]);
return skb;
}
static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt)
+ struct packet_type *pt)
{
u16 *lan9303_tag;
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_switch *ds;
+ u16 lan9303_tag1;
unsigned int source_port;
- ds = dst->ds[0];
-
- if (unlikely(!ds)) {
- dev_warn_ratelimited(&dev->dev, "Dropping packet, due to missing DSA switch device\n");
- return NULL;
- }
-
if (unlikely(!pskb_may_pull(skb, LAN9303_TAG_LEN))) {
dev_warn_ratelimited(&dev->dev,
"Dropping packet, cannot pull\n");
@@ -101,27 +117,22 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev,
return NULL;
}
- source_port = ntohs(lan9303_tag[1]) & 0x3;
+ lan9303_tag1 = ntohs(lan9303_tag[1]);
+ source_port = lan9303_tag1 & 0x3;
- if (source_port >= ds->num_ports) {
+ skb->dev = dsa_master_find_slave(dev, 0, source_port);
+ if (!skb->dev) {
dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n");
return NULL;
}
- if (!ds->ports[source_port].netdev) {
- dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid netdev or device\n");
- return NULL;
- }
-
/* remove the special VLAN tag between the MAC addresses
* and the current ethertype field.
*/
skb_pull_rcsum(skb, 2 + 2);
memmove(skb->data - ETH_HLEN, skb->data - (ETH_HLEN + LAN9303_TAG_LEN),
2 * ETH_ALEN);
-
- /* forward the packet to the dedicated interface */
- skb->dev = ds->ports[source_port].netdev;
+ skb->offload_fwd_mark = !(lan9303_tag1 & LAN9303_TAG_RX_TRAPPED_TO_CPU);
return skb;
}
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index ec8ee5f43255..8475434af7d5 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -23,7 +23,7 @@
static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
u8 *mtk_tag;
if (skb_cow_head(skb, MTK_HDR_LEN) < 0)
@@ -36,7 +36,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
/* Build the tag after the MAC Source Address */
mtk_tag = skb->data + 2 * ETH_ALEN;
mtk_tag[0] = 0;
- mtk_tag[1] = (1 << p->dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
+ mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
mtk_tag[2] = 0;
mtk_tag[3] = 0;
@@ -46,8 +46,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt)
{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_switch *ds;
int port;
__be16 *phdr, hdr;
@@ -68,20 +66,12 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
skb->data - ETH_HLEN - MTK_HDR_LEN,
2 * ETH_ALEN);
- /* This protocol doesn't support cascading multiple
- * switches so it's safe to assume the switch is first
- * in the tree.
- */
- ds = dst->ds[0];
- if (!ds)
- return NULL;
-
/* Get source port information */
port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK);
- if (!ds->ports[port].netdev)
- return NULL;
- skb->dev = ds->ports[port].netdev;
+ skb->dev = dsa_master_find_slave(dev, 0, port);
+ if (!skb->dev)
+ return NULL;
return skb;
}
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 1d4c70711c0f..613f4ee97771 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -38,7 +38,7 @@
static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
u16 *phdr, hdr;
dev->stats.tx_packets++;
@@ -54,8 +54,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
/* Set the version field, and set destination port information */
hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S |
- QCA_HDR_XMIT_FROM_CPU |
- BIT(p->dp->index);
+ QCA_HDR_XMIT_FROM_CPU | BIT(dp->index);
*phdr = htons(hdr);
@@ -65,9 +64,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt)
{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
- struct dsa_switch *ds;
u8 ver;
int port;
__be16 *phdr, hdr;
@@ -92,20 +88,12 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - QCA_HDR_LEN,
ETH_HLEN - QCA_HDR_LEN);
- /* This protocol doesn't support cascading multiple switches so it's
- * safe to assume the switch is first in the tree
- */
- ds = cpu_dp->ds;
- if (!ds)
- return NULL;
-
/* Get source port information */
port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK);
- if (!ds->ports[port].netdev)
- return NULL;
- /* Update skb & forward the frame accordingly */
- skb->dev = ds->ports[port].netdev;
+ skb->dev = dsa_master_find_slave(dev, 0, port);
+ if (!skb->dev)
+ return NULL;
return skb;
}
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index d2fd4923aa3e..7d20e1f3de28 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -16,7 +16,7 @@
static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
{
- struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
struct sk_buff *nskb;
int padlen;
u8 *trailer;
@@ -48,7 +48,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
trailer = skb_put(nskb, 4);
trailer[0] = 0x80;
- trailer[1] = 1 << p->dp->index;
+ trailer[1] = 1 << dp->index;
trailer[2] = 0x10;
trailer[3] = 0x00;
@@ -58,9 +58,6 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt)
{
- struct dsa_switch_tree *dst = dev->dsa_ptr;
- struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
- struct dsa_switch *ds = cpu_dp->ds;
u8 *trailer;
int source_port;
@@ -73,13 +70,13 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
return NULL;
source_port = trailer[1] & 7;
- if (source_port >= ds->num_ports || !ds->ports[source_port].netdev)
+
+ skb->dev = dsa_master_find_slave(dev, 0, source_port);
+ if (!skb->dev)
return NULL;
pskb_trim_rcsum(skb, skb->len - 4);
- skb->dev = ds->ports[source_port].netdev;
-
return skb;
}
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 172d8309f89e..b8cd43c9ed5b 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -328,12 +328,12 @@ out:
/* Announce (supervision frame) timer function
*/
-static void hsr_announce(unsigned long data)
+static void hsr_announce(struct timer_list *t)
{
struct hsr_priv *hsr;
struct hsr_port *master;
- hsr = (struct hsr_priv *) data;
+ hsr = from_timer(hsr, t, announce_timer);
rcu_read_lock();
master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
@@ -463,9 +463,8 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
hsr->sequence_nr = HSR_SEQNR_START;
hsr->sup_sequence_nr = HSR_SUP_SEQNR_START;
- setup_timer(&hsr->announce_timer, hsr_announce, (unsigned long)hsr);
-
- setup_timer(&hsr->prune_timer, hsr_prune_nodes, (unsigned long)hsr);
+ timer_setup(&hsr->announce_timer, hsr_announce, 0);
+ timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0);
ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr);
hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec;
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 284a9b820df8..286ceb41ac0c 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -365,16 +365,14 @@ static struct hsr_port *get_late_port(struct hsr_priv *hsr,
/* Remove stale sequence_nr records. Called by timer every
* HSR_LIFE_CHECK_INTERVAL (two seconds or so).
*/
-void hsr_prune_nodes(unsigned long data)
+void hsr_prune_nodes(struct timer_list *t)
{
- struct hsr_priv *hsr;
+ struct hsr_priv *hsr = from_timer(hsr, t, prune_timer);
struct hsr_node *node;
struct hsr_port *port;
unsigned long timestamp;
unsigned long time_a, time_b;
- hsr = (struct hsr_priv *) data;
-
rcu_read_lock();
list_for_each_entry_rcu(node, &hsr->node_db, mac_list) {
/* Shorthand */
diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h
index 4e04f0e868e9..370b45998121 100644
--- a/net/hsr/hsr_framereg.h
+++ b/net/hsr/hsr_framereg.h
@@ -33,7 +33,7 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port,
int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node,
u16 sequence_nr);
-void hsr_prune_nodes(unsigned long data);
+void hsr_prune_nodes(struct timer_list *t);
int hsr_create_self_node(struct list_head *self_node_db,
unsigned char addr_a[ETH_ALEN],
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index f85b08baff16..85bf86ad6b18 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -80,12 +80,13 @@ static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
fq->daddr = *arg->dst;
}
-static void lowpan_frag_expire(unsigned long data)
+static void lowpan_frag_expire(struct timer_list *t)
{
+ struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct frag_queue *fq;
struct net *net;
- fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+ fq = container_of(frag, struct frag_queue, q);
net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags);
spin_lock(&fq->q.lock);
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 6bde9e5a5503..96636e3b7aa9 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -89,7 +89,7 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info)
return genlmsg_reply(msg, info);
}
-static const struct genl_ops ieee8021154_ops[] = {
+static const struct genl_ops ieee802154_ops[] = {
/* see nl-phy.c */
IEEE802154_DUMP(IEEE802154_LIST_PHY, ieee802154_list_phy,
ieee802154_dump_phy),
@@ -137,8 +137,8 @@ struct genl_family nl802154_family __ro_after_init = {
.version = 1,
.maxattr = IEEE802154_ATTR_MAX,
.module = THIS_MODULE,
- .ops = ieee8021154_ops,
- .n_ops = ARRAY_SIZE(ieee8021154_ops),
+ .ops = ieee802154_ops,
+ .n_ops = ARRAY_SIZE(ieee802154_ops),
.mcgrps = ieee802154_mcgrps,
.n_mcgrps = ARRAY_SIZE(ieee802154_mcgrps),
};
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e31108e5ef79..ce4aa827be05 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -195,7 +195,7 @@ int inet_listen(struct socket *sock, int backlog)
{
struct sock *sk = sock->sk;
unsigned char old_state;
- int err;
+ int err, tcp_fastopen;
lock_sock(sk);
@@ -217,11 +217,12 @@ int inet_listen(struct socket *sock, int backlog)
* because the socket was in TCP_LISTEN state previously but
* was shutdown() rather than close().
*/
- if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
- (sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+ tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+ if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
+ (tcp_fastopen & TFO_SERVER_ENABLE) &&
!inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
fastopen_queue_tune(sk, backlog);
- tcp_fastopen_init_key_once(true);
+ tcp_fastopen_init_key_once(sock_net(sk));
}
err = inet_csk_listen_start(sk, backlog);
@@ -826,6 +827,7 @@ int inet_shutdown(struct socket *sock, int how)
err = -ENOTCONN;
/* Hack to wake up other listeners, who can poll for
POLLHUP, even on eg. unconnected UDP sockets -- RR */
+ /* fall through */
default:
sk->sk_shutdown |= how;
if (sk->sk_prot->shutdown)
@@ -839,7 +841,7 @@ int inet_shutdown(struct socket *sock, int how)
case TCP_LISTEN:
if (!(how & RCV_SHUTDOWN))
break;
- /* Fall through */
+ /* fall through */
case TCP_SYN_SENT:
err = sk->sk_prot->disconnect(sk, O_NONBLOCK);
sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 7c45b8896709..a8d7c5a9fb05 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1180,6 +1180,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
case SIOCSARP:
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
+ /* fall through */
case SIOCGARP:
err = copy_from_user(&r, arg, sizeof(struct arpreq));
if (err)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d7adc0616599..a4573bccd6da 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -137,22 +137,12 @@ static void inet_hash_remove(struct in_ifaddr *ifa)
*/
struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
{
- u32 hash = inet_addr_hash(net, addr);
struct net_device *result = NULL;
struct in_ifaddr *ifa;
rcu_read_lock();
- hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) {
- if (ifa->ifa_local == addr) {
- struct net_device *dev = ifa->ifa_dev->dev;
-
- if (!net_eq(dev_net(dev), net))
- continue;
- result = dev;
- break;
- }
- }
- if (!result) {
+ ifa = inet_lookup_ifaddr_rcu(net, addr);
+ if (!ifa) {
struct flowi4 fl4 = { .daddr = addr };
struct fib_result res = { 0 };
struct fib_table *local;
@@ -165,6 +155,8 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
!fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
res.type == RTN_LOCAL)
result = FIB_RES_DEV(res);
+ } else {
+ result = ifa->ifa_dev->dev;
}
if (result && devref)
dev_hold(result);
@@ -173,6 +165,20 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
}
EXPORT_SYMBOL(__ip_dev_find);
+/* called under RCU lock */
+struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr)
+{
+ u32 hash = inet_addr_hash(net, addr);
+ struct in_ifaddr *ifa;
+
+ hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash)
+ if (ifa->ifa_local == addr &&
+ net_eq(dev_net(ifa->ifa_dev->dev), net))
+ return ifa;
+
+ return NULL;
+}
+
static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
@@ -438,7 +444,7 @@ static void check_lifetime(struct work_struct *work);
static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime);
static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
- u32 portid)
+ u32 portid, struct netlink_ext_ack *extack)
{
struct in_device *in_dev = ifa->ifa_dev;
struct in_ifaddr *ifa1, **ifap, **last_primary;
@@ -483,6 +489,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
*/
ivi.ivi_addr = ifa->ifa_address;
ivi.ivi_dev = ifa->ifa_dev;
+ ivi.extack = extack;
ret = blocking_notifier_call_chain(&inetaddr_validator_chain,
NETDEV_UP, &ivi);
ret = notifier_to_errno(ret);
@@ -515,7 +522,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
static int inet_insert_ifa(struct in_ifaddr *ifa)
{
- return __inet_insert_ifa(ifa, NULL, 0);
+ return __inet_insert_ifa(ifa, NULL, 0, NULL);
}
static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
@@ -896,7 +903,8 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
return ret;
}
}
- return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid);
+ return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid,
+ extack);
} else {
inet_free_ifa(ifa);
@@ -1516,6 +1524,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
if (inetdev_valid_mtu(dev->mtu))
break;
/* disable IP when MTU is not enough */
+ /* fall through */
case NETDEV_UNREGISTER:
inetdev_destroy(in_dev);
break;
@@ -1751,7 +1760,7 @@ static int inet_validate_link_af(const struct net_device *dev,
struct nlattr *a, *tb[IFLA_INET_MAX+1];
int err, rem;
- if (dev && !__in_dev_get_rtnl(dev))
+ if (dev && !__in_dev_get_rcu(dev))
return -EAFNOSUPPORT;
err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL);
@@ -1775,7 +1784,7 @@ static int inet_validate_link_af(const struct net_device *dev,
static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla)
{
- struct in_device *in_dev = __in_dev_get_rtnl(dev);
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
struct nlattr *a, *tb[IFLA_INET_MAX+1];
int rem;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 37819ab4cc74..f52d27a422c3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -73,6 +73,11 @@ 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)
@@ -128,6 +133,11 @@ 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,
@@ -345,9 +355,6 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
if (res.type != RTN_UNICAST &&
(res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
goto e_inval;
- if (!rpf && !fib_num_tclassid_users(net) &&
- (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev)))
- goto last_resort;
fib_combine_itag(itag, &res);
dev_match = false;
@@ -402,13 +409,28 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
struct in_device *idev, u32 *itag)
{
int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
+ struct net *net = dev_net(dev);
- if (!r && !fib_num_tclassid_users(dev_net(dev)) &&
- IN_DEV_ACCEPT_LOCAL(idev) &&
+ if (!r && !fib_num_tclassid_users(net) &&
(dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
+ if (IN_DEV_ACCEPT_LOCAL(idev))
+ goto ok;
+ /* with custom local routes in place, checking local addresses
+ * only will be too optimistic, with custom rules, checking
+ * local addresses only can be too strict, e.g. due to vrf
+ */
+ if (net->ipv4.fib_has_custom_local_routes ||
+ fib4_has_custom_rules(net))
+ goto full_check;
+ if (inet_lookup_ifaddr_rcu(net, src))
+ return -EINVAL;
+
+ok:
*itag = 0;
return 0;
}
+
+full_check:
return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag);
}
@@ -759,6 +781,8 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
}
err = fib_table_insert(net, tb, &cfg, extack);
+ if (!err && cfg.fc_type == RTN_LOCAL)
+ net->ipv4.fib_has_custom_local_routes = true;
errout:
return err;
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 01ed22139ac2..f04d944f8abe 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -601,17 +601,9 @@ static void fib_rebalance(struct fib_info *fi)
atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
} endfor_nexthops(fi);
}
-
-static inline void fib_add_weight(struct fib_info *fi,
- const struct fib_nh *nh)
-{
- fi->fib_weight += nh->nh_weight;
-}
-
#else /* CONFIG_IP_ROUTE_MULTIPATH */
#define fib_rebalance(fi) do { } while (0)
-#define fib_add_weight(fi, nh) do { } while (0)
#endif /* CONFIG_IP_ROUTE_MULTIPATH */
@@ -718,7 +710,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
bool ecn_ca = false;
nla_strlcpy(tmp, nla, sizeof(tmp));
- val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
+ val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
} else {
val = nla_get_u32(nla);
}
@@ -774,8 +766,8 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
* |
* |-> {local prefix} (terminal node)
*/
-static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
- struct fib_nh *nh, struct netlink_ext_ack *extack)
+static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
+ struct netlink_ext_ack *extack)
{
int err = 0;
struct net *net;
@@ -1038,7 +1030,7 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
char tmp[TCP_CA_NAME_MAX];
nla_strlcpy(tmp, nla, sizeof(tmp));
- val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
+ val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
if (val == TCP_CA_UNSPEC)
return -EINVAL;
} else {
@@ -1258,7 +1250,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
int linkdown = 0;
change_nexthops(fi) {
- err = fib_check_nh(cfg, fi, nexthop_nh, extack);
+ err = fib_check_nh(cfg, nexthop_nh, extack);
if (err != 0)
goto failure;
if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
@@ -1275,7 +1267,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
change_nexthops(fi) {
fib_info_update_nh_saddr(net, nexthop_nh);
- fib_add_weight(fi, nexthop_nh);
} endfor_nexthops(fi)
fib_rebalance(fi);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index c636650a6a70..5ddc4aefff12 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -87,32 +87,32 @@
static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
enum fib_event_type event_type, u32 dst,
- int dst_len, struct fib_info *fi,
- u8 tos, u8 type, u32 tb_id)
+ int dst_len, struct fib_alias *fa)
{
struct fib_entry_notifier_info info = {
.dst = dst,
.dst_len = dst_len,
- .fi = fi,
- .tos = tos,
- .type = type,
- .tb_id = tb_id,
+ .fi = fa->fa_info,
+ .tos = fa->fa_tos,
+ .type = fa->fa_type,
+ .tb_id = fa->tb_id,
};
return call_fib4_notifier(nb, net, event_type, &info.info);
}
static int call_fib_entry_notifiers(struct net *net,
enum fib_event_type event_type, u32 dst,
- int dst_len, struct fib_info *fi,
- u8 tos, u8 type, u32 tb_id)
+ 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 = fi,
- .tos = tos,
- .type = type,
- .tb_id = tb_id,
+ .fi = fa->fa_info,
+ .tos = fa->fa_tos,
+ .type = fa->fa_type,
+ .tb_id = fa->tb_id,
};
return call_fib4_notifiers(net, event_type, &info.info);
}
@@ -1216,9 +1216,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
new_fa->fa_default = -1;
call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE,
- key, plen, fi,
- new_fa->fa_tos, cfg->fc_type,
- tb->tb_id);
+ key, plen, new_fa, extack);
rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
tb->tb_id, &cfg->fc_nlinfo, nlflags);
@@ -1273,8 +1271,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
tb->tb_num_default++;
rt_cache_flush(cfg->fc_nlinfo.nl_net);
- call_fib_entry_notifiers(net, event, key, plen, fi, tos, cfg->fc_type,
- tb->tb_id);
+ call_fib_entry_notifiers(net, event, key, plen, new_fa, extack);
rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id,
&cfg->fc_nlinfo, nlflags);
succeeded:
@@ -1574,8 +1571,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
return -ESRCH;
call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen,
- fa_to_delete->fa_info, tos,
- fa_to_delete->fa_type, tb->tb_id);
+ fa_to_delete, extack);
rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
&cfg->fc_nlinfo, 0);
@@ -1892,9 +1888,8 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL,
n->key,
- KEYLENGTH - fa->fa_slen,
- fi, fa->fa_tos, fa->fa_type,
- tb->tb_id);
+ KEYLENGTH - fa->fa_slen, fa,
+ NULL);
hlist_del_rcu(&fa->fa_list);
fib_release_info(fa->fa_info);
alias_free_mem_rcu(fa);
@@ -1932,8 +1927,7 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l,
continue;
call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key,
- KEYLENGTH - fa->fa_slen, fi, fa->fa_tos,
- fa->fa_type, fa->tb_id);
+ KEYLENGTH - fa->fa_slen, fa);
}
}
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 681e33998e03..1617604c9284 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -782,7 +782,7 @@ static bool icmp_tag_validation(int proto)
}
/*
- * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and
+ * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and
* ICMP_PARAMETERPROB.
*/
@@ -810,7 +810,8 @@ static bool icmp_unreach(struct sk_buff *skb)
if (iph->ihl < 5) /* Mangled header, drop. */
goto out_err;
- if (icmph->type == ICMP_DEST_UNREACH) {
+ switch (icmph->type) {
+ case ICMP_DEST_UNREACH:
switch (icmph->code & 15) {
case ICMP_NET_UNREACH:
case ICMP_HOST_UNREACH:
@@ -846,8 +847,16 @@ static bool icmp_unreach(struct sk_buff *skb)
}
if (icmph->code > NR_ICMP_UNREACH)
goto out;
- } else if (icmph->type == ICMP_PARAMETERPROB)
+ break;
+ case ICMP_PARAMETERPROB:
info = ntohl(icmph->un.gateway) >> 24;
+ break;
+ case ICMP_TIME_EXCEEDED:
+ __ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS);
+ if (icmph->code == ICMP_EXC_FRAGTIME)
+ goto out;
+ break;
+ }
/*
* Throw it at our lower layers
@@ -959,8 +968,9 @@ static bool icmp_timestamp(struct sk_buff *skb)
*/
icmp_param.data.times[1] = inet_current_timestamp();
icmp_param.data.times[2] = icmp_param.data.times[1];
- if (skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4))
- BUG();
+
+ BUG_ON(skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4));
+
icmp_param.data.icmph = *icmp_hdr(skb);
icmp_param.data.icmph.type = ICMP_TIMESTAMPREPLY;
icmp_param.data.icmph.code = 0;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b47a59cb3573..4ca46dc08e63 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -39,11 +39,11 @@ EXPORT_SYMBOL(inet_csk_timer_bug_msg);
* IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
* and 0.0.0.0 equals to 0.0.0.0 only
*/
-static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
- const struct in6_addr *sk2_rcv_saddr6,
- __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
- bool sk1_ipv6only, bool sk2_ipv6only,
- bool match_wildcard)
+static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
+ const struct in6_addr *sk2_rcv_saddr6,
+ __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
+ bool sk1_ipv6only, bool sk2_ipv6only,
+ bool match_wildcard)
{
int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
@@ -52,29 +52,29 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) {
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
- return 1;
+ return true;
if (!sk1_rcv_saddr || !sk2_rcv_saddr)
return match_wildcard;
}
- return 0;
+ return false;
}
if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
- return 1;
+ return true;
if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
!(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
- return 1;
+ return true;
if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
!(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
- return 1;
+ return true;
if (sk2_rcv_saddr6 &&
ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6))
- return 1;
+ return true;
- return 0;
+ return false;
}
#endif
@@ -82,20 +82,20 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
* match_wildcard == false: addresses must be exactly the same, i.e.
* 0.0.0.0 only equals to 0.0.0.0
*/
-static int ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
- bool sk2_ipv6only, bool match_wildcard)
+static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
+ bool sk2_ipv6only, bool match_wildcard)
{
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
- return 1;
+ return true;
if (!sk1_rcv_saddr || !sk2_rcv_saddr)
return match_wildcard;
}
- return 0;
+ return false;
}
-int inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
- bool match_wildcard)
+bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
+ bool match_wildcard)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6)
@@ -495,17 +495,15 @@ EXPORT_SYMBOL(inet_csk_accept);
* to optimize.
*/
void inet_csk_init_xmit_timers(struct sock *sk,
- void (*retransmit_handler)(unsigned long),
- void (*delack_handler)(unsigned long),
- void (*keepalive_handler)(unsigned long))
+ void (*retransmit_handler)(struct timer_list *t),
+ void (*delack_handler)(struct timer_list *t),
+ void (*keepalive_handler)(struct timer_list *t))
{
struct inet_connection_sock *icsk = inet_csk(sk);
- setup_timer(&icsk->icsk_retransmit_timer, retransmit_handler,
- (unsigned long)sk);
- setup_timer(&icsk->icsk_delack_timer, delack_handler,
- (unsigned long)sk);
- setup_timer(&sk->sk_timer, keepalive_handler, (unsigned long)sk);
+ timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0);
+ timer_setup(&icsk->icsk_delack_timer, delack_handler, 0);
+ timer_setup(&sk->sk_timer, keepalive_handler, 0);
icsk->icsk_pending = icsk->icsk_ack.pending = 0;
}
EXPORT_SYMBOL(inet_csk_init_xmit_timers);
@@ -676,9 +674,9 @@ void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req
}
EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
-static void reqsk_timer_handler(unsigned long data)
+static void reqsk_timer_handler(struct timer_list *t)
{
- struct request_sock *req = (struct request_sock *)data;
+ struct request_sock *req = from_timer(req, t, rsk_timer);
struct sock *sk_listener = req->rsk_listener;
struct net *net = sock_net(sk_listener);
struct inet_connection_sock *icsk = inet_csk(sk_listener);
@@ -749,8 +747,7 @@ static void reqsk_queue_hash_req(struct request_sock *req,
req->num_timeout = 0;
req->sk = NULL;
- setup_pinned_timer(&req->rsk_timer, reqsk_timer_handler,
- (unsigned long)req);
+ timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
mod_timer(&req->rsk_timer, jiffies + timeout);
inet_ehash_insert(req_to_sk(req), NULL);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index f9597ba26599..26a3d0315728 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -147,7 +147,7 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
spin_unlock(&hb->chain_lock);
hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
- f->frag_expire((unsigned long) fq);
+ f->frag_expire(&fq->timer);
return evicted;
}
@@ -366,7 +366,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
f->constructor(q, arg);
add_frag_mem_limit(nf, f->qsize);
- setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
+ timer_setup(&q->timer, f->frag_expire, 0);
spin_lock_init(&q->lock);
refcount_set(&q->refcnt, 1);
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 5b039159e67a..a4bab81f1462 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -142,9 +142,9 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
}
EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
-static void tw_timer_handler(unsigned long data)
+static void tw_timer_handler(struct timer_list *t)
{
- struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data;
+ struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer);
if (tw->tw_kill)
__NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
@@ -188,8 +188,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
tw->tw_prot = sk->sk_prot_creator;
atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
twsk_net_set(tw, sock_net(sk));
- setup_pinned_timer(&tw->tw_timer, tw_timer_handler,
- (unsigned long)tw);
+ timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED);
/*
* Because we use RCU lookups, we should not set tw_refcnt
* to a non null value before everything is setup for this
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index b20c8ac64081..914d56928578 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -284,14 +284,17 @@ EXPORT_SYMBOL(inet_peer_xrlim_allow);
void inetpeer_invalidate_tree(struct inet_peer_base *base)
{
- struct inet_peer *p, *n;
+ struct rb_node *p = rb_first(&base->rb_root);
- rbtree_postorder_for_each_entry_safe(p, n, &base->rb_root, rb_node) {
- inet_putpeer(p);
+ while (p) {
+ struct inet_peer *peer = rb_entry(p, struct inet_peer, rb_node);
+
+ p = rb_next(p);
+ rb_erase(&peer->rb_node, &base->rb_root);
+ inet_putpeer(peer);
cond_resched();
}
- base->rb_root = RB_ROOT;
base->total = 0;
}
EXPORT_SYMBOL(inetpeer_invalidate_tree);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index df8fe0503de0..bbf1b94942c0 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -191,12 +191,13 @@ static bool frag_expire_skip_icmp(u32 user)
/*
* Oops, a fragment queue timed out. Kill it and send an ICMP reply.
*/
-static void ip_expire(unsigned long arg)
+static void ip_expire(struct timer_list *t)
{
+ struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct ipq *qp;
struct net *net;
- qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
+ qp = container_of(frag, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
rcu_read_lock();
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 467e44d7587d..bb6239169b1a 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -579,8 +579,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
if (gre_handle_offloads(skb, false))
goto err_free_rt;
- if (skb->len > dev->mtu) {
- pskb_trim(skb, dev->mtu);
+ if (skb->len > dev->mtu + dev->hard_header_len) {
+ pskb_trim(skb, dev->mtu + dev->hard_header_len);
truncate = true;
}
@@ -731,8 +731,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
if (skb_cow_head(skb, dev->needed_headroom))
goto free_skb;
- if (skb->len - dev->hard_header_len > dev->mtu) {
- pskb_trim(skb, dev->mtu);
+ if (skb->len > dev->mtu + dev->hard_header_len) {
+ pskb_trim(skb, dev->mtu + dev->hard_header_len);
truncate = true;
}
@@ -773,20 +773,46 @@ free_skb:
return NETDEV_TX_OK;
}
+static void ipgre_link_update(struct net_device *dev, bool set_mtu)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ int len;
+
+ len = tunnel->tun_hlen;
+ tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
+ len = tunnel->tun_hlen - len;
+ tunnel->hlen = tunnel->hlen + len;
+
+ dev->needed_headroom = dev->needed_headroom + len;
+ if (set_mtu)
+ dev->mtu = max_t(int, dev->mtu - len, 68);
+
+ if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) {
+ if (!(tunnel->parms.o_flags & TUNNEL_CSUM) ||
+ tunnel->encap.type == TUNNEL_ENCAP_NONE) {
+ dev->features |= NETIF_F_GSO_SOFTWARE;
+ dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+ }
+ dev->features |= NETIF_F_LLTX;
+ }
+}
+
static int ipgre_tunnel_ioctl(struct net_device *dev,
struct ifreq *ifr, int cmd)
{
- int err;
struct ip_tunnel_parm p;
+ int err;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
return -EFAULT;
+
if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
- p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
- ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)))
+ p.iph.ihl != 5 || (p.iph.frag_off & htons(~IP_DF)) ||
+ ((p.i_flags | p.o_flags) & (GRE_VERSION | GRE_ROUTING)))
return -EINVAL;
}
+
p.i_flags = gre_flags_to_tnl_flags(p.i_flags);
p.o_flags = gre_flags_to_tnl_flags(p.o_flags);
@@ -794,11 +820,22 @@ static int ipgre_tunnel_ioctl(struct net_device *dev,
if (err)
return err;
+ if (cmd == SIOCCHGTUNNEL) {
+ struct ip_tunnel *t = netdev_priv(dev);
+
+ t->parms.i_flags = p.i_flags;
+ t->parms.o_flags = p.o_flags;
+
+ if (strcmp(dev->rtnl_link_ops->kind, "erspan"))
+ ipgre_link_update(dev, true);
+ }
+
p.i_flags = gre_tnl_flags_to_gre_flags(p.i_flags);
p.o_flags = gre_tnl_flags_to_gre_flags(p.o_flags);
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
return -EFAULT;
+
return 0;
}
@@ -1011,15 +1048,14 @@ static int __net_init ipgre_init_net(struct net *net)
return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL);
}
-static void __net_exit ipgre_exit_net(struct net *net)
+static void __net_exit ipgre_exit_batch_net(struct list_head *list_net)
{
- struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
- ip_tunnel_delete_net(itn, &ipgre_link_ops);
+ ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops);
}
static struct pernet_operations ipgre_net_ops = {
.init = ipgre_init_net,
- .exit = ipgre_exit_net,
+ .exit_batch = ipgre_exit_batch_net,
.id = &ipgre_net_id,
.size = sizeof(struct ip_tunnel_net),
};
@@ -1308,9 +1344,9 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
struct netlink_ext_ack *extack)
{
struct ip_tunnel *t = netdev_priv(dev);
- struct ip_tunnel_parm p;
struct ip_tunnel_encap ipencap;
__u32 fwmark = t->fwmark;
+ struct ip_tunnel_parm p;
int err;
if (ipgre_netlink_encap_parms(data, &ipencap)) {
@@ -1323,7 +1359,18 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
if (err < 0)
return err;
- return ip_tunnel_changelink(dev, tb, &p, fwmark);
+
+ err = ip_tunnel_changelink(dev, tb, &p, fwmark);
+ if (err < 0)
+ return err;
+
+ t->parms.i_flags = p.i_flags;
+ t->parms.o_flags = p.o_flags;
+
+ if (strcmp(dev->rtnl_link_ops->kind, "erspan"))
+ ipgre_link_update(dev, !tb[IFLA_MTU]);
+
+ return 0;
}
static size_t ipgre_get_size(const struct net_device *dev)
@@ -1542,15 +1589,14 @@ static int __net_init ipgre_tap_init_net(struct net *net)
return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0");
}
-static void __net_exit ipgre_tap_exit_net(struct net *net)
+static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net)
{
- struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
- ip_tunnel_delete_net(itn, &ipgre_tap_ops);
+ ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops);
}
static struct pernet_operations ipgre_tap_net_ops = {
.init = ipgre_tap_init_net,
- .exit = ipgre_tap_exit_net,
+ .exit_batch = ipgre_tap_exit_batch_net,
.id = &gre_tap_net_id,
.size = sizeof(struct ip_tunnel_net),
};
@@ -1561,16 +1607,14 @@ static int __net_init erspan_init_net(struct net *net)
&erspan_link_ops, "erspan0");
}
-static void __net_exit erspan_exit_net(struct net *net)
+static void __net_exit erspan_exit_batch_net(struct list_head *net_list)
{
- struct ip_tunnel_net *itn = net_generic(net, erspan_net_id);
-
- ip_tunnel_delete_net(itn, &erspan_link_ops);
+ ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops);
}
static struct pernet_operations erspan_net_ops = {
.init = erspan_init_net,
- .exit = erspan_exit_net,
+ .exit_batch = erspan_exit_batch_net,
.id = &erspan_net_id,
.size = sizeof(struct ip_tunnel_net),
};
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index e9805ad664ac..fe6fee728ce4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1061,16 +1061,22 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
}
}
-void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
+void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id,
+ struct rtnl_link_ops *ops)
{
+ struct ip_tunnel_net *itn;
+ struct net *net;
LIST_HEAD(list);
rtnl_lock();
- ip_tunnel_destroy(itn, &list, ops);
+ list_for_each_entry(net, net_list, exit_list) {
+ itn = net_generic(net, id);
+ ip_tunnel_destroy(itn, &list, ops);
+ }
unregister_netdevice_many(&list);
rtnl_unlock();
}
-EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
+EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets);
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p, __u32 fwmark)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 89453cf62158..949f432a5f04 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -198,15 +198,6 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
goto tx_error;
}
- if (tunnel->err_count > 0) {
- if (time_before(jiffies,
- tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
- tunnel->err_count--;
- dst_link_failure(skb);
- } else
- tunnel->err_count = 0;
- }
-
mtu = dst_mtu(dst);
if (skb->len > mtu) {
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
@@ -453,15 +444,14 @@ static int __net_init vti_init_net(struct net *net)
return 0;
}
-static void __net_exit vti_exit_net(struct net *net)
+static void __net_exit vti_exit_batch_net(struct list_head *list_net)
{
- struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
- ip_tunnel_delete_net(itn, &vti_link_ops);
+ ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops);
}
static struct pernet_operations vti_net_ops = {
.init = vti_init_net,
- .exit = vti_exit_net,
+ .exit_batch = vti_exit_batch_net,
.id = &vti_net_id,
.size = sizeof(struct ip_tunnel_net),
};
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index cdd627355ed1..c891235b4966 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -659,15 +659,14 @@ static int __net_init ipip_init_net(struct net *net)
return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
}
-static void __net_exit ipip_exit_net(struct net *net)
+static void __net_exit ipip_exit_batch_net(struct list_head *list_net)
{
- struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
- ip_tunnel_delete_net(itn, &ipip_link_ops);
+ ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops);
}
static struct pernet_operations ipip_net_ops = {
.init = ipip_init_net,
- .exit = ipip_exit_net,
+ .exit_batch = ipip_exit_batch_net,
.id = &ipip_net_id,
.size = sizeof(struct ip_tunnel_net),
};
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c9b3e6e069ae..40a43ad294cb 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -67,6 +67,7 @@
#include <net/fib_rules.h>
#include <linux/netconf.h>
#include <net/nexthop.h>
+#include <net/switchdev.h>
struct ipmr_rule {
struct fib_rule common;
@@ -264,6 +265,22 @@ static void __net_exit ipmr_rules_exit(struct net *net)
fib_rules_unregister(net->ipv4.mr_rules_ops);
rtnl_unlock();
}
+
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+ return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR);
+}
+
+static unsigned int ipmr_rules_seq_read(struct net *net)
+{
+ return fib_rules_seq_read(net, RTNL_FAMILY_IPMR);
+}
+
+bool ipmr_rule_default(const struct fib_rule *rule)
+{
+ return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT;
+}
+EXPORT_SYMBOL(ipmr_rule_default);
#else
#define ipmr_for_each_table(mrt, net) \
for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
@@ -298,6 +315,22 @@ static void __net_exit ipmr_rules_exit(struct net *net)
net->ipv4.mrt = NULL;
rtnl_unlock();
}
+
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+ return 0;
+}
+
+static unsigned int ipmr_rules_seq_read(struct net *net)
+{
+ return 0;
+}
+
+bool ipmr_rule_default(const struct fib_rule *rule)
+{
+ return true;
+}
+EXPORT_SYMBOL(ipmr_rule_default);
#endif
static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -587,6 +620,82 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
}
#endif
+static int call_ipmr_vif_entry_notifier(struct notifier_block *nb,
+ struct net *net,
+ enum fib_event_type event_type,
+ struct vif_device *vif,
+ vifi_t vif_index, u32 tb_id)
+{
+ struct vif_entry_notifier_info info = {
+ .info = {
+ .family = RTNL_FAMILY_IPMR,
+ .net = net,
+ },
+ .dev = vif->dev,
+ .vif_index = vif_index,
+ .vif_flags = vif->flags,
+ .tb_id = tb_id,
+ };
+
+ return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_ipmr_vif_entry_notifiers(struct net *net,
+ enum fib_event_type event_type,
+ struct vif_device *vif,
+ vifi_t vif_index, u32 tb_id)
+{
+ struct vif_entry_notifier_info info = {
+ .info = {
+ .family = RTNL_FAMILY_IPMR,
+ .net = net,
+ },
+ .dev = vif->dev,
+ .vif_index = vif_index,
+ .vif_flags = vif->flags,
+ .tb_id = tb_id,
+ };
+
+ ASSERT_RTNL();
+ net->ipv4.ipmr_seq++;
+ return call_fib_notifiers(net, event_type, &info.info);
+}
+
+static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb,
+ struct net *net,
+ enum fib_event_type event_type,
+ struct mfc_cache *mfc, u32 tb_id)
+{
+ struct mfc_entry_notifier_info info = {
+ .info = {
+ .family = RTNL_FAMILY_IPMR,
+ .net = net,
+ },
+ .mfc = mfc,
+ .tb_id = tb_id
+ };
+
+ return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_ipmr_mfc_entry_notifiers(struct net *net,
+ enum fib_event_type event_type,
+ struct mfc_cache *mfc, u32 tb_id)
+{
+ struct mfc_entry_notifier_info info = {
+ .info = {
+ .family = RTNL_FAMILY_IPMR,
+ .net = net,
+ },
+ .mfc = mfc,
+ .tb_id = tb_id
+ };
+
+ ASSERT_RTNL();
+ net->ipv4.ipmr_seq++;
+ return call_fib_notifiers(net, event_type, &info.info);
+}
+
/**
* vif_delete - Delete a VIF entry
* @notify: Set to 1, if the caller is a notifier_call
@@ -594,6 +703,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
static int vif_delete(struct mr_table *mrt, int vifi, int notify,
struct list_head *head)
{
+ struct net *net = read_pnet(&mrt->net);
struct vif_device *v;
struct net_device *dev;
struct in_device *in_dev;
@@ -603,6 +713,10 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
v = &mrt->vif_table[vifi];
+ if (VIF_EXISTS(mrt, vifi))
+ call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, vifi,
+ mrt->id);
+
write_lock_bh(&mrt_lock);
dev = v->dev;
v->dev = NULL;
@@ -652,10 +766,11 @@ static void ipmr_cache_free_rcu(struct rcu_head *head)
kmem_cache_free(mrt_cachep, c);
}
-static inline void ipmr_cache_free(struct mfc_cache *c)
+void ipmr_cache_free(struct mfc_cache *c)
{
call_rcu(&c->rcu, ipmr_cache_free_rcu);
}
+EXPORT_SYMBOL(ipmr_cache_free);
/* Destroy an unresolved cache entry, killing queued skbs
* and reporting error to netlink readers.
@@ -754,6 +869,9 @@ static int vif_add(struct net *net, struct mr_table *mrt,
struct vifctl *vifc, int mrtsock)
{
int vifi = vifc->vifc_vifi;
+ struct switchdev_attr attr = {
+ .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
+ };
struct vif_device *v = &mrt->vif_table[vifi];
struct net_device *dev;
struct in_device *in_dev;
@@ -828,6 +946,13 @@ static int vif_add(struct net *net, struct mr_table *mrt,
/* Fill in the VIF structures */
+ attr.orig_dev = dev;
+ if (!switchdev_port_attr_get(dev, &attr)) {
+ memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len);
+ v->dev_parent_id.id_len = attr.u.ppid.id_len;
+ } else {
+ v->dev_parent_id.id_len = 0;
+ }
v->rate_limit = vifc->vifc_rate_limit;
v->local = vifc->vifc_lcl_addr.s_addr;
v->remote = vifc->vifc_rmt_addr.s_addr;
@@ -851,6 +976,7 @@ static int vif_add(struct net *net, struct mr_table *mrt,
if (vifi+1 > mrt->maxvif)
mrt->maxvif = vifi+1;
write_unlock_bh(&mrt_lock);
+ call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, vifi, mrt->id);
return 0;
}
@@ -949,6 +1075,7 @@ static struct mfc_cache *ipmr_cache_alloc(void)
if (c) {
c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->mfc_un.res.minvif = MAXVIFS;
+ refcount_set(&c->mfc_un.res.refcount, 1);
}
return c;
}
@@ -1150,6 +1277,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi,
static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
{
+ struct net *net = read_pnet(&mrt->net);
struct mfc_cache *c;
/* The entries are added/deleted only under RTNL */
@@ -1161,8 +1289,9 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
return -ENOENT;
rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
list_del_rcu(&c->list);
+ call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
- ipmr_cache_free(c);
+ ipmr_cache_put(c);
return 0;
}
@@ -1189,6 +1318,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
write_unlock_bh(&mrt_lock);
+ call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c,
+ mrt->id);
mroute_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
}
@@ -1238,6 +1369,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
ipmr_cache_resolve(net, mrt, uc, c);
ipmr_cache_free(uc);
}
+ call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id);
mroute_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
}
@@ -1245,6 +1377,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
/* Close the multicast socket, and clear the vif tables etc */
static void mroute_clean_tables(struct mr_table *mrt, bool all)
{
+ struct net *net = read_pnet(&mrt->net);
struct mfc_cache *c, *tmp;
LIST_HEAD(list);
int i;
@@ -1263,8 +1396,10 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
continue;
rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
list_del_rcu(&c->list);
+ call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c,
+ mrt->id);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
- ipmr_cache_free(c);
+ ipmr_cache_put(c);
}
if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
@@ -1393,6 +1528,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
case MRT_ADD_MFC:
case MRT_DEL_MFC:
parent = -1;
+ /* fall through */
case MRT_ADD_MFC_PROXY:
case MRT_DEL_MFC_PROXY:
if (optlen != sizeof(mfc)) {
@@ -1724,10 +1860,33 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk,
return dst_output(net, sk, skb);
}
+#ifdef CONFIG_NET_SWITCHDEV
+static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt,
+ int in_vifi, int out_vifi)
+{
+ struct vif_device *out_vif = &mrt->vif_table[out_vifi];
+ struct vif_device *in_vif = &mrt->vif_table[in_vifi];
+
+ if (!skb->offload_mr_fwd_mark)
+ return false;
+ if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len)
+ return false;
+ return netdev_phys_item_id_same(&out_vif->dev_parent_id,
+ &in_vif->dev_parent_id);
+}
+#else
+static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt,
+ int in_vifi, int out_vifi)
+{
+ return false;
+}
+#endif
+
/* Processing handlers for ipmr_forward */
static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
- struct sk_buff *skb, struct mfc_cache *c, int vifi)
+ int in_vifi, struct sk_buff *skb,
+ struct mfc_cache *c, int vifi)
{
const struct iphdr *iph = ip_hdr(skb);
struct vif_device *vif = &mrt->vif_table[vifi];
@@ -1748,6 +1907,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
goto out_free;
}
+ if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi))
+ goto out_free;
+
if (vif->flags & VIFF_TUNNEL) {
rt = ip_route_output_ports(net, &fl4, NULL,
vif->remote, vif->local,
@@ -1925,8 +2087,8 @@ forward:
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
- ipmr_queue_xmit(net, mrt, skb2, cache,
- psend);
+ ipmr_queue_xmit(net, mrt, true_vifi,
+ skb2, cache, psend);
}
psend = ct;
}
@@ -1937,9 +2099,10 @@ last_forward:
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
- ipmr_queue_xmit(net, mrt, skb2, cache, psend);
+ ipmr_queue_xmit(net, mrt, true_vifi, skb2,
+ cache, psend);
} else {
- ipmr_queue_xmit(net, mrt, skb, cache, psend);
+ ipmr_queue_xmit(net, mrt, true_vifi, skb, cache, psend);
return;
}
}
@@ -2156,6 +2319,9 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0)
return -EMSGSIZE;
+ if (c->mfc_flags & MFC_OFFLOAD)
+ rtm->rtm_flags |= RTNH_F_OFFLOAD;
+
if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH)))
return -EMSGSIZE;
@@ -3048,14 +3214,87 @@ static const struct net_protocol pim_protocol = {
};
#endif
+static unsigned int ipmr_seq_read(struct net *net)
+{
+ ASSERT_RTNL();
+
+ return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net);
+}
+
+static int ipmr_dump(struct net *net, struct notifier_block *nb)
+{
+ struct mr_table *mrt;
+ int err;
+
+ err = ipmr_rules_dump(net, nb);
+ if (err)
+ return err;
+
+ ipmr_for_each_table(mrt, net) {
+ struct vif_device *v = &mrt->vif_table[0];
+ struct mfc_cache *mfc;
+ int vifi;
+
+ /* Notifiy on table VIF entries */
+ read_lock(&mrt_lock);
+ for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
+ if (!v->dev)
+ continue;
+
+ call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD,
+ v, vifi, mrt->id);
+ }
+ read_unlock(&mrt_lock);
+
+ /* Notify on table MFC entries */
+ list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
+ call_ipmr_mfc_entry_notifier(nb, net,
+ FIB_EVENT_ENTRY_ADD, mfc,
+ mrt->id);
+ }
+
+ return 0;
+}
+
+static const struct fib_notifier_ops ipmr_notifier_ops_template = {
+ .family = RTNL_FAMILY_IPMR,
+ .fib_seq_read = ipmr_seq_read,
+ .fib_dump = ipmr_dump,
+ .owner = THIS_MODULE,
+};
+
+static int __net_init ipmr_notifier_init(struct net *net)
+{
+ struct fib_notifier_ops *ops;
+
+ net->ipv4.ipmr_seq = 0;
+
+ ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net);
+ if (IS_ERR(ops))
+ return PTR_ERR(ops);
+ net->ipv4.ipmr_notifier_ops = ops;
+
+ return 0;
+}
+
+static void __net_exit ipmr_notifier_exit(struct net *net)
+{
+ fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops);
+ net->ipv4.ipmr_notifier_ops = NULL;
+}
+
/* Setup for IP multicast routing */
static int __net_init ipmr_net_init(struct net *net)
{
int err;
+ err = ipmr_notifier_init(net);
+ if (err)
+ goto ipmr_notifier_fail;
+
err = ipmr_rules_init(net);
if (err < 0)
- goto fail;
+ goto ipmr_rules_fail;
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
@@ -3072,7 +3311,9 @@ proc_cache_fail:
proc_vif_fail:
ipmr_rules_exit(net);
#endif
-fail:
+ipmr_rules_fail:
+ ipmr_notifier_exit(net);
+ipmr_notifier_fail:
return err;
}
@@ -3082,6 +3323,7 @@ static void __net_exit ipmr_net_exit(struct net *net)
remove_proc_entry("ip_mr_cache", net->proc_net);
remove_proc_entry("ip_mr_vif", net->proc_net);
#endif
+ ipmr_notifier_exit(net);
ipmr_rules_exit(net);
}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 9e2770fd00be..f88221aebc9d 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -634,6 +634,25 @@ static void get_counters(const struct xt_table_info *t,
}
}
+static void get_old_counters(const struct xt_table_info *t,
+ struct xt_counters counters[])
+{
+ struct arpt_entry *iter;
+ unsigned int cpu, i;
+
+ for_each_possible_cpu(cpu) {
+ i = 0;
+ xt_entry_foreach(iter, t->entries, t->size) {
+ struct xt_counters *tmp;
+
+ tmp = xt_get_per_cpu_counter(&iter->counters, cpu);
+ ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt);
+ ++i;
+ }
+ cond_resched();
+ }
+}
+
static struct xt_counters *alloc_counters(const struct xt_table *table)
{
unsigned int countersize;
@@ -910,8 +929,7 @@ static int __do_replace(struct net *net, const char *name,
(newinfo->number <= oldinfo->initial_entries))
module_put(t->me);
- /* Get the old counters, and synchronize with replace */
- get_counters(oldinfo, counters);
+ get_old_counters(oldinfo, counters);
/* Decrease module usage counts and free resource */
loc_cpu_old_entry = oldinfo->entries;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 39286e543ee6..4cbe5e80f3bf 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -781,6 +781,26 @@ get_counters(const struct xt_table_info *t,
}
}
+static void get_old_counters(const struct xt_table_info *t,
+ struct xt_counters counters[])
+{
+ struct ipt_entry *iter;
+ unsigned int cpu, i;
+
+ for_each_possible_cpu(cpu) {
+ i = 0;
+ xt_entry_foreach(iter, t->entries, t->size) {
+ const struct xt_counters *tmp;
+
+ tmp = xt_get_per_cpu_counter(&iter->counters, cpu);
+ ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt);
+ ++i; /* macro does multi eval of i */
+ }
+
+ cond_resched();
+ }
+}
+
static struct xt_counters *alloc_counters(const struct xt_table *table)
{
unsigned int countersize;
@@ -1070,8 +1090,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
(newinfo->number <= oldinfo->initial_entries))
module_put(t->me);
- /* Get the old counters, and synchronize with replace */
- get_counters(oldinfo, counters);
+ get_old_counters(oldinfo, counters);
/* Decrease module usage counts and free resource */
xt_entry_foreach(iter, oldinfo->entries, oldinfo->size)
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index fe374da4bc13..89af9d88ca21 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -344,7 +344,7 @@ static void ipv4_hooks_unregister(struct net *net)
mutex_unlock(&register_ipv4_hooks);
}
-struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
+const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
.l3proto = PF_INET,
.pkt_to_tuple = ipv4_pkt_to_tuple,
.invert_tuple = ipv4_invert_tuple,
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index a046c298413a..1849fedd9b81 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -81,7 +81,6 @@ static int icmp_packet(struct nf_conn *ct,
const struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
- u_int8_t pf,
unsigned int *timeout)
{
/* Do not immediately delete the connection after the first
@@ -165,6 +164,12 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
return NF_ACCEPT;
}
+static void icmp_error_log(const struct sk_buff *skb, struct net *net,
+ u8 pf, const char *msg)
+{
+ nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMP, "%s", msg);
+}
+
/* Small and modified version of icmp_rcv */
static int
icmp_error(struct net *net, struct nf_conn *tmpl,
@@ -177,18 +182,14 @@ icmp_error(struct net *net, struct nf_conn *tmpl,
/* Not enough header? */
icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih);
if (icmph == NULL) {
- if (LOG_INVALID(net, IPPROTO_ICMP))
- nf_log_packet(net, PF_INET, 0, skb, NULL, NULL,
- NULL, "nf_ct_icmp: short packet ");
+ icmp_error_log(skb, net, pf, "short packet");
return -NF_ACCEPT;
}
/* See ip_conntrack_proto_tcp.c */
if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
nf_ip_checksum(skb, hooknum, dataoff, 0)) {
- if (LOG_INVALID(net, IPPROTO_ICMP))
- nf_log_packet(net, PF_INET, 0, skb, NULL, NULL, NULL,
- "nf_ct_icmp: bad HW ICMP checksum ");
+ icmp_error_log(skb, net, pf, "bad hw icmp checksum");
return -NF_ACCEPT;
}
@@ -199,9 +200,7 @@ icmp_error(struct net *net, struct nf_conn *tmpl,
* discarded.
*/
if (icmph->type > NR_ICMP_TYPES) {
- if (LOG_INVALID(net, IPPROTO_ICMP))
- nf_log_packet(net, PF_INET, 0, skb, NULL, NULL, NULL,
- "nf_ct_icmp: invalid ICMP type ");
+ icmp_error_log(skb, net, pf, "invalid icmp type");
return -NF_ACCEPT;
}
@@ -259,9 +258,14 @@ static int icmp_nlattr_to_tuple(struct nlattr *tb[],
return 0;
}
-static int icmp_nlattr_tuple_size(void)
+static unsigned int icmp_nlattr_tuple_size(void)
{
- return nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1);
+ static unsigned int size __read_mostly;
+
+ if (!size)
+ size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1);
+
+ return size;
}
#endif
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index a0f37b208268..0443ca4120b0 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -276,7 +276,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
else
return NF_ACCEPT;
}
- /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
+ /* Only ICMPs can be IP_CT_IS_REPLY: */
+ /* fall through */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
* or local packets.
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 127153f1ed8a..9f37c4727861 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -212,7 +212,6 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPRenoRecovery", LINUX_MIB_TCPRENORECOVERY),
SNMP_MIB_ITEM("TCPSackRecovery", LINUX_MIB_TCPSACKRECOVERY),
SNMP_MIB_ITEM("TCPSACKReneging", LINUX_MIB_TCPSACKRENEGING),
- SNMP_MIB_ITEM("TCPFACKReorder", LINUX_MIB_TCPFACKREORDER),
SNMP_MIB_ITEM("TCPSACKReorder", LINUX_MIB_TCPSACKREORDER),
SNMP_MIB_ITEM("TCPRenoReorder", LINUX_MIB_TCPRENOREORDER),
SNMP_MIB_ITEM("TCPTSReorder", LINUX_MIB_TCPTSREORDER),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c0864562083b..3b427757b1f8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1250,7 +1250,7 @@ static void set_class_tag(struct rtable *rt, u32 tag)
static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
{
unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr);
- unsigned int advmss = max_t(unsigned int, dst->dev->mtu - header_size,
+ unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
ip_rt_min_advmss);
return min(advmss, IPV4_MAX_PMTU - header_size);
@@ -3038,7 +3038,6 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
int __init ip_rt_init(void)
{
- int rc = 0;
int cpu;
ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
@@ -3095,7 +3094,7 @@ int __init ip_rt_init(void)
#endif
register_pernet_subsys(&rt_genid_ops);
register_pernet_subsys(&ipv4_inetpeer_ops);
- return rc;
+ return 0;
}
#ifdef CONFIG_SYSCTL
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 77cf32a80952..fda37f2862c9 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -385,7 +385,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
/* Try to redo what tcp_v4_send_synack did. */
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
- tcp_select_initial_window(tcp_full_space(sk), req->mss,
+ tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(&rt->dst, RTAX_INITRWND));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0989e739d098..93e172118a94 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -26,6 +26,7 @@
#include <net/inet_frag.h>
#include <net/ping.h>
#include <net/protocol.h>
+#include <net/netevent.h>
static int zero;
static int one = 1;
@@ -200,6 +201,8 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
+ struct net *net = container_of(ctl->data, struct net,
+ ipv4.tcp_congestion_control);
char val[TCP_CA_NAME_MAX];
struct ctl_table tbl = {
.data = val,
@@ -207,11 +210,11 @@ static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
};
int ret;
- tcp_get_default_congestion_control(val);
+ tcp_get_default_congestion_control(net, val);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0)
- ret = tcp_set_default_congestion_control(val);
+ ret = tcp_set_default_congestion_control(net, val);
return ret;
}
@@ -252,10 +255,12 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl,
return ret;
}
-static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
+static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
+ struct net *net = container_of(table->data, struct net,
+ ipv4.sysctl_tcp_fastopen);
struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
struct tcp_fastopen_context *ctxt;
int ret;
@@ -266,7 +271,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
return -ENOMEM;
rcu_read_lock();
- ctxt = rcu_dereference(tcp_fastopen_ctx);
+ ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
if (ctxt)
memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
else
@@ -283,12 +288,8 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
ret = -EINVAL;
goto bad_key;
}
- /* Generate a dummy secret but don't publish it. This
- * is needed so we don't regenerate a new key on the
- * first invocation of tcp_fastopen_cookie_gen
- */
- tcp_fastopen_init_key_once(false);
- tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
+ tcp_fastopen_reset_cipher(net, NULL, user_key,
+ TCP_FASTOPEN_KEY_LENGTH);
}
bad_key:
@@ -359,11 +360,13 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
+ struct net *net = container_of(table->data, struct net,
+ ipv4.sysctl_tcp_fastopen_blackhole_timeout);
int ret;
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (write && ret == 0)
- tcp_fastopen_active_timeout_reset();
+ atomic_set(&net->ipv4.tfo_active_disable_times, 0);
return ret;
}
@@ -386,15 +389,25 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
return ret;
}
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ struct net *net = container_of(table->data, struct net,
+ ipv4.sysctl_fib_multipath_hash_policy);
+ int ret;
+
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ if (write && ret == 0)
+ call_netevent_notifiers(NETEVENT_MULTIPATH_HASH_UPDATE, net);
+
+ return ret;
+}
+#endif
+
static struct ctl_table ipv4_table[] = {
{
- .procname = "tcp_retrans_collapse",
- .data = &sysctl_tcp_retrans_collapse,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_max_orphans",
.data = &sysctl_tcp_max_orphans,
.maxlen = sizeof(int),
@@ -402,48 +415,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "tcp_fastopen",
- .data = &sysctl_tcp_fastopen,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "tcp_fastopen_key",
- .mode = 0600,
- .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
- .proc_handler = proc_tcp_fastopen_key,
- },
- {
- .procname = "tcp_fastopen_blackhole_timeout_sec",
- .data = &sysctl_tcp_fastopen_blackhole_timeout,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_tfo_blackhole_detect_timeout,
- .extra1 = &zero,
- },
- {
- .procname = "tcp_abort_on_overflow",
- .data = &sysctl_tcp_abort_on_overflow,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_stdurg",
- .data = &sysctl_tcp_stdurg,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_rfc1337",
- .data = &sysctl_tcp_rfc1337,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "inet_peer_threshold",
.data = &inet_peer_threshold,
.maxlen = sizeof(int),
@@ -465,34 +436,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec_jiffies,
},
{
- .procname = "tcp_fack",
- .data = &sysctl_tcp_fack,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_recovery",
- .data = &sysctl_tcp_recovery,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "tcp_max_reordering",
- .data = &sysctl_tcp_max_reordering,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_dsack",
- .data = &sysctl_tcp_dsack,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_mem",
.maxlen = sizeof(sysctl_tcp_mem),
.data = &sysctl_tcp_mem,
@@ -500,113 +443,12 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_doulongvec_minmax,
},
{
- .procname = "tcp_wmem",
- .data = &sysctl_tcp_wmem,
- .maxlen = sizeof(sysctl_tcp_wmem),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
- },
- {
- .procname = "tcp_rmem",
- .data = &sysctl_tcp_rmem,
- .maxlen = sizeof(sysctl_tcp_rmem),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
- },
- {
- .procname = "tcp_app_win",
- .data = &sysctl_tcp_app_win,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_adv_win_scale",
- .data = &sysctl_tcp_adv_win_scale,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &tcp_adv_win_scale_min,
- .extra2 = &tcp_adv_win_scale_max,
- },
- {
- .procname = "tcp_frto",
- .data = &sysctl_tcp_frto,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_min_rtt_wlen",
- .data = &sysctl_tcp_min_rtt_wlen,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_low_latency",
.data = &sysctl_tcp_low_latency,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
- {
- .procname = "tcp_no_metrics_save",
- .data = &sysctl_tcp_nometrics_save,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "tcp_moderate_rcvbuf",
- .data = &sysctl_tcp_moderate_rcvbuf,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "tcp_tso_win_divisor",
- .data = &sysctl_tcp_tso_win_divisor,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "tcp_congestion_control",
- .mode = 0644,
- .maxlen = TCP_CA_NAME_MAX,
- .proc_handler = proc_tcp_congestion_control,
- },
- {
- .procname = "tcp_workaround_signed_windows",
- .data = &sysctl_tcp_workaround_signed_windows,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_limit_output_bytes",
- .data = &sysctl_tcp_limit_output_bytes,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_challenge_ack_limit",
- .data = &sysctl_tcp_challenge_ack_limit,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_slow_start_after_idle",
- .data = &sysctl_tcp_slow_start_after_idle,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
#ifdef CONFIG_NETLABEL
{
.procname = "cipso_cache_enable",
@@ -650,65 +492,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_allowed_congestion_control,
},
{
- .procname = "tcp_thin_linear_timeouts",
- .data = &sysctl_tcp_thin_linear_timeouts,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_early_retrans",
- .data = &sysctl_tcp_early_retrans,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &four,
- },
- {
- .procname = "tcp_min_tso_segs",
- .data = &sysctl_tcp_min_tso_segs,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
- .extra2 = &gso_max_segs,
- },
- {
- .procname = "tcp_pacing_ss_ratio",
- .data = &sysctl_tcp_pacing_ss_ratio,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &thousand,
- },
- {
- .procname = "tcp_pacing_ca_ratio",
- .data = &sysctl_tcp_pacing_ca_ratio,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &thousand,
- },
- {
- .procname = "tcp_autocorking",
- .data = &sysctl_tcp_autocorking,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &one,
- },
- {
- .procname = "tcp_invalid_ratelimit",
- .data = &sysctl_tcp_invalid_ratelimit,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_ms_jiffies,
- },
- {
.procname = "tcp_available_ulp",
.maxlen = TCP_ULP_BUF_MAX,
.mode = 0444,
@@ -977,6 +760,13 @@ static struct ctl_table ipv4_net_table[] = {
},
#endif
{
+ .procname = "tcp_congestion_control",
+ .data = &init_net.ipv4.tcp_congestion_control,
+ .mode = 0644,
+ .maxlen = TCP_CA_NAME_MAX,
+ .proc_handler = proc_tcp_congestion_control,
+ },
+ {
.procname = "tcp_keepalive_time",
.data = &init_net.ipv4.sysctl_tcp_keepalive_time,
.maxlen = sizeof(int),
@@ -1086,6 +876,28 @@ static struct ctl_table ipv4_net_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "tcp_fastopen",
+ .data = &init_net.ipv4.sysctl_tcp_fastopen,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "tcp_fastopen_key",
+ .mode = 0600,
+ .data = &init_net.ipv4.sysctl_tcp_fastopen,
+ .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
+ .proc_handler = proc_tcp_fastopen_key,
+ },
+ {
+ .procname = "tcp_fastopen_blackhole_timeout_sec",
+ .data = &init_net.ipv4.sysctl_tcp_fastopen_blackhole_timeout,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_tfo_blackhole_detect_timeout,
+ .extra1 = &zero,
+ },
#ifdef CONFIG_IP_ROUTE_MULTIPATH
{
.procname = "fib_multipath_use_neigh",
@@ -1101,7 +913,7 @@ static struct ctl_table ipv4_net_table[] = {
.data = &init_net.ipv4.sysctl_fib_multipath_hash_policy,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_fib_multipath_hash_policy,
.extra1 = &zero,
.extra2 = &one,
},
@@ -1145,6 +957,216 @@ static struct ctl_table ipv4_net_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "tcp_early_retrans",
+ .data = &init_net.ipv4.sysctl_tcp_early_retrans,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &four,
+ },
+ {
+ .procname = "tcp_recovery",
+ .data = &init_net.ipv4.sysctl_tcp_recovery,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "tcp_thin_linear_timeouts",
+ .data = &init_net.ipv4.sysctl_tcp_thin_linear_timeouts,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_slow_start_after_idle",
+ .data = &init_net.ipv4.sysctl_tcp_slow_start_after_idle,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_retrans_collapse",
+ .data = &init_net.ipv4.sysctl_tcp_retrans_collapse,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_stdurg",
+ .data = &init_net.ipv4.sysctl_tcp_stdurg,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_rfc1337",
+ .data = &init_net.ipv4.sysctl_tcp_rfc1337,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_abort_on_overflow",
+ .data = &init_net.ipv4.sysctl_tcp_abort_on_overflow,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_fack",
+ .data = &init_net.ipv4.sysctl_tcp_fack,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_max_reordering",
+ .data = &init_net.ipv4.sysctl_tcp_max_reordering,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_dsack",
+ .data = &init_net.ipv4.sysctl_tcp_dsack,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_app_win",
+ .data = &init_net.ipv4.sysctl_tcp_app_win,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_adv_win_scale",
+ .data = &init_net.ipv4.sysctl_tcp_adv_win_scale,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &tcp_adv_win_scale_min,
+ .extra2 = &tcp_adv_win_scale_max,
+ },
+ {
+ .procname = "tcp_frto",
+ .data = &init_net.ipv4.sysctl_tcp_frto,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_no_metrics_save",
+ .data = &init_net.ipv4.sysctl_tcp_nometrics_save,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "tcp_moderate_rcvbuf",
+ .data = &init_net.ipv4.sysctl_tcp_moderate_rcvbuf,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "tcp_tso_win_divisor",
+ .data = &init_net.ipv4.sysctl_tcp_tso_win_divisor,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "tcp_workaround_signed_windows",
+ .data = &init_net.ipv4.sysctl_tcp_workaround_signed_windows,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_limit_output_bytes",
+ .data = &init_net.ipv4.sysctl_tcp_limit_output_bytes,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_challenge_ack_limit",
+ .data = &init_net.ipv4.sysctl_tcp_challenge_ack_limit,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_min_tso_segs",
+ .data = &init_net.ipv4.sysctl_tcp_min_tso_segs,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ .extra2 = &gso_max_segs,
+ },
+ {
+ .procname = "tcp_min_rtt_wlen",
+ .data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_autocorking",
+ .data = &init_net.ipv4.sysctl_tcp_autocorking,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {
+ .procname = "tcp_invalid_ratelimit",
+ .data = &init_net.ipv4.sysctl_tcp_invalid_ratelimit,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_ms_jiffies,
+ },
+ {
+ .procname = "tcp_pacing_ss_ratio",
+ .data = &init_net.ipv4.sysctl_tcp_pacing_ss_ratio,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &thousand,
+ },
+ {
+ .procname = "tcp_pacing_ca_ratio",
+ .data = &init_net.ipv4.sysctl_tcp_pacing_ca_ratio,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &thousand,
+ },
+ {
+ .procname = "tcp_wmem",
+ .data = &init_net.ipv4.sysctl_tcp_wmem,
+ .maxlen = sizeof(init_net.ipv4.sysctl_tcp_wmem),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ },
+ {
+ .procname = "tcp_rmem",
+ .data = &init_net.ipv4.sysctl_tcp_rmem,
+ .maxlen = sizeof(init_net.ipv4.sysctl_tcp_rmem),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ },
{ }
};
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5091402720ab..bf97317e6c97 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -270,6 +270,7 @@
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/errqueue.h>
+#include <linux/static_key.h>
#include <net/icmp.h>
#include <net/inet_common.h>
@@ -282,24 +283,22 @@
#include <asm/ioctls.h>
#include <net/busy_poll.h>
-int sysctl_tcp_min_tso_segs __read_mostly = 2;
-
-int sysctl_tcp_autocorking __read_mostly = 1;
+#include <trace/events/tcp.h>
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
long sysctl_tcp_mem[3] __read_mostly;
-int sysctl_tcp_wmem[3] __read_mostly;
-int sysctl_tcp_rmem[3] __read_mostly;
-
EXPORT_SYMBOL(sysctl_tcp_mem);
-EXPORT_SYMBOL(sysctl_tcp_rmem);
-EXPORT_SYMBOL(sysctl_tcp_wmem);
atomic_long_t tcp_memory_allocated; /* Current allocated memory. */
EXPORT_SYMBOL(tcp_memory_allocated);
+#if IS_ENABLED(CONFIG_SMC)
+DEFINE_STATIC_KEY_FALSE(tcp_have_smc);
+EXPORT_SYMBOL(tcp_have_smc);
+#endif
+
/*
* Current number of TCP sockets.
*/
@@ -413,8 +412,10 @@ void tcp_init_sock(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
tp->out_of_order_queue = RB_ROOT;
+ sk->tcp_rtx_queue = RB_ROOT;
tcp_init_xmit_timers(sk);
INIT_LIST_HEAD(&tp->tsq_node);
+ INIT_LIST_HEAD(&tp->tsorted_sent_queue);
icsk->icsk_rto = TCP_TIMEOUT_INIT;
tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
@@ -441,6 +442,7 @@ void tcp_init_sock(struct sock *sk)
tcp_assign_congestion_control(sk);
tp->tsoffset = 0;
+ tp->rack.reo_wnd_steps = 1;
sk->sk_state = TCP_CLOSE;
@@ -449,15 +451,29 @@ void tcp_init_sock(struct sock *sk)
icsk->icsk_sync_mss = tcp_sync_mss;
- sk->sk_sndbuf = sysctl_tcp_wmem[1];
- sk->sk_rcvbuf = sysctl_tcp_rmem[1];
+ sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
+ sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
sk_sockets_allocated_inc(sk);
}
EXPORT_SYMBOL(tcp_init_sock);
-static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb)
+void tcp_init_transfer(struct sock *sk, int bpf_op)
{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ tcp_mtup_init(sk);
+ icsk->icsk_af_ops->rebuild_header(sk);
+ tcp_init_metrics(sk);
+ tcp_call_bpf(sk, bpf_op);
+ tcp_init_congestion_control(sk);
+ tcp_init_buffer_space(sk);
+}
+
+static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
+{
+ struct sk_buff *skb = tcp_write_queue_tail(sk);
+
if (tsflags && skb) {
struct skb_shared_info *shinfo = skb_shinfo(skb);
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
@@ -675,7 +691,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
int size_goal)
{
return skb->len < size_goal &&
- sysctl_tcp_autocorking &&
+ sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
skb != tcp_write_queue_head(sk) &&
refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
}
@@ -686,10 +702,9 @@ static void tcp_push(struct sock *sk, int flags, int mss_now,
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- if (!tcp_send_head(sk))
- return;
-
skb = tcp_write_queue_tail(sk);
+ if (!skb)
+ return;
if (!(flags & MSG_MORE) || forced_push(tp))
tcp_mark_push(tp, skb);
@@ -869,6 +884,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
* available to the caller, no more, no less.
*/
skb->reserved_tailroom = skb->end - skb->tail - size;
+ INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
return skb;
}
__kfree_skb(skb);
@@ -948,14 +964,14 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
int copy, i;
bool can_coalesce;
- if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0 ||
+ if (!skb || (copy = size_goal - skb->len) <= 0 ||
!tcp_skb_can_collapse_to(skb)) {
new_segment:
if (!sk_stream_memory_free(sk))
goto wait_for_sndbuf;
skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
- skb_queue_empty(&sk->sk_write_queue));
+ tcp_rtx_and_write_queues_empty(sk));
if (!skb)
goto wait_for_memory;
@@ -1027,7 +1043,7 @@ wait_for_memory:
out:
if (copied) {
- tcp_tx_timestamp(sk, sk->sk_tsflags, tcp_write_queue_tail(sk));
+ tcp_tx_timestamp(sk, sk->sk_tsflags);
if (!(flags & MSG_SENDPAGE_NOTLAST))
tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
}
@@ -1126,7 +1142,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
struct sockaddr *uaddr = msg->msg_name;
int err, flags;
- if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+ if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
(uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
uaddr->sa_family == AF_UNSPEC))
return -EOPNOTSUPP;
@@ -1183,7 +1199,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
goto out_err;
}
- skb = tcp_send_head(sk) ? tcp_write_queue_tail(sk) : NULL;
+ skb = tcp_write_queue_tail(sk);
uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb));
if (!uarg) {
err = -ENOBUFS;
@@ -1259,7 +1275,7 @@ restart:
int max = size_goal;
skb = tcp_write_queue_tail(sk);
- if (tcp_send_head(sk)) {
+ if (skb) {
if (skb->ip_summed == CHECKSUM_NONE)
max = mss_now;
copy = max - skb->len;
@@ -1279,7 +1295,7 @@ new_segment:
process_backlog = false;
goto restart;
}
- first_skb = skb_queue_empty(&sk->sk_write_queue);
+ first_skb = tcp_rtx_and_write_queues_empty(sk);
skb = sk_stream_alloc_skb(sk,
select_size(sk, sg, first_skb),
sk->sk_allocation,
@@ -1404,7 +1420,7 @@ wait_for_memory:
out:
if (copied) {
- tcp_tx_timestamp(sk, sockc.tsflags, tcp_write_queue_tail(sk));
+ tcp_tx_timestamp(sk, sockc.tsflags);
tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
}
out_nopush:
@@ -1505,6 +1521,13 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
/* XXX -- need to support SO_PEEK_OFF */
+ skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
+ err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
+ if (err)
+ return err;
+ copied += skb->len;
+ }
+
skb_queue_walk(&sk->sk_write_queue, skb) {
err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
if (err)
@@ -2017,6 +2040,8 @@ void tcp_set_state(struct sock *sk, int state)
{
int oldstate = sk->sk_state;
+ trace_tcp_set_state(sk, oldstate, state);
+
switch (state) {
case TCP_ESTABLISHED:
if (oldstate != TCP_ESTABLISHED)
@@ -2304,6 +2329,37 @@ static inline bool tcp_need_reset(int state)
TCPF_FIN_WAIT2 | TCPF_SYN_RECV);
}
+static void tcp_rtx_queue_purge(struct sock *sk)
+{
+ struct rb_node *p = rb_first(&sk->tcp_rtx_queue);
+
+ while (p) {
+ struct sk_buff *skb = rb_to_skb(p);
+
+ p = rb_next(p);
+ /* Since we are deleting whole queue, no need to
+ * list_del(&skb->tcp_tsorted_anchor)
+ */
+ tcp_rtx_queue_unlink(skb, sk);
+ sk_wmem_free_skb(sk, skb);
+ }
+}
+
+void tcp_write_queue_purge(struct sock *sk)
+{
+ struct sk_buff *skb;
+
+ tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+ while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
+ tcp_skb_tsorted_anchor_cleanup(skb);
+ sk_wmem_free_skb(sk, skb);
+ }
+ tcp_rtx_queue_purge(sk);
+ INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
+ sk_mem_reclaim(sk);
+ tcp_clear_all_retrans_hints(tcp_sk(sk));
+}
+
int tcp_disconnect(struct sock *sk, int flags)
{
struct inet_sock *inet = inet_sk(sk);
@@ -2362,7 +2418,6 @@ int tcp_disconnect(struct sock *sk, int flags)
* issue in __tcp_select_window()
*/
icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
- tcp_init_send_head(sk);
memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
__sk_dst_reset(sk);
dst_release(sk->sk_rx_dst);
@@ -2454,8 +2509,6 @@ static int tcp_repair_options_est(struct sock *sk,
return -EINVAL;
tp->rx_opt.sack_ok |= TCP_SACK_SEEN;
- if (sysctl_tcp_fack)
- tcp_enable_fack(tp);
break;
case TCPOPT_TIMESTAMP:
if (opt.opt_val != 0)
@@ -2518,6 +2571,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
release_sock(sk);
return err;
}
+ case TCP_FASTOPEN_KEY: {
+ __u8 key[TCP_FASTOPEN_KEY_LENGTH];
+
+ if (optlen != sizeof(key))
+ return -EINVAL;
+
+ if (copy_from_user(key, optval, optlen))
+ return -EFAULT;
+
+ return tcp_fastopen_reset_cipher(net, sk, key, sizeof(key));
+ }
default:
/* fallthru */
break;
@@ -2749,7 +2813,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_FASTOPEN:
if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
TCPF_LISTEN))) {
- tcp_fastopen_init_key_once(true);
+ tcp_fastopen_init_key_once(net);
fastopen_queue_tune(sk, val);
} else {
@@ -2759,7 +2823,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_FASTOPEN_CONNECT:
if (val > 1 || val < 0) {
err = -EINVAL;
- } else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+ } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
if (sk->sk_state == TCP_CLOSE)
tp->fastopen_connect = val;
else
@@ -2768,6 +2832,14 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
err = -EOPNOTSUPP;
}
break;
+ case TCP_FASTOPEN_NO_COOKIE:
+ if (val > 1 || val < 0)
+ err = -EINVAL;
+ else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+ err = -EINVAL;
+ else
+ tp->fastopen_no_cookie = val;
+ break;
case TCP_TIMESTAMP:
if (!tp->repair)
err = -EPERM;
@@ -2905,7 +2977,6 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_lost = tp->lost_out;
info->tcpi_retrans = tp->retrans_out;
- info->tcpi_fackets = tp->fackets_out;
now = tcp_jiffies32;
info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
@@ -3104,6 +3175,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
return -EFAULT;
return 0;
+ case TCP_FASTOPEN_KEY: {
+ __u8 key[TCP_FASTOPEN_KEY_LENGTH];
+ struct tcp_fastopen_context *ctx;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ rcu_read_lock();
+ ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx);
+ if (ctx)
+ memcpy(key, ctx->key, sizeof(key));
+ else
+ len = 0;
+ rcu_read_unlock();
+
+ len = min_t(unsigned int, len, sizeof(key));
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, key, len))
+ return -EFAULT;
+ return 0;
+ }
case TCP_THIN_LINEAR_TIMEOUTS:
val = tp->thin_lto;
break;
@@ -3166,6 +3259,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
val = tp->fastopen_connect;
break;
+ case TCP_FASTOPEN_NO_COOKIE:
+ val = tp->fastopen_no_cookie;
+ break;
+
case TCP_TIMESTAMP:
val = tcp_time_stamp_raw() + tp->tsoffset;
break;
@@ -3531,13 +3628,13 @@ void __init tcp_init(void)
max_wshare = min(4UL*1024*1024, limit);
max_rshare = min(6UL*1024*1024, limit);
- sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
- sysctl_tcp_wmem[1] = 16*1024;
- sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
+ init_net.ipv4.sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
+ init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024;
+ init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
- sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
- sysctl_tcp_rmem[1] = 87380;
- sysctl_tcp_rmem[2] = max(87380, max_rshare);
+ init_net.ipv4.sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
+ init_net.ipv4.sysctl_tcp_rmem[1] = 87380;
+ init_net.ipv4.sysctl_tcp_rmem[2] = max(87380, max_rshare);
pr_info("Hash tables configured (established %u bind %u)\n",
tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
index 66ac69f7bd19..06fbe102a425 100644
--- a/net/ipv4/tcp_cdg.c
+++ b/net/ipv4/tcp_cdg.c
@@ -389,7 +389,7 @@ static void tcp_cdg_release(struct sock *sk)
kfree(ca->gradients);
}
-struct tcp_congestion_ops tcp_cdg __read_mostly = {
+static struct tcp_congestion_ops tcp_cdg __read_mostly = {
.cong_avoid = tcp_cdg_cong_avoid,
.cwnd_event = tcp_cdg_cwnd_event,
.pkts_acked = tcp_cdg_acked,
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 2f26124fd160..bc6c02f16243 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -33,9 +33,11 @@ static struct tcp_congestion_ops *tcp_ca_find(const char *name)
}
/* Must be called with rcu lock held */
-static const struct tcp_congestion_ops *__tcp_ca_find_autoload(const char *name)
+static struct tcp_congestion_ops *tcp_ca_find_autoload(struct net *net,
+ const char *name)
{
- const struct tcp_congestion_ops *ca = tcp_ca_find(name);
+ struct tcp_congestion_ops *ca = tcp_ca_find(name);
+
#ifdef CONFIG_MODULES
if (!ca && capable(CAP_NET_ADMIN)) {
rcu_read_unlock();
@@ -115,7 +117,7 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
}
EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
-u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca)
+u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca)
{
const struct tcp_congestion_ops *ca;
u32 key = TCP_CA_UNSPEC;
@@ -123,7 +125,7 @@ u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca)
might_sleep();
rcu_read_lock();
- ca = __tcp_ca_find_autoload(name);
+ ca = tcp_ca_find_autoload(net, name);
if (ca) {
key = ca->key;
*ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN;
@@ -153,23 +155,18 @@ EXPORT_SYMBOL_GPL(tcp_ca_get_name_by_key);
/* Assign choice of congestion control. */
void tcp_assign_congestion_control(struct sock *sk)
{
+ struct net *net = sock_net(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
- struct tcp_congestion_ops *ca;
+ const struct tcp_congestion_ops *ca;
rcu_read_lock();
- list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
- if (likely(try_module_get(ca->owner))) {
- icsk->icsk_ca_ops = ca;
- goto out;
- }
- /* Fallback to next available. The last really
- * guaranteed fallback is Reno from this list.
- */
- }
-out:
+ ca = rcu_dereference(net->ipv4.tcp_congestion_control);
+ if (unlikely(!try_module_get(ca->owner)))
+ ca = &tcp_reno;
+ icsk->icsk_ca_ops = ca;
rcu_read_unlock();
- memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+ memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
if (ca->flags & TCP_CONG_NEEDS_ECN)
INET_ECN_xmit(sk);
else
@@ -214,29 +211,27 @@ void tcp_cleanup_congestion_control(struct sock *sk)
}
/* Used by sysctl to change default congestion control */
-int tcp_set_default_congestion_control(const char *name)
+int tcp_set_default_congestion_control(struct net *net, const char *name)
{
struct tcp_congestion_ops *ca;
- int ret = -ENOENT;
-
- spin_lock(&tcp_cong_list_lock);
- ca = tcp_ca_find(name);
-#ifdef CONFIG_MODULES
- if (!ca && capable(CAP_NET_ADMIN)) {
- spin_unlock(&tcp_cong_list_lock);
+ const struct tcp_congestion_ops *prev;
+ int ret;
- request_module("tcp_%s", name);
- spin_lock(&tcp_cong_list_lock);
- ca = tcp_ca_find(name);
- }
-#endif
+ rcu_read_lock();
+ ca = tcp_ca_find_autoload(net, name);
+ if (!ca) {
+ ret = -ENOENT;
+ } else if (!try_module_get(ca->owner)) {
+ ret = -EBUSY;
+ } else {
+ prev = xchg(&net->ipv4.tcp_congestion_control, ca);
+ if (prev)
+ module_put(prev->owner);
- if (ca) {
- ca->flags |= TCP_CONG_NON_RESTRICTED; /* default is always allowed */
- list_move(&ca->list, &tcp_cong_list);
+ ca->flags |= TCP_CONG_NON_RESTRICTED;
ret = 0;
}
- spin_unlock(&tcp_cong_list_lock);
+ rcu_read_unlock();
return ret;
}
@@ -244,7 +239,8 @@ int tcp_set_default_congestion_control(const char *name)
/* Set default value from kernel configuration at bootup */
static int __init tcp_congestion_default(void)
{
- return tcp_set_default_congestion_control(CONFIG_DEFAULT_TCP_CONG);
+ return tcp_set_default_congestion_control(&init_net,
+ CONFIG_DEFAULT_TCP_CONG);
}
late_initcall(tcp_congestion_default);
@@ -264,14 +260,12 @@ void tcp_get_available_congestion_control(char *buf, size_t maxlen)
}
/* Get current default congestion control */
-void tcp_get_default_congestion_control(char *name)
+void tcp_get_default_congestion_control(struct net *net, char *name)
{
- struct tcp_congestion_ops *ca;
- /* We will always have reno... */
- BUG_ON(list_empty(&tcp_cong_list));
+ const struct tcp_congestion_ops *ca;
rcu_read_lock();
- ca = list_entry(tcp_cong_list.next, struct tcp_congestion_ops, list);
+ ca = rcu_dereference(net->ipv4.tcp_congestion_control);
strncpy(name, ca->name, TCP_CA_NAME_MAX);
rcu_read_unlock();
}
@@ -351,12 +345,14 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, boo
if (!load)
ca = tcp_ca_find(name);
else
- ca = __tcp_ca_find_autoload(name);
+ ca = tcp_ca_find_autoload(sock_net(sk), name);
+
/* No change asking for existing value */
if (ca == icsk->icsk_ca_ops) {
icsk->icsk_ca_setsockopt = 1;
goto out;
}
+
if (!ca) {
err = -ENOENT;
} else if (!load) {
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index fbbeda647774..78c192ee03a4 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -10,15 +10,18 @@
#include <net/inetpeer.h>
#include <net/tcp.h>
-int sysctl_tcp_fastopen __read_mostly = TFO_CLIENT_ENABLE;
-
-struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
-
-static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock);
-
-void tcp_fastopen_init_key_once(bool publish)
+void tcp_fastopen_init_key_once(struct net *net)
{
- static u8 key[TCP_FASTOPEN_KEY_LENGTH];
+ u8 key[TCP_FASTOPEN_KEY_LENGTH];
+ struct tcp_fastopen_context *ctxt;
+
+ rcu_read_lock();
+ ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
+ if (ctxt) {
+ rcu_read_unlock();
+ return;
+ }
+ rcu_read_unlock();
/* tcp_fastopen_reset_cipher publishes the new context
* atomically, so we allow this race happening here.
@@ -26,8 +29,8 @@ void tcp_fastopen_init_key_once(bool publish)
* All call sites of tcp_fastopen_cookie_gen also check
* for a valid cookie, so this is an acceptable risk.
*/
- if (net_get_random_once(key, sizeof(key)) && publish)
- tcp_fastopen_reset_cipher(key, sizeof(key));
+ get_random_bytes(key, sizeof(key));
+ tcp_fastopen_reset_cipher(net, NULL, key, sizeof(key));
}
static void tcp_fastopen_ctx_free(struct rcu_head *head)
@@ -38,10 +41,37 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head)
kfree(ctx);
}
-int tcp_fastopen_reset_cipher(void *key, unsigned int len)
+void tcp_fastopen_destroy_cipher(struct sock *sk)
+{
+ struct tcp_fastopen_context *ctx;
+
+ ctx = rcu_dereference_protected(
+ inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1);
+ if (ctx)
+ call_rcu(&ctx->rcu, tcp_fastopen_ctx_free);
+}
+
+void tcp_fastopen_ctx_destroy(struct net *net)
+{
+ struct tcp_fastopen_context *ctxt;
+
+ spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
+
+ ctxt = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+ lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+ rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, NULL);
+ spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
+
+ if (ctxt)
+ call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free);
+}
+
+int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
+ void *key, unsigned int len)
{
- int err;
struct tcp_fastopen_context *ctx, *octx;
+ struct fastopen_queue *q;
+ int err;
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
@@ -62,26 +92,37 @@ error: kfree(ctx);
}
memcpy(ctx->key, key, len);
- spin_lock(&tcp_fastopen_ctx_lock);
- octx = rcu_dereference_protected(tcp_fastopen_ctx,
- lockdep_is_held(&tcp_fastopen_ctx_lock));
- rcu_assign_pointer(tcp_fastopen_ctx, ctx);
- spin_unlock(&tcp_fastopen_ctx_lock);
+ spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
+ if (sk) {
+ q = &inet_csk(sk)->icsk_accept_queue.fastopenq;
+ octx = rcu_dereference_protected(q->ctx,
+ lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+ rcu_assign_pointer(q->ctx, ctx);
+ } else {
+ octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+ lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+ rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx);
+ }
+ spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
if (octx)
call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
return err;
}
-static bool __tcp_fastopen_cookie_gen(const void *path,
+static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path,
struct tcp_fastopen_cookie *foc)
{
struct tcp_fastopen_context *ctx;
bool ok = false;
rcu_read_lock();
- ctx = rcu_dereference(tcp_fastopen_ctx);
+
+ ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx);
+ if (!ctx)
+ ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx);
+
if (ctx) {
crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
foc->len = TCP_FASTOPEN_COOKIE_SIZE;
@@ -97,7 +138,8 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
*
* XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
*/
-static bool tcp_fastopen_cookie_gen(struct request_sock *req,
+static bool tcp_fastopen_cookie_gen(struct sock *sk,
+ struct request_sock *req,
struct sk_buff *syn,
struct tcp_fastopen_cookie *foc)
{
@@ -105,7 +147,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
const struct iphdr *iph = ip_hdr(syn);
__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
- return __tcp_fastopen_cookie_gen(path, foc);
+ return __tcp_fastopen_cookie_gen(sk, path, foc);
}
#if IS_ENABLED(CONFIG_IPV6)
@@ -113,13 +155,13 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
const struct ipv6hdr *ip6h = ipv6_hdr(syn);
struct tcp_fastopen_cookie tmp;
- if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
+ if (__tcp_fastopen_cookie_gen(sk, &ip6h->saddr, &tmp)) {
struct in6_addr *buf = &tmp.addr;
int i;
for (i = 0; i < 4; i++)
buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
- return __tcp_fastopen_cookie_gen(buf, foc);
+ return __tcp_fastopen_cookie_gen(sk, buf, foc);
}
}
#endif
@@ -217,12 +259,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
refcount_set(&req->rsk_refcnt, 2);
/* Now finish processing the fastopen child socket. */
- inet_csk(child)->icsk_af_ops->rebuild_header(child);
- tcp_init_congestion_control(child);
- tcp_mtup_init(child);
- tcp_init_metrics(child);
- tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
- tcp_init_buffer_space(child);
+ tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
@@ -272,33 +309,45 @@ static bool tcp_fastopen_queue_check(struct sock *sk)
return true;
}
+static bool tcp_fastopen_no_cookie(const struct sock *sk,
+ const struct dst_entry *dst,
+ int flag)
+{
+ return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) ||
+ tcp_sk(sk)->fastopen_no_cookie ||
+ (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE));
+}
+
/* Returns true if we should perform Fast Open on the SYN. The cookie (foc)
* may be updated and return the client in the SYN-ACK later. E.g., Fast Open
* cookie request (foc->len == 0).
*/
struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
- struct tcp_fastopen_cookie *foc)
+ struct tcp_fastopen_cookie *foc,
+ const struct dst_entry *dst)
{
- struct tcp_fastopen_cookie valid_foc = { .len = -1 };
bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
+ int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+ struct tcp_fastopen_cookie valid_foc = { .len = -1 };
struct sock *child;
if (foc->len == 0) /* Client requests a cookie */
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD);
- if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+ if (!((tcp_fastopen & TFO_SERVER_ENABLE) &&
(syn_data || foc->len >= 0) &&
tcp_fastopen_queue_check(sk))) {
foc->len = -1;
return NULL;
}
- if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+ if (syn_data &&
+ tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD))
goto fastopen;
if (foc->len >= 0 && /* Client presents or requests a cookie */
- tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
+ tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc) &&
foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
foc->len == valid_foc.len &&
!memcmp(foc->val, valid_foc.val, foc->len)) {
@@ -331,6 +380,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
struct tcp_fastopen_cookie *cookie)
{
unsigned long last_syn_loss = 0;
+ const struct dst_entry *dst;
int syn_loss = 0;
tcp_fastopen_cache_get(sk, mss, cookie, &syn_loss, &last_syn_loss);
@@ -348,7 +398,9 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
return false;
}
- if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
+ dst = __sk_dst_get(sk);
+
+ if (tcp_fastopen_no_cookie(sk, dst, TFO_CLIENT_NO_COOKIE)) {
cookie->len = -1;
return true;
}
@@ -402,25 +454,16 @@ EXPORT_SYMBOL(tcp_fastopen_defer_connect);
* TFO connection with data exchanges.
*/
-/* Default to 1hr */
-unsigned int sysctl_tcp_fastopen_blackhole_timeout __read_mostly = 60 * 60;
-static atomic_t tfo_active_disable_times __read_mostly = ATOMIC_INIT(0);
-static unsigned long tfo_active_disable_stamp __read_mostly;
-
/* Disable active TFO and record current jiffies and
* tfo_active_disable_times
*/
void tcp_fastopen_active_disable(struct sock *sk)
{
- atomic_inc(&tfo_active_disable_times);
- tfo_active_disable_stamp = jiffies;
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENBLACKHOLE);
-}
+ struct net *net = sock_net(sk);
-/* Reset tfo_active_disable_times to 0 */
-void tcp_fastopen_active_timeout_reset(void)
-{
- atomic_set(&tfo_active_disable_times, 0);
+ atomic_inc(&net->ipv4.tfo_active_disable_times);
+ net->ipv4.tfo_active_disable_stamp = jiffies;
+ NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE);
}
/* Calculate timeout for tfo active disable
@@ -429,17 +472,18 @@ void tcp_fastopen_active_timeout_reset(void)
*/
bool tcp_fastopen_active_should_disable(struct sock *sk)
{
- int tfo_da_times = atomic_read(&tfo_active_disable_times);
- int multiplier;
+ unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
+ int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
unsigned long timeout;
+ int multiplier;
if (!tfo_da_times)
return false;
/* Limit timout to max: 2^6 * initial timeout */
multiplier = 1 << min(tfo_da_times - 1, 6);
- timeout = multiplier * sysctl_tcp_fastopen_blackhole_timeout * HZ;
- if (time_before(jiffies, tfo_active_disable_stamp + timeout))
+ timeout = multiplier * tfo_bh_timeout * HZ;
+ if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
return true;
/* Mark check bit so we can check for successful active TFO
@@ -458,27 +502,25 @@ bool tcp_fastopen_active_should_disable(struct sock *sk)
void tcp_fastopen_active_disable_ofo_check(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct rb_node *p;
- struct sk_buff *skb;
struct dst_entry *dst;
+ struct sk_buff *skb;
if (!tp->syn_fastopen)
return;
if (!tp->data_segs_in) {
- p = rb_first(&tp->out_of_order_queue);
- if (p && !rb_next(p)) {
- skb = rb_entry(p, struct sk_buff, rbnode);
+ skb = skb_rb_first(&tp->out_of_order_queue);
+ if (skb && !skb_rb_next(skb)) {
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
tcp_fastopen_active_disable(sk);
return;
}
}
} else if (tp->syn_fastopen_ch &&
- atomic_read(&tfo_active_disable_times)) {
+ atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) {
dst = sk_dst_get(sk);
if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK)))
- tcp_fastopen_active_timeout_reset();
+ atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0);
dst_release(dst);
}
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 887585045b27..dabbf1d392fb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -76,25 +76,10 @@
#include <linux/ipsec.h>
#include <asm/unaligned.h>
#include <linux/errqueue.h>
+#include <trace/events/tcp.h>
+#include <linux/static_key.h>
-int sysctl_tcp_fack __read_mostly;
-int sysctl_tcp_max_reordering __read_mostly = 300;
-int sysctl_tcp_dsack __read_mostly = 1;
-int sysctl_tcp_app_win __read_mostly = 31;
-int sysctl_tcp_adv_win_scale __read_mostly = 1;
-EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
-
-/* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 1000;
-
-int sysctl_tcp_stdurg __read_mostly;
-int sysctl_tcp_rfc1337 __read_mostly;
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
-int sysctl_tcp_frto __read_mostly = 2;
-int sysctl_tcp_min_rtt_wlen __read_mostly = 300;
-int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
-int sysctl_tcp_early_retrans __read_mostly = 3;
-int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
@@ -335,7 +320,7 @@ static void tcp_sndbuf_expand(struct sock *sk)
sndmem *= nr_segs * per_mss;
if (sk->sk_sndbuf < sndmem)
- sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]);
+ sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]);
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -368,8 +353,8 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
- int truesize = tcp_win_from_space(skb->truesize) >> 1;
- int window = tcp_win_from_space(sysctl_tcp_rmem[2]) >> 1;
+ int truesize = tcp_win_from_space(sk, skb->truesize) >> 1;
+ int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
while (tp->rcv_ssthresh <= window) {
if (truesize <= skb->len)
@@ -394,7 +379,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
/* Check #2. Increase window, if skb with such overhead
* will fit to rcvbuf in future.
*/
- if (tcp_win_from_space(skb->truesize) <= skb->len)
+ if (tcp_win_from_space(sk, skb->truesize) <= skb->len)
incr = 2 * tp->advmss;
else
incr = __tcp_grow_window(sk, skb);
@@ -420,11 +405,11 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
/* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
* Allow enough cushion so that sender is not limited by our window
*/
- if (sysctl_tcp_moderate_rcvbuf)
+ if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)
rcvmem <<= 2;
if (sk->sk_rcvbuf < rcvmem)
- sk->sk_rcvbuf = min(rcvmem, sysctl_tcp_rmem[2]);
+ sk->sk_rcvbuf = min(rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
}
/* 4. Try to fixup all. It is made immediately after connection enters
@@ -432,6 +417,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
*/
void tcp_init_buffer_space(struct sock *sk)
{
+ int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
struct tcp_sock *tp = tcp_sk(sk);
int maxwin;
@@ -450,14 +436,14 @@ void tcp_init_buffer_space(struct sock *sk)
if (tp->window_clamp >= maxwin) {
tp->window_clamp = maxwin;
- if (sysctl_tcp_app_win && maxwin > 4 * tp->advmss)
+ if (tcp_app_win && maxwin > 4 * tp->advmss)
tp->window_clamp = max(maxwin -
- (maxwin >> sysctl_tcp_app_win),
+ (maxwin >> tcp_app_win),
4 * tp->advmss);
}
/* Force reservation of one segment. */
- if (sysctl_tcp_app_win &&
+ if (tcp_app_win &&
tp->window_clamp > 2 * tp->advmss &&
tp->window_clamp + tp->advmss > maxwin)
tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss);
@@ -471,15 +457,16 @@ static void tcp_clamp_window(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct net *net = sock_net(sk);
icsk->icsk_ack.quick =