aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-07-09 18:24:39 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2013-07-09 18:24:39 -0700
commit496322bc91e35007ed754184dcd447a02b6dd685 (patch)
treef5298d0a74c0a6e65c0e98050b594b8d020904c1 /net
parent2e17c5a97e231f3cb426f4b7895eab5be5c5442e (diff)
parent56e0ef527b184b3de2d7f88c6190812b2b2ac6bf (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "This is a re-do of the net-next pull request for the current merge window. The only difference from the one I made the other day is that this has Eliezer's interface renames and the timeout handling changes made based upon your feedback, as well as a few bug fixes that have trickeled in. Highlights: 1) Low latency device polling, eliminating the cost of interrupt handling and context switches. Allows direct polling of a network device from socket operations, such as recvmsg() and poll(). Currently ixgbe, mlx4, and bnx2x support this feature. Full high level description, performance numbers, and design in commit 0a4db187a999 ("Merge branch 'll_poll'") From Eliezer Tamir. 2) With the routing cache removed, ip_check_mc_rcu() gets exercised more than ever before in the case where we have lots of multicast addresses. Use a hash table instead of a simple linked list, from Eric Dumazet. 3) Add driver for Atheros CQA98xx 802.11ac wireless devices, from Bartosz Markowski, Janusz Dziedzic, Kalle Valo, Marek Kwaczynski, Marek Puzyniak, Michal Kazior, and Sujith Manoharan. 4) Support reporting the TUN device persist flag to userspace, from Pavel Emelyanov. 5) Allow controlling network device VF link state using netlink, from Rony Efraim. 6) Support GRE tunneling in openvswitch, from Pravin B Shelar. 7) Adjust SOCK_MIN_RCVBUF and SOCK_MIN_SNDBUF for modern times, from Daniel Borkmann and Eric Dumazet. 8) Allow controlling of TCP quickack behavior on a per-route basis, from Cong Wang. 9) Several bug fixes and improvements to vxlan from Stephen Hemminger, Pravin B Shelar, and Mike Rapoport. In particular, support receiving on multiple UDP ports. 10) Major cleanups, particular in the area of debugging and cookie lifetime handline, to the SCTP protocol code. From Daniel Borkmann. 11) Allow packets to cross network namespaces when traversing tunnel devices. From Nicolas Dichtel. 12) Allow monitoring netlink traffic via AF_PACKET sockets, in a manner akin to how we monitor real network traffic via ptype_all. From Daniel Borkmann. 13) Several bug fixes and improvements for the new alx device driver, from Johannes Berg. 14) Fix scalability issues in the netem packet scheduler's time queue, by using an rbtree. From Eric Dumazet. 15) Several bug fixes in TCP loss recovery handling, from Yuchung Cheng. 16) Add support for GSO segmentation of MPLS packets, from Simon Horman. 17) Make network notifiers have a real data type for the opaque pointer that's passed into them. Use this to properly handle network device flag changes in arp_netdev_event(). From Jiri Pirko and Timo Teräs. 18) Convert several drivers over to module_pci_driver(), from Peter Huewe. 19) tcp_fixup_rcvbuf() can loop 500 times over loopback, just use a O(1) calculation instead. From Eric Dumazet. 20) Support setting of explicit tunnel peer addresses in ipv6, just like ipv4. From Nicolas Dichtel. 21) Protect x86 BPF JIT against spraying attacks, from Eric Dumazet. 22) Prevent a single high rate flow from overruning an individual cpu during RX packet processing via selective flow shedding. From Willem de Bruijn. 23) Don't use spinlocks in TCP md5 signing fast paths, from Eric Dumazet. 24) Don't just drop GSO packets which are above the TBF scheduler's burst limit, chop them up so they are in-bounds instead. Also from Eric Dumazet. 25) VLAN offloads are missed when configured on top of a bridge, fix from Vlad Yasevich. 26) Support IPV6 in ping sockets. From Lorenzo Colitti. 27) Receive flow steering targets should be updated at poll() time too, from David Majnemer. 28) Fix several corner case regressions in PMTU/redirect handling due to the routing cache removal, from Timo Teräs. 29) We have to be mindful of ipv4 mapped ipv6 sockets in upd_v6_push_pending_frames(). From Hannes Frederic Sowa. 30) Fix L2TP sequence number handling bugs, from James Chapman." * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1214 commits) drivers/net: caif: fix wrong rtnl_is_locked() usage drivers/net: enic: release rtnl_lock on error-path vhost-net: fix use-after-free in vhost_net_flush net: mv643xx_eth: do not use port number as platform device id net: sctp: confirm route during forward progress virtio_net: fix race in RX VQ processing virtio: support unlocked queue poll net/cadence/macb: fix bug/typo in extracting gem_irq_read_clear bit Documentation: Fix references to defunct linux-net@vger.kernel.org net/fs: change busy poll time accounting net: rename low latency sockets functions to busy poll bridge: fix some kernel warning in multicast timer sfc: Fix memory leak when discarding scattered packets sit: fix tunnel update via netlink dt:net:stmmac: Add dt specific phy reset callback support. dt:net:stmmac: Add support to dwmac version 3.610 and 3.710 dt:net:stmmac: Allocate platform data only if its NULL. net:stmmac: fix memleak in the open method ipv6: rt6_check_neigh should successfully verify neigh if no NUD information are available net: ipv6: fix wrong ping_v6_sendmsg return value ...
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c2
-rw-r--r--net/Kconfig17
-rw-r--r--net/Makefile1
-rw-r--r--net/appletalk/aarp.c2
-rw-r--r--net/appletalk/ddp.c2
-rw-r--r--net/atm/clip.c8
-rw-r--r--net/atm/mpc.c6
-rw-r--r--net/ax25/af_ax25.c6
-rw-r--r--net/ax25/sysctl_net_ax25.c2
-rw-r--r--net/batman-adv/Makefile1
-rw-r--r--net/batman-adv/bat_iv_ogm.c123
-rw-r--r--net/batman-adv/bridge_loop_avoidance.c94
-rw-r--r--net/batman-adv/bridge_loop_avoidance.h12
-rw-r--r--net/batman-adv/distributed-arp-table.c82
-rw-r--r--net/batman-adv/hard-interface.c98
-rw-r--r--net/batman-adv/icmp_socket.c4
-rw-r--r--net/batman-adv/main.c1
-rw-r--r--net/batman-adv/main.h18
-rw-r--r--net/batman-adv/network-coding.c22
-rw-r--r--net/batman-adv/network-coding.h6
-rw-r--r--net/batman-adv/originator.c6
-rw-r--r--net/batman-adv/originator.h2
-rw-r--r--net/batman-adv/ring_buffer.c51
-rw-r--r--net/batman-adv/ring_buffer.h27
-rw-r--r--net/batman-adv/routing.c64
-rw-r--r--net/batman-adv/routing.h1
-rw-r--r--net/batman-adv/send.c36
-rw-r--r--net/batman-adv/send.h6
-rw-r--r--net/batman-adv/soft-interface.c6
-rw-r--r--net/batman-adv/translation-table.c74
-rw-r--r--net/batman-adv/translation-table.h2
-rw-r--r--net/batman-adv/types.h6
-rw-r--r--net/batman-adv/unicast.c2
-rw-r--r--net/batman-adv/vis.c19
-rw-r--r--net/bluetooth/hci_core.c192
-rw-r--r--net/bluetooth/hci_event.c71
-rw-r--r--net/bluetooth/hidp/core.c14
-rw-r--r--net/bluetooth/l2cap_core.c121
-rw-r--r--net/bluetooth/l2cap_sock.c4
-rw-r--r--net/bluetooth/mgmt.c229
-rw-r--r--net/bridge/br_device.c21
-rw-r--r--net/bridge/br_fdb.c5
-rw-r--r--net/bridge/br_forward.c14
-rw-r--r--net/bridge/br_if.c2
-rw-r--r--net/bridge/br_input.c15
-rw-r--r--net/bridge/br_mdb.c2
-rw-r--r--net/bridge/br_multicast.c74
-rw-r--r--net/bridge/br_netfilter.c4
-rw-r--r--net/bridge/br_netlink.c10
-rw-r--r--net/bridge/br_notify.c2
-rw-r--r--net/bridge/br_private.h9
-rw-r--r--net/bridge/br_sysfs_br.c26
-rw-r--r--net/bridge/br_sysfs_if.c4
-rw-r--r--net/bridge/netfilter/ebt_ulog.c6
-rw-r--r--net/bridge/netfilter/ebtables.c6
-rw-r--r--net/caif/caif_dev.c4
-rw-r--r--net/caif/caif_usb.c4
-rw-r--r--net/can/af_can.c4
-rw-r--r--net/can/bcm.c4
-rw-r--r--net/can/gw.c4
-rw-r--r--net/can/raw.c4
-rw-r--r--net/core/datagram.c5
-rw-r--r--net/core/dev.c238
-rw-r--r--net/core/drop_monitor.c4
-rw-r--r--net/core/dst.c2
-rw-r--r--net/core/ethtool.c24
-rw-r--r--net/core/fib_rules.c4
-rw-r--r--net/core/gen_estimator.c12
-rw-r--r--net/core/gen_stats.c22
-rw-r--r--net/core/link_watch.c3
-rw-r--r--net/core/neighbour.c34
-rw-r--r--net/core/net-procfs.c16
-rw-r--r--net/core/netpoll.c16
-rw-r--r--net/core/netprio_cgroup.c2
-rw-r--r--net/core/pktgen.c81
-rw-r--r--net/core/rtnetlink.c32
-rw-r--r--net/core/skbuff.c69
-rw-r--r--net/core/sock.c26
-rw-r--r--net/core/sysctl_net_core.c139
-rw-r--r--net/decnet/af_decnet.c4
-rw-r--r--net/decnet/dn_dev.c6
-rw-r--r--net/decnet/sysctl_net_decnet.c6
-rw-r--r--net/ieee802154/6lowpan.c5
-rw-r--r--net/ipv4/Kconfig11
-rw-r--r--net/ipv4/Makefile7
-rw-r--r--net/ipv4/af_inet.c26
-rw-r--r--net/ipv4/ah4.c7
-rw-r--r--net/ipv4/arp.c8
-rw-r--r--net/ipv4/devinet.c9
-rw-r--r--net/ipv4/esp4.c7
-rw-r--r--net/ipv4/fib_frontend.c4
-rw-r--r--net/ipv4/fib_semantics.c3
-rw-r--r--net/ipv4/gre.c253
-rw-r--r--net/ipv4/gre_demux.c414
-rw-r--r--net/ipv4/gre_offload.c127
-rw-r--r--net/ipv4/icmp.c51
-rw-r--r--net/ipv4/igmp.c79
-rw-r--r--net/ipv4/inet_fragment.c2
-rw-r--r--net/ipv4/ip_gre.c258
-rw-r--r--net/ipv4/ip_tunnel.c177
-rw-r--r--net/ipv4/ip_tunnel_core.c122
-rw-r--r--net/ipv4/ip_vti.c7
-rw-r--r--net/ipv4/ipcomp.c7
-rw-r--r--net/ipv4/ipip.c20
-rw-r--r--net/ipv4/ipmr.c4
-rw-r--r--net/ipv4/netfilter/Kconfig2
-rw-r--r--net/ipv4/netfilter/ipt_MASQUERADE.c7
-rw-r--r--net/ipv4/netfilter/ipt_ULOG.c6
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c2
-rw-r--r--net/ipv4/ping.c641
-rw-r--r--net/ipv4/proc.c1
-rw-r--r--net/ipv4/route.c144
-rw-r--r--net/ipv4/sysctl_net_ipv4.c31
-rw-r--r--net/ipv4/tcp.c344
-rw-r--r--net/ipv4/tcp_input.c517
-rw-r--r--net/ipv4/tcp_ipv4.c78
-rw-r--r--net/ipv4/tcp_minisocks.c6
-rw-r--r--net/ipv4/tcp_offload.c332
-rw-r--r--net/ipv4/tcp_output.c39
-rw-r--r--net/ipv4/udp.c90
-rw-r--r--net/ipv4/udp_offload.c100
-rw-r--r--net/ipv4/xfrm4_tunnel.c2
-rw-r--r--net/ipv6/Makefile2
-rw-r--r--net/ipv6/addrconf.c304
-rw-r--r--net/ipv6/addrconf_core.c1
-rw-r--r--net/ipv6/af_inet6.c12
-rw-r--r--net/ipv6/datagram.c27
-rw-r--r--net/ipv6/exthdrs_core.c2
-rw-r--r--net/ipv6/icmp.c23
-rw-r--r--net/ipv6/ip6_offload.c1
-rw-r--r--net/ipv6/ip6_output.c16
-rw-r--r--net/ipv6/ip6mr.c2
-rw-r--r--net/ipv6/mcast.c75
-rw-r--r--net/ipv6/mip6.c6
-rw-r--r--net/ipv6/ndisc.c11
-rw-r--r--net/ipv6/netfilter/ip6t_MASQUERADE.c6
-rw-r--r--net/ipv6/output_core.c3
-rw-r--r--net/ipv6/ping.c277
-rw-r--r--net/ipv6/raw.c48
-rw-r--r--net/ipv6/route.c24
-rw-r--r--net/ipv6/sit.c211
-rw-r--r--net/ipv6/sysctl_net_ipv6.c4
-rw-r--r--net/ipv6/tcp_ipv6.c2
-rw-r--r--net/ipv6/udp.c62
-rw-r--r--net/ipv6/udp_offload.c3
-rw-r--r--net/ipx/af_ipx.c2
-rw-r--r--net/irda/irsysctl.c6
-rw-r--r--net/iucv/af_iucv.c2
-rw-r--r--net/l2tp/l2tp_core.c114
-rw-r--r--net/l2tp/l2tp_core.h5
-rw-r--r--net/l2tp/l2tp_ppp.c3
-rw-r--r--net/mac80211/aes_ccm.c6
-rw-r--r--net/mac80211/cfg.c67
-rw-r--r--net/mac80211/debugfs_netdev.c15
-rw-r--r--net/mac80211/driver-ops.h3
-rw-r--r--net/mac80211/ht.c8
-rw-r--r--net/mac80211/ibss.c114
-rw-r--r--net/mac80211/ieee80211_i.h37
-rw-r--r--net/mac80211/iface.c34
-rw-r--r--net/mac80211/key.c24
-rw-r--r--net/mac80211/key.h15
-rw-r--r--net/mac80211/main.c7
-rw-r--r--net/mac80211/mesh.c107
-rw-r--r--net/mac80211/mesh.h7
-rw-r--r--net/mac80211/mesh_plink.c8
-rw-r--r--net/mac80211/mlme.c436
-rw-r--r--net/mac80211/rate.c8
-rw-r--r--net/mac80211/rx.c56
-rw-r--r--net/mac80211/scan.c9
-rw-r--r--net/mac80211/sta_info.c8
-rw-r--r--net/mac80211/sta_info.h9
-rw-r--r--net/mac80211/tx.c11
-rw-r--r--net/mac80211/util.c41
-rw-r--r--net/mac80211/vht.c2
-rw-r--r--net/mac80211/wep.c48
-rw-r--r--net/mac80211/wpa.c68
-rw-r--r--net/mpls/Kconfig9
-rw-r--r--net/mpls/Makefile4
-rw-r--r--net/mpls/mpls_gso.c108
-rw-r--r--net/netfilter/core.c21
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c35
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c4
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c35
-rw-r--r--net/netfilter/ipvs/ip_vs_dh.c10
-rw-r--r--net/netfilter/ipvs/ip_vs_lblc.c14
-rw-r--r--net/netfilter/ipvs/ip_vs_lblcr.c14
-rw-r--r--net/netfilter/ipvs/ip_vs_lc.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_nq.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_sctp.c860
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_tcp.c14
-rw-r--r--net/netfilter/ipvs/ip_vs_rr.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_sed.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_sh.c108
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c19
-rw-r--r--net/netfilter/ipvs/ip_vs_wlc.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_wrr.c3
-rw-r--r--net/netfilter/nf_conntrack_ftp.c73
-rw-r--r--net/netfilter/nf_conntrack_netlink.c30
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c6
-rw-r--r--net/netfilter/nf_conntrack_standalone.c4
-rw-r--r--net/netfilter/nf_log.c6
-rw-r--r--net/netfilter/nf_nat_helper.c2
-rw-r--r--net/netfilter/nfnetlink_cthelper.c16
-rw-r--r--net/netfilter/nfnetlink_cttimeout.c6
-rw-r--r--net/netfilter/nfnetlink_queue_core.c47
-rw-r--r--net/netfilter/xt_CT.c10
-rw-r--r--net/netfilter/xt_TEE.c2
-rw-r--r--net/netfilter/xt_rateest.c2
-rw-r--r--net/netfilter/xt_socket.c96
-rw-r--r--net/netlabel/netlabel_unlabeled.c7
-rw-r--r--net/netlink/af_netlink.c178
-rw-r--r--net/netlink/af_netlink.h1
-rw-r--r--net/netrom/af_netrom.c2
-rw-r--r--net/netrom/sysctl_net_netrom.c2
-rw-r--r--net/nfc/core.c224
-rw-r--r--net/nfc/hci/core.c75
-rw-r--r--net/nfc/llcp.h3
-rw-r--r--net/nfc/llcp_commands.c22
-rw-r--r--net/nfc/llcp_core.c16
-rw-r--r--net/nfc/llcp_sock.c19
-rw-r--r--net/nfc/nci/Kconfig10
-rw-r--r--net/nfc/nci/Makefile4
-rw-r--r--net/nfc/nci/core.c37
-rw-r--r--net/nfc/nci/data.c2
-rw-r--r--net/nfc/nci/spi.c378
-rw-r--r--net/nfc/netlink.c183
-rw-r--r--net/nfc/nfc.h11
-rw-r--r--net/openvswitch/Kconfig14
-rw-r--r--net/openvswitch/Makefile3
-rw-r--r--net/openvswitch/actions.c8
-rw-r--r--net/openvswitch/datapath.c371
-rw-r--r--net/openvswitch/datapath.h4
-rw-r--r--net/openvswitch/dp_notify.c2
-rw-r--r--net/openvswitch/flow.c211
-rw-r--r--net/openvswitch/flow.h47
-rw-r--r--net/openvswitch/vport-gre.c275
-rw-r--r--net/openvswitch/vport-internal_dev.c3
-rw-r--r--net/openvswitch/vport-netdev.c9
-rw-r--r--net/openvswitch/vport-netdev.h1
-rw-r--r--net/openvswitch/vport.c34
-rw-r--r--net/openvswitch/vport.h23
-rw-r--r--net/packet/af_packet.c5
-rw-r--r--net/phonet/pn_dev.c4
-rw-r--r--net/phonet/sysctl.c4
-rw-r--r--net/rds/ib_sysctl.c2
-rw-r--r--net/rds/iw_sysctl.c2
-rw-r--r--net/rds/sysctl.c2
-rw-r--r--net/rose/af_rose.c6
-rw-r--r--net/rose/sysctl_net_rose.c2
-rw-r--r--net/sched/act_mirred.c2
-rw-r--r--net/sched/sch_cbq.c2
-rw-r--r--net/sched/sch_drr.c2
-rw-r--r--net/sched/sch_generic.c44
-rw-r--r--net/sched/sch_hfsc.c2
-rw-r--r--net/sched/sch_htb.c261
-rw-r--r--net/sched/sch_netem.c111
-rw-r--r--net/sched/sch_qfq.c2
-rw-r--r--net/sched/sch_tbf.c47
-rw-r--r--net/sctp/Kconfig11
-rw-r--r--net/sctp/associola.c84
-rw-r--r--net/sctp/bind_addr.c2
-rw-r--r--net/sctp/chunk.c7
-rw-r--r--net/sctp/debug.c4
-rw-r--r--net/sctp/endpointola.c25
-rw-r--r--net/sctp/input.c12
-rw-r--r--net/sctp/inqueue.c9
-rw-r--r--net/sctp/ipv6.c29
-rw-r--r--net/sctp/output.c40
-rw-r--r--net/sctp/outqueue.c214
-rw-r--r--net/sctp/proc.c12
-rw-r--r--net/sctp/protocol.c56
-rw-r--r--net/sctp/sm_make_chunk.c54
-rw-r--r--net/sctp/sm_sideeffect.c107
-rw-r--r--net/sctp/sm_statefuns.c85
-rw-r--r--net/sctp/socket.c289
-rw-r--r--net/sctp/sysctl.c10
-rw-r--r--net/sctp/transport.c51
-rw-r--r--net/sctp/tsnmap.c10
-rw-r--r--net/sctp/ulpevent.c10
-rw-r--r--net/socket.c23
-rw-r--r--net/sunrpc/sysctl.c10
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma.c8
-rw-r--r--net/sunrpc/xprtrdma/transport.c4
-rw-r--r--net/sunrpc/xprtsock.c4
-rw-r--r--net/tipc/Makefile3
-rw-r--r--net/tipc/bcast.c3
-rw-r--r--net/tipc/bcast.h3
-rw-r--r--net/tipc/config.c119
-rw-r--r--net/tipc/core.c22
-rw-r--r--net/tipc/core.h17
-rw-r--r--net/tipc/discover.c7
-rw-r--r--net/tipc/eth_media.c19
-rw-r--r--net/tipc/ib_media.c17
-rw-r--r--net/tipc/link.c88
-rw-r--r--net/tipc/msg.c19
-rw-r--r--net/tipc/msg.h8
-rw-r--r--net/tipc/name_table.c10
-rw-r--r--net/tipc/name_table.h11
-rw-r--r--net/tipc/node_subscr.c2
-rw-r--r--net/tipc/port.c320
-rw-r--r--net/tipc/port.h85
-rw-r--r--net/tipc/server.c596
-rw-r--r--net/tipc/server.h94
-rw-r--r--net/tipc/socket.c146
-rw-r--r--net/tipc/subscr.c348
-rw-r--r--net/tipc/subscr.h21
-rw-r--r--net/tipc/sysctl.c64
-rw-r--r--net/unix/sysctl_net_unix.c2
-rw-r--r--net/vmw_vsock/af_vsock.c55
-rw-r--r--net/vmw_vsock/vmci_transport.c18
-rw-r--r--net/wireless/chan.c57
-rw-r--r--net/wireless/core.c270
-rw-r--r--net/wireless/core.h123
-rw-r--r--net/wireless/debugfs.c4
-rw-r--r--net/wireless/ibss.c16
-rw-r--r--net/wireless/mesh.c15
-rw-r--r--net/wireless/mlme.c433
-rw-r--r--net/wireless/nl80211.c814
-rw-r--r--net/wireless/reg.c138
-rw-r--r--net/wireless/scan.c51
-rw-r--r--net/wireless/sme.c652
-rw-r--r--net/wireless/sysfs.c8
-rw-r--r--net/wireless/trace.h46
-rw-r--r--net/wireless/util.c39
-rw-r--r--net/wireless/wext-compat.c22
-rw-r--r--net/wireless/wext-sme.c49
-rw-r--r--net/x25/af_x25.c17
-rw-r--r--net/xfrm/xfrm_input.c5
-rw-r--r--net/xfrm/xfrm_output.c9
-rw-r--r--net/xfrm/xfrm_policy.c2
-rw-r--r--net/xfrm/xfrm_proc.c1
331 files changed, 11095 insertions, 7956 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 9424f3718ea7..2fb2d88e8c2e 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -341,7 +341,7 @@ static void __vlan_device_event(struct net_device *dev, unsigned long event)
static int vlan_device_event(struct notifier_block *unused, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct vlan_group *grp;
struct vlan_info *vlan_info;
int i, flgs;
diff --git a/net/Kconfig b/net/Kconfig
index 6dfe1c636a80..37702491abe9 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -219,6 +219,7 @@ source "net/batman-adv/Kconfig"
source "net/openvswitch/Kconfig"
source "net/vmw_vsock/Kconfig"
source "net/netlink/Kconfig"
+source "net/mpls/Kconfig"
config RPS
boolean
@@ -243,6 +244,10 @@ config NETPRIO_CGROUP
Cgroup subsystem for use in assigning processes to network priorities on
a per-interface basis
+config NET_LL_RX_POLL
+ boolean
+ default y
+
config BQL
boolean
depends on SYSFS
@@ -260,6 +265,18 @@ config BPF_JIT
packet sniffing (libpcap/tcpdump). Note : Admin should enable
this feature changing /proc/sys/net/core/bpf_jit_enable
+config NET_FLOW_LIMIT
+ boolean
+ depends on RPS
+ default y
+ ---help---
+ The network stack has to drop packets when a receive processing CPU's
+ backlog reaches netdev_max_backlog. If a few out of many active flows
+ generate the vast majority of load, drop their traffic earlier to
+ maintain capacity for the other flows. This feature provides servers
+ with many clients some protection against DoS by a single (spoofed)
+ flow that greatly exceeds average workload.
+
menu "Network testing"
config NET_PKTGEN
diff --git a/net/Makefile b/net/Makefile
index 091e7b04f301..9492e8cb64e9 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -70,3 +70,4 @@ obj-$(CONFIG_BATMAN_ADV) += batman-adv/
obj-$(CONFIG_NFC) += nfc/
obj-$(CONFIG_OPENVSWITCH) += openvswitch/
obj-$(CONFIG_VSOCKETS) += vmw_vsock/
+obj-$(CONFIG_NET_MPLS_GSO) += mpls/
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index 173a2e82f486..690356fa52b9 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -332,7 +332,7 @@ static void aarp_expire_timeout(unsigned long unused)
static int aarp_device_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
int ct;
if (!net_eq(dev_net(dev), &init_net))
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index ef12839a7cfe..7fee50d637f9 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -644,7 +644,7 @@ static inline void atalk_dev_down(struct net_device *dev)
static int ddp_device_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
if (!net_eq(dev_net(dev), &init_net))
return NOTIFY_DONE;
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 8ae3a7879335..8215f7cb170b 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -539,9 +539,9 @@ static int clip_create(int number)
}
static int clip_device_event(struct notifier_block *this, unsigned long event,
- void *arg)
+ void *ptr)
{
- struct net_device *dev = arg;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
if (!net_eq(dev_net(dev), &init_net))
return NOTIFY_DONE;
@@ -575,6 +575,7 @@ static int clip_inet_event(struct notifier_block *this, unsigned long event,
void *ifa)
{
struct in_device *in_dev;
+ struct netdev_notifier_info info;
in_dev = ((struct in_ifaddr *)ifa)->ifa_dev;
/*
@@ -583,7 +584,8 @@ static int clip_inet_event(struct notifier_block *this, unsigned long event,
*/
if (event != NETDEV_UP)
return NOTIFY_DONE;
- return clip_device_event(this, NETDEV_CHANGE, in_dev->dev);
+ netdev_notifier_info_init(&info, in_dev->dev);
+ return clip_device_event(this, NETDEV_CHANGE, &info);
}
static struct notifier_block clip_dev_notifier = {
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index d4cc1be5c364..3af12755cd04 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -998,14 +998,12 @@ int msg_to_mpoad(struct k_message *mesg, struct mpoa_client *mpc)
}
static int mpoa_event_listener(struct notifier_block *mpoa_notifier,
- unsigned long event, void *dev_ptr)
+ unsigned long event, void *ptr)
{
- struct net_device *dev;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct mpoa_client *mpc;
struct lec_priv *priv;
- dev = dev_ptr;
-
if (!net_eq(dev_net(dev), &init_net))
return NOTIFY_DONE;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index e277e38f736b..4b4d2b779ec1 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -111,9 +111,9 @@ again:
* Handle device status changes.
*/
static int ax25_device_event(struct notifier_block *this, unsigned long event,
- void *ptr)
+ void *ptr)
{
- struct net_device *dev = (struct net_device *)ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
if (!net_eq(dev_net(dev), &init_net))
return NOTIFY_DONE;
@@ -1974,7 +1974,7 @@ static struct packet_type ax25_packet_type __read_mostly = {
};
static struct notifier_block ax25_dev_notifier = {
- .notifier_call =ax25_device_event,
+ .notifier_call = ax25_device_event,
};
static int __init ax25_init(void)
diff --git a/net/ax25/sysctl_net_ax25.c b/net/ax25/sysctl_net_ax25.c
index d5744b752511..919a5ce47515 100644
--- a/net/ax25/sysctl_net_ax25.c
+++ b/net/ax25/sysctl_net_ax25.c
@@ -29,7 +29,7 @@ static int min_proto[1], max_proto[] = { AX25_PROTO_MAX };
static int min_ds_timeout[1], max_ds_timeout[] = {65535000};
#endif
-static const ctl_table ax25_param_table[] = {
+static const struct ctl_table ax25_param_table[] = {
{
.procname = "ip_default_mode",
.maxlen = sizeof(int),
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index acbac2a9c62f..489bb36f1b94 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -32,7 +32,6 @@ batman-adv-y += icmp_socket.o
batman-adv-y += main.o
batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o
batman-adv-y += originator.o
-batman-adv-y += ring_buffer.o
batman-adv-y += routing.o
batman-adv-y += send.o
batman-adv-y += soft-interface.o
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index f680ee101878..62da5278014a 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -19,7 +19,6 @@
#include "main.h"
#include "translation-table.h"
-#include "ring_buffer.h"
#include "originator.h"
#include "routing.h"
#include "gateway_common.h"
@@ -30,6 +29,49 @@
#include "network-coding.h"
/**
+ * batadv_ring_buffer_set - update the ring buffer with the given value
+ * @lq_recv: pointer to the ring buffer
+ * @lq_index: index to store the value at
+ * @value: value to store in the ring buffer
+ */
+static void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index,
+ uint8_t value)
+{
+ lq_recv[*lq_index] = value;
+ *lq_index = (*lq_index + 1) % BATADV_TQ_GLOBAL_WINDOW_SIZE;
+}
+
+/**
+ * batadv_ring_buffer_set - compute the average of all non-zero values stored
+ * in the given ring buffer
+ * @lq_recv: pointer to the ring buffer
+ *
+ * Returns computed average value.
+ */
+static uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[])
+{
+ const uint8_t *ptr;
+ uint16_t count = 0, i = 0, sum = 0;
+
+ ptr = lq_recv;
+
+ while (i < BATADV_TQ_GLOBAL_WINDOW_SIZE) {
+ if (*ptr != 0) {
+ count++;
+ sum += *ptr;
+ }
+
+ i++;
+ ptr++;
+ }
+
+ if (count == 0)
+ return 0;
+
+ return (uint8_t)(sum / count);
+}
+
+/*
* batadv_dup_status - duplicate status
* @BATADV_NO_DUP: the packet is a duplicate
* @BATADV_ORIG_DUP: OGM is a duplicate in the originator (but not for the
@@ -48,12 +90,11 @@ static struct batadv_neigh_node *
batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface,
const uint8_t *neigh_addr,
struct batadv_orig_node *orig_node,
- struct batadv_orig_node *orig_neigh, __be32 seqno)
+ struct batadv_orig_node *orig_neigh)
{
struct batadv_neigh_node *neigh_node;
- neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr,
- ntohl(seqno));
+ neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr);
if (!neigh_node)
goto out;
@@ -428,18 +469,16 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
else
skb_size = packet_len;
- skb_size += ETH_HLEN + NET_IP_ALIGN;
+ skb_size += ETH_HLEN;
- forw_packet_aggr->skb = dev_alloc_skb(skb_size);
+ forw_packet_aggr->skb = netdev_alloc_skb_ip_align(NULL, skb_size);
if (!forw_packet_aggr->skb) {
if (!own_packet)
atomic_inc(&bat_priv->batman_queue_left);
kfree(forw_packet_aggr);
goto out;
}
- skb_reserve(forw_packet_aggr->skb, ETH_HLEN + NET_IP_ALIGN);
-
- INIT_HLIST_NODE(&forw_packet_aggr->list);
+ skb_reserve(forw_packet_aggr->skb, ETH_HLEN);
skb_buff = skb_put(forw_packet_aggr->skb, packet_len);
forw_packet_aggr->packet_len = packet_len;
@@ -605,6 +644,41 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node,
if_incoming, 0, batadv_iv_ogm_fwd_send_time());
}
+/**
+ * batadv_iv_ogm_slide_own_bcast_window - bitshift own OGM broadcast windows for
+ * the given interface
+ * @hard_iface: the interface for which the windows have to be shifted
+ */
+static void
+batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface)
+{
+ struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+ struct batadv_hashtable *hash = bat_priv->orig_hash;
+ struct hlist_head *head;
+ struct batadv_orig_node *orig_node;
+ unsigned long *word;
+ uint32_t i;
+ size_t word_index;
+ uint8_t *w;
+
+ for (i = 0; i < hash->size; i++) {
+ head = &hash->table[i];
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
+ spin_lock_bh(&orig_node->ogm_cnt_lock);
+ word_index = hard_iface->if_num * BATADV_NUM_WORDS;
+ word = &(orig_node->bcast_own[word_index]);
+
+ batadv_bit_get_packet(bat_priv, word, 1, 0);
+ w = &orig_node->bcast_own_sum[hard_iface->if_num];
+ *w = bitmap_weight(word, BATADV_TQ_LOCAL_WINDOW_SIZE);
+ spin_unlock_bh(&orig_node->ogm_cnt_lock);
+ }
+ rcu_read_unlock();
+ }
+}
+
static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
{
struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
@@ -649,7 +723,7 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
batadv_ogm_packet->gw_flags = BATADV_NO_FLAGS;
}
- batadv_slide_own_bcast_window(hard_iface);
+ batadv_iv_ogm_slide_own_bcast_window(hard_iface);
batadv_iv_ogm_queue_add(bat_priv, hard_iface->bat_iv.ogm_buff,
hard_iface->bat_iv.ogm_buff_len, hard_iface, 1,
batadv_iv_ogm_emit_send_time(bat_priv));
@@ -685,7 +759,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
if (batadv_compare_eth(neigh_addr, ethhdr->h_source) &&
tmp_neigh_node->if_incoming == if_incoming &&
atomic_inc_not_zero(&tmp_neigh_node->refcount)) {
- if (neigh_node)
+ if (WARN(neigh_node, "too many matching neigh_nodes"))
batadv_neigh_node_free_ref(neigh_node);
neigh_node = tmp_neigh_node;
continue;
@@ -711,8 +785,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
neigh_node = batadv_iv_ogm_neigh_new(if_incoming,
ethhdr->h_source,
- orig_node, orig_tmp,
- batadv_ogm_packet->seqno);
+ orig_node, orig_tmp);
batadv_orig_node_free_ref(orig_tmp);
if (!neigh_node)
@@ -844,8 +917,7 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node,
neigh_node = batadv_iv_ogm_neigh_new(if_incoming,
orig_neigh_node->orig,
orig_neigh_node,
- orig_neigh_node,
- batadv_ogm_packet->seqno);
+ orig_neigh_node);
if (!neigh_node)
goto out;
@@ -1013,7 +1085,7 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
struct batadv_neigh_node *orig_neigh_router = NULL;
int has_directlink_flag;
int is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0;
- int is_broadcast = 0, is_bidirect;
+ int is_bidirect;
bool is_single_hop_neigh = false;
bool is_from_best_next_hop = false;
int sameseq, similar_ttl;
@@ -1077,19 +1149,9 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
if (batadv_compare_eth(batadv_ogm_packet->prev_sender,
hard_iface->net_dev->dev_addr))
is_my_oldorig = 1;
-
- if (is_broadcast_ether_addr(ethhdr->h_source))
- is_broadcast = 1;
}
rcu_read_unlock();
- if (batadv_ogm_packet->header.version != BATADV_COMPAT_VERSION) {
- batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
- "Drop packet: incompatible batman version (%i)\n",
- batadv_ogm_packet->header.version);
- return;
- }
-
if (is_my_addr) {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"Drop packet: received my own broadcast (sender: %pM)\n",
@@ -1097,13 +1159,6 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
return;
}
- if (is_broadcast) {
- batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
- "Drop packet: ignoring all packets with broadcast source addr (sender: %pM)\n",
- ethhdr->h_source);
- return;
- }
-
if (is_my_orig) {
unsigned long *word;
int offset;
@@ -1312,7 +1367,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb,
skb->len + ETH_HLEN);
packet_len = skb_headlen(skb);
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
packet_buff = skb->data;
batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff;
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index de27b3175cfd..e14531f1ce1c 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -180,7 +180,7 @@ static struct batadv_bla_claim
*/
static struct batadv_bla_backbone_gw *
batadv_backbone_hash_find(struct batadv_priv *bat_priv,
- uint8_t *addr, short vid)
+ uint8_t *addr, unsigned short vid)
{
struct batadv_hashtable *hash = bat_priv->bla.backbone_hash;
struct hlist_head *head;
@@ -257,7 +257,7 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw)
* @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...)
*/
static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac,
- short vid, int claimtype)
+ unsigned short vid, int claimtype)
{
struct sk_buff *skb;
struct ethhdr *ethhdr;
@@ -307,7 +307,8 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac,
*/
memcpy(ethhdr->h_source, mac, ETH_ALEN);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
- "bla_send_claim(): CLAIM %pM on vid %d\n", mac, vid);
+ "bla_send_claim(): CLAIM %pM on vid %d\n", mac,
+ BATADV_PRINT_VID(vid));
break;
case BATADV_CLAIM_TYPE_UNCLAIM:
/* unclaim frame
@@ -316,7 +317,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac,
memcpy(hw_src, mac, ETH_ALEN);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): UNCLAIM %pM on vid %d\n", mac,
- vid);
+ BATADV_PRINT_VID(vid));
break;
case BATADV_CLAIM_TYPE_ANNOUNCE:
/* announcement frame
@@ -325,7 +326,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac,
memcpy(hw_src, mac, ETH_ALEN);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): ANNOUNCE of %pM on vid %d\n",
- ethhdr->h_source, vid);
+ ethhdr->h_source, BATADV_PRINT_VID(vid));
break;
case BATADV_CLAIM_TYPE_REQUEST:
/* request frame
@@ -335,13 +336,15 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac,
memcpy(hw_src, mac, ETH_ALEN);
memcpy(ethhdr->h_dest, mac, ETH_ALEN);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
- "bla_send_claim(): REQUEST of %pM to %pMon vid %d\n",
- ethhdr->h_source, ethhdr->h_dest, vid);
+ "bla_send_claim(): REQUEST of %pM to %pM on vid %d\n",
+ ethhdr->h_source, ethhdr->h_dest,
+ BATADV_PRINT_VID(vid));
break;
}
- if (vid != -1)
- skb = vlan_insert_tag(skb, htons(ETH_P_8021Q), vid);
+ if (vid & BATADV_VLAN_HAS_TAG)
+ skb = vlan_insert_tag(skb, htons(ETH_P_8021Q),
+ vid & VLAN_VID_MASK);
skb_reset_mac_header(skb);
skb->protocol = eth_type_trans(skb, soft_iface);
@@ -367,7 +370,7 @@ out:
*/
static struct batadv_bla_backbone_gw *
batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig,
- short vid, bool own_backbone)
+ unsigned short vid, bool own_backbone)
{
struct batadv_bla_backbone_gw *entry;
struct batadv_orig_node *orig_node;
@@ -380,7 +383,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_get_backbone_gw(): not found (%pM, %d), creating new entry\n",
- orig, vid);
+ orig, BATADV_PRINT_VID(vid));
entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
if (!entry)
@@ -434,7 +437,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig,
static void
batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv,
struct batadv_hard_iface *primary_if,
- short vid)
+ unsigned short vid)
{
struct batadv_bla_backbone_gw *backbone_gw;
@@ -456,7 +459,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv,
*/
static void batadv_bla_answer_request(struct batadv_priv *bat_priv,
struct batadv_hard_iface *primary_if,
- short vid)
+ unsigned short vid)
{
struct hlist_head *head;
struct batadv_hashtable *hash;
@@ -547,7 +550,7 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv,
* @backbone_gw: the backbone gateway which claims it
*/
static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
- const uint8_t *mac, const short vid,
+ const uint8_t *mac, const unsigned short vid,
struct batadv_bla_backbone_gw *backbone_gw)
{
struct batadv_bla_claim *claim;
@@ -572,7 +575,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
atomic_set(&claim->refcount, 2);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_add_claim(): adding new entry %pM, vid %d to hash ...\n",
- mac, vid);
+ mac, BATADV_PRINT_VID(vid));
hash_added = batadv_hash_add(bat_priv->bla.claim_hash,
batadv_compare_claim,
batadv_choose_claim, claim,
@@ -591,7 +594,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_add_claim(): changing ownership for %pM, vid %d\n",
- mac, vid);
+ mac, BATADV_PRINT_VID(vid));
claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN);
batadv_backbone_gw_free_ref(claim->backbone_gw);
@@ -611,7 +614,7 @@ claim_free_ref:
* given mac address and vid.
*/
static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
- const uint8_t *mac, const short vid)
+ const uint8_t *mac, const unsigned short vid)
{
struct batadv_bla_claim search_claim, *claim;
@@ -622,7 +625,7 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
return;
batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_del_claim(): %pM, vid %d\n",
- mac, vid);
+ mac, BATADV_PRINT_VID(vid));
batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim,
batadv_choose_claim, claim);
@@ -637,7 +640,7 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
/* check for ANNOUNCE frame, return 1 if handled */
static int batadv_handle_announce(struct batadv_priv *bat_priv,
uint8_t *an_addr, uint8_t *backbone_addr,
- short vid)
+ unsigned short vid)
{
struct batadv_bla_backbone_gw *backbone_gw;
uint16_t crc;
@@ -658,12 +661,13 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n",
- vid, backbone_gw->orig, crc);
+ BATADV_PRINT_VID(vid), backbone_gw->orig, crc);
if (backbone_gw->crc != crc) {
batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv,
"handle_announce(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n",
- backbone_gw->orig, backbone_gw->vid,
+ backbone_gw->orig,
+ BATADV_PRINT_VID(backbone_gw->vid),
backbone_gw->crc, crc);
batadv_bla_send_request(backbone_gw);
@@ -685,7 +689,7 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv,
static int batadv_handle_request(struct batadv_priv *bat_priv,
struct batadv_hard_iface *primary_if,
uint8_t *backbone_addr,
- struct ethhdr *ethhdr, short vid)
+ struct ethhdr *ethhdr, unsigned short vid)
{
/* check for REQUEST frame */
if (!batadv_compare_eth(backbone_addr, ethhdr->h_dest))
@@ -699,7 +703,7 @@ static int batadv_handle_request(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"handle_request(): REQUEST vid %d (sent by %pM)...\n",
- vid, ethhdr->h_source);
+ BATADV_PRINT_VID(vid), ethhdr->h_source);
batadv_bla_answer_request(bat_priv, primary_if, vid);
return 1;
@@ -709,7 +713,7 @@ static int batadv_handle_request(struct batadv_priv *bat_priv,
static int batadv_handle_unclaim(struct batadv_priv *bat_priv,
struct batadv_hard_iface *primary_if,
uint8_t *backbone_addr,
- uint8_t *claim_addr, short vid)
+ uint8_t *claim_addr, unsigned short vid)
{
struct batadv_bla_backbone_gw *backbone_gw;
@@ -727,7 +731,7 @@ static int batadv_handle_unclaim(struct batadv_priv *bat_priv,
/* this must be an UNCLAIM frame */
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"handle_unclaim(): UNCLAIM %pM on vid %d (sent by %pM)...\n",
- claim_addr, vid, backbone_gw->orig);
+ claim_addr, BATADV_PRINT_VID(vid), backbone_gw->orig);
batadv_bla_del_claim(bat_priv, claim_addr, vid);
batadv_backbone_gw_free_ref(backbone_gw);
@@ -738,7 +742,7 @@ static int batadv_handle_unclaim(struct batadv_priv *bat_priv,
static int batadv_handle_claim(struct batadv_priv *bat_priv,
struct batadv_hard_iface *primary_if,
uint8_t *backbone_addr, uint8_t *claim_addr,
- short vid)
+ unsigned short vid)
{
struct batadv_bla_backbone_gw *backbone_gw;
@@ -861,14 +865,15 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
struct batadv_bla_claim_dst *bla_dst;
uint16_t proto;
int headlen;
- short vid = -1;
+ unsigned short vid = BATADV_NO_FLAGS;
int ret;
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) {
vhdr = (struct vlan_ethhdr *)ethhdr;
vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK;
+ vid |= BATADV_VLAN_HAS_TAG;
proto = ntohs(vhdr->h_vlan_encapsulated_proto);
headlen = sizeof(*vhdr);
} else {
@@ -885,7 +890,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
return 0;
/* pskb_may_pull() may have modified the pointers, get ethhdr again */
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
arphdr = (struct arphdr *)((uint8_t *)ethhdr + headlen);
/* Check whether the ARP frame carries a valid
@@ -910,7 +915,8 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
if (ret == 1)
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_process_claim(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n",
- ethhdr->h_source, vid, hw_src, hw_dst);
+ ethhdr->h_source, BATADV_PRINT_VID(vid), hw_src,
+ hw_dst);
if (ret < 2)
return ret;
@@ -945,7 +951,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_process_claim(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n",
- ethhdr->h_source, vid, hw_src, hw_dst);
+ ethhdr->h_source, BATADV_PRINT_VID(vid), hw_src, hw_dst);
return 1;
}
@@ -1362,7 +1368,7 @@ int batadv_bla_is_backbone_gw(struct sk_buff *skb,
struct ethhdr *ethhdr;
struct vlan_ethhdr *vhdr;
struct batadv_bla_backbone_gw *backbone_gw;
- short vid = -1;
+ unsigned short vid = BATADV_NO_FLAGS;
if (!atomic_read(&orig_node->bat_priv->bridge_loop_avoidance))
return 0;
@@ -1379,6 +1385,7 @@ int batadv_bla_is_backbone_gw(struct sk_buff *skb,
vhdr = (struct vlan_ethhdr *)(skb->data + hdr_size);
vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK;
+ vid |= BATADV_VLAN_HAS_TAG;
}
/* see if this originator is a backbone gw for this VLAN */
@@ -1428,15 +1435,15 @@ void batadv_bla_free(struct batadv_priv *bat_priv)
* returns 1, otherwise it returns 0 and the caller shall further
* process the skb.
*/
-int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid,
- bool is_bcast)
+int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
+ unsigned short vid, bool is_bcast)
{
struct ethhdr *ethhdr;
struct batadv_bla_claim search_claim, *claim = NULL;
struct batadv_hard_iface *primary_if;
int ret;
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
primary_if = batadv_primary_if_get_selected(bat_priv);
if (!primary_if)
@@ -1523,7 +1530,8 @@ out:
* returns 1, otherwise it returns 0 and the caller shall further
* process the skb.
*/
-int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid)
+int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
+ unsigned short vid)
{
struct ethhdr *ethhdr;
struct batadv_bla_claim search_claim, *claim = NULL;
@@ -1543,7 +1551,7 @@ int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid)
if (batadv_bla_process_claim(bat_priv, primary_if, skb))
goto handled;
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
if (unlikely(atomic_read(&bat_priv->bla.num_requests)))
/* don't allow broadcasts while requests are in flight */
@@ -1627,8 +1635,8 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset)
hlist_for_each_entry_rcu(claim, head, hash_entry) {
is_own = batadv_compare_eth(claim->backbone_gw->orig,
primary_addr);
- seq_printf(seq, " * %pM on % 5d by %pM [%c] (%#.4x)\n",
- claim->addr, claim->vid,
+ seq_printf(seq, " * %pM on %5d by %pM [%c] (%#.4x)\n",
+ claim->addr, BATADV_PRINT_VID(claim->vid),
claim->backbone_gw->orig,
(is_own ? 'x' : ' '),
claim->backbone_gw->crc);
@@ -1680,10 +1688,10 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset)
if (is_own)
continue;
- seq_printf(seq,
- " * %pM on % 5d % 4i.%03is (%#.4x)\n",
- backbone_gw->orig, backbone_gw->vid,
- secs, msecs, backbone_gw->crc);
+ seq_printf(seq, " * %pM on %5d %4i.%03is (%#.4x)\n",
+ backbone_gw->orig,
+ BATADV_PRINT_VID(backbone_gw->vid), secs,
+ msecs, backbone_gw->crc);
}
rcu_read_unlock();
}
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index dea2fbc5d98d..4b102e71e5bd 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -21,9 +21,10 @@
#define _NET_BATMAN_ADV_BLA_H_
#ifdef CONFIG_BATMAN_ADV_BLA
-int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid,
- bool is_bcast);
-int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid);
+int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
+ unsigned short vid, bool is_bcast);
+int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
+ unsigned short vid);
int batadv_bla_is_backbone_gw(struct sk_buff *skb,
struct batadv_orig_node *orig_node, int hdr_size);
int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset);
@@ -42,13 +43,14 @@ void batadv_bla_free(struct batadv_priv *bat_priv);
#else /* ifdef CONFIG_BATMAN_ADV_BLA */
static inline int batadv_bla_rx(struct batadv_priv *bat_priv,
- struct sk_buff *skb, short vid, bool is_bcast)
+ struct sk_buff *skb, unsigned short vid,
+ bool is_bcast)
{
return 0;
}
static inline int batadv_bla_tx(struct batadv_priv *bat_priv,
- struct sk_buff *skb, short vid)
+ struct sk_buff *skb, unsigned short vid)
{
return 0;
}
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 239992021b1d..06345d401588 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -45,9 +45,9 @@ static void batadv_dat_start_timer(struct batadv_priv *bat_priv)
}
/**
- * batadv_dat_entry_free_ref - decrements the dat_entry refcounter and possibly
+ * batadv_dat_entry_free_ref - decrement the dat_entry refcounter and possibly
* free it
- * @dat_entry: the oentry to free
+ * @dat_entry: the entry to free
*/
static void batadv_dat_entry_free_ref(struct batadv_dat_entry *dat_entry)
{
@@ -56,10 +56,10 @@ static void batadv_dat_entry_free_ref(struct batadv_dat_entry *dat_entry)
}
/**
- * batadv_dat_to_purge - checks whether a dat_entry has to be purged or not
+ * batadv_dat_to_purge - check whether a dat_entry has to be purged or not
* @dat_entry: the entry to check
*
- * Returns true if the entry has to be purged now, false otherwise
+ * Returns true if the entry has to be purged now, false otherwise.
*/
static bool batadv_dat_to_purge(struct batadv_dat_entry *dat_entry)
{
@@ -75,8 +75,8 @@ static bool batadv_dat_to_purge(struct batadv_dat_entry *dat_entry)
* returns a boolean value: true is the entry has to be deleted,
* false otherwise
*
- * Loops over each entry in the DAT local storage and delete it if and only if
- * the to_purge function passed as argument returns true
+ * Loops over each entry in the DAT local storage and deletes it if and only if
+ * the to_purge function passed as argument returns true.
*/
static void __batadv_dat_purge(struct batadv_priv *bat_priv,
bool (*to_purge)(struct batadv_dat_entry *))
@@ -97,7 +97,7 @@ static void __batadv_dat_purge(struct batadv_priv *bat_priv,
spin_lock_bh(list_lock);
hlist_for_each_entry_safe(dat_entry, node_tmp, head,
hash_entry) {
- /* if an helper function has been passed as parameter,
+ /* if a helper function has been passed as parameter,
* ask it if the entry has to be purged or not
*/
if (to_purge && !to_purge(dat_entry))
@@ -134,7 +134,7 @@ static void batadv_dat_purge(struct work_struct *work)
* @node: node in the local table
* @data2: second object to compare the node to
*
- * Returns 1 if the two entry are the same, 0 otherwise
+ * Returns 1 if the two entries are the same, 0 otherwise.
*/
static int batadv_compare_dat(const struct hlist_node *node, const void *data2)
{
@@ -149,7 +149,7 @@ static int batadv_compare_dat(const struct hlist_node *node, const void *data2)
* @skb: ARP packet
* @hdr_size: size of the possible header before the ARP packet
*
- * Returns the value of the hw_src field in the ARP packet
+ * Returns the value of the hw_src field in the ARP packet.
*/
static uint8_t *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size)
{
@@ -166,7 +166,7 @@ static uint8_t *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size)
* @skb: ARP packet
* @hdr_size: size of the possible header before the ARP packet
*
- * Returns the value of the ip_src field in the ARP packet
+ * Returns the value of the ip_src field in the ARP packet.
*/
static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size)
{
@@ -178,7 +178,7 @@ static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size)
* @skb: ARP packet
* @hdr_size: size of the possible header before the ARP packet
*
- * Returns the value of the hw_dst field in the ARP packet
+ * Returns the value of the hw_dst field in the ARP packet.
*/
static uint8_t *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size)
{
@@ -190,7 +190,7 @@ static uint8_t *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size)
* @skb: ARP packet
* @hdr_size: size of the possible header before the ARP packet
*
- * Returns the value of the ip_dst field in the ARP packet
+ * Returns the value of the ip_dst field in the ARP packet.
*/
static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size)
{
@@ -202,7 +202,7 @@ static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size)
* @data: data to hash
* @size: size of the hash table
*
- * Returns the selected index in the hash table for the given data
+ * Returns the selected index in the hash table for the given data.
*/
static uint32_t batadv_hash_dat(const void *data, uint32_t size)
{
@@ -224,12 +224,12 @@ static uint32_t batadv_hash_dat(const void *data, uint32_t size)
}
/**
- * batadv_dat_entry_hash_find - looks for a given dat_entry in the local hash
+ * batadv_dat_entry_hash_find - look for a given dat_entry in the local hash
* table
* @bat_priv: the bat priv with all the soft interface information
* @ip: search key
*
- * Returns the dat_entry if found, NULL otherwise
+ * Returns the dat_entry if found, NULL otherwise.
*/
static struct batadv_dat_entry *
batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip)
@@ -343,9 +343,6 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb,
if (hdr_size == 0)
return;
- /* if the ARP packet is encapsulated in a batman packet, let's print
- * some debug messages
- */
unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
switch (unicast_4addr_packet->u.header.packet_type) {
@@ -409,7 +406,8 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb,
* @candidate: orig_node under evaluation
* @max_orig_node: last selected candidate
*
- * Returns true if the node has been elected as next candidate or false othrwise
+ * Returns true if the node has been elected as next candidate or false
+ * otherwise.
*/
static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res,
int select, batadv_dat_addr_t tmp_max,
@@ -472,7 +470,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv,
*/
cands[select].type = BATADV_DAT_CANDIDATE_NOT_FOUND;
- /* iterate over the originator list and find the node with closest
+ /* iterate over the originator list and find the node with the closest
* dat_address which has not been selected yet
*/
for (i = 0; i < hash->size; i++) {
@@ -480,7 +478,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv,
rcu_read_lock();
hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
- /* the dht space is a ring and addresses are unsigned */
+ /* the dht space is a ring using unsigned addresses */
tmp_max = BATADV_DAT_ADDR_MAX - orig_node->dat_addr +
ip_key;
@@ -512,7 +510,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv,
}
/**
- * batadv_dat_select_candidates - selects the nodes which the DHT message has to
+ * batadv_dat_select_candidates - select the nodes which the DHT message has to
* be sent to
* @bat_priv: the bat priv with all the soft interface information
* @ip_dst: ipv4 to look up in the DHT
@@ -521,7 +519,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv,
* closest values (from the LEFT, with wrap around if needed) then the hash
* value of the key. ip_dst is the key.
*
- * Returns the candidate array of size BATADV_DAT_CANDIDATE_NUM
+ * Returns the candidate array of size BATADV_DAT_CANDIDATE_NUM.
*/
static struct batadv_dat_candidate *
batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst)
@@ -558,10 +556,11 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst)
* @ip: the DHT key
* @packet_subtype: unicast4addr packet subtype to use
*
- * In this function the skb is copied by means of pskb_copy() and is sent as
- * unicast packet to each of the selected candidates
+ * This function copies the skb with pskb_copy() and is sent as unicast packet
+ * to each of the selected candidates.
*
- * Returns true if the packet is sent to at least one candidate, false otherwise
+ * Returns true if the packet is sent to at least one candidate, false
+ * otherwise.
*/
static bool batadv_dat_send_data(struct batadv_priv *bat_priv,
struct sk_buff *skb, __be32 ip,
@@ -727,7 +726,7 @@ out:
* @skb: packet to analyse
* @hdr_size: size of the possible header before the ARP packet in the skb
*
- * Returns the ARP type if the skb contains a valid ARP packet, 0 otherwise
+ * Returns the ARP type if the skb contains a valid ARP packet, 0 otherwise.
*/
static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv,
struct sk_buff *skb, int hdr_size)
@@ -754,9 +753,7 @@ static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv,
arphdr = (struct arphdr *)(skb->data + hdr_size + ETH_HLEN);
- /* Check whether the ARP packet carries a valid
- * IP information
- */
+ /* check whether the ARP packet carries a valid IP information */
if (arphdr->ar_hrd != htons(ARPHRD_ETHER))
goto out;
@@ -784,7 +781,7 @@ static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv,
if (is_zero_ether_addr(hw_src) || is_multicast_ether_addr(hw_src))
goto out;
- /* we don't care about the destination MAC address in ARP requests */
+ /* don't care about the destination MAC address in ARP requests */
if (arphdr->ar_op != htons(ARPOP_REQUEST)) {
hw_dst = batadv_arp_hw_dst(skb, hdr_size);
if (is_zero_ether_addr(hw_dst) ||
@@ -804,8 +801,8 @@ out:
* @skb: packet to check
*
* Returns true if the message has been sent to the dht candidates, false
- * otherwise. In case of true the message has to be enqueued to permit the
- * fallback
+ * otherwise. In case of a positive return value the message has to be enqueued
+ * to permit the fallback.
*/
bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
struct sk_buff *skb)
@@ -867,7 +864,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_DAT, bat_priv, "ARP request replied locally\n");
ret = true;
} else {
- /* Send the request on the DHT */
+ /* Send the request to the DHT */
ret = batadv_dat_send_data(bat_priv, skb, ip_dst,
BATADV_P_DAT_DHT_GET);
}
@@ -884,7 +881,7 @@ out:
* @skb: packet to check
* @hdr_size: size of the encapsulation header
*
- * Returns true if the request has been answered, false otherwise
+ * Returns true if the request has been answered, false otherwise.
*/
bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
struct sk_buff *skb, int hdr_size)
@@ -924,10 +921,9 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
if (!skb_new)
goto out;
- /* to preserve backwards compatibility, here the node has to answer
- * using the same packet type it received for the request. This is due
- * to that if a node is not using the 4addr packet format it may not
- * support it.
+ /* To preserve backwards compatibility, the node has choose the outgoing
+ * format based on the incoming request packet type. The assumption is
+ * that a node not using the 4addr packet format doesn't support it.
*/
if (hdr_size == sizeof(struct batadv_unicast_4addr_packet))
err = batadv_unicast_4addr_send_skb(bat_priv, skb_new,
@@ -977,7 +973,7 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
batadv_dat_entry_add(bat_priv, ip_dst, hw_dst);
/* Send the ARP reply to the candidates for both the IP addresses that
- * the node got within the ARP reply
+ * the node obtained from the ARP reply
*/
batadv_dat_send_data(bat_priv, skb, ip_src, BATADV_P_DAT_DHT_PUT);
batadv_dat_send_data(bat_priv, skb, ip_dst, BATADV_P_DAT_DHT_PUT);
@@ -987,7 +983,7 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
* DAT storage only
* @bat_priv: the bat priv with all the soft interface information
* @skb: packet to check
- * @hdr_size: siaze of the encapsulation header
+ * @hdr_size: size of the encapsulation header
*/
bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
struct sk_buff *skb, int hdr_size)
@@ -1031,11 +1027,11 @@ out:
/**
* batadv_dat_drop_broadcast_packet - check if an ARP request has to be dropped
- * (because the node has already got the reply via DAT) or not
+ * (because the node has already obtained the reply via DAT) or not
* @bat_priv: the bat priv with all the soft interface information
* @forw_packet: the broadcast packet
*
- * Returns true if the node can drop the packet, false otherwise
+ * Returns true if the node can drop the packet, false otherwise.
*/
bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv,
struct batadv_forw_packet *forw_packet)
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 522243aff2f3..c478e6bcf89b 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -117,6 +117,58 @@ static int batadv_is_valid_iface(const struct net_device *net_dev)
return 1;
}
+/**
+ * batadv_is_wifi_netdev - check if the given net_device struct is a wifi
+ * interface
+ * @net_device: the device to check
+ *
+ * Returns true if the net device is a 802.11 wireless device, false otherwise.
+ */
+static bool batadv_is_wifi_netdev(struct net_device *net_device)
+{
+#ifdef CONFIG_WIRELESS_EXT
+ /* pre-cfg80211 drivers have to implement WEXT, so it is possible to
+ * check for wireless_handlers != NULL
+ */
+ if (net_device->wireless_handlers)
+ return true;
+#endif
+
+ /* cfg80211 drivers have to set ieee80211_ptr */
+ if (net_device->ieee80211_ptr)
+ return true;
+
+ return false;
+}
+
+/**
+ * batadv_is_wifi_iface - check if the given interface represented by ifindex
+ * is a wifi interface
+ * @ifindex: interface index to check
+ *
+ * Returns true if the interface represented by ifindex is a 802.11 wireless
+ * device, false otherwise.
+ */
+bool batadv_is_wifi_iface(int ifindex)
+{
+ struct net_device *net_device = NULL;
+ bool ret = false;
+
+ if (ifindex == BATADV_NULL_IFINDEX)
+ goto out;
+
+ net_device = dev_get_by_index(&init_net, ifindex);
+ if (!net_device)
+ goto out;
+
+ ret = batadv_is_wifi_netdev(net_device);
+
+out:
+ if (net_device)
+ dev_put(net_device);
+ return ret;
+}
+
static struct batadv_hard_iface *
batadv_hardif_get_active(const struct net_device *soft_iface)
{
@@ -525,7 +577,7 @@ batadv_hardif_add_interface(struct net_device *net_dev)
dev_hold(net_dev);
- hard_iface = kmalloc(sizeof(*hard_iface), GFP_ATOMIC);
+ hard_iface = kzalloc(sizeof(*hard_iface), GFP_ATOMIC);
if (!hard_iface)
goto release_dev;
@@ -541,18 +593,16 @@ batadv_hardif_add_interface(struct net_device *net_dev)
INIT_WORK(&hard_iface->cleanup_work,
batadv_hardif_remove_interface_finish);
+ hard_iface->num_bcasts = BATADV_NUM_BCASTS_DEFAULT;
+ if (batadv_is_wifi_netdev(net_dev))
+ hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS;
+
/* extra reference for return */
atomic_set(&hard_iface->refcount, 2);
batadv_check_known_mac_addr(hard_iface->net_dev);
list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list);
- /* This can't be called via a bat_priv callback because
- * we have no bat_priv yet.
- */
- atomic_set(&hard_iface->bat_iv.ogm_seqno, 1);
- hard_iface->bat_iv.ogm_buff = NULL;
-
return hard_iface;
free_if:
@@ -595,7 +645,7 @@ void batadv_hardif_remove_interfaces(void)
static int batadv_hard_if_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
- struct net_device *net_dev = ptr;
+ struct net_device *net_dev = netdev_notifier_info_to_dev(ptr);
struct batadv_hard_iface *hard_iface;
struct batadv_hard_iface *primary_if = NULL;
struct batadv_priv *bat_priv;
@@ -657,38 +707,6 @@ out:
return NOTIFY_DONE;
}
-/* This function returns true if the interface represented by ifindex is a
- * 802.11 wireless device
- */
-bool batadv_is_wifi_iface(int ifindex)
-{
- struct net_device *net_device = NULL;
- bool ret = false;
-
- if (ifindex == BATADV_NULL_IFINDEX)
- goto out;
-
- net_device = dev_get_by_index(&init_net, ifindex);
- if (!net_device)
- goto out;
-
-#ifdef CONFIG_WIRELESS_EXT
- /* pre-cfg80211 drivers have to implement WEXT, so it is possible to
- * check for wireless_handlers != NULL
- */
- if (net_device->wireless_handlers)
- ret = true;
- else
-#endif
- /* cfg80211 drivers have to set ieee80211_ptr */
- if (net_device->ieee80211_ptr)
- ret = true;
-out:
- if (net_device)
- dev_put(net_device);
- return ret;
-}
-
struct notifier_block batadv_hard_if_notifier = {
.notifier_call = batadv_hard_if_event,
};
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 0ba6c899b2d3..b27508b8085c 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -177,13 +177,13 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff,
if (len >= sizeof(struct batadv_icmp_packet_rr))
packet_len = sizeof(struct batadv_icmp_packet_rr);
- skb = dev_alloc_skb(packet_len + ETH_HLEN + NET_IP_ALIGN);
+ skb = netdev_alloc_skb_ip_align(NULL, packet_len + ETH_HLEN);
if (!skb) {
len = -ENOMEM;
goto out;
}
- skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN);
+ skb_reserve(skb, ETH_HLEN);
icmp_packet = (struct batadv_icmp_packet_rr *)skb_put(skb, packet_len);
if (copy_from_user(icmp_packet, buff, packet_len)) {
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 51aafd669cbb..08125f3f6064 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -473,7 +473,6 @@ __be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr)
crc = crc32c(crc, data, len);
consumed += len;
}
- skb_abort_seq_read(&st);
return htonl(crc);
}
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 59a0d6af15c8..5e9aebb7d56b 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -26,7 +26,7 @@
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2013.2.0"
+#define BATADV_SOURCE_VERSION "2013.3.0"
#endif
/* B.A.T.M.A.N. parameters */
@@ -76,6 +76,11 @@
#define BATADV_LOG_BUF_LEN 8192 /* has to be a power of 2 */
+/* number of packets to send for broadcasts on different interface types */
+#define BATADV_NUM_BCASTS_DEFAULT 1
+#define BATADV_NUM_BCASTS_WIRELESS 3
+#define BATADV_NUM_BCASTS_MAX 3
+
/* msecs after which an ARP_REQUEST is sent in broadcast as fallback */
#define ARP_REQ_DELAY 250
/* numbers of originator to contact for any PUT/GET DHT operation */
@@ -157,6 +162,17 @@ enum batadv_uev_type {
#include <linux/seq_file.h>
#include "types.h"
+/**
+ * batadv_vlan_flags - flags for the four MSB of any vlan ID field
+ * @BATADV_VLAN_HAS_TAG: whether the field contains a valid vlan tag or not
+ */
+enum batadv_vlan_flags {
+ BATADV_VLAN_HAS_TAG = BIT(15),
+};
+
+#define BATADV_PRINT_VID(vid) (vid & BATADV_VLAN_HAS_TAG ? \
+ (int)(vid & VLAN_VID_MASK) : -1)
+
extern char batadv_routing_algo[];
extern struct list_head batadv_hardif_list;
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index e84629ece9b7..a487d46e0aec 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -1245,7 +1245,7 @@ static void batadv_nc_skb_store_before_coding(struct batadv_priv *bat_priv,
return;
/* Set the mac header as if we actually sent the packet uncoded */
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
memcpy(ethhdr->h_source, ethhdr->h_dest, ETH_ALEN);
memcpy(ethhdr->h_dest, eth_dst_new, ETH_ALEN);
@@ -1359,18 +1359,17 @@ static bool batadv_nc_skb_add_to_path(struct sk_buff *skb,
* buffer
* @skb: data skb to forward
* @neigh_node: next hop to forward packet to
- * @ethhdr: pointer to the ethernet header inside the skb
*
* Returns true if the skb was consumed (encoded packet sent) or false otherwise
*/
bool batadv_nc_skb_forward(struct sk_buff *skb,
- struct batadv_neigh_node *neigh_node,
- struct ethhdr *ethhdr)
+ struct batadv_neigh_node *neigh_node)
{
const struct net_device *netdev = neigh_node->if_incoming->soft_iface;
struct batadv_priv *bat_priv = netdev_priv(netdev);
struct batadv_unicast_packet *packet;
struct batadv_nc_path *nc_path;
+ struct ethhdr *ethhdr = eth_hdr(skb);
__be32 packet_id;
u8 *payload;
@@ -1423,7 +1422,7 @@ void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
{
struct batadv_unicast_packet *packet;
struct batadv_nc_path *nc_path;
- struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ struct ethhdr *ethhdr = eth_hdr(skb);
__be32 packet_id;
u8 *payload;
@@ -1482,7 +1481,7 @@ out:
void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
struct sk_buff *skb)
{
- struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ struct ethhdr *ethhdr = eth_hdr(skb);
if (batadv_is_my_mac(bat_priv, ethhdr->h_dest))
return;
@@ -1533,7 +1532,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
skb_reset_network_header(skb);
/* Reconstruct original mac header */
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
memcpy(ethhdr, &ethhdr_tmp, sizeof(*ethhdr));
/* Select the correct unicast header information based on the location
@@ -1677,7 +1676,7 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb,
return NET_RX_DROP;
coded_packet = (struct batadv_coded_packet *)skb->data;
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
/* Verify frame is destined for us */
if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest) &&
@@ -1763,6 +1762,13 @@ int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset)
/* For each orig_node in this bin */
rcu_read_lock();
hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
+ /* no need to print the orig node if it does not have
+ * network coding neighbors
+ */
+ if (list_empty(&orig_node->in_coding_list) &&
+ list_empty(&orig_node->out_coding_list))
+ continue;
+
seq_printf(seq, "Node: %pM\n", orig_node->orig);
seq_puts(seq, " Ingoing: ");
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
index 4fa6d0caddbd..85a4ec81ad50 100644
--- a/net/batman-adv/network-coding.h
+++ b/net/batman-adv/network-coding.h
@@ -36,8 +36,7 @@ void batadv_nc_purge_orig(struct batadv_priv *bat_priv,
void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv);
void batadv_nc_init_orig(struct batadv_orig_node *orig_node);
bool batadv_nc_skb_forward(struct sk_buff *skb,
- struct batadv_neigh_node *neigh_node,
- struct ethhdr *ethhdr);
+ struct batadv_neigh_node *neigh_node);
void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
struct sk_buff *skb);
void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
@@ -87,8 +86,7 @@ static inline void batadv_nc_init_orig(struct batadv_orig_node *orig_node)
}
static inline bool batadv_nc_skb_forward(struct sk_buff *skb,
- struct batadv_neigh_node *neigh_node,
- struct ethhdr *ethhdr)
+ struct batadv_neigh_node *neigh_node)
{
return false;
}
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index fad1a2093e15..f50553a7de62 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -92,7 +92,7 @@ batadv_orig_node_get_router(struct batadv_orig_node *orig_node)
struct batadv_neigh_node *
batadv_neigh_node_new(struct batadv_hard_iface *hard_iface,
- const uint8_t *neigh_addr, uint32_t seqno)
+ const uint8_t *neigh_addr)
{
struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
struct batadv_neigh_node *neigh_node;
@@ -110,8 +110,8 @@ batadv_neigh_node_new(struct batadv_hard_iface *hard_iface,
atomic_set(&neigh_node->refcount, 2);
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
- "Creating new neighbor %pM, initial seqno %d\n",
- neigh_addr, seqno);
+ "Creating new neighbor %pM on interface %s\n", neigh_addr,
+ hard_iface->net_dev->name);
out:
return neigh_node;
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index 734e5a3d8a5b..7887b84a9af4 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -31,7 +31,7 @@ struct batadv_orig_node *batadv_get_orig_node(struct batadv_priv *bat_priv,
const uint8_t *addr);
struct batadv_neigh_node *
batadv_neigh_node_new(struct batadv_hard_iface *hard_iface,
- const uint8_t *neigh_addr, uint32_t seqno);
+ const uint8_t *neigh_addr);
void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node);
struct batadv_neigh_node *
batadv_orig_node_get_router(struct batadv_orig_node *orig_node);
diff --git a/net/batman-adv/ring_buffer.c b/net/batman-adv/ring_buffer.c
deleted file mode 100644
index ccab0bbdbb59..000000000000
--- a/net/batman-adv/ring_buffer.c
+++ /dev/null
@@ -1,51 +0,0 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
- *
- * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
- */
-
-#include "main.h"
-#include "ring_buffer.h"
-
-void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index,
- uint8_t value)
-{
- lq_recv[*lq_index] = value;
- *lq_index = (*lq_index + 1) % BATADV_TQ_GLOBAL_WINDOW_SIZE;
-}
-
-uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[])
-{
- const uint8_t *ptr;
- uint16_t count = 0, i = 0, sum = 0;
-
- ptr = lq_recv;
-
- while (i < BATADV_TQ_GLOBAL_WINDOW_SIZE) {
- if (*ptr != 0) {
- count++;
- sum += *ptr;
- }
-
- i++;
- ptr++;
- }
-
- if (count == 0)
- return 0;
-
- return (uint8_t)(sum / count);
-}
diff --git a/net/batman-adv/ring_buffer.h b/net/batman-adv/ring_buffer.h
deleted file mode 100644
index 3f92ae248e83..000000000000
--- a/net/batman-adv/ring_buffer.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
- *
- * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
- */
-
-#ifndef _NET_BATMAN_ADV_RING_BUFFER_H_
-#define _NET_BATMAN_ADV_RING_BUFFER_H_
-
-void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index,
- uint8_t value);
-uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]);
-
-#endif /* _NET_BATMAN_ADV_RING_BUFFER_H_ */
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index b27a4d792d15..2f0bd3ffe6e8 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -34,35 +34,6 @@
static int batadv_route_unicast_packet(struct sk_buff *skb,
struct batadv_hard_iface *recv_if);
-void batadv_slide_own_bcast_window(struct batadv_hard_iface *hard_iface)
-{
- struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
- struct batadv_hashtable *hash = bat_priv->orig_hash;
- struct hlist_head *head;
- struct batadv_orig_node *orig_node;
- unsigned long *word;
- uint32_t i;
- size_t word_index;
- uint8_t *w;
-
- for (i = 0; i < hash->size; i++) {
- head = &hash->table[i];
-
- rcu_read_lock();
- hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
- spin_lock_bh(&orig_node->ogm_cnt_lock);
- word_index = hard_iface->if_num * BATADV_NUM_WORDS;
- word = &(orig_node->bcast_own[word_index]);
-
- batadv_bit_get_packet(bat_priv, word, 1, 0);
- w = &orig_node->bcast_own_sum[hard_iface->if_num];
- *w = bitmap_weight(word, BATADV_TQ_LOCAL_WINDOW_SIZE);
- spin_unlock_bh(&orig_node->ogm_cnt_lock);
- }
- rcu_read_unlock();
- }
-}
-
static void _batadv_update_route(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
struct batadv_neigh_node *neigh_node)
@@ -256,7 +227,7 @@ bool batadv_check_management_packet(struct sk_buff *skb,
if (unlikely(!pskb_may_pull(skb, header_len)))
return false;
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
/* packet with broadcast indication but unicast recipient */
if (!is_broadcast_ether_addr(ethhdr->h_dest))
@@ -314,7 +285,7 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv,
icmp_packet->msg_type = BATADV_ECHO_REPLY;
icmp_packet->header.ttl = BATADV_TTL;
- if (batadv_send_skb_to_orig(skb, orig_node, NULL))
+ if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
ret = NET_RX_SUCCESS;
out:
@@ -362,7 +333,7 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
icmp_packet->msg_type = BATADV_TTL_EXCEEDED;
icmp_packet->header.ttl = BATADV_TTL;
- if (batadv_send_skb_to_orig(skb, orig_node, NULL))
+ if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
ret = NET_RX_SUCCESS;
out:
@@ -392,7 +363,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
if (unlikely(!pskb_may_pull(skb, hdr_size)))
goto out;
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
/* packet with unicast indication but broadcast recipient */
if (is_broadcast_ether_addr(ethhdr->h_dest))
@@ -439,7 +410,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
icmp_packet->header.ttl--;
/* route it */
- if (batadv_send_skb_to_orig(skb, orig_node, recv_if))
+ if (batadv_send_skb_to_orig(skb, orig_node, recv_if) != NET_XMIT_DROP)
ret = NET_RX_SUCCESS;
out:
@@ -569,7 +540,7 @@ static int batadv_check_unicast_packet(struct batadv_priv *bat_priv,
if (unlikely(!pskb_may_pull(skb, hdr_size)))
return -ENODATA;
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
/* packet with unicast indication but broadcast recipient */
if (is_broadcast_ether_addr(ethhdr->h_dest))
@@ -803,8 +774,8 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
struct batadv_orig_node *orig_node = NULL;
struct batadv_neigh_node *neigh_node = NULL;
struct batadv_unicast_packet *unicast_packet;
- struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb);
- int ret = NET_RX_DROP;
+ struct ethhdr *ethhdr = eth_hdr(skb);
+ int res, ret = NET_RX_DROP;
struct sk_buff *new_skb;
unicast_packet = (struct batadv_unicast_packet *)skb->data;
@@ -864,16 +835,19 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
/* decrement ttl */
unicast_packet->header.ttl--;
- /* network code packet if possible */
- if (batadv_nc_skb_forward(skb, neigh_node, ethhdr)) {
- ret = NET_RX_SUCCESS;
- } else if (batadv_send_skb_to_orig(skb, orig_node, recv_if)) {
- ret = NET_RX_SUCCESS;
+ res = batadv_send_skb_to_orig(skb, orig_node, recv_if);
- /* Update stats counter */
+ /* translate transmit result into receive result */
+ if (res == NET_XMIT_SUCCESS) {
+ /* skb was transmitted and consumed */
batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD);
batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES,
skb->len + ETH_HLEN);
+
+ ret = NET_RX_SUCCESS;
+ } else if (res == NET_XMIT_POLICED) {
+ /* skb was buffered and consumed */
+ ret = NET_RX_SUCCESS;
}
out:
@@ -1165,7 +1139,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
if (unlikely(!pskb_may_pull(skb, hdr_size)))
goto out;
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
/* packet with broadcast indication but unicast recipient */
if (!is_broadcast_ether_addr(ethhdr->h_dest))
@@ -1265,7 +1239,7 @@ int batadv_recv_vis_packet(struct sk_buff *skb,
return NET_RX_DROP;
vis_packet = (struct batadv_vis_packet *)skb->data;
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
/* not for me */
if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest))
diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h
index 99eeafaba407..72a29bde2010 100644
--- a/net/batman-adv/routing.h
+++ b/net/batman-adv/routing.h
@@ -20,7 +20,6 @@
#ifndef _NET_BATMAN_ADV_ROUTING_H_
#define _NET_BATMAN_ADV_ROUTING_H_
-void batadv_slide_own_bcast_window(struct batadv_hard_iface *hard_iface);
bool batadv_check_management_packet(struct sk_buff *skb,
struct batadv_hard_iface *hard_iface,
int header_len);
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 263cfd1ccee7..e9ff8d801201 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -61,7 +61,7 @@ int batadv_send_skb_packet(struct sk_buff *skb,
skb_reset_mac_header(skb);
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
memcpy(ethhdr->h_source, hard_iface->net_dev->dev_addr, ETH_ALEN);
memcpy(ethhdr->h_dest, dst_addr, ETH_ALEN);
ethhdr->h_proto = __constant_htons(ETH_P_BATMAN);
@@ -96,26 +96,37 @@ send_skb_err:
* host, NULL can be passed as recv_if and no interface alternating is
* attempted.
*
- * Returns TRUE on success; FALSE otherwise.
+ * Returns NET_XMIT_SUCCESS on success, NET_XMIT_DROP on failure, or
+ * NET_XMIT_POLICED if the skb is buffered for later transmit.
*/
-bool batadv_send_skb_to_orig(struct sk_buff *skb,
- struct batadv_orig_node *orig_node,
- struct batadv_hard_iface *recv_if)
+int batadv_send_skb_to_orig(struct sk_buff *skb,
+ struct batadv_orig_node *orig_node,
+ struct batadv_hard_iface *recv_if)
{
struct batadv_priv *bat_priv = orig_node->bat_priv;
struct batadv_neigh_node *neigh_node;
+ int ret = NET_XMIT_DROP;
/* batadv_find_router() increases neigh_nodes refcount if found. */
neigh_node = batadv_find_router(bat_priv, orig_node, recv_if);
if (!neigh_node)
- return false;
+ return ret;
- /* route it */
- batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
+ /* try to network code the packet, if it is received on an interface
+ * (i.e. being forwarded). If the packet originates from this node or if
+ * network coding fails, then send the packet as usual.
+ */
+ if (recv_if && batadv_nc_skb_forward(skb, neigh_node)) {
+ ret = NET_XMIT_POLICED;
+ } else {
+ batadv_send_skb_packet(skb, neigh_node->if_incoming,
+ neigh_node->addr);
+ ret = NET_XMIT_SUCCESS;
+ }
batadv_neigh_node_free_ref(neigh_node);
- return true;
+ return ret;
}
void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface)
@@ -152,8 +163,6 @@ _batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
struct batadv_forw_packet *forw_packet,
unsigned long send_time)
{
- INIT_HLIST_NODE(&forw_packet->list);
-
/* add new packet to packet list */
spin_lock_bh(&bat_priv->forw_bcast_list_lock);
hlist_add_head(&forw_packet->list, &bat_priv->forw_bcast_list);
@@ -260,6 +269,9 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
if (hard_iface->soft_iface != soft_iface)
continue;
+ if (forw_packet->num_packets >= hard_iface->num_bcasts)
+ continue;
+
/* send a copy of the saved skb */
skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC);
if (skb1)
@@ -271,7 +283,7 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
forw_packet->num_packets++;
/* if we still have some more bcasts to send */
- if (forw_packet->num_packets < 3) {
+ if (forw_packet->num_packets < BATADV_NUM_BCASTS_MAX) {
_batadv_add_bcast_packet_to_list(bat_priv, forw_packet,
msecs_to_jiffies(5));
return;
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index 38e662f619ac..e7b17880fca4 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -23,9 +23,9 @@
int batadv_send_skb_packet(struct sk_buff *skb,
struct batadv_hard_iface *hard_iface,
const uint8_t *dst_addr);
-bool batadv_send_skb_to_orig(struct sk_buff *skb,
- struct batadv_orig_node *orig_node,
- struct batadv_hard_iface *recv_if);
+int batadv_send_skb_to_orig(struct sk_buff *skb,
+ struct batadv_orig_node *orig_node,
+ struct batadv_hard_iface *recv_if);
void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface);
int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
const struct sk_buff *skb,
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 819dfb006cdf..700d0b49742d 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -154,7 +154,7 @@ static int batadv_interface_tx(struct sk_buff *skb,
0x00, 0x00};
unsigned int header_len = 0;
int data_len = skb->len, ret;
- short vid __maybe_unused = -1;
+ unsigned short vid __maybe_unused = BATADV_NO_FLAGS;
bool do_bcast = false;
uint32_t seqno;
unsigned long brd_delay = 1;
@@ -303,7 +303,7 @@ void batadv_interface_rx(struct net_device *soft_iface,
struct ethhdr *ethhdr;
struct vlan_ethhdr *vhdr;
struct batadv_header *batadv_header = (struct batadv_header *)skb->data;
- short vid __maybe_unused = -1;
+ unsigned short vid __maybe_unused = BATADV_NO_FLAGS;
__be16 ethertype = __constant_htons(ETH_P_BATMAN);
bool is_bcast;
@@ -316,7 +316,7 @@ void batadv_interface_rx(struct net_device *soft_iface,
skb_pull_rcsum(skb, hdr_size);
skb_reset_mac_header(skb);
- ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ ethhdr = eth_hdr(skb);
switch (ntohs(ethhdr->h_proto)) {
case ETH_P_8021Q:
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 9e8748575845..429aeef3d8b2 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -163,10 +163,19 @@ batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry)
call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu);
}
+/**
+ * batadv_tt_local_event - store a local TT event (ADD/DEL)
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tt_local_entry: the TT entry involved in the event
+ * @event_flags: flags to store in the event structure
+ */
static void batadv_tt_local_event(struct batadv_priv *bat_priv,
- const uint8_t *addr, uint8_t flags)
+ struct batadv_tt_local_entry *tt_local_entry,
+ uint8_t event_flags)
{
struct batadv_tt_change_node *tt_change_node, *entry, *safe;
+ struct batadv_tt_common_entry *common = &tt_local_entry->common;
+ uint8_t flags = common->flags | event_flags;
bool event_removed = false;
bool del_op_requested, del_op_entry;
@@ -176,7 +185,7 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv,
return;
tt_change_node->change.flags = flags;
- memcpy(tt_change_node->change.addr, addr, ETH_ALEN);
+ memcpy(tt_change_node->change.addr, common->addr, ETH_ALEN);
del_op_requested = flags & BATADV_TT_CLIENT_DEL;
@@ -184,7 +193,7 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv,
spin_lock_bh(&bat_priv->tt.changes_list_lock);
list_for_each_entry_safe(entry, safe, &bat_priv->tt.changes_list,
list) {
- if (!batadv_compare_eth(entry->change.addr, addr))
+ if (!batadv_compare_eth(entry->change.addr, common->addr))
continue;
/* DEL+ADD in the same orig interval have no effect and can be
@@ -332,7 +341,7 @@ void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
}
add_event:
- batadv_tt_local_event(bat_priv, addr, tt_local->common.flags);
+ batadv_tt_local_event(bat_priv, tt_local, BATADV_NO_FLAGS);
check_roaming:
/* Check whether it is a roaming, but don't do anything if the roaming
@@ -529,8 +538,7 @@ batadv_tt_local_set_pending(struct batadv_priv *bat_priv,
struct batadv_tt_local_entry *tt_local_entry,
uint16_t flags, const char *message)
{
- batadv_tt_local_event(bat_priv, tt_local_entry->common.addr,
- tt_local_entry->common.flags | flags);
+ batadv_tt_local_event(bat_priv, tt_local_entry, flags);
/* The local client has to be marked as "pending to be removed" but has
* to be kept in the table in order to send it in a full table
@@ -584,8 +592,7 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv,
/* if this client has been added right now, it is possible to
* immediately purge it
*/
- batadv_tt_local_event(bat_priv, tt_local_entry->common.addr,
- curr_flags | BATADV_TT_CLIENT_DEL);
+ batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL);
hlist_del_rcu(&tt_local_entry->common.hash_entry);
batadv_tt_local_entry_free_ref(tt_local_entry);
@@ -791,10 +798,25 @@ out:
batadv_tt_orig_list_entry_free_ref(orig_entry);
}
-/* caller must hold orig_node refcount */
+/**
+ * batadv_tt_global_add - add a new TT global entry or update an existing one
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: the originator announcing the client
+ * @tt_addr: the mac address of the non-mesh client
+ * @flags: TT flags that have to be set for this non-mesh client
+ * @ttvn: the tt version number ever announcing this non-mesh client
+ *
+ * Add a new TT global entry for the given originator. If the entry already
+ * exists add a new reference to the given originator (a global entry can have
+ * references to multiple originators) and adjust the flags attribute to reflect
+ * the function argument.
+ * If a TT local entry exists for this non-mesh client remove it.
+ *
+ * The caller must hold orig_node refcount.
+ */
int batadv_tt_global_add(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
- const unsigned char *tt_addr, uint8_t flags,
+ const unsigned char *tt_addr, uint16_t flags,
uint8_t ttvn)
{
struct batadv_tt_global_entry *tt_global_entry;
@@ -1600,11 +1622,11 @@ batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn,
tt_tot = tt_len / sizeof(struct batadv_tt_change);
len = tt_query_size + tt_len;
- skb = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN);
+ skb = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN);
if (!skb)
goto out;
- skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN);
+ skb_reserve(skb, ETH_HLEN);
tt_response = (struct batadv_tt_query_packet *)skb_put(skb, len);
tt_response->ttvn = ttvn;
@@ -1665,11 +1687,11 @@ static int batadv_send_tt_request(struct batadv_priv *bat_priv,
if (!tt_req_node)
goto out;
- skb = dev_alloc_skb(sizeof(*tt_request) + ETH_HLEN + NET_IP_ALIGN);
+ skb = netdev_alloc_skb_ip_align(NULL, sizeof(*tt_request) + ETH_HLEN);
if (!skb)
goto out;
- skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN);
+ skb_reserve(skb, ETH_HLEN);
tt_req_len = sizeof(*tt_request);
tt_request = (struct batadv_tt_query_packet *)skb_put(skb, tt_req_len);
@@ -1691,7 +1713,7 @@ static int batadv_send_tt_request(struct batadv_priv *bat_priv,
batadv_inc_counter(bat_priv, BATADV_CNT_TT_REQUEST_TX);
- if (batadv_send_skb_to_orig(skb, dst_orig_node, NULL))
+ if (batadv_send_skb_to_orig(skb, dst_orig_node, NULL) != NET_XMIT_DROP)
ret = 0;
out:
@@ -1715,7 +1737,7 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv,
struct batadv_orig_node *req_dst_orig_node;
struct batadv_orig_node *res_dst_orig_node = NULL;
uint8_t orig_ttvn, req_ttvn, ttvn;
- int ret = false;
+ int res, ret = false;
unsigned char *tt_buff;
bool full_table;
uint16_t tt_len, tt_tot;
@@ -1762,11 +1784,11 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv,
tt_tot = tt_len / sizeof(struct batadv_tt_change);
len = sizeof(*tt_response) + tt_len;
- skb = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN);
+ skb = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN);
if (!skb)
goto unlock;
- skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN);
+ skb_reserve(skb, ETH_HLEN);
packet_pos = skb_put(skb, len);
tt_response = (struct batadv_tt_query_packet *)packet_pos;
tt_response->ttvn = req_ttvn;
@@ -1810,8 +1832,10 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv,
batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_TX);
- if (batadv_send_skb_to_orig(skb, res_dst_orig_node, NULL))
+ res = batadv_send_skb_to_orig(skb, res_dst_orig_node, NULL);
+ if (res != NET_XMIT_DROP)
ret = true;
+
goto out;
unlock:
@@ -1878,11 +1902,11 @@ batadv_send_my_tt_response(struct batadv_priv *bat_priv,
tt_tot = tt_len / sizeof(struct batadv_tt_change);
len = sizeof(*tt_response) + tt_len;
- skb = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN);
+ skb = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN);
if (!skb)
goto unlock;
- skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN);
+ skb_reserve(skb, ETH_HLEN);
packet_pos = skb_put(skb, len);
tt_response = (struct batadv_tt_query_packet *)packet_pos;
tt_response->ttvn = req_ttvn;
@@ -1925,7 +1949,7 @@ batadv_send_my_tt_response(struct batadv_priv *bat_priv,
batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_TX);
- if (batadv_send_skb_to_orig(skb, orig_node, NULL))
+ if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
ret = true;
goto out;
@@ -2212,11 +2236,11 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client,
if (!batadv_tt_check_roam_count(bat_priv, client))
goto out;
- skb = dev_alloc_skb(sizeof(*roam_adv_packet) + ETH_HLEN + NET_IP_ALIGN);
+ skb = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN);
if (!skb)
goto out;
- skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN);
+ skb_reserve(skb, ETH_HLEN);
roam_adv_packet = (struct batadv_roam_adv_packet *)skb_put(skb, len);
@@ -2238,7 +2262,7 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client,
batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_TX);
- if (batadv_send_skb_to_orig(skb, orig_node, NULL))
+ if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
ret = 0;
out:
diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h
index ab8e683b402f..659a3bb759ce 100644
--- a/net/batman-adv/translation-table.h
+++ b/net/batman-adv/translation-table.h
@@ -33,7 +33,7 @@ void batadv_tt_global_add_orig(struct batadv_priv *bat_priv,
const unsigned char *tt_buff, int tt_buff_len);
int batadv_tt_global_add(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
- const unsigned char *addr, uint8_t flags,
+ const unsigned char *addr, uint16_t flags,
uint8_t ttvn);
int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset);
void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index aba8364c3689..b2c94e139319 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -61,6 +61,7 @@ struct batadv_hard_iface_bat_iv {
* @if_status: status of the interface for batman-adv
* @net_dev: pointer to the net_device
* @frag_seqno: last fragment sequence number sent by this interface
+ * @num_bcasts: number of payload re-broadcasts on this interface (ARQ)
* @hardif_obj: kobject of the per interface sysfs "mesh" directory
* @refcount: number of contexts the object is used
* @batman_adv_ptype: packet type describing packets that should be processed by
@@ -76,6 +77,7 @@ struct batadv_hard_iface {
char if_status;
struct net_device *net_dev;
atomic_t frag_seqno;
+ uint8_t num_bcasts;
struct kobject *hardif_obj;
atomic_t refcount;
struct packet_type batman_adv_ptype;
@@ -640,7 +642,7 @@ struct batadv_socket_packet {
#ifdef CONFIG_BATMAN_ADV_BLA
struct batadv_bla_backbone_gw {
uint8_t orig[ETH_ALEN];
- short vid;
+ unsigned short vid;
struct hlist_node hash_entry;
struct batadv_priv *bat_priv;
unsigned long lasttime;
@@ -663,7 +665,7 @@ struct batadv_bla_backbone_gw {
*/
struct batadv_bla_claim {
uint8_t addr[ETH_ALEN];
- short vid;
+ unsigned short vid;
struct batadv_bla_backbone_gw *backbone_gw;
unsigned long lasttime;
struct hlist_node hash_entry;
diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c
index 0bb3b5982f94..dc8b5d4dd636 100644
--- a/net/batman-adv/unicast.c
+++ b/net/batman-adv/unicast.c
@@ -464,7 +464,7 @@ find_router:
goto out;
}
- if (batadv_send_skb_to_orig(skb, orig_node, NULL))
+ if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
ret = 0;
out:
diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c
index 1625e5793a89..4983340f1943 100644
--- a/net/batman-adv/vis.c
+++ b/net/batman-adv/vis.c
@@ -392,12 +392,12 @@ batadv_add_packet(struct batadv_priv *bat_priv,
return NULL;
len = sizeof(*packet) + vis_info_len;
- info->skb_packet = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN);
+ info->skb_packet = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN);
if (!info->skb_packet) {
kfree(info);
return NULL;
}
- skb_reserve(info->skb_packet, ETH_HLEN + NET_IP_ALIGN);
+ skb_reserve(info->skb_packet, ETH_HLEN);
packet = (struct batadv_vis_packet *)skb_put(info->skb_packet, len);
kref_init(&info->refcount);
@@ -697,7 +697,7 @@ static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node;
struct batadv_vis_packet *packet;
struct sk_buff *skb;
- uint32_t i;
+ uint32_t i, res;
packet = (struct batadv_vis_packet *)info->skb_packet->data;
@@ -724,7 +724,8 @@ static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv,
if (!skb)
continue;
- if (!batadv_send_skb_to_orig(skb, orig_node, NULL))
+ res = batadv_send_skb_to_orig(skb, orig_node, NULL);
+ if (res == NET_XMIT_DROP)
kfree_skb(skb);
}
rcu_read_unlock();
@@ -748,7 +749,7 @@ static void batadv_unicast_vis_packet(struct batadv_priv *bat_priv,
if (!skb)
goto out;
- if (!batadv_send_skb_to_orig(skb, orig_node, NULL))
+ if (batadv_send_skb_to_orig(skb, orig_node, NULL) == NET_XMIT_DROP)
kfree_skb(skb);
out:
@@ -854,13 +855,13 @@ int batadv_vis_init(struct batadv_priv *bat_priv)
if (!bat_priv->vis.my_info)
goto err;
- len = sizeof(*packet) + BATADV_MAX_VIS_PACKET_SIZE;
- len += ETH_HLEN + NET_IP_ALIGN;
- bat_priv->vis.my_info->skb_packet = dev_alloc_skb(len);
+ len = sizeof(*packet) + BATADV_MAX_VIS_PACKET_SIZE + ETH_HLEN;
+ bat_priv->vis.my_info->skb_packet = netdev_alloc_skb_ip_align(NULL,
+ len);
if (!bat_priv->vis.my_info->skb_packet)
goto free_info;
- skb_reserve(bat_priv->vis.my_info->skb_packet, ETH_HLEN + NET_IP_ALIGN);
+ skb_reserve(bat_priv->vis.my_info->skb_packet, ETH_HLEN);
tmp_skb = bat_priv->vis.my_info->skb_packet;
packet = (struct batadv_vis_packet *)skb_put(tmp_skb, sizeof(*packet));
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index db7de80b88a2..e3a349977595 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -597,7 +597,15 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
struct hci_dev *hdev = req->hdev;
u8 p;
- /* Only send HCI_Delete_Stored_Link_Key if it is supported */
+ /* Some Broadcom based Bluetooth controllers do not support the
+ * Delete Stored Link Key command. They are clearly indicating its
+ * absence in the bit mask of supported commands.
+ *
+ * Check the supported commands and only if the the command is marked
+ * as supported send it. If not supported assume that the controller
+ * does not have actual support for stored link keys which makes this
+ * command redundant anyway.
+ */
if (hdev->commands[6] & 0x80) {
struct hci_cp_delete_stored_link_key cp;
@@ -751,7 +759,7 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state)
hdev->discovery.state = state;
}
-static void inquiry_cache_flush(struct hci_dev *hdev)
+void hci_inquiry_cache_flush(struct hci_dev *hdev)
{
struct discovery_state *cache = &hdev->discovery;
struct inquiry_entry *p, *n;
@@ -964,7 +972,7 @@ int hci_inquiry(void __user *arg)
hci_dev_lock(hdev);
if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX ||
inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) {
- inquiry_cache_flush(hdev);
+ hci_inquiry_cache_flush(hdev);
do_inquiry = 1;
}
hci_dev_unlock(hdev);
@@ -1201,8 +1209,6 @@ static int hci_dev_do_close(struct hci_dev *hdev)
{
BT_DBG("%s %p", hdev->name, hdev);
- cancel_work_sync(&hdev->le_scan);
-
cancel_delayed_work(&hdev->power_off);
hci_req_cancel(hdev, ENODEV);
@@ -1230,7 +1236,7 @@ static int hci_dev_do_close(struct hci_dev *hdev)
cancel_delayed_work_sync(&hdev->le_scan_disable);
hci_dev_lock(hdev);
- inquiry_cache_flush(hdev);
+ hci_inquiry_cache_flush(hdev);
hci_conn_hash_flush(hdev);
hci_dev_unlock(hdev);
@@ -1331,7 +1337,7 @@ int hci_dev_reset(__u16 dev)
skb_queue_purge(&hdev->cmd_q);
hci_dev_lock(hdev);
- inquiry_cache_flush(hdev);
+ hci_inquiry_cache_flush(hdev);
hci_conn_hash_flush(hdev);
hci_dev_unlock(hdev);
@@ -1991,80 +1997,59 @@ int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
return mgmt_device_unblocked(hdev, bdaddr, type);
}
-static void le_scan_param_req(struct hci_request *req, unsigned long opt)
+static void inquiry_complete(struct hci_dev *hdev, u8 status)
{
- struct le_scan_params *param = (struct le_scan_params *) opt;
- struct hci_cp_le_set_scan_param cp;
-
- memset(&cp, 0, sizeof(cp));
- cp.type = param->type;
- cp.interval = cpu_to_le16(param->interval);
- cp.window = cpu_to_le16(param->window);
+ if (status) {
+ BT_ERR("Failed to start inquiry: status %d", status);
- hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(cp), &cp);
-}
-
-static void le_scan_enable_req(struct hci_request *req, unsigned long opt)
-{
- struct hci_cp_le_set_scan_enable cp;
-
- memset(&cp, 0, sizeof(cp));
- cp.enable = LE_SCAN_ENABLE;
- cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
-
- hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+ hci_dev_lock(hdev);
+ hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+ hci_dev_unlock(hdev);
+ return;
+ }
}
-static int hci_do_le_scan(struct hci_dev *hdev, u8 type, u16 interval,
- u16 window, int timeout)
+static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status)
{
- long timeo = msecs_to_jiffies(3000);
- struct le_scan_params param;
+ /* General inquiry access code (GIAC) */
+ u8 lap[3] = { 0x33, 0x8b, 0x9e };
+ struct hci_request req;
+ struct hci_cp_inquiry cp;
int err;
- BT_DBG("%s", hdev->name);
-
- if (test_bit(HCI_LE_SCAN, &hdev->dev_flags))
- return -EINPROGRESS;
-
- param.type = type;
- param.interval = interval;
- param.window = window;
-
- hci_req_lock(hdev);
-
- err = __hci_req_sync(hdev, le_scan_param_req, (unsigned long) &param,
- timeo);
- if (!err)
- err = __hci_req_sync(hdev, le_scan_enable_req, 0, timeo);
-
- hci_req_unlock(hdev);
+ if (status) {
+ BT_ERR("Failed to disable LE scanning: status %d", status);
+ return;
+ }
- if (err < 0)
- return err;
+ switch (hdev->discovery.type) {
+ case DISCOV_TYPE_LE:
+ hci_dev_lock(hdev);
+ hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+ hci_dev_unlock(hdev);
+ break;
- queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable,
- timeout);
+ case DISCOV_TYPE_INTERLEAVED:
+ hci_req_init(&req, hdev);
- return 0;
-}
+ memset(&cp, 0, sizeof(cp));
+ memcpy(&cp.lap, lap, sizeof(cp.lap));
+ cp.length = DISCOV_INTERLEAVED_INQUIRY_LEN;
+ hci_req_add(&req, HCI_OP_INQUIRY, sizeof(cp), &cp);
-int hci_cancel_le_scan(struct hci_dev *hdev)
-{
- BT_DBG("%s", hdev->name);
+ hci_dev_lock(hdev);
- if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags))
- return -EALREADY;
+ hci_inquiry_cache_flush(hdev);
- if (cancel_delayed_work(&hdev->le_scan_disable)) {
- struct hci_cp_le_set_scan_enable cp;
+ err = hci_req_run(&req, inquiry_complete);
+ if (err) {
+ BT_ERR("Inquiry request failed: err %d", err);
+ hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+ }
- /* Send HCI command to disable LE Scan */
- memset(&cp, 0, sizeof(cp));
- hci_send_cmd(hdev, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+ hci_dev_unlock(hdev);
+ break;
}
-
- return 0;
}
static void le_scan_disable_work(struct work_struct *work)
@@ -2072,46 +2057,20 @@ static void le_scan_disable_work(struct work_struct *work)
struct hci_dev *hdev = container_of(work, struct hci_dev,
le_scan_disable.work);
struct hci_cp_le_set_scan_enable cp;
+ struct hci_request req;
+ int err;
BT_DBG("%s", hdev->name);
- memset(&cp, 0, sizeof(cp));
-
- hci_send_cmd(hdev, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
-}
-
-static void le_scan_work(struct work_struct *work)
-{
- struct hci_dev *hdev = container_of(work, struct hci_dev, le_scan);
- struct le_scan_params *param = &hdev->le_scan_params;
+ hci_req_init(&req, hdev);
- BT_DBG("%s", hdev->name);
+ memset(&cp, 0, sizeof(cp));
+ cp.enable = LE_SCAN_DISABLE;
+ hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
- hci_do_le_scan(hdev, param->type, param->interval, param->window,
- param->timeout);
-}
-
-int hci_le_scan(struct hci_dev *hdev, u8 type, u16 interval, u16 window,
- int timeout)
-{
- struct le_scan_params *param = &hdev->le_scan_params;
-
- BT_DBG("%s", hdev->name);
-
- if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags))
- return -ENOTSUPP;
-
- if (work_busy(&hdev->le_scan))
- return -EINPROGRESS;
-
- param->type = type;
- param->interval = interval;
- param->window = window;
- param->timeout = timeout;
-
- queue_work(system_long_wq, &hdev->le_scan);
-
- return 0;
+ err = hci_req_run(&req, le_scan_disable_work_complete);
+ if (err)
+ BT_ERR("Disable LE scanning request failed: err %d", err);
}
/* Alloc HCI device */
@@ -2148,7 +2107,6 @@ struct hci_dev *hci_alloc_dev(void)
INIT_WORK(&hdev->cmd_work, hci_cmd_work);
INIT_WORK(&hdev->tx_work, hci_tx_work);
INIT_WORK(&hdev->power_on, hci_power_on);
- INIT_WORK(&hdev->le_scan, le_scan_work);
INIT_DELAYED_WORK(&hdev->power_off, hci_power_off);
INIT_DELAYED_WORK(&hdev->discov_off, hci_discov_off);
@@ -3550,36 +3508,6 @@ static void hci_cmd_work(struct work_struct *work)
}
}
-int hci_do_inquiry(struct hci_dev *hdev, u8 length)
-{
- /* General inquiry access code (GIAC) */
- u8 lap[3] = { 0x33, 0x8b, 0x9e };
- struct hci_cp_inquiry cp;
-
- BT_DBG("%s", hdev->name);
-
- if (test_bit(HCI_INQUIRY, &hdev->flags))
- return -EINPROGRESS;
-
- inquiry_cache_flush(hdev);
-
- memset(&cp, 0, sizeof(cp));
- memcpy(&cp.lap, lap, sizeof(cp.lap));
- cp.length = length;
-
- return hci_send_cmd(hdev, HCI_OP_INQUIRY, sizeof(cp), &cp);
-}
-
-int hci_cancel_inquiry(struct hci_dev *hdev)
-{
- BT_DBG("%s", hdev->name);
-
- if (!test_bit(HCI_INQUIRY, &hdev->flags))
- return -EALREADY;
-
- return hci_send_cmd(hdev, HCI_OP_INQUIRY_CANCEL, 0, NULL);
-}
-
u8 bdaddr_to_le(u8 bdaddr_type)
{
switch (bdaddr_type) {
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index b93cd2eb5d58..0437200d92f4 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -40,21 +40,13 @@ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb)
BT_DBG("%s status 0x%2.2x", hdev->name, status);
- if (status) {
- hci_dev_lock(hdev);
- mgmt_stop_discovery_failed(hdev, status);
- hci_dev_unlock(hdev);
+ if (status)
return;
- }
clear_bit(HCI_INQUIRY, &hdev->flags);
smp_mb__after_clear_bit(); /* wake_up_bit advises about this barrier */
wake_up_bit(&hdev->flags, HCI_INQUIRY);
- hci_dev_lock(hdev);
- hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
- hci_dev_unlock(hdev);
-
hci_conn_check_pending(hdev);
}
@@ -937,20 +929,6 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
hci_dev_unlock(hdev);
}
-static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb)
-{
- __u8 status = *((__u8 *) skb->data);
-
- BT_DBG("%s status 0x%2.2x", hdev->name, status);
-
- if (status) {
- hci_dev_lock(hdev);
- mgmt_start_discovery_failed(hdev, status);
- hci_dev_unlock(hdev);
- return;
- }
-}
-
static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
struct sk_buff *skb)
{
@@ -963,41 +941,16 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
if (!cp)
return;
+ if (status)
+ return;
+
switch (cp->enable) {
case LE_SCAN_ENABLE:
- if (status) {
- hci_dev_lock(hdev);
- mgmt_start_discovery_failed(hdev, status);
- hci_dev_unlock(hdev);
- return;
- }
-
set_bit(HCI_LE_SCAN, &hdev->dev_flags);
-
- hci_dev_lock(hdev);
- hci_discovery_set_state(hdev, DISCOVERY_FINDING);
- hci_dev_unlock(hdev);
break;
case LE_SCAN_DISABLE:
- if (status) {
- hci_dev_lock(hdev);
- mgmt_stop_discovery_failed(hdev, status);
- hci_dev_unlock(hdev);
- return;
- }
-
clear_bit(HCI_LE_SCAN, &hdev->dev_flags);
-
- if (hdev->discovery.type == DISCOV_TYPE_INTERLEAVED &&
- hdev->discovery.state == DISCOVERY_FINDING) {
- mgmt_interleaved_discovery(hdev);
- } else {
- hci_dev_lock(hdev);
- hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
- hci_dev_unlock(hdev);
- }
-
break;
default:
@@ -1077,18 +1030,10 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
if (status) {
hci_conn_check_pending(hdev);
- hci_dev_lock(hdev);
- if (test_bit(HCI_MGMT, &hdev->dev_flags))
- mgmt_start_discovery_failed(hdev, status);
- hci_dev_unlock(hdev);
return;
}
set_bit(HCI_INQUIRY, &hdev->flags);
-
- hci_dev_lock(hdev);
- hci_discovery_set_state(hdev, DISCOVERY_FINDING);
- hci_dev_unlock(hdev);
}
static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status)
@@ -2298,10 +2243,6 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
hci_cc_user_passkey_neg_reply(hdev, skb);
break;
- case HCI_OP_LE_SET_SCAN_PARAM:
- hci_cc_le_set_scan_param(hdev, skb);
- break;
-
case HCI_OP_LE_SET_ADV_ENABLE:
hci_cc_le_set_adv_enable(hdev, skb);
break;
@@ -2670,7 +2611,7 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
BT_DBG("%s", hdev->name);
- if (!test_bit(HCI_LINK_KEYS, &hdev->dev_flags))
+ if (!test_bit(HCI_MGMT, &hdev->dev_flags))
return;
hci_dev_lock(hdev);
@@ -2746,7 +2687,7 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb)
hci_conn_drop(conn);
}
- if (test_bit(HCI_LINK_KEYS, &hdev->dev_flags))
+ if (test_bit(HCI_MGMT, &hdev->dev_flags))
hci_add_link_key(hdev, conn, 1, &ev->bdaddr, ev->link_key,
ev->key_type, pin_len);
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 46c6a148f0b3..0c699cdc3696 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -76,25 +76,19 @@ static void hidp_copy_session(struct hidp_session *session, struct hidp_conninfo
ci->flags = session->flags;
ci->state = BT_CONNECTED;
- ci->vendor = 0x0000;
- ci->product = 0x0000;
- ci->version = 0x0000;
-
if (session->input) {
ci->vendor = session->input->id.vendor;
ci->product = session->input->id.product;
ci->version = session->input->id.version;
if (session->input->name)
- strncpy(ci->name, session->input->name, 128);
+ strlcpy(ci->name, session->input->name, 128);
else
- strncpy(ci->name, "HID Boot Device", 128);
- }
-
- if (session->hid) {
+ strlcpy(ci->name, "HID Boot Device", 128);
+ } else if (session->hid) {
ci->vendor = session->hid->vendor;
ci->product = session->hid->product;
ci->version = session->hid->version;
- strncpy(ci->name, session->hid->name, 128);
+ strlcpy(ci->name, session->hid->name, 128);
}
}
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 68843a28a7af..8c3499bec893 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -504,8 +504,10 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
if (conn->hcon->type == LE_LINK) {
/* LE connection */
chan->omtu = L2CAP_DEFAULT_MTU;
- chan->scid = L2CAP_CID_LE_DATA;
- chan->dcid = L2CAP_CID_LE_DATA;
+ if (chan->dcid == L2CAP_CID_ATT)
+ chan->scid = L2CAP_CID_ATT;
+ else
+ chan->scid = l2cap_alloc_cid(conn);
} else {
/* Alloc CID for connection-oriented socket */
chan->scid = l2cap_alloc_cid(conn);
@@ -543,6 +545,8 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
l2cap_chan_hold(chan);
+ hci_conn_hold(conn->hcon);
+
list_add(&chan->list, &conn->chan_l);
}
@@ -1338,17 +1342,21 @@ static struct l2cap_chan *l2cap_global_chan_by_scid(int state, u16 cid,
static void l2cap_le_conn_ready(struct l2cap_conn *conn)
{
- struct sock *parent, *sk;
+ struct sock *parent;
struct l2cap_chan *chan, *pchan;
BT_DBG("");
/* Check if we have socket listening on cid */
- pchan = l2cap_global_chan_by_scid(BT_LISTEN, L2CAP_CID_LE_DATA,
+ pchan = l2cap_global_chan_by_scid(BT_LISTEN, L2CAP_CID_ATT,
conn->src, conn->dst);
if (!pchan)
return;
+ /* Client ATT sockets should override the server one */
+ if (__l2cap_get_chan_by_dcid(conn, L2CAP_CID_ATT))
+ return;
+
parent = pchan->sk;
lock_sock(parent);
@@ -1357,17 +1365,12 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn)
if (!chan)
goto clean;
- sk = chan->sk;
-
- hci_conn_hold(conn->hcon);
- conn->hcon->disc_timeout = HCI_DISCONN_TIMEOUT;
-
- bacpy(&bt_sk(sk)->src, conn->src);
- bacpy(&bt_sk(sk)->dst, conn->dst);
+ chan->dcid = L2CAP_CID_ATT;
- l2cap_chan_add(conn, chan);
+ bacpy(&bt_sk(chan->sk)->src, conn->src);
+ bacpy(&bt_sk(chan->sk)->dst, conn->dst);
- l2cap_chan_ready(chan);
+ __l2cap_chan_add(conn, chan);
clean:
release_sock(parent);
@@ -1380,14 +1383,17 @@ static void l2cap_conn_ready(struct l2cap_conn *conn)
BT_DBG("conn %p", conn);
- if (!hcon->out && hcon->type == LE_LINK)
- l2cap_le_conn_ready(conn);
-
+ /* For outgoing pairing which doesn't necessarily have an
+ * associated socket (e.g. mgmt_pair_device).
+ */
if (hcon->out && hcon->type == LE_LINK)
smp_conn_security(hcon, hcon->pending_sec_level);
mutex_lock(&conn->chan_lock);
+ if (hcon->type == LE_LINK)
+ l2cap_le_conn_ready(conn);
+
list_for_each_entry(chan, &conn->chan_l, list) {
l2cap_chan_lock(chan);
@@ -1792,7 +1798,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
auth_type = l2cap_get_auth_type(chan);
- if (chan->dcid == L2CAP_CID_LE_DATA)
+ if (bdaddr_type_is_le(dst_type))
hcon = hci_connect(hdev, LE_LINK, dst, dst_type,
chan->sec_level, auth_type);
else
@@ -1811,16 +1817,10 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
goto done;
}
- if (hcon->type == LE_LINK) {
- err = 0;
-
- if (!list_empty(&conn->chan_l)) {
- err = -EBUSY;
- hci_conn_drop(hcon);
- }
-
- if (err)
- goto done;
+ if (cid && __l2cap_get_chan_by_dcid(conn, cid)) {
+ hci_conn_drop(hcon);
+ err = -EBUSY;
+ goto done;
}
/* Update source addr of the socket */
@@ -1830,6 +1830,9 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
l2cap_chan_add(conn, chan);
l2cap_chan_lock(chan);
+ /* l2cap_chan_add takes its own ref so we can drop this one */
+ hci_conn_drop(hcon);
+
l2cap_state_change(chan, BT_CONNECT);
__set_chan_timer(chan, sk->sk_sndtimeo);
@@ -3751,8 +3754,6 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn,
sk = chan->sk;
- hci_conn_hold(conn->hcon);
-
bacpy(&bt_sk(sk)->src, conn->src);
bacpy(&bt_sk(sk)->dst, conn->dst);
chan->psm = psm;
@@ -5292,6 +5293,51 @@ static inline int l2cap_le_sig_cmd(struct l2cap_conn *conn,
}
}
+static inline void l2cap_le_sig_channel(struct l2cap_conn *conn,
+ struct sk_buff *skb)
+{
+ u8 *data = skb->data;
+ int len = skb->len;
+ struct l2cap_cmd_hdr cmd;
+ int err;
+
+ l2cap_raw_recv(conn, skb);
+
+ while (len >= L2CAP_CMD_HDR_SIZE) {
+ u16 cmd_len;
+ memcpy(&cmd, data, L2CAP_CMD_HDR_SIZE);
+ data += L2CAP_CMD_HDR_SIZE;
+ len -= L2CAP_CMD_HDR_SIZE;
+
+ cmd_len = le16_to_cpu(cmd.len);
+
+ BT_DBG("code 0x%2.2x len %d id 0x%2.2x", cmd.code, cmd_len,
+ cmd.ident);
+
+ if (cmd_len > len || !cmd.ident) {
+ BT_DBG("corrupted command");
+ break;
+ }
+
+ err = l2cap_le_sig_cmd(conn, &cmd, data);
+ if (err) {
+ struct l2cap_cmd_rej_unk rej;
+
+ BT_ERR("Wrong link type (%d)", err);
+
+ /* FIXME: Map err to a valid reason */
+ rej.reason = __constant_cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
+ l2cap_send_cmd(conn, cmd.ident, L2CAP_COMMAND_REJ,
+ sizeof(rej), &rej);
+ }
+
+ data += cmd_len;
+ len -= cmd_len;
+ }
+
+ kfree_skb(skb);
+}
+
static inline void l2cap_sig_channel(struct l2cap_conn *conn,
struct sk_buff *skb)
{
@@ -5318,11 +5364,7 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn,
break;
}
- if (conn->hcon->type == LE_LINK)
- err = l2cap_le_sig_cmd(conn, &cmd, data);
- else
- err = l2cap_bredr_sig_cmd(conn, &cmd, cmd_len, data);
-
+ err = l2cap_bredr_sig_cmd(conn, &cmd, cmd_len, data);
if (err) {
struct l2cap_cmd_rej_unk rej;
@@ -6356,16 +6398,13 @@ static void l2cap_att_channel(struct l2cap_conn *conn,
{
struct l2cap_chan *chan;
- chan = l2cap_global_chan_by_scid(0, L2CAP_CID_LE_DATA,
+ chan = l2cap_global_chan_by_scid(BT_CONNECTED, L2CAP_CID_ATT,
conn->src, conn->dst);
if (!chan)
goto drop;
BT_DBG("chan %p, len %d", chan, skb->len);
- if (chan->state != BT_BOUND && chan->state != BT_CONNECTED)
- goto drop;
-
if (chan->imtu < skb->len)
goto drop;
@@ -6395,6 +6434,8 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb)
switch (cid) {
case L2CAP_CID_LE_SIGNALING:
+ l2cap_le_sig_channel(conn, skb);
+ break;
case L2CAP_CID_SIGNALING:
l2cap_sig_channel(conn, skb);
break;
@@ -6405,7 +6446,7 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb)
l2cap_conless_channel(conn, psm, skb);
break;
- case L2CAP_CID_LE_DATA:
+ case L2CAP_CID_ATT:
l2cap_att_channel(conn, skb);
break;
@@ -6531,7 +6572,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
continue;
}
- if (chan->scid == L2CAP_CID_LE_DATA) {
+ if (chan->scid == L2CAP_CID_ATT) {
if (!status && encrypt) {
chan->sec_level = hcon->sec_level;
l2cap_chan_ready(chan);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 36fed40c162c..0098af80b213 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -466,7 +466,7 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname,
static bool l2cap_valid_mtu(struct l2cap_chan *chan, u16 mtu)
{
switch (chan->scid) {
- case L2CAP_CID_LE_DATA:
+ case L2CAP_CID_ATT:
if (mtu < L2CAP_LE_MIN_MTU)
return false;
break;
@@ -630,7 +630,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
conn = chan->conn;
/*change security for LE channels */
- if (chan->scid == L2CAP_CID_LE_DATA) {
+ if (chan->scid == L2CAP_CID_ATT) {
if (!conn->hcon->out) {
err = -EINVAL;
break;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index f8ecbc70293d..fedc5399d465 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -102,18 +102,6 @@ static const u16 mgmt_events[] = {
MGMT_EV_PASSKEY_NOTIFY,
};
-/*
- * These LE scan and inquiry parameters were chosen according to LE General
- * Discovery Procedure specification.
- */
-#define LE_SCAN_WIN 0x12
-#define LE_SCAN_INT 0x12
-#define LE_SCAN_TIMEOUT_LE_ONLY msecs_to_jiffies(10240)
-#define LE_SCAN_TIMEOUT_BREDR_LE msecs_to_jiffies(5120)
-
-#define INQUIRY_LEN_BREDR 0x08 /* TGAP(100) */
-#define INQUIRY_LEN_BREDR_LE 0x04 /* TGAP(100)/2 */
-
#define CACHE_TIMEOUT msecs_to_jiffies(2 * 1000)
#define hdev_is_powered(hdev) (test_bit(HCI_UP, &hdev->flags) && \
@@ -1748,8 +1736,6 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
hci_link_keys_clear(hdev);
- set_bit(HCI_LINK_KEYS, &hdev->dev_flags);
-
if (cp->debug_keys)
set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags);
else
@@ -2633,28 +2619,72 @@ static int remove_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
return err;
}
-int mgmt_interleaved_discovery(struct hci_dev *hdev)
+static int mgmt_start_discovery_failed(struct hci_dev *hdev, u8 status)
{
+ struct pending_cmd *cmd;
+ u8 type;
int err;
- BT_DBG("%s", hdev->name);
+ hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
- hci_dev_lock(hdev);
+ cmd = mgmt_pending_find(MGMT_OP_START_DISCOVERY, hdev);
+ if (!cmd)
+ return -ENOENT;
- err = hci_do_inquiry(hdev, INQUIRY_LEN_BREDR_LE);
- if (err < 0)
- hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+ type = hdev->discovery.type;
- hci_dev_unlock(hdev);
+ err = cmd_complete(cmd->sk, hdev->id, cmd->opcode, mgmt_status(status),
+ &type, sizeof(type));
+ mgmt_pending_remove(cmd);
return err;
}
+static void start_discovery_complete(struct hci_dev *hdev, u8 status)
+{
+ BT_DBG("status %d", status);
+
+ if (status) {
+ hci_dev_lock(hdev);
+ mgmt_start_discovery_failed(hdev, status);
+ hci_dev_unlock(hdev);
+ return;
+ }
+
+ hci_dev_lock(hdev);
+ hci_discovery_set_state(hdev, DISCOVERY_FINDING);
+ hci_dev_unlock(hdev);
+
+ switch (hdev->discovery.type) {
+ case DISCOV_TYPE_LE:
+ queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable,
+ DISCOV_LE_TIMEOUT);
+ break;
+
+ case DISCOV_TYPE_INTERLEAVED:
+ queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable,
+ DISCOV_INTERLEAVED_TIMEOUT);
+ break;
+
+ case DISCOV_TYPE_BREDR:
+ break;
+
+ default:
+ BT_ERR("Invalid discovery type %d", hdev->discovery.type);
+ }
+}
+
static int start_discovery(struct sock *sk, struct hci_dev *hdev,
void *data, u16 len)
{
struct mgmt_cp_start_discovery *cp = data;
struct pending_cmd *cmd;
+ struct hci_cp_le_set_scan_param param_cp;
+ struct hci_cp_le_set_scan_enable enable_cp;
+ struct hci_cp_inquiry inq_cp;
+ struct hci_request req;
+ /* General inquiry access code (GIAC) */
+ u8 lap[3] = { 0x33, 0x8b, 0x9e };
int err;
BT_DBG("%s", hdev->name);
@@ -2687,6 +2717,8 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
hdev->discovery.type = cp->type;
+ hci_req_init(&req, hdev);
+
switch (hdev->discovery.type) {
case DISCOV_TYPE_BREDR:
if (!lmp_bredr_capable(hdev)) {
@@ -2696,10 +2728,23 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
goto failed;
}
- err = hci_do_inquiry(hdev, INQUIRY_LEN_BREDR);
+ if (test_bit(HCI_INQUIRY, &hdev->flags)) {
+ err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
+ MGMT_STATUS_BUSY);
+ mgmt_pending_remove(cmd);
+ goto failed;
+ }
+
+ hci_inquiry_cache_flush(hdev);
+
+ memset(&inq_cp, 0, sizeof(inq_cp));
+ memcpy(&inq_cp.lap, lap, sizeof(inq_cp.lap));
+ inq_cp.length = DISCOV_BREDR_INQUIRY_LEN;
+ hci_req_add(&req, HCI_OP_INQUIRY, sizeof(inq_cp), &inq_cp);
break;
case DISCOV_TYPE_LE:
+ case DISCOV_TYPE_INTERLEAVED:
if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) {
err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
MGMT_STATUS_NOT_SUPPORTED);
@@ -2707,20 +2752,40 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
goto failed;
}
- err = hci_le_scan(hdev, LE_SCAN_ACTIVE, LE_SCAN_INT,
- LE_SCAN_WIN, LE_SCAN_TIMEOUT_LE_ONLY);
- break;
-
- case DISCOV_TYPE_INTERLEAVED:
- if (!lmp_host_le_capable(hdev) || !lmp_bredr_capable(hdev)) {
+ if (hdev->discovery.type == DISCOV_TYPE_INTERLEAVED &&
+ !lmp_bredr_capable(hdev)) {
err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
MGMT_STATUS_NOT_SUPPORTED);
mgmt_pending_remove(cmd);
goto failed;
}
- err = hci_le_scan(hdev, LE_SCAN_ACTIVE, LE_SCAN_INT,
- LE_SCAN_WIN, LE_SCAN_TIMEOUT_BREDR_LE);
+ if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
+ err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
+ MGMT_STATUS_REJECTED);
+ mgmt_pending_remove(cmd);
+ goto failed;
+ }
+
+ if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) {
+ err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
+ MGMT_STATUS_BUSY);
+ mgmt_pending_remove(cmd);
+ goto failed;
+ }
+
+ memset(&param_cp, 0, sizeof(param_cp));
+ param_cp.type = LE_SCAN_ACTIVE;
+ param_cp.interval = cpu_to_le16(DISCOV_LE_SCAN_INT);
+ param_cp.window = cpu_to_le16(DISCOV_LE_SCAN_WIN);
+ hci_req_add(&req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
+ &param_cp);
+
+ memset(&enable_cp, 0, sizeof(enable_cp));
+ enable_cp.enable = LE_SCAN_ENABLE;
+ enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
+ hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp),
+ &enable_cp);
break;
default:
@@ -2730,6 +2795,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
goto failed;
}
+ err = hci_req_run(&req, start_discovery_complete);
if (err < 0)
mgmt_pending_remove(cmd);
else
@@ -2740,6 +2806,39 @@ failed:
return err;
}
+static int mgmt_stop_discovery_failed(struct hci_dev *hdev, u8 status)
+{
+ struct pending_cmd *cmd;
+ int err;
+
+ cmd = mgmt_pending_find(MGMT_OP_STOP_DISCOVERY, hdev);
+ if (!cmd)
+ return -ENOENT;
+
+ err = cmd_complete(cmd->sk, hdev->id, cmd->opcode, mgmt_status(status),
+ &hdev->discovery.type, sizeof(hdev->discovery.type));
+ mgmt_pending_remove(cmd);
+
+ return err;
+}
+
+static void stop_discovery_complete(struct hci_dev *hdev, u8 status)
+{
+ BT_DBG("status %d", status);
+
+ hci_dev_lock(hdev);
+
+ if (status) {
+ mgmt_stop_discovery_failed(hdev, status);
+ goto unlock;
+ }
+
+ hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+
+unlock:
+ hci_dev_unlock(hdev);
+}
+
static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
u16 len)
{
@@ -2747,6 +2846,8 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
struct pending_cmd *cmd;
struct hci_cp_remote_name_req_cancel cp;
struct inquiry_entry *e;
+ struct hci_request req;
+ struct hci_cp_le_set_scan_enable enable_cp;
int err;
BT_DBG("%s", hdev->name);
@@ -2773,12 +2874,20 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
goto unlock;
}
+ hci_req_init(&req, hdev);
+
switch (hdev->discovery.state) {
case DISCOVERY_FINDING:
- if (test_bit(HCI_INQUIRY, &hdev->flags))
- err = hci_cancel_inquiry(hdev);
- else
- err = hci_cancel_le_scan(hdev);
+ if (test_bit(HCI_INQUIRY, &hdev->flags)) {
+ hci_req_add(&req, HCI_OP_INQUIRY_CANCEL, 0, NULL);
+ } else {
+ cancel_delayed_work(&hdev->le_scan_disable);
+
+ memset(&enable_cp, 0, sizeof(enable_cp));
+ enable_cp.enable = LE_SCAN_DISABLE;
+ hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE,
+ sizeof(enable_cp), &enable_cp);
+ }
break;
@@ -2796,16 +2905,22 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
}
bacpy(&cp.bdaddr, &e->data.bdaddr);
- err = hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ_CANCEL,
- sizeof(cp), &cp);
+ hci_req_add(&req, HCI_OP_REMOTE_NAME_REQ_CANCEL, sizeof(cp),
+ &cp);
break;
default:
BT_DBG("unknown discovery state %u", hdev->discovery.state);
- err = -EFAULT;
+
+ mgmt_pending_remove(cmd);
+ err = cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY,
+ MGMT_STATUS_FAILED, &mgmt_cp->type,
+ sizeof(mgmt_cp->type));
+ goto unlock;
}
+ err = hci_req_run(&req, stop_discovery_complete);
if (err < 0)
mgmt_pending_remove(cmd);
else
@@ -4063,6 +4178,9 @@ int mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
struct mgmt_ev_device_found *ev = (void *) buf;
size_t ev_size;
+ if (!hci_discovery_active(hdev))
+ return -EPERM;
+
/* Leave 5 bytes for a potential CoD field */
if (sizeof(*ev) + eir_len + 5 > sizeof(buf))
return -EINVAL;
@@ -4114,43 +4232,6 @@ int mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
sizeof(*ev) + eir_len, NULL);
}
-int mgmt_start_discovery_failed(struct hci_dev *hdev, u8 status)
-{
- struct pending_cmd *cmd;
- u8 type;
- int err;
-
- hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
-
- cmd = mgmt_pending_find(MGMT_OP_START_DISCOVERY, hdev);
- if (!cmd)
- return -ENOENT;
-
- type = hdev->discovery.type;
-
- err = cmd_complete(cmd->sk, hdev->id, cmd->opcode, mgmt_status(status),
- &type, sizeof(type));
- mgmt_pending_remove(cmd);
-
- return err;
-}
-
-int mgmt_stop_discovery_failed(struct hci_dev *hdev, u8 status)
-{
- struct pending_cmd *cmd;
- int err;
-
- cmd = mgmt_pending_find(MGMT_OP_STOP_DISCOVERY, hdev);
- if (!cmd)
- return -ENOENT;
-
- err = cmd_complete(cmd->sk, hdev->id, cmd->opcode, mgmt_status(status),
- &hdev->discovery.type, sizeof(hdev->discovery.type));
- mgmt_pending_remove(cmd);
-
- return err;
-}
-
int mgmt_discovering(struct hci_dev *hdev, u8 discovering)
{
struct mgmt_ev_discovering ev;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 967312803e41..2ef66781fedb 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -22,6 +22,9 @@
#include <asm/uaccess.h>
#include "br_private.h"
+#define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \
+ NETIF_F_GSO_MASK | NETIF_F_HW_CSUM)
+
/* net device transmit always called with BH disabled */
netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
{
@@ -55,10 +58,10 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
skb_pull(skb, ETH_HLEN);
if (is_broadcast_ether_addr(dest))
- br_flood_deliver(br, skb);
+ br_flood_deliver(br, skb, false);
else if (is_multicast_ether_addr(dest)) {
if (unlikely(netpoll_tx_running(dev))) {
- br_flood_deliver(br, skb);
+ br_flood_deliver(br, skb, false);
goto out;
}
if (br_multicast_rcv(br, NULL, skb)) {
@@ -70,11 +73,11 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb))
br_multicast_deliver(mdst, skb);
else
- br_flood_deliver(br, skb);
+ br_flood_deliver(br, skb, false);
} else if ((dst = __br_fdb_get(br, dest, vid)) != NULL)
br_deliver(dst->dst, skb);
else
- br_flood_deliver(br, skb);
+ br_flood_deliver(br, skb, true);
out:
rcu_read_unlock();
@@ -346,12 +349,10 @@ void br_dev_setup(struct net_device *dev)
dev->tx_queue_len = 0;
dev->priv_flags = IFF_EBRIDGE;
- dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
- NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_LLTX |
- NETIF_F_NETNS_LOCAL | NETIF_F_HW_VLAN_CTAG_TX;
- dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
- NETIF_F_GSO_MASK | NETIF_F_HW_CSUM |
- NETIF_F_HW_VLAN_CTAG_TX;
+ dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL |
+ NETIF_F_HW_VLAN_CTAG_TX;
+ dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX;
+ dev->vlan_features = COMMON_FEATURES;
br->dev = dev;
spin_lock_init(&br->lock);
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index ebfa4443c69b..60aca9109a50 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -707,6 +707,11 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
}
}
+ if (is_zero_ether_addr(addr)) {
+ pr_info("bridge: RTM_NEWNEIGH with invalid ether address\n");
+ return -EINVAL;
+ }
+
p = br_port_get_rtnl(dev);
if (p == NULL) {
pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n",
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 092b20e4ee4c..4b81b1471789 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -174,7 +174,8 @@ out:
static void br_flood(struct net_bridge *br, struct sk_buff *skb,
struct sk_buff *skb0,
void (*__packet_hook)(const struct net_bridge_port *p,
- struct sk_buff *skb))
+ struct sk_buff *skb),
+ bool unicast)
{
struct net_bridge_port *p;
struct net_bridge_port *prev;
@@ -182,6 +183,9 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb,
prev = NULL;
list_for_each_entry_rcu(p, &br->port_list, list) {
+ /* Do not flood unicast traffic to ports that turn it off */
+ if (unicast && !(p->flags & BR_FLOOD))
+ continue;
prev = maybe_deliver(prev, p, skb, __packet_hook);
if (IS_ERR(prev))
goto out;
@@ -203,16 +207,16 @@ out:
/* called with rcu_read_lock */
-void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb)
+void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast)
{
- br_flood(br, skb, NULL, __br_deliver);
+ br_flood(br, skb, NULL, __br_deliver, unicast);
}
/* called under bridge lock */
void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
- struct sk_buff *skb2)
+ struct sk_buff *skb2, bool unicast)
{
- br_flood(br, skb, skb2, __br_forward);
+ br_flood(br, skb, skb2, __br_forward, unicast);
}
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 4cdba60926ff..5623be6b9ecd 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -221,7 +221,7 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br,
p->path_cost = port_cost(dev);
p->priority = 0x8000 >> BR_PORT_BITS;
p->port_no = index;
- p->flags = 0;
+ p->flags = BR_LEARNING | BR_FLOOD;
br_init_port(p);
p->state = BR_STATE_DISABLED;
br_stp_port_timer_init(p);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 828e2bcc1f52..1b8b8b824cd7 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -65,6 +65,7 @@ int br_handle_frame_finish(struct sk_buff *skb)
struct net_bridge_fdb_entry *dst;
struct net_bridge_mdb_entry *mdst;
struct sk_buff *skb2;
+ bool unicast = true;
u16 vid = 0;
if (!p || p->state == BR_STATE_DISABLED)
@@ -75,7 +76,8 @@ int br_handle_frame_finish(struct sk_buff *skb)
/* insert into forwarding database after filtering to avoid spoofing */
br = p->br;
- br_fdb_update(br, p, eth_hdr(skb)->h_source, vid);
+ if (p->flags & BR_LEARNING)
+ br_fdb_update(br, p, eth_hdr(skb)->h_source, vid);
if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) &&
br_multicast_rcv(br, p, skb))
@@ -94,9 +96,10 @@ int br_handle_frame_finish(struct sk_buff *skb)
dst = NULL;
- if (is_broadcast_ether_addr(dest))
+ if (is_broadcast_ether_addr(dest)) {
skb2 = skb;
- else if (is_multicast_ether_addr(dest)) {
+ unicast = false;
+ } else if (is_multicast_ether_addr(dest)) {
mdst = br_mdb_get(br, skb, vid);
if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) {
if ((mdst && mdst->mglist) ||
@@ -109,6 +112,7 @@ int br_handle_frame_finish(struct sk_buff *skb)
} else
skb2 = skb;
+ unicast = false;
br->dev->stats.multicast++;
} else if ((dst = __br_fdb_get(br, dest, vid)) &&
dst->is_local) {
@@ -122,7 +126,7 @@ int br_handle_frame_finish(struct sk_buff *skb)
dst->used = jiffies;
br_forward(dst->dst, skb, skb2);
} else
- br_flood_forward(br, skb, skb2);
+ br_flood_forward(br, skb, skb2, unicast);
}
if (skb2)
@@ -142,7 +146,8 @@ static int br_handle_local_finish(struct sk_buff *skb)
u16 vid = 0;
br_vlan_get_tag(skb, &vid);
- br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid);
+ if (p->flags & BR_LEARNING)
+ br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid);
return 0; /* process further */
}
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 19942e38fd2d..0daae3ec2355 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -447,7 +447,7 @@ 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->mglist && mp->timer_armed &&
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 d6448e35e027..69af490cce44 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -23,6 +23,7 @@
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/timer.h>
+#include <linux/inetdevice.h>
#include <net/ip.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
@@ -269,7 +270,7 @@ static void br_multicast_del_pg(struct net_bridge *br,
del_timer(&p->timer);
call_rcu_bh(&p->rcu, br_multicast_free_pg);
- if (!mp->ports && !mp->mglist &&
+ if (!mp->ports && !mp->mglist && mp->timer_armed &&
netif_running(br->dev))
mod_timer(&mp->timer, jiffies);
@@ -381,7 +382,8 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
iph->frag_off = htons(IP_DF);
iph->ttl = 1;
iph->protocol = IPPROTO_IGMP;
- iph->saddr = 0;
+ iph->saddr = br->multicast_query_use_ifaddr ?
+ inet_select_addr(br->dev, 0, RT_SCOPE_LINK) : 0;
iph->daddr = htonl(INADDR_ALLHOSTS_GROUP);
((u8 *)&iph[1])[0] = IPOPT_RA;
((u8 *)&iph[1])[1] = 4;
@@ -616,8 +618,6 @@ rehash:
mp->br = br;
mp->addr = *group;
- setup_timer(&mp->timer, br_multicast_group_expired,
- (unsigned long)mp);
hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]);
mdb->size++;
@@ -655,7 +655,6 @@ static int br_multicast_add_group(struct net_bridge *br,
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
struct net_bridge_port_group __rcu **pp;
- unsigned long now = jiffies;
int err;
spin_lock(&br->multicast_lock);
@@ -670,7 +669,6 @@ static int br_multicast_add_group(struct net_bridge *br,
if (!port) {
mp->mglist = true;
- mod_timer(&mp->timer, now + br->multicast_membership_interval);
goto out;
}
@@ -678,7 +676,7 @@ static int br_multicast_add_group(struct net_bridge *br,
(p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (p->port == port)
- goto found;
+ goto out;
if ((unsigned long)p->port < (unsigned long)port)
break;
}
@@ -689,8 +687,6 @@ static int br_multicast_add_group(struct net_bridge *br,
rcu_assign_pointer(*pp, p);
br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
-found:
- mod_timer(&p->timer, now + br->multicast_membership_interval);
out:
err = 0;
@@ -1016,7 +1012,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
#endif
/*
- * Add port to rotuer_list
+ * Add port to router_list
* list is maintained ordered by pointer value
* and locked by br->multicast_lock and RCU
*/
@@ -1130,6 +1126,10 @@ static int br_ip4_multicast_query(struct net_bridge *br,
if (!mp)
goto out;
+ setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp);
+ mod_timer(&mp->timer, now + br->multicast_membership_interval);
+ mp->timer_armed = true;
+
max_delay *= br->multicast_last_member_count;
if (mp->mglist &&
@@ -1204,6 +1204,10 @@ static int br_ip6_multicast_query(struct net_bridge *br,
if (!mp)
goto out;
+ setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp);
+ mod_timer(&mp->timer, now + br->multicast_membership_interval);
+ mp->timer_armed = true;
+
max_delay *= br->multicast_last_member_count;
if (mp->mglist &&
(timer_pending(&mp->timer) ?
@@ -1247,6 +1251,32 @@ static void br_multicast_leave_group(struct net_bridge *br,
if (!mp)
goto out;
+ if (br->multicast_querier &&
+ !timer_pending(&br->multicast_querier_timer)) {
+ __br_multicast_send_query(br, port, &mp->addr);
+
+ time = jiffies + br->multicast_last_member_count *
+ br->multicast_last_member_interval;
+ mod_timer(port ? &port->multicast_query_timer :
+ &br->multicast_query_timer, time);
+
+ for (p = mlock_dereference(mp->ports, br);
+ p != NULL;
+ p = mlock_dereference(p->next, br)) {
+ if (p->port != port)
+ continue;
+
+ if (!hlist_unhashed(&p->mglist) &&
+ (timer_pending(&p->timer) ?
+ time_after(p->timer.expires, time) :
+ try_to_del_timer_sync(&p->timer) >= 0)) {
+ mod_timer(&p->timer, time);
+ }
+
+ break;
+ }
+ }
+
if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) {
struct net_bridge_port_group __rcu **pp;
@@ -1262,7 +1292,7 @@ static void br_multicast_leave_group(struct net_bridge *br,
call_rcu_bh(&p->rcu, br_multicast_free_pg);
br_mdb_notify(br->dev, port, group, RTM_DELMDB);
- if (!mp->ports && !mp->mglist &&
+ if (!mp->ports && !mp->mglist && mp->timer_armed &&
netif_running(br->dev))
mod_timer(&mp->timer, jiffies);
}
@@ -1274,30 +1304,12 @@ static void br_multicast_leave_group(struct net_bridge *br,
br->multicast_last_member_interval;
if (!port) {
- if (mp->mglist &&
+ if (mp->mglist && mp->timer_armed &&
(timer_pending(&mp->timer) ?
time_after(mp->timer.expires, time) :
try_to_del_timer_sync(&mp->timer) >= 0)) {
mod_timer(&mp->timer, time);
}
-
- goto out;
- }
-
- for (p = mlock_dereference(mp->ports, br);
- p != NULL;
- p = mlock_dereference(p->next, br)) {
- if (p->port != port)
- continue;
-
- if (!hlist_unhashed(&p->mglist) &&
- (timer_pending(&p->timer) ?
- time_after(p->timer.expires, time) :
- try_to_del_timer_sync(&p->timer) >= 0)) {
- mod_timer(&p->timer, time);
- }
-
- break;
}
out:
@@ -1619,6 +1631,7 @@ void br_multicast_init(struct net_bridge *br)
br->multicast_router = 1;
br->multicast_querier = 0;
+ br->multicast_query_use_ifaddr = 0;
br->multicast_last_member_count = 2;
br->multicast_startup_query_count = 2;
@@ -1672,6 +1685,7 @@ void br_multicast_stop(struct net_bridge *br)
hlist_for_each_entry_safe(mp, n, &mdb->mhash[i],
hlist[ver]) {
del_timer(&mp->timer);
+ mp->timer_armed = false;
call_rcu_bh(&mp->rcu, br_multicast_free_group);
}
}
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 1ed75bfd8d1d..f87736270eaa 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -992,7 +992,7 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
#ifdef CONFIG_SYSCTL
static
-int brnf_sysctl_call_tables(ctl_table * ctl, int write,
+int brnf_sysctl_call_tables(struct ctl_table *ctl, int write,
void __user * buffer, size_t * lenp, loff_t * ppos)
{
int ret;
@@ -1004,7 +1004,7 @@ int brnf_sysctl_call_tables(ctl_table * ctl, int write,
return ret;
}
-static ctl_table brnf_table[] = {
+static struct ctl_table brnf_table[] = {
{
.procname = "bridge-nf-call-arptables",
.data = &brnf_call_arptables,
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 8e3abf564798..1fc30abd3a52 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -30,6 +30,8 @@ static inline size_t br_port_info_size(void)
+ nla_total_size(1) /* IFLA_BRPORT_GUARD */
+ nla_total_size(1) /* IFLA_BRPORT_PROTECT */
+ nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */
+ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */
+ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */
+ 0;
}
@@ -56,7 +58,9 @@ static int br_port_fill_attrs(struct sk_buff *skb,
nla_put_u8(skb, IFLA_BRPORT_MODE, mode) ||
nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) ||
nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) ||
- nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)))
+ nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) ||
+ nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) ||
+ nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)))
return -EMSGSIZE;
return 0;
@@ -281,6 +285,8 @@ static const struct nla_policy ifla_brport_policy[IFLA_BRPORT_MAX + 1] = {
[IFLA_BRPORT_MODE] = { .type = NLA_U8 },
[IFLA_BRPORT_GUARD] = { .type = NLA_U8 },
[IFLA_BRPORT_PROTECT] = { .type = NLA_U8 },
+ [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 },
+ [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 },
};
/* Change the state of the port and notify spanning tree */
@@ -328,6 +334,8 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE);
br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK);
+ br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING);
+ br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD);
if (tb[IFLA_BRPORT_COST]) {
err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));
diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c
index 1644b3e1f947..3a3f371b2841 100644
--- a/net/bridge/br_notify.c
+++ b/net/bridge/br_notify.c
@@ -31,7 +31,7 @@ struct notifier_block br_device_notifier = {
*/
static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net_bridge_port *p;
struct net_bridge *br;
bool changed_addr;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d2c043a857b6..3be89b3ce17b 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -112,6 +112,7 @@ struct net_bridge_mdb_entry
struct timer_list timer;
struct br_ip addr;
bool mglist;
+ bool timer_armed;
};
struct net_bridge_mdb_htable
@@ -157,6 +158,8 @@ struct net_bridge_port
#define BR_ROOT_BLOCK 0x00000004
#define BR_MULTICAST_FAST_LEAVE 0x00000008
#define BR_ADMIN_COST 0x00000010
+#define BR_LEARNING 0x00000020
+#define BR_FLOOD 0x00000040
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
u32 multicast_startup_queries_sent;
@@ -249,6 +252,7 @@ struct net_bridge
u8 multicast_disabled:1;
u8 multicast_querier:1;
+ u8 multicast_query_use_ifaddr:1;
u32 hash_elasticity;
u32 hash_max;
@@ -411,9 +415,10 @@ extern int br_dev_queue_push_xmit(struct sk_buff *skb);
extern void br_forward(const struct net_bridge_port *to,
struct sk_buff *skb, struct sk_buff *skb0);
extern int br_forward_finish(struct sk_buff *skb);
-extern void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb);
+extern void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb,
+ bool unicast);
extern void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
- struct sk_buff *skb2);
+ struct sk_buff *skb2, bool unicast);
/* br_if.c */
extern void br_port_carrier_check(struct net_bridge_port *p);
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index 8baa9c08e1a4..394bb96b6087 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -375,6 +375,31 @@ static ssize_t store_multicast_snooping(struct device *d,
static DEVICE_ATTR(multicast_snooping, S_IRUGO | S_IWUSR,
show_multicast_snooping, store_multicast_snooping);
+static ssize_t show_multicast_query_use_ifaddr(struct device *d,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct net_bridge *br = to_bridge(d);
+ return sprintf(buf, "%d\n", br->multicast_query_use_ifaddr);
+}
+
+static int set_query_use_ifaddr(struct net_bridge *br, unsigned long val)
+{
+ br->multicast_query_use_ifaddr = !!val;
+ return 0;
+}
+
+static ssize_t
+store_multicast_query_use_ifaddr(struct device *d,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ return store_bridge_parm(d, buf, len, set_query_use_ifaddr);
+}
+static DEVICE_ATTR(multicast_query_use_ifaddr, S_IRUGO | S_IWUSR,
+ show_multicast_query_use_ifaddr,
+ store_multicast_query_use_ifaddr);
+
static ssize_t show_multicast_querier(struct device *d,
struct device_attribute *attr,
char *buf)
@@ -734,6 +759,7 @@ static struct attribute *bridge_attrs[] = {
&dev_attr_multicast_router.attr,
&dev_attr_multicast_snooping.attr,
&dev_attr_multicast_querier.attr,
+ &dev_attr_multicast_query_use_ifaddr.attr,
&dev_attr_hash_elasticity.attr,
&dev_attr_hash_max.attr,
&dev_attr_multicast_last_member_count.attr,
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index a1ef1b6e14dc..2a2cdb756d51 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -158,6 +158,8 @@ static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush);
BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE);
BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK);
+BRPORT_ATTR_FLAG(learning, BR_LEARNING);
+BRPORT_ATTR_FLAG(unicast_flood, BR_FLOOD);
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -195,6 +197,8 @@ static const struct brport_attribute *brport_attrs[] = {
&brport_attr_hairpin_mode,
&brport_attr_bpdu_guard,
&brport_attr_root_block,
+ &brport_attr_learning,
+ &brport_attr_unicast_flood,
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
&brport_attr_multicast_router,
&brport_attr_multicast_fast_leave,
diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c
index df0364aa12d5..518093802d1d 100644
--- a/net/bridge/netfilter/ebt_ulog.c
+++ b/net/bridge/netfilter/ebt_ulog.c
@@ -271,6 +271,12 @@ static int ebt_ulog_tg_check(const struct xt_tgchk_param *par)
{
struct ebt_ulog_info *uloginfo = par->targinfo;
+ if (!par->net->xt.ebt_ulog_warn_deprecated) {
+ pr_info("ebt_ulog is deprecated and it will be removed soon, "
+ "use ebt_nflog instead\n");
+ par->net->xt.ebt_ulog_warn_deprecated = true;
+ }
+
if (uloginfo->nlgroup > 31)
return -EINVAL;
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 3d110c4fc787..ac7802428384 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1339,7 +1339,7 @@ static inline int ebt_make_matchname(const struct ebt_entry_match *m,
/* ebtables expects 32 bytes long names but xt_match names are 29 bytes
long. Copy 29 bytes and fill remaining bytes with zeroes. */
- strncpy(name, m->u.match->name, sizeof(name));
+ strlcpy(name, m->u.match->name, sizeof(name));
if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN))
return -EFAULT;
return 0;
@@ -1351,7 +1351,7 @@ static inline int ebt_make_watchername(const struct ebt_entry_watcher *w,
char __user *hlp = ubase + ((char *)w - base);
char name[EBT_FUNCTION_MAXNAMELEN] = {};
- strncpy(name, w->u.watcher->name, sizeof(name));
+ strlcpy(name, w->u.watcher->name, sizeof(name));
if (copy_to_user(hlp , name, EBT_FUNCTION_MAXNAMELEN))
return -EFAULT;
return 0;
@@ -1377,7 +1377,7 @@ ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase)
ret = EBT_WATCHER_ITERATE(e, ebt_make_watchername, base, ubase);
if (ret != 0)
return ret;
- strncpy(name, t->u.target->name, sizeof(name));
+ strlcpy(name, t->u.target->name, sizeof(name));
if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN))
return -EFAULT;
return 0;
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index 1f9ece1a9c34..4dca159435cf 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -352,9 +352,9 @@ EXPORT_SYMBOL(caif_enroll_dev);
/* notify Caif of device events */
static int caif_device_notify(struct notifier_block *me, unsigned long what,
- void *arg)
+ void *ptr)
{
- struct net_device *dev = arg;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct caif_device_entry *caifd = NULL;
struct caif_dev_common *caifdev;
struct cfcnfg *cfg;
diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c
index 942e00a425fd..75ed04b78fa4 100644
--- a/net/caif/caif_usb.c
+++ b/net/caif/caif_usb.c
@@ -121,9 +121,9 @@ static struct packet_type caif_usb_type __read_mostly = {
};
static int cfusbl_device_notify(struct notifier_block *me, unsigned long what,
- void *arg)
+ void *ptr)
{
- struct net_device *dev = arg;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct caif_dev_common common;
struct cflayer *layer, *link_support;
struct usbnet *usbnet;
diff --git a/net/can/af_can.c b/net/can/af_can.c
index c4e50852c9f4..3ab8dd2e1282 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -794,9 +794,9 @@ EXPORT_SYMBOL(can_proto_unregister);
* af_can notifier to create/remove CAN netdevice specific structs
*/
static int can_notifier(struct notifier_block *nb, unsigned long msg,
- void *data)
+ void *ptr)
{
- struct net_device *dev = (struct net_device *)data;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct dev_rcv_lists *d;
if (!net_eq(dev_net(dev), &init_net))
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 8f113e6ff327..46f20bfafc0e 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1350,9 +1350,9 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock,
* notification handler for netdevice status changes
*/
static int bcm_notifier(struct notifier_block *nb, unsigned long msg,
- void *data)
+ void *ptr)
{
- struct net_device *dev = (struct net_device *)data;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier);
struct sock *sk = &bo->sk;
struct bcm_op *op;
diff --git a/net/can/gw.c b/net/can/gw.c
index 3ee690e8c7d3..2f291f961a17 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -445,9 +445,9 @@ static inline void cgw_unregister_filter(struct cgw_job *gwj)
}
static int cgw_notifier(struct notifier_block *nb,
- unsigned long msg, void *data)
+ unsigned long msg, void *ptr)
{
- struct net_device *dev = (struct net_device *)data;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
if (!net_eq(dev_net(dev), &init_net))
return NOTIFY_DONE;
diff --git a/net/can/raw.c b/net/can/raw.c
index 1085e65f848e..641e1c895123 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -239,9 +239,9 @@ static int raw_enable_allfilters(struct net_device *dev, struct sock *sk)
}
static int raw_notifier(struct notifier_block *nb,
- unsigned long msg, void *data)
+ unsigned long msg, void *ptr)
{
- struct net_device *dev = (struct net_device *)data;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct raw_sock *ro = container_of(nb, struct raw_sock, notifier);
struct sock *sk = &ro->sk;
diff --git a/net/core/datagram.c b/net/core/datagram.c
index b71423db7785..6e9ab31e457e 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -56,6 +56,7 @@
#include <net/sock.h>
#include <net/tcp_states.h>
#include <trace/events/skb.h>
+#include <net/ll_poll.h>
/*
* Is a socket 'connection oriented' ?
@@ -207,6 +208,10 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
}
spin_unlock_irqrestore(&queue->lock, cpu_flags);
+ if (sk_can_busy_loop(sk) &&
+ sk_busy_loop(sk, flags & MSG_DONTWAIT))
+ continue;
+
/* User doesn't want to wait */
error = -EAGAIN;
if (!timeo)
diff --git a/net/core/dev.c b/net/core/dev.c
index faebb398fb46..560dafd83adf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -129,6 +129,8 @@
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
+#include <linux/hashtable.h>
+#include <linux/vmalloc.h>
#include "net-sysfs.h"
@@ -166,6 +168,12 @@ static struct list_head offload_base __read_mostly;
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base_lock);
+/* protects napi_hash addition/deletion and napi_gen_id */
+static DEFINE_SPINLOCK(napi_hash_lock);
+
+static unsigned int napi_gen_id;
+static DEFINE_HASHTABLE(napi_hash, 8);
+
seqcount_t devnet_rename_seq;
static inline void dev_base_seq_inc(struct net *net)
@@ -1232,9 +1240,7 @@ static int __dev_open(struct net_device *dev)
* If we don't do this there is a chance ndo_poll_controller
* or ndo_poll may be running while we open the device
*/
- ret = netpoll_rx_disable(dev);
- if (ret)
- return ret;
+ netpoll_rx_disable(dev);
ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
ret = notifier_to_errno(ret);
@@ -1343,9 +1349,7 @@ static int __dev_close(struct net_device *dev)
LIST_HEAD(single);
/* Temporarily disable netpoll until the interface is down */
- retval = netpoll_rx_disable(dev);
- if (retval)
- return retval;
+ netpoll_rx_disable(dev);
list_add(&dev->unreg_list, &single);
retval = __dev_close_many(&single);
@@ -1387,14 +1391,11 @@ static int dev_close_many(struct list_head *head)
*/
int dev_close(struct net_device *dev)
{
- int ret = 0;
if (dev->flags & IFF_UP) {
LIST_HEAD(single);
/* Block netpoll rx while the interface is going down */
- ret = netpoll_rx_disable(dev);
- if (ret)
- return ret;
+ netpoll_rx_disable(dev);
list_add(&dev->unreg_list, &single);
dev_close_many(&single);
@@ -1402,7 +1403,7 @@ int dev_close(struct net_device *dev)
netpoll_rx_enable(dev);
}
- return ret;
+ return 0;
}
EXPORT_SYMBOL(dev_close);
@@ -1432,6 +1433,14 @@ void dev_disable_lro(struct net_device *dev)
}
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;
+
+ netdev_notifier_info_init(&info, dev);
+ return nb->notifier_call(nb, val, &info);
+}
static int dev_boot_phase = 1;
@@ -1464,7 +1473,7 @@ int register_netdevice_notifier(struct notifier_block *nb)
goto unlock;
for_each_net(net) {
for_each_netdev(net, dev) {
- err = nb->notifier_call(nb, NETDEV_REGISTER, dev);
+ err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
err = notifier_to_errno(err);
if (err)
goto rollback;
@@ -1472,7 +1481,7 @@ int register_netdevice_notifier(struct notifier_block *nb)
if (!(dev->flags & IFF_UP))
continue;
- nb->notifier_call(nb, NETDEV_UP, dev);
+ call_netdevice_notifier(nb, NETDEV_UP, dev);
}
}
@@ -1488,10 +1497,11 @@ rollback:
goto outroll;
if (dev->flags & IFF_UP) {
- nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
- nb->notifier_call(nb, NETDEV_DOWN, dev);
+ call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+ dev);
+ call_netdevice_notifier(nb, NETDEV_DOWN, dev);
}
- nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+ call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
}
}
@@ -1529,10 +1539,11 @@ int unregister_netdevice_notifier(struct notifier_block *nb)
for_each_net(net) {
for_each_netdev(net, dev) {
if (dev->flags & IFF_UP) {
- nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
- nb->notifier_call(nb, NETDEV_DOWN, dev);
+ call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+ dev);
+ call_netdevice_notifier(nb, NETDEV_DOWN, dev);
}
- nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+ call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
}
}
unlock:
@@ -1542,6 +1553,25 @@ unlock:
EXPORT_SYMBOL(unregister_netdevice_notifier);
/**
+ * call_netdevice_notifiers_info - call all network notifier blocks
+ * @val: value passed unmodified to notifier function
+ * @dev: net_device pointer passed unmodified to notifier function
+ * @info: notifier information data
+ *
+ * Call all network notifier blocks. Parameters and return value
+ * are as for raw_notifier_call_chain().
+ */
+
+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);
+}
+EXPORT_SYMBOL(call_netdevice_notifiers_info);
+
+/**
* call_netdevice_notifiers - call all network notifier blocks
* @val: value passed unmodified to notifier function
* @dev: net_device pointer passed unmodified to notifier function
@@ -1552,8 +1582,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
- ASSERT_RTNL();
- return raw_notifier_call_chain(&netdev_chain, val, dev);
+ struct netdev_notifier_info info;
+
+ return call_netdevice_notifiers_info(val, dev, &info);
}
EXPORT_SYMBOL(call_netdevice_notifiers);
@@ -1655,23 +1686,19 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
}
}
- skb_orphan(skb);
-
if (unlikely(!is_skb_forwardable(dev, skb))) {
atomic_long_inc(&dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
}
- skb->skb_iif = 0;
- skb->dev = dev;
- skb_dst_drop(skb);
- skb->tstamp.tv64 = 0;
- skb->pkt_type = PACKET_HOST;
+ skb_scrub_packet(skb);
skb->protocol = eth_type_trans(skb, dev);
- skb->mark = 0;
- secpath_reset(skb);
- nf_reset(skb);
- nf_reset_trace(skb);
+
+ /* eth_type_trans() can set pkt_type.
+ * clear pkt_type _after_ calling eth_type_trans()
+ */
+ skb->pkt_type = PACKET_HOST;
+
return netif_rx(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -1736,7 +1763,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
skb_reset_mac_header(skb2);
if (skb_network_header(skb2) < skb2->data ||
- skb2->network_header > skb2->tail) {
+ skb_network_header(skb2) > skb_tail_pointer(skb2)) {
net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
ntohs(skb2->protocol),
dev->name);
@@ -3099,6 +3126,46 @@ static int rps_ipi_queued(struct softnet_data *sd)
return 0;
}
+#ifdef CONFIG_NET_FLOW_LIMIT
+int netdev_flow_limit_table_len __read_mostly = (1 << 12);
+#endif
+
+static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
+{
+#ifdef CONFIG_NET_FLOW_LIMIT
+ struct sd_flow_limit *fl;
+ struct softnet_data *sd;
+ unsigned int old_flow, new_flow;
+
+ if (qlen < (netdev_max_backlog >> 1))
+ return false;
+
+ sd = &__get_cpu_var(softnet_data);
+
+ rcu_read_lock();
+ fl = rcu_dereference(sd->flow_limit);
+ if (fl) {
+ new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1);
+ old_flow = fl->history[fl->history_head];
+ fl->history[fl->history_head] = new_flow;
+
+ fl->history_head++;
+ fl->history_head &= FLOW_LIMIT_HISTORY - 1;
+
+ if (likely(fl->buckets[old_flow]))
+ fl->buckets[old_flow]--;
+
+ if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) {
+ fl->count++;
+ rcu_read_unlock();
+ return true;
+ }
+ }
+ rcu_read_unlock();
+#endif
+ return false;
+}
+
/*
* enqueue_to_backlog is called to queue an skb to a per CPU backlog
* queue (may be a remote CPU queue).
@@ -3108,13 +3175,15 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
{
struct softnet_data *sd;
unsigned long flags;
+ unsigned int qlen;
sd = &per_cpu(softnet_data, cpu);
local_irq_save(flags);
rps_lock(sd);
- if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
+ qlen = skb_queue_len(&sd->input_pkt_queue);
+ if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
if (skb_queue_len(&sd->input_pkt_queue)) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
@@ -3862,7 +3931,7 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
NAPI_GRO_CB(skb)->frag0 = NULL;
NAPI_GRO_CB(skb)->frag0_len = 0;
- if (skb->mac_header == skb->tail &&
+ if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
pinfo->nr_frags &&
!PageHighMem(skb_frag_page(frag0))) {
NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
@@ -4106,6 +4175,58 @@ void napi_complete(struct napi_struct *n)
}
EXPORT_SYMBOL(napi_complete);
+/* must be called under rcu_read_lock(), as we dont take a reference */
+struct napi_struct *napi_by_id(unsigned int napi_id)
+{
+ unsigned int hash = napi_id % HASH_SIZE(napi_hash);
+ struct napi_struct *napi;
+
+ hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node)
+ if (napi->napi_id == napi_id)
+ return napi;
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(napi_by_id);
+
+void napi_hash_add(struct napi_struct *napi)
+{
+ if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) {
+
+ spin_lock(&napi_hash_lock);
+
+ /* 0 is not a valid id, we also skip an id that is taken
+ * we expect both events to be extremely rare
+ */
+ napi->napi_id = 0;
+ while (!napi->napi_id) {
+ napi->napi_id = ++napi_gen_id;
+ if (napi_by_id(napi->napi_id))
+ napi->napi_id = 0;
+ }
+
+ hlist_add_head_rcu(&napi->napi_hash_node,
+ &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
+
+ spin_unlock(&napi_hash_lock);
+ }
+}
+EXPORT_SYMBOL_GPL(napi_hash_add);
+
+/* Warning : caller is responsible to make sure rcu grace period
+ * is respected before freeing memory containing @napi
+ */
+void napi_hash_del(struct napi_struct *napi)
+{
+ spin_lock(&napi_hash_lock);
+
+ if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state))
+ hlist_del_rcu(&napi->napi_hash_node);
+
+ spin_unlock(&napi_hash_lock);
+}
+EXPORT_SYMBOL_GPL(napi_hash_del);
+
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight)
{
@@ -4404,7 +4525,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
else
list_add_tail_rcu(&upper->list, &dev->upper_dev_list);
dev_hold(upper_dev);
-
+ call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
return 0;
}
@@ -4464,6 +4585,7 @@ void netdev_upper_dev_unlink(struct net_device *dev,
list_del_rcu(&upper->list);
dev_put(upper_dev);
kfree_rcu(upper, rcu);
+ call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
@@ -4734,8 +4856,13 @@ 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)))
- call_netdevice_notifiers(NETDEV_CHANGE, dev);
+ (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) {
+ struct netdev_notifier_change_info change_info;
+
+ change_info.flags_changed = changes;
+ call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+ &change_info.info);
+ }
}
/**
@@ -5158,17 +5285,28 @@ static void netdev_init_one_queue(struct net_device *dev,
#endif
}
+static void netif_free_tx_queues(struct net_device *dev)
+{
+ if (is_vmalloc_addr(dev->_tx))
+ vfree(dev->_tx);
+ else
+ kfree(dev->_tx);
+}
+
static int netif_alloc_netdev_queues(struct net_device *dev)
{
unsigned int count = dev->num_tx_queues;
struct netdev_queue *tx;
+ size_t sz = count * sizeof(*tx);
- BUG_ON(count < 1);
-
- tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL);
- if (!tx)
- return -ENOMEM;
+ BUG_ON(count < 1 || count > 0xffff);
+ tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+ if (!tx) {
+ tx = vzalloc(sz);
+ if (!tx)
+ return -ENOMEM;
+ }
dev->_tx = tx;
netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
@@ -5269,6 +5407,10 @@ int register_netdevice(struct net_device *dev)
*/
dev->hw_enc_features |= NETIF_F_SG;
+ /* Make NETIF_F_SG inheritable to MPLS.
+ */
+ dev->mpls_features |= NETIF_F_SG;
+
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
if (ret)
@@ -5712,7 +5854,7 @@ free_all:
free_pcpu:
free_percpu(dev->pcpu_refcnt);
- kfree(dev->_tx);
+ netif_free_tx_queues(dev);
#ifdef CONFIG_RPS
kfree(dev->_rx);
#endif
@@ -5737,7 +5879,7 @@ void free_netdev(struct net_device *dev)
release_net(dev_net(dev));
- kfree(dev->_tx);
+ netif_free_tx_queues(dev);
#ifdef CONFIG_RPS
kfree(dev->_rx);
#endif
@@ -6048,7 +6190,7 @@ netdev_features_t netdev_increment_features(netdev_features_t all,
}
EXPORT_SYMBOL(netdev_increment_features);
-static struct hlist_head *netdev_create_hash(void)
+static struct hlist_head * __net_init netdev_create_hash(void)
{
int i;
struct hlist_head *hash;
@@ -6304,6 +6446,10 @@ static int __init net_dev_init(void)
sd->backlog.weight = weight_p;
sd->backlog.gro_list = NULL;
sd->backlog.gro_count = 0;
+
+#ifdef CONFIG_NET_FLOW_LIMIT
+ sd->flow_limit = NULL;
+#endif
}
dev_boot_phase = 0;
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index d23b6682f4e9..5e78d44333b9 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -295,9 +295,9 @@ static int net_dm_cmd_trace(struct sk_buff *skb,
}
static int dropmon_net_event(struct notifier_block *ev_block,
- unsigned long event, void *ptr)
+ unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct dm_hw_stat_delta *new_stat = NULL;
struct dm_hw_stat_delta *tmp;
diff --git a/net/core/dst.c b/net/core/dst.c
index df9cc810ec8e..ca4231ec7347 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -372,7 +372,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
static int dst_dev_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct dst_entry *dst, *last = NULL;
switch (event) {
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index ce91766eeca9..ab5fa6336c84 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -82,6 +82,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_FSO_BIT] = "tx-fcoe-segmentation",
[NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation",
[NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation",
+ [NETIF_F_GSO_MPLS_BIT] = "tx-mpls-segmentation",
[NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
[NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp",
@@ -1319,10 +1320,19 @@ static int ethtool_get_dump_data(struct net_device *dev,
if (ret)
return ret;
- len = (tmp.len > dump.len) ? dump.len : tmp.len;
+ len = min(tmp.len, dump.len);
if (!len)
return -EFAULT;
+ /* Don't ever let the driver think there's more space available
+ * than it requested with .get_dump_flag().
+ */
+ dump.len = len;
+
+ /* Always allocate enough space to hold the whole thing so that the
+ * driver does not need to check the length and bother with partial
+ * dumping.
+ */
data = vzalloc(tmp.len);
if (!data)
return -ENOMEM;
@@ -1330,6 +1340,16 @@ static int ethtool_get_dump_data(struct net_device *dev,
if (ret)
goto out;
+ /* There are two sane possibilities:
+ * 1. The driver's .get_dump_data() does not touch dump.len.
+ * 2. Or it may set dump.len to how much it really writes, which
+ * should be tmp.len (or len if it can do a partial dump).
+ * In any case respond to userspace with the actual length of data
+ * it's receiving.
+ */
+ WARN_ON(dump.len != len && dump.len != tmp.len);
+ dump.len = len;
+
if (copy_to_user(useraddr, &dump, sizeof(dump))) {
ret = -EFAULT;
goto out;
@@ -1413,7 +1433,7 @@ static int ethtool_get_module_eeprom(struct net_device *dev,
modinfo.eeprom_len);
}
-/* The main entry point in this file. Called from net/core/dev.c */
+/* The main entry point in this file. Called from net/core/dev_ioctl.c */
int dev_ethtool(struct net *net, struct ifreq *ifr)
{
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index d5a9f8ead0d8..21735440c44a 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -705,9 +705,9 @@ static void detach_rules(struct list_head *rules, struct net_device *dev)
static int fib_rules_event(struct notifier_block *this, unsigned long event,
- void *ptr)
+ void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct fib_rules_ops *ops;
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index d9d198aa9fed..6b5b6e7013ca 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -82,7 +82,7 @@ struct gen_estimator
{
struct list_head list;
struct gnet_stats_basic_packed *bstats;
- struct gnet_stats_rate_est *rate_est;
+ struct gnet_stats_rate_est64 *rate_est;
spinlock_t *stats_lock;
int ewma_log;
u64 last_bytes;
@@ -167,7 +167,7 @@ static void gen_add_node(struct gen_estimator *est)
static
struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats,
- const struct gnet_stats_rate_est *rate_est)
+ const struct gnet_stats_rate_est64 *rate_est)
{
struct rb_node *p = est_root.rb_node;
@@ -203,7 +203,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats
*
*/
int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
- struct gnet_stats_rate_est *rate_est,
+ struct gnet_stats_rate_est64 *rate_est,
spinlock_t *stats_lock,
struct nlattr *opt)
{
@@ -258,7 +258,7 @@ EXPORT_SYMBOL(gen_new_estimator);
* Note : Caller should respect an RCU grace period before freeing stats_lock
*/
void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
- struct gnet_stats_rate_est *rate_est)
+ struct gnet_stats_rate_est64 *rate_est)
{
struct gen_estimator *e;
@@ -290,7 +290,7 @@ EXPORT_SYMBOL(gen_kill_estimator);
* Returns 0 on success or a negative error code.
*/
int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
- struct gnet_stats_rate_est *rate_est,
+ struct gnet_stats_rate_est64 *rate_est,
spinlock_t *stats_lock, struct nlattr *opt)
{
gen_kill_estimator(bstats, rate_est);
@@ -306,7 +306,7 @@ EXPORT_SYMBOL(gen_replace_estimator);
* Returns true if estimator is active, and false if not.
*/
bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
- const struct gnet_stats_rate_est *rate_est)
+ const struct gnet_stats_rate_est64 *rate_est)
{
bool res;
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index ddedf211e588..9d3d9e78397b 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -143,18 +143,30 @@ EXPORT_SYMBOL(gnet_stats_copy_basic);
int
gnet_stats_copy_rate_est(struct gnet_dump *d,
const struct gnet_stats_basic_packed *b,
- struct gnet_stats_rate_est *r)
+ struct gnet_stats_rate_est64 *r)
{
+ struct gnet_stats_rate_est est;
+ int res;
+
if (b && !gen_estimator_active(b, r))
return 0;
+ est.bps = min_t(u64, UINT_MAX, r->bps);
+ /* we have some time before reaching 2^32 packets per second */
+ est.pps = r->pps;
+
if (d->compat_tc_stats) {
- d->tc_stats.bps = r->bps;
- d->tc_stats.pps = r->pps;
+ d->tc_stats.bps = est.bps;
+ d->tc_stats.pps = est.pps;
}
- if (d->tail)
- return gnet_stats_copy(d, TCA_STATS_RATE_EST, r, sizeof(*r));
+ if (d->tail) {
+ res = gnet_stats_copy(d, TCA_STATS_RATE_EST, &est, sizeof(est));
+ if (res < 0 || est.bps == r->bps)
+ return res;
+ /* emit 64bit stats only if needed */
+ return gnet_stats_copy(d, TCA_STATS_RATE_EST64, r, sizeof(*r));
+ }
return 0;
}
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 8f82a5cc3851..9c3a839322ba 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -92,6 +92,9 @@ static bool linkwatch_urgent_event(struct net_device *dev)
if (dev->ifindex != dev->iflink)
return true;
+ if (dev->priv_flags & IFF_TEAM_PORT)
+ return true;
+
return netif_carrier_ok(dev) && qdisc_tx_changing(dev);
}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 5c56b217b999..b7de821f98df 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -231,7 +231,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev)
we must kill timers etc. and move
it to safe state.
*/
- skb_queue_purge(&n->arp_queue);
+ __skb_queue_purge(&n->arp_queue);
n->arp_queue_len_bytes = 0;
n->output = neigh_blackhole;
if (n->nud_state & NUD_VALID)
@@ -286,7 +286,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device
if (!n)
goto out_entries;
- skb_queue_head_init(&n->arp_queue);
+ __skb_queue_head_init(&n->arp_queue);
rwlock_init(&n->lock);
seqlock_init(&n->ha_lock);
n->updated = n->used = now;
@@ -708,7 +708,9 @@ void neigh_destroy(struct neighbour *neigh)
if (neigh_del_timer(neigh))
pr_warn("Impossible event\n");
- skb_queue_purge(&neigh->arp_queue);
+ write_lock_bh(&neigh->lock);
+ __skb_queue_purge(&neigh->arp_queue);
+ write_unlock_bh(&neigh->lock);
neigh->arp_queue_len_bytes = 0;
if (dev->netdev_ops->ndo_neigh_destroy)
@@ -858,7 +860,7 @@ static void neigh_invalidate(struct neighbour *neigh)
neigh->ops->error_report(neigh, skb);
write_lock(&neigh->lock);
}
- skb_queue_purge(&neigh->arp_queue);
+ __skb_queue_purge(&neigh->arp_queue);
neigh->arp_queue_len_bytes = 0;
}
@@ -1210,7 +1212,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
write_lock_bh(&neigh->lock);
}
- skb_queue_purge(&neigh->arp_queue);
+ __skb_queue_purge(&neigh->arp_queue);
neigh->arp_queue_len_bytes = 0;
}
out:
@@ -1419,7 +1421,7 @@ static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl,
for (p = &tbl->parms; p; p = p->next) {
if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) ||
- (!p->dev && !ifindex))
+ (!p->dev && !ifindex && net_eq(net, &init_net)))
return p;
}
@@ -1429,15 +1431,11 @@ static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl,
struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
struct neigh_table *tbl)
{
- struct neigh_parms *p, *ref;
+ struct neigh_parms *p;
struct net *net = dev_net(dev);
const struct net_device_ops *ops = dev->netdev_ops;
- ref = lookup_neigh_parms(tbl, net, 0);
- if (!ref)
- return NULL;
-
- p = kmemdup(ref, sizeof(*p), GFP_KERNEL);
+ p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL);
if (p) {
p->tbl = tbl;
atomic_set(&p->refcnt, 1);
@@ -2053,6 +2051,12 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
}
}
+ err = -ENOENT;
+ if ((tb[NDTA_THRESH1] || tb[NDTA_THRESH2] ||
+ tb[NDTA_THRESH3] || tb[NDTA_GC_INTERVAL]) &&
+ !net_eq(net, &init_net))
+ goto errout_tbl_lock;
+
if (tb[NDTA_THRESH1])
tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]);
@@ -2765,11 +2769,11 @@ EXPORT_SYMBOL(neigh_app_ns);
static int zero;
static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN);
-static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer,
- size_t *lenp, loff_t *ppos)
+static int proc_unres_qlen(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
{
int size, ret;
- ctl_table tmp = *ctl;
+ struct ctl_table tmp = *ctl;
tmp.extra1 = &zero;
tmp.extra2 = &unres_qlen_max;
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 569d355fec3e..2bf83299600a 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -146,11 +146,23 @@ static void softnet_seq_stop(struct seq_file *seq, void *v)
static int softnet_seq_show(struct seq_file *seq, void *v)
{
struct softnet_data *sd = v;
+ unsigned int flow_limit_count = 0;
- seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+#ifdef CONFIG_NET_FLOW_LIMIT
+ struct sd_flow_limit *fl;
+
+ rcu_read_lock();
+ fl = rcu_dereference(sd->flow_limit);
+ if (fl)
+ flow_limit_count = fl->count;
+ rcu_read_unlock();
+#endif
+
+ seq_printf(seq,
+ "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
sd->processed, sd->dropped, sd->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- sd->cpu_collision, sd->received_rps);
+ sd->cpu_collision, sd->received_rps, flow_limit_count);
return 0;
}
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 35a9f0804b6f..2c637e9a0b27 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -248,7 +248,7 @@ static void netpoll_poll_dev(struct net_device *dev)
zap_completion_queue();
}
-int netpoll_rx_disable(struct net_device *dev)
+void netpoll_rx_disable(struct net_device *dev)
{
struct netpoll_info *ni;
int idx;
@@ -258,7 +258,6 @@ int netpoll_rx_disable(struct net_device *dev)
if (ni)
down(&ni->dev_lock);
srcu_read_unlock(&netpoll_srcu, idx);
- return 0;
}
EXPORT_SYMBOL(netpoll_rx_disable);
@@ -691,25 +690,20 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
send_skb->dev = skb->dev;
skb_reset_network_header(send_skb);
- skb_put(send_skb, sizeof(struct ipv6hdr));
- hdr = ipv6_hdr(send_skb);
-
+ hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr));
*(__be32*)hdr = htonl(0x60000000);
-
hdr->payload_len = htons(size);
hdr->nexthdr = IPPROTO_ICMPV6;
hdr->hop_limit = 255;
hdr->saddr = *saddr;
hdr->daddr = *daddr;
- send_skb->transport_header = send_skb->tail;
- skb_put(send_skb, size);
-
- icmp6h = (struct icmp6hdr *)skb_transport_header(skb);
+ icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr));
icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
icmp6h->icmp6_router = 0;
icmp6h->icmp6_solicited = 1;
- target = (struct in6_addr *)(skb_transport_header(send_skb) + sizeof(struct icmp6hdr));
+
+ target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr));
*target = msg->target;
icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size,
IPPROTO_ICMPV6,
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 0777d0aa18c3..e533259dce3c 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -261,7 +261,7 @@ struct cgroup_subsys net_prio_subsys = {
static int netprio_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct netprio_map *old;
/*
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 11f2704c3810..9640972ec50e 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1921,7 +1921,7 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
static int pktgen_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id);
if (pn->pktgen_exiting)
@@ -2627,6 +2627,29 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb,
pgh->tv_usec = htonl(timestamp.tv_usec);
}
+static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
+ struct pktgen_dev *pkt_dev,
+ unsigned int extralen)
+{
+ struct sk_buff *skb = NULL;
+ unsigned int size = pkt_dev->cur_pkt_size + 64 + extralen +
+ pkt_dev->pkt_overhead;
+
+ if (pkt_dev->flags & F_NODE) {
+ int node = pkt_dev->node >= 0 ? pkt_dev->node : numa_node_id();
+
+ skb = __alloc_skb(NET_SKB_PAD + size, GFP_NOWAIT, 0, node);
+ if (likely(skb)) {
+ skb_reserve(skb, NET_SKB_PAD);
+ skb->dev = dev;
+ }
+ } else {
+ skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT);
+ }
+
+ return skb;
+}
+
static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
struct pktgen_dev *pkt_dev)
{
@@ -2657,32 +2680,13 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
datalen = (odev->hard_header_len + 16) & ~0xf;
- if (pkt_dev->flags & F_NODE) {
- int node;
-
- if (pkt_dev->node >= 0)
- node = pkt_dev->node;
- else
- node = numa_node_id();
-
- skb = __alloc_skb(NET_SKB_PAD + pkt_dev->cur_pkt_size + 64
- + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT, 0, node);
- if (likely(skb)) {
- skb_reserve(skb, NET_SKB_PAD);
- skb->dev = odev;
- }
- }
- else
- skb = __netdev_alloc_skb(odev,
- pkt_dev->cur_pkt_size + 64
- + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT);
-
+ skb = pktgen_alloc_skb(odev, pkt_dev, datalen);
if (!skb) {
sprintf(pkt_dev->result, "No memory");
return NULL;
}
- prefetchw(skb->data);
+ prefetchw(skb->data);
skb_reserve(skb, datalen);
/* Reserve for ethernet and IP header */
@@ -2708,15 +2712,15 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
*vlan_encapsulated_proto = htons(ETH_P_IP);
}
- skb->network_header = skb->tail;
- skb->transport_header = skb->network_header + sizeof(struct iphdr);
- skb_put(skb, sizeof(struct iphdr) + sizeof(struct udphdr));
+ skb_set_mac_header(skb, 0);
+ skb_set_network_header(skb, skb->len);
+ iph = (struct iphdr *) skb_put(skb, sizeof(struct iphdr));
+
+ skb_set_transport_header(skb, skb->len);
+ udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr));
skb_set_queue_mapping(skb, queue_map);
skb->priority = pkt_dev->skb_priority;
- iph = ip_hdr(skb);
- udph = udp_hdr(skb);
-
memcpy(eth, pkt_dev->hh, 12);
*(__be16 *) & eth[12] = protocol;
@@ -2746,8 +2750,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
iph->check = 0;
iph->check = ip_fast_csum((void *)iph, iph->ihl);
skb->protocol = protocol;
- skb->mac_header = (skb->network_header - ETH_HLEN -
- pkt_dev->pkt_overhead);
skb->dev = odev;
skb->pkt_type = PACKET_HOST;
pktgen_finalize_skb(pkt_dev, skb, datalen);
@@ -2788,15 +2790,13 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
mod_cur_headers(pkt_dev);
queue_map = pkt_dev->cur_queue_map;
- skb = __netdev_alloc_skb(odev,
- pkt_dev->cur_pkt_size + 64
- + 16 + pkt_dev->pkt_overhead, GFP_NOWAIT);
+ skb = pktgen_alloc_skb(odev, pkt_dev, 16);
if (!skb) {
sprintf(pkt_dev->result, "No memory");
return NULL;
}
- prefetchw(skb->data);
+ prefetchw(skb->data);
skb_reserve(skb, 16);
/* Reserve for ethernet and IP header */
@@ -2822,13 +2822,14 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
*vlan_encapsulated_proto = htons(ETH_P_IPV6);
}
- skb->network_header = skb->tail;
- skb->transport_header = skb->network_header + sizeof(struct ipv6hdr);
- skb_put(skb, sizeof(struct ipv6hdr) + sizeof(struct udphdr));
+ skb_set_mac_header(skb, 0);
+ skb_set_network_header(skb, skb->len);
+ iph = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr));
+
+ skb_set_transport_header(skb, skb->len);
+ udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr));
skb_set_queue_mapping(skb, queue_map);
skb->priority = pkt_dev->skb_priority;
- iph = ipv6_hdr(skb);
- udph = udp_hdr(skb);
memcpy(eth, pkt_dev->hh, 12);
*(__be16 *) &eth[12] = protocol;
@@ -2863,8 +2864,6 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
iph->daddr = pkt_dev->cur_in6_daddr;
iph->saddr = pkt_dev->cur_in6_saddr;
- skb->mac_header = (skb->network_header - ETH_HLEN -
- pkt_dev->pkt_overhead);
skb->protocol = protocol;
skb->dev = odev;
skb->pkt_type = PACKET_HOST;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a08bd2b7fe3f..3de740834d1f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -947,6 +947,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
struct ifla_vf_vlan vf_vlan;
struct ifla_vf_tx_rate vf_tx_rate;
struct ifla_vf_spoofchk vf_spoofchk;
+ struct ifla_vf_link_state vf_linkstate;
/*
* Not all SR-IOV capable drivers support the
@@ -956,18 +957,24 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
*/
ivi.spoofchk = -1;
memset(ivi.mac, 0, sizeof(ivi.mac));
+ /* The default value for VF link state is "auto"
+ * IFLA_VF_LINK_STATE_AUTO which equals zero
+ */
+ ivi.linkstate = 0;
if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi))
break;
vf_mac.vf =
vf_vlan.vf =
vf_tx_rate.vf =
- vf_spoofchk.vf = ivi.vf;
+ vf_spoofchk.vf =
+ vf_linkstate.vf = ivi.vf;
memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
vf_vlan.vlan = ivi.vlan;
vf_vlan.qos = ivi.qos;
vf_tx_rate.rate = ivi.tx_rate;
vf_spoofchk.setting = ivi.spoofchk;
+ vf_linkstate.link_state = ivi.linkstate;
vf = nla_nest_start(skb, IFLA_VF_INFO);
if (!vf) {
nla_nest_cancel(skb, vfinfo);
@@ -978,7 +985,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
&vf_tx_rate) ||
nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
- &vf_spoofchk))
+ &vf_spoofchk) ||
+ nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate),
+ &vf_linkstate))
goto nla_put_failure;
nla_nest_end(skb, vf);
}
@@ -1238,6 +1247,15 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
ivs->setting);
break;
}
+ case IFLA_VF_LINK_STATE: {
+ struct ifla_vf_link_state *ivl;
+ ivl = nla_data(vf);
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_link_state)
+ err = ops->ndo_set_vf_link_state(dev, ivl->vf,
+ ivl->link_state);
+ break;
+ }
default:
err = -EINVAL;
break;
@@ -2091,10 +2109,6 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
}
addr = nla_data(tb[NDA_LLADDR]);
- if (is_zero_ether_addr(addr)) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ether address\n");
- return -EINVAL;
- }
err = -EOPNOTSUPP;
@@ -2192,10 +2206,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
}
addr = nla_data(tb[NDA_LLADDR]);
- if (is_zero_ether_addr(addr)) {
- pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ether address\n");
- return -EINVAL;
- }
err = -EOPNOTSUPP;
@@ -2667,7 +2677,7 @@ static void rtnetlink_rcv(struct sk_buff *skb)
static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
switch (event) {
case NETDEV_UP:
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1c1738cc4538..724bb7cb173f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -199,9 +199,7 @@ struct sk_buff *__alloc_skb_head(gfp_t gfp_mask, int node)
skb->truesize = sizeof(struct sk_buff);
atomic_set(&skb->users, 1);
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
- skb->mac_header = ~0U;
-#endif
+ skb->mac_header = (typeof(skb->mac_header))~0U;
out:
return skb;
}
@@ -275,10 +273,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
skb->data = data;
skb_reset_tail_pointer(skb);
skb->end = skb->tail + size;
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
- skb->mac_header = ~0U;
- skb->transport_header = ~0U;
-#endif
+ skb->mac_header = (typeof(skb->mac_header))~0U;
+ skb->transport_header = (typeof(skb->transport_header))~0U;
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);
@@ -344,10 +340,8 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
skb->data = data;
skb_reset_tail_pointer(skb);
skb->end = skb->tail + size;
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
- skb->mac_header = ~0U;
- skb->transport_header = ~0U;
-#endif
+ skb->mac_header = (typeof(skb->mac_header))~0U;
+ skb->transport_header = (typeof(skb->transport_header))~0U;
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);
@@ -703,6 +697,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->transport_header = old->transport_header;
new->network_header = old->network_header;
new->mac_header = old->mac_header;
+ new->inner_protocol = old->inner_protocol;
new->inner_transport_header = old->inner_transport_header;
new->inner_network_header = old->inner_network_header;
new->inner_mac_header = old->inner_mac_header;
@@ -743,6 +738,10 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->vlan_tci = old->vlan_tci;
skb_copy_secmark(new, old);
+
+#ifdef CONFIG_NET_LL_RX_POLL
+ new->napi_id = old->napi_id;
+#endif
}
/*
@@ -915,18 +914,8 @@ static void skb_headers_offset_update(struct sk_buff *skb, int off)
static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
-#ifndef NET_SKBUFF_DATA_USES_OFFSET
- /*
- * Shift between the two data areas in bytes
- */
- unsigned long offset = new->data - old->data;
-#endif
-
__copy_skb_header(new, old);
-#ifndef NET_SKBUFF_DATA_USES_OFFSET
- skb_headers_offset_update(new, offset);
-#endif
skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
@@ -1118,7 +1107,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
skb->end = skb->head + size;
#endif
skb->tail += off;
- skb_headers_offset_update(skb, off);
+ skb_headers_offset_update(skb, nhead);
/* Only adjust this if it actually is csum_start rather than csum */
if (skb->ip_summed == CHECKSUM_PARTIAL)
skb->csum_start += nhead;
@@ -1213,9 +1202,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
off = newheadroom - oldheadroom;
if (n->ip_summed == CHECKSUM_PARTIAL)
n->csum_start += off;
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
+
skb_headers_offset_update(n, off);
-#endif
return n;
}
@@ -2558,8 +2546,13 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
unsigned int block_limit, abs_offset = consumed + st->lower_offset;
skb_frag_t *frag;
- if (unlikely(abs_offset >= st->upper_offset))
+ if (unlikely(abs_offset >= st->upper_offset)) {
+ if (st->frag_data) {
+ kunmap_atomic(st->frag_data);
+ st->frag_data = NULL;
+ }
return 0;
+ }
next_skb:
block_limit = skb_headlen(st->cur_skb) + st->stepped_offset;
@@ -2857,7 +2850,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
doffset + tnl_hlen);
if (fskb != skb_shinfo(skb)->frag_list)
- continue;
+ goto perform_csum_check;
if (!sg) {
nskb->ip_summed = CHECKSUM_NONE;
@@ -2921,6 +2914,7 @@ skip_fraglist:
nskb->len += nskb->data_len;
nskb->truesize += nskb->data_len;
+perform_csum_check:
if (!csum) {
nskb->csum = skb_checksum(nskb, doffset,
nskb->len - doffset, 0);
@@ -3503,3 +3497,26 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
return true;
}
EXPORT_SYMBOL(skb_try_coalesce);
+
+/**
+ * skb_scrub_packet - scrub an skb before sending it to another netns
+ *
+ * @skb: buffer to clean
+ *
+ * skb_scrub_packet can be used to clean an skb before injecting it in
+ * another namespace. We have to clear all information in the skb that
+ * could impact namespace isolation.
+ */
+void skb_scrub_packet(struct sk_buff *skb)
+{
+ skb_orphan(skb);
+ skb->tstamp.tv64 = 0;
+ skb->pkt_type = PACKET_HOST;
+ skb->skb_iif = 0;
+ skb_dst_drop(skb);
+ skb->mark = 0;
+ secpath_reset(skb);
+ nf_reset(skb);
+ nf_reset_trace(skb);
+}
+EXPORT_SYMBOL_GPL(skb_scrub_packet);
diff --git a/net/core/sock.c b/net/core/sock.c
index d6d024cfaaaf..ab06b719f5b1 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -139,6 +139,8 @@
#include <net/tcp.h>
#endif
+#include <net/ll_poll.h>
+
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
@@ -898,6 +900,19 @@ set_rcvbuf:
sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
break;
+#ifdef CONFIG_NET_LL_RX_POLL
+ case SO_LL:
+ /* allow unprivileged users to decrease the value */
+ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
+ ret = -EPERM;
+ else {
+ if (val < 0)
+ ret = -EINVAL;
+ else
+ sk->sk_ll_usec = val;
+ }
+ break;
+#endif
default:
ret = -ENOPROTOOPT;
break;
@@ -1155,6 +1170,12 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
break;
+#ifdef CONFIG_NET_LL_RX_POLL
+ case SO_LL:
+ v.val = sk->sk_ll_usec;
+ break;
+#endif
+
default:
return -ENOPROTOOPT;
}
@@ -2271,6 +2292,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_stamp = ktime_set(-1L, 0);
+#ifdef CONFIG_NET_LL_RX_POLL
+ sk->sk_napi_id = 0;
+ sk->sk_ll_usec = sysctl_net_ll_read;
+#endif
+
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cfdb46ab3a7f..afc677eadd93 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -19,16 +19,17 @@
#include <net/ip.h>
#include <net/sock.h>
#include <net/net_ratelimit.h>
+#include <net/ll_poll.h>
static int one = 1;
#ifdef CONFIG_RPS
-static int rps_sock_flow_sysctl(ctl_table *table, int write,
+static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
unsigned int orig_size, size;
int ret, i;
- ctl_table tmp = {
+ struct ctl_table tmp = {
.data = &size,
.maxlen = sizeof(size),
.mode = table->mode
@@ -87,6 +88,109 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write,
}
#endif /* CONFIG_RPS */
+#ifdef CONFIG_NET_FLOW_LIMIT
+static DEFINE_MUTEX(flow_limit_update_mutex);
+
+static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ struct sd_flow_limit *cur;
+ struct softnet_data *sd;
+ cpumask_var_t mask;
+ int i, len, ret = 0;
+
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+ return -ENOMEM;
+
+ if (write) {
+ ret = cpumask_parse_user(buffer, *lenp, mask);
+ if (ret)
+ goto done;
+
+ mutex_lock(&flow_limit_update_mutex);
+ len = sizeof(*cur) + netdev_flow_limit_table_len;
+ for_each_possible_cpu(i) {
+ sd = &per_cpu(softnet_data, i);
+ cur = rcu_dereference_protected(sd->flow_limit,
+ lockdep_is_held(&flow_limit_update_mutex));
+ if (cur && !cpumask_test_cpu(i, mask)) {
+ RCU_INIT_POINTER(sd->flow_limit, NULL);
+ synchronize_rcu();
+ kfree(cur);
+ } else if (!cur && cpumask_test_cpu(i, mask)) {
+ cur = kzalloc(len, GFP_KERNEL);
+ if (!cur) {
+ /* not unwinding previous changes */
+ ret = -ENOMEM;
+ goto write_unlock;
+ }
+ cur->num_buckets = netdev_flow_limit_table_len;
+ rcu_assign_pointer(sd->flow_limit, cur);
+ }
+ }
+write_unlock:
+ mutex_unlock(&flow_limit_update_mutex);
+ } else {
+ char kbuf[128];
+
+ if (*ppos || !*lenp) {
+ *lenp = 0;
+ goto done;
+ }
+
+ cpumask_clear(mask);
+ rcu_read_lock();
+ for_each_possible_cpu(i) {
+ sd = &per_cpu(softnet_data, i);
+ if (rcu_dereference(sd->flow_limit))
+ cpumask_set_cpu(i, mask);
+ }
+ rcu_read_unlock();
+
+ len = min(sizeof(kbuf) - 1, *lenp);
+ len = cpumask_scnprintf(kbuf, len, mask);
+ if (!len) {
+ *lenp = 0;
+ goto done;
+ }
+ if (len < *lenp)
+ kbuf[len++] = '\n';
+ if (copy_to_user(buffer, kbuf, len)) {
+ ret = -EFAULT;
+ goto done;
+ }
+ *lenp = len;
+ *ppos += len;
+ }
+
+done:
+ free_cpumask_var(mask);
+ return ret;
+}
+
+static int flow_limit_table_len_sysctl(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ unsigned int old, *ptr;
+ int ret;
+
+ mutex_lock(&flow_limit_update_mutex);
+
+ ptr = table->data;
+ old = *ptr;
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ if (!ret && write && !is_power_of_2(*ptr)) {
+ *ptr = old;
+ ret = -EINVAL;
+ }
+
+ mutex_unlock(&flow_limit_update_mutex);
+ return ret;
+}
+#endif /* CONFIG_NET_FLOW_LIMIT */
+
static struct ctl_table net_core_table[] = {
#ifdef CONFIG_NET
{
@@ -180,6 +284,37 @@ static struct ctl_table net_core_table[] = {
.proc_handler = rps_sock_flow_sysctl
},
#endif
+#ifdef CONFIG_NET_FLOW_LIMIT
+ {
+ .procname = "flow_limit_cpu_bitmap",
+ .mode = 0644,
+ .proc_handler = flow_limit_cpu_sysctl
+ },
+ {
+ .procname = "flow_limit_table_len",
+ .data = &netdev_flow_limit_table_len,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = flow_limit_table_len_sysctl
+ },
+#endif /* CONFIG_NET_FLOW_LIMIT */
+#ifdef CONFIG_NET_LL_RX_POLL
+ {
+ .procname = "low_latency_poll",
+ .data = &sysctl_net_ll_poll,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "low_latency_read",
+ .data = &sysctl_net_ll_read,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+#
+#endif
#endif /* CONFIG_NET */
{
.procname = "netdev_budget",
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index c21f200eed93..dd4d506ef923 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -2078,9 +2078,9 @@ out_err:
}
static int dn_device_event(struct notifier_block *this, unsigned long event,
- void *ptr)
+ void *ptr)
{
- struct net_device *dev = (struct net_device *)ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
if (!net_eq(dev_net(dev), &init_net))
return NOTIFY_DONE;
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 7d9197063ebb..dd0dfb25f4b1 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -158,11 +158,11 @@ static int max_t3[] = { 8191 }; /* Must fit in 16 bits when multiplied by BCT3MU
static int min_priority[1];
static int max_priority[] = { 127 }; /* From DECnet spec */
-static int dn_forwarding_proc(ctl_table *, int,
+static int dn_forwarding_proc(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
static struct dn_dev_sysctl_table {
struct ctl_table_header *sysctl_header;
- ctl_table dn_dev_vars[5];
+ struct ctl_table dn_dev_vars[5];
} dn_dev_sysctl = {
NULL,
{
@@ -242,7 +242,7 @@ static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms)
}
}
-static int dn_forwarding_proc(ctl_table *table, int write,
+static int dn_forwarding_proc(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c
index a55eeccaa72f..5325b541c526 100644
--- a/net/decnet/sysctl_net_decnet.c
+++ b/net/decnet/sysctl_net_decnet.c
@@ -132,7 +132,7 @@ static int parse_addr(__le16 *addr, char *str)
return 0;
}
-static int dn_node_address_handler(ctl_table *table, int write,
+static int dn_node_address_handler(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
@@ -183,7 +183,7 @@ static int dn_node_address_handler(ctl_table *table, int write,
return 0;
}
-static int dn_def_dev_handler(ctl_table *table, int write,
+static int dn_def_dev_handler(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
@@ -246,7 +246,7 @@ static int dn_def_dev_handler(ctl_table *table, int write,
return 0;
}
-static ctl_table dn_table[] = {
+static struct ctl_table dn_table[] = {
{
.procname = "node_address",
.maxlen = 7,
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
index 55e1fd5b3e56..3b9d5f20bd1c 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan.c
@@ -1352,10 +1352,9 @@ static inline void lowpan_netlink_fini(void)
}
static int lowpan_device_event(struct notifier_block *unused,
- unsigned long event,
- void *ptr)
+ unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
LIST_HEAD(del_list);
struct lowpan_dev_record *entry, *tmp;
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 8603ca827104..37cf1a6ea3ad 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -9,10 +9,7 @@ config IP_MULTICAST
intend to participate in the MBONE, a high bandwidth network on top
of the Internet which carries audio and video broadcasts. More
information about the MBONE is on the WWW at
- <http://www.savetz.com/mbone/>. Information about the multicast
- capabilities of the various network cards is contained in
- <file:Documentation/networking/multicast.txt>. For most people, it's
- safe to say N.
+ <http://www.savetz.com/mbone/>. For most people, it's safe to say N.
config IP_ADVANCED_ROUTER
bool "IP: advanced router"
@@ -223,10 +220,8 @@ config IP_MROUTE
packets that have several destination addresses. It is needed on the
MBONE, a high bandwidth network on top of the Internet which carries
audio and video broadcasts. In order to do that, you would most
- likely run the program mrouted. Information about the multicast
- capabilities of the various network cards is contained in
- <file:Documentation/networking/multicast.txt>. If you haven't heard
- about it, you don't need it.
+ likely run the program mrouted. If you haven't heard about it, you
+ don't need it.
config IP_MROUTE_MULTIPLE_TABLES
bool "IP: multicast policy routing"
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 089cb9f36387..4b81e91c80fe 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -8,10 +8,10 @@ obj-y := route.o inetpeer.o protocol.o \
inet_timewait_sock.o inet_connection_sock.o \
tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \
- datagram.o raw.o udp.o udplite.o \
- arp.o icmp.o devinet.o af_inet.o igmp.o \
+ tcp_offload.o datagram.o raw.o udp.o udplite.o \
+ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
fib_frontend.o fib_semantics.o fib_trie.o \
- inet_fragment.o ping.o
+ inet_fragment.o ping.o ip_tunnel_core.o
obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
@@ -19,6 +19,7 @@ obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
obj-$(CONFIG_IP_MROUTE) += ipmr.o
obj-$(CONFIG_NET_IPIP) += ipip.o
+gre-y := gre_demux.o gre_offload.o
obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o
obj-$(CONFIG_NET_IPGRE) += ip_gre.o
obj-$(CONFIG_NET_IPVTI) += ip_vti.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d01be2a3ae53..b4d0be2b7ce9 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1295,6 +1295,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
SKB_GSO_GRE |
SKB_GSO_TCPV6 |
SKB_GSO_UDP_TUNNEL |
+ SKB_GSO_MPLS |
0)))
goto out;
@@ -1384,7 +1385,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
goto out_unlock;
id = ntohl(*(__be32 *)&iph->id);
- flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
+ flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF));
id >>= 16;
for (p = *head; p; p = p->next) {
@@ -1406,6 +1407,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
NAPI_GRO_CB(p)->flush |=
(iph->ttl ^ iph2->ttl) |
(iph->tos ^ iph2->tos) |
+ (__force int)((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) |
((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
NAPI_GRO_CB(p)->flush |= flush;
@@ -1557,15 +1559,6 @@ static const struct net_protocol tcp_protocol = {
.netns_ok = 1,
};
-static const struct net_offload tcp_offload = {
- .callbacks = {
- .gso_send_check = tcp_v4_gso_send_check,
- .gso_segment = tcp_tso_segment,
- .gro_receive = tcp4_gro_receive,
- .gro_complete = tcp4_gro_complete,
- },
-};
-
static const struct net_protocol udp_protocol = {
.handler = udp_rcv,
.err_handler = udp_err,
@@ -1573,13 +1566,6 @@ static const struct net_protocol udp_protocol = {
.netns_ok = 1,
};
-static const struct net_offload udp_offload = {
- .callbacks = {
- .gso_send_check = udp4_ufo_send_check,
- .gso_segment = udp4_ufo_fragment,
- },
-};
-
static const struct net_protocol icmp_protocol = {
.handler = icmp_rcv,
.err_handler = icmp_err,
@@ -1679,10 +1665,10 @@ static int __init ipv4_offload_init(void)
/*
* Add offloads
*/
- if (inet_add_offload(&udp_offload, IPPROTO_UDP) < 0)
+ if (udpv4_offload_init() < 0)
pr_crit("%s: Cannot add UDP protocol offload\n", __func__);
- if (inet_add_offload(&tcp_offload, IPPROTO_TCP) < 0)
- pr_crit("%s: Cannot add TCP protocol offlaod\n", __func__);
+ if (tcpv4_offload_init() < 0)
+ pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
dev_add_offload(&ip_packet_offload);
return 0;
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 2e7f1948216f..717902669d2f 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -419,12 +419,9 @@ static void ah4_err(struct sk_buff *skb, u32 info)
if (!x)
return;
- if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
- atomic_inc(&flow_cache_genid);
- rt_genid_bump(net);
-
+ if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
- } else
+ else
ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 247ec1951c35..4429b013f269 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1234,13 +1234,19 @@ out:
static int arp_netdev_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct netdev_notifier_change_info *change_info;
switch (event) {
case NETDEV_CHANGEADDR:
neigh_changeaddr(&arp_tbl, dev);
rt_cache_flush(dev_net(dev));
break;
+ case NETDEV_CHANGE:
+ change_info = ptr;
+ if (change_info->flags_changed & IFF_NOARP)
+ neigh_changeaddr(&arp_tbl, dev);
+ break;
default:
break;
}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index dfc39d4d48b7..8d48c392adcc 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -215,6 +215,7 @@ void in_dev_finish_destroy(struct in_device *idev)
WARN_ON(idev->ifa_list);
WARN_ON(idev->mc_list);
+ kfree(rcu_dereference_protected(idev->mc_hash, 1));
#ifdef NET_REFCNT_DEBUG
pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL");
#endif
@@ -1333,7 +1334,7 @@ static void inetdev_send_gratuitous_arp(struct net_device *dev,
static int inetdev_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct in_device *in_dev = __in_dev_get_rtnl(dev);
ASSERT_RTNL();
@@ -1941,7 +1942,7 @@ static void inet_forward_change(struct net *net)
}
}
-static int devinet_conf_proc(ctl_table *ctl, int write,
+static int devinet_conf_proc(struct ctl_table *ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
@@ -1984,7 +1985,7 @@ static int devinet_conf_proc(ctl_table *ctl, int write,
return ret;
}
-static int devinet_sysctl_forward(ctl_table *ctl, int write,
+static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
@@ -2027,7 +2028,7 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write,
return ret;
}
-static int ipv4_doint_and_flush(ctl_table *ctl, int write,
+static int ipv4_doint_and_flush(struct ctl_table *ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4cfe34d4cc96..ab3d814bc80a 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -502,12 +502,9 @@ static void esp4_err(struct sk_buff *skb, u32 info)
if (!x)
return;
- if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
- atomic_inc(&flow_cache_genid);
- rt_genid_bump(net);
-
+ if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
- } else
+ else
ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c7629a209f9d..b3f627ac4ed8 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -961,7 +961,7 @@ static void nl_fib_input(struct sk_buff *skb)
nlmsg_len(nlh) < sizeof(*frn))
return;
- skb = skb_clone(skb, GFP_KERNEL);
+ skb = netlink_skb_clone(skb, GFP_KERNEL);
if (skb == NULL)
return;
nlh = nlmsg_hdr(skb);
@@ -1038,7 +1038,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct in_device *in_dev;
struct net *net = dev_net(dev);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 8f6cb7a87cd6..d5dbca5ecf62 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -169,7 +169,8 @@ static void free_nh_exceptions(struct fib_nh *nh)
next = rcu_dereference_protected(fnhe->fnhe_next, 1);
- rt_fibinfo_free(&fnhe->fnhe_rth);
+ rt_fibinfo_free(&fnhe->fnhe_rth_input);
+ rt_fibinfo_free(&fnhe->fnhe_rth_output);
kfree(fnhe);
diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c
deleted file mode 100644
index 7856d1651d05..000000000000
--- a/net/ipv4/gre.c
+++ /dev/null
@@ -1,253 +0,0 @@
-/*
- * GRE over IPv4 demultiplexer driver
- *
- * Authors: Dmitry Kozlov (xeb@mail.ru)
- *
- * 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.
- *
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/kmod.h>
-#include <linux/skbuff.h>
-#include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/netdevice.h>
-#include <linux/if_tunnel.h>
-#include <linux/spinlock.h>
-#include <net/protocol.h>
-#include <net/gre.h>
-
-
-static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly;
-static DEFINE_SPINLOCK(gre_proto_lock);
-
-int gre_add_protocol(const struct gre_protocol *proto, u8 version)
-{
- if (version >= GREPROTO_MAX)
- goto err_out;
-
- spin_lock(&gre_proto_lock);
- if (gre_proto[version])
- goto err_out_unlock;
-
- RCU_INIT_POINTER(gre_proto[version], proto);
- spin_unlock(&gre_proto_lock);
- return 0;
-
-err_out_unlock:
- spin_unlock(&gre_proto_lock);
-err_out:
- return -1;
-}
-EXPORT_SYMBOL_GPL(gre_add_protocol);
-
-int gre_del_protocol(const struct gre_protocol *proto, u8 version)
-{
- if (version >= GREPROTO_MAX)
- goto err_out;
-
- spin_lock(&gre_proto_lock);
- if (rcu_dereference_protected(gre_proto[version],
- lockdep_is_held(&gre_proto_lock)) != proto)
- goto err_out_unlock;
- RCU_INIT_POINTER(gre_proto[version], NULL);
- spin_unlock(&gre_proto_lock);
- synchronize_rcu();
- return 0;
-
-err_out_unlock:
- spin_unlock(&gre_proto_lock);
-err_out:
- return -1;
-}
-EXPORT_SYMBOL_GPL(gre_del_protocol);
-
-static int gre_rcv(struct sk_buff *skb)
-{
- const struct gre_protocol *proto;
- u8 ver;
- int ret;
-
- if (!pskb_may_pull(skb, 12))
- goto drop;
-
- ver = skb->data[1]&0x7f;
- if (ver >= GREPROTO_MAX)
- goto drop;
-
- rcu_read_lock();
- proto = rcu_dereference(gre_proto[ver]);
- if (!proto || !proto->handler)
- goto drop_unlock;
- ret = proto->handler(skb);
- rcu_read_unlock();
- return ret;
-
-drop_unlock:
- rcu_read_unlock();
-drop:
- kfree_skb(skb);
- return NET_RX_DROP;
-}
-
-static void gre_err(struct sk_buff *skb, u32 info)
-{
- const struct gre_protocol *proto;
- const struct iphdr *iph = (const struct iphdr *)skb->data;
- u8 ver = skb->data[(iph->ihl<<2) + 1]&0x7f;
-
- if (ver >= GREPROTO_MAX)
- return;
-
- rcu_read_lock();
- proto = rcu_dereference(gre_proto[ver]);
- if (proto && proto->err_handler)
- proto->err_handler(skb, info);
- rcu_read_unlock();
-}
-
-static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
- netdev_features_t features)
-{
- struct sk_buff *segs = ERR_PTR(-EINVAL);
- netdev_features_t enc_features;
- int ghl = GRE_HEADER_SECTION;
- struct gre_base_hdr *greh;
- int mac_len = skb->mac_len;
- __be16 protocol = skb->protocol;
- int tnl_hlen;
- bool csum;
-
- if (unlikely(skb_shinfo(skb)->gso_type &
- ~(SKB_GSO_TCPV4 |
- SKB_GSO_TCPV6 |
- SKB_GSO_UDP |
- SKB_GSO_DODGY |
- SKB_GSO_TCP_ECN |
- SKB_GSO_GRE)))
- goto out;
-
- if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
- goto out;
-
- greh = (struct gre_base_hdr *)skb_transport_header(skb);
-
- if (greh->flags & GRE_KEY)
- ghl += GRE_HEADER_SECTION;
- if (greh->flags & GRE_SEQ)
- ghl += GRE_HEADER_SECTION;
- if (greh->flags & GRE_CSUM) {
- ghl += GRE_HEADER_SECTION;
- csum = true;
- } else
- csum = false;
-
- /* setup inner skb. */
- skb->protocol = greh->protocol;
- skb->encapsulation = 0;
-
- if (unlikely(!pskb_may_pull(skb, ghl)))
- goto out;
- __skb_pull(skb, ghl);
- skb_reset_mac_header(skb);
- skb_set_network_header(skb, skb_inner_network_offset(skb));
- skb->mac_len = skb_inner_network_offset(skb);
-
- /* segment inner packet. */
- enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
- segs = skb_mac_gso_segment(skb, enc_features);
- if (!segs || IS_ERR(segs))
- goto out;
-
- skb = segs;
- tnl_hlen = skb_tnl_header_len(skb);
- do {
- __skb_push(skb, ghl);
- if (csum) {
- __be32 *pcsum;
-
- if (skb_has_shared_frag(skb)) {
- int err;
-
- err = __skb_linearize(skb);
- if (err) {
- kfree_skb_list(segs);
- segs = ERR_PTR(err);
- goto out;
- }
- }
-
- greh = (struct gre_base_hdr *)(skb->data);
- pcsum = (__be32 *)(greh + 1);
- *pcsum = 0;
- *(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0));
- }
- __skb_push(skb, tnl_hlen - ghl);
-
- skb_reset_mac_header(skb);
- skb_set_network_header(skb, mac_len);
- skb->mac_len = mac_len;
- skb->protocol = protocol;
- } while ((skb = skb->next));
-out:
- return segs;
-}
-
-static int gre_gso_send_check(struct sk_buff *skb)
-{
- if (!skb->encapsulation)
- return -EINVAL;
- return 0;
-}
-
-static const struct net_protocol net_gre_protocol = {
- .handler = gre_rcv,
- .err_handler = gre_err,
- .netns_ok = 1,
-};
-
-static const struct net_offload gre_offload = {
- .callbacks = {
- .gso_send_check = gre_gso_send_check,
- .gso_segment = gre_gso_segment,
- },
-};
-
-static int __init gre_init(void)
-{
- pr_info("GRE over IPv4 demultiplexor driver\n");
-
- if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) {
- pr_err("can't add protocol\n");
- return -EAGAIN;
- }
-
- if (inet_add_offload(&gre_offload, IPPROTO_GRE)) {
- pr_err("can't add protocol offload\n");
- inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
- return -EAGAIN;
- }
-
- return 0;
-}
-
-static void __exit gre_exit(void)
-{
- inet_del_offload(&gre_offload, IPPROTO_GRE);
- inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
-}
-
-module_init(gre_init);
-module_exit(gre_exit);
-
-MODULE_DESCRIPTION("GRE over IPv4 demultiplexer driver");
-MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)");
-MODULE_LICENSE("GPL");
-
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
new file mode 100644
index 000000000000..736c9fc3ef93
--- /dev/null
+++ b/net/ipv4/gre_demux.c
@@ -0,0 +1,414 @@
+/*
+ * GRE over IPv4 demultiplexer driver
+ *
+ * Authors: Dmitry Kozlov (xeb@mail.ru)
+ *
+ * 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.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/if.h>
+#include <linux/icmp.h>
+#include <linux/kernel.h>
+#include <linux/kmod.h>
+#include <linux/skbuff.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/netdevice.h>
+#include <linux/if_tunnel.h>
+#include <linux/spinlock.h>
+#include <net/protocol.h>
+#include <net/gre.h>
+
+#include <net/icmp.h>
+#include <net/route.h>
+#include <net/xfrm.h>
+
+static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly;
+static struct gre_cisco_protocol __rcu *gre_cisco_proto_list[GRE_IP_PROTO_MAX];
+
+int gre_add_protocol(const struct gre_protocol *proto, u8 version)
+{
+ if (version >= GREPROTO_MAX)
+ return -EINVAL;
+
+ return (cmpxchg((const struct gre_protocol **)&gre_proto[version], NULL, proto) == NULL) ?
+ 0 : -EBUSY;
+}
+EXPORT_SYMBOL_GPL(gre_add_protocol);
+
+int gre_del_protocol(const struct gre_protocol *proto, u8 version)
+{
+ int ret;
+
+ if (version >= GREPROTO_MAX)
+ return -EINVAL;
+
+ ret = (cmpxchg((const struct gre_protocol **)&gre_proto[version], proto, NULL) == proto) ?
+ 0 : -EBUSY;
+
+ if (ret)
+ return ret;
+
+ synchronize_rcu();
+ return 0;
+}
+EXPORT_SYMBOL_GPL(gre_del_protocol);
+
+void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
+ int hdr_len)
+{
+ struct gre_base_hdr *greh;
+
+ skb_push(skb, hdr_len);
+
+ greh = (struct gre_base_hdr *)skb->data;
+ greh->flags = tnl_flags_to_gre_flags(tpi->flags);
+ greh->protocol = tpi->proto;
+
+ if (tpi->flags&(TUNNEL_KEY|TUNNEL_CSUM|TUNNEL_SEQ)) {
+ __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
+
+ if (tpi->flags&TUNNEL_SEQ) {
+ *ptr = tpi->seq;
+ ptr--;
+ }
+ if (tpi->flags&TUNNEL_KEY) {
+ *ptr = tpi->key;
+ ptr--;
+ }
+ if (tpi->flags&TUNNEL_CSUM &&
+ !(skb_shinfo(skb)->gso_type & SKB_GSO_GRE)) {
+ *ptr = 0;
+ *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0,
+ skb->len, 0));
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(gre_build_header);
+
+struct sk_buff *gre_handle_offloads(struct sk_buff *skb, bool gre_csum)
+{
+ int err;
+
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
+ }
+
+ if (skb_is_gso(skb)) {
+ err = skb_unclone(skb, GFP_ATOMIC);
+ if (unlikely(err))
+ goto error;
+ skb_shinfo(skb)->gso_type |= SKB_GSO_GRE;
+ return skb;
+ } else if (skb->ip_summed == CHECKSUM_PARTIAL && gre_csum) {
+ err = skb_checksum_help(skb);
+ if (unlikely(err))
+ goto error;
+ } else if (skb->ip_summed != CHECKSUM_PARTIAL)
+ skb->ip_summed = CHECKSUM_NONE;
+
+ return skb;
+error:
+ kfree_skb(skb);
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(gre_handle_offloads);
+
+static __sum16 check_checksum(struct sk_buff *skb)
+{
+ __sum16 csum = 0;
+
+ switch (skb->ip_summed) {
+ case CHECKSUM_COMPLETE:
+ csum = csum_fold(skb->csum);
+
+ if (!csum)
+ break;
+ /* Fall through. */
+
+ case CHECKSUM_NONE:
+ skb->csum = 0;
+ csum = __skb_checksum_complete(skb);
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ break;
+ }
+
+ return csum;
+}
+
+static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
+ bool *csum_err)
+{
+ unsigned int ip_hlen = ip_hdrlen(skb);
+ const struct gre_base_hdr *greh;
+ __be32 *options;
+ int hdr_len;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr))))
+ return -EINVAL;
+
+ greh = (struct gre_base_hdr *)(skb_network_header(skb) + ip_hlen);
+ if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING)))
+ return -EINVAL;
+
+ tpi->flags = gre_flags_to_tnl_flags(greh->flags);
+ hdr_len = ip_gre_calc_hlen(tpi->flags);
+
+ if (!pskb_may_pull(skb, hdr_len))
+ return -EINVAL;
+
+ greh = (struct gre_base_hdr *)(skb_network_header(skb) + ip_hlen);
+ tpi->proto = greh->protocol;
+
+ options = (__be32 *)(greh + 1);
+ if (greh->flags & GRE_CSUM) {
+ if (check_checksum(skb)) {
+ *csum_err = true;
+ return -EINVAL;
+ }
+ options++;
+ }
+
+ if (greh->flags & GRE_KEY) {
+ tpi->key = *options;
+ options++;
+ } else
+ tpi->key = 0;
+
+ if (unlikely(greh->flags & GRE_SEQ)) {
+ tpi->seq = *options;
+ options++;
+ } else
+ tpi->seq = 0;
+
+ /* WCCP version 1 and 2 protocol decoding.
+ * - Change protocol to IP
+ * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
+ */
+ if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) {
+ tpi->proto = htons(ETH_P_IP);
+ if ((*(u8 *)options & 0xF0) != 0x40) {
+ hdr_len += 4;
+ if (!pskb_may_pull(skb, hdr_len))
+ return -EINVAL;
+ }
+ }
+
+ return iptunnel_pull_header(skb, hdr_len, tpi->proto);
+}
+
+static int gre_cisco_rcv(struct sk_buff *skb)
+{
+ struct tnl_ptk_info tpi;
+ int i;
+ bool csum_err = false;
+
+ if (parse_gre_header(skb, &tpi, &csum_err) < 0)
+ goto drop;
+
+ rcu_read_lock();
+ for (i = 0; i < GRE_IP_PROTO_MAX; i++) {
+ struct gre_cisco_protocol *proto;
+ int ret;
+
+ proto = rcu_dereference(gre_cisco_proto_list[i]);
+ if (!proto)
+ continue;
+ ret = proto->handler(skb, &tpi);
+ if (ret == PACKET_RCVD) {
+ rcu_read_unlock();
+ return 0;
+ }
+ }
+ rcu_read_unlock();
+
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+
+static void gre_cisco_err(struct sk_buff *skb, u32 info)
+{
+ /* All the routers (except for Linux) return only
+ * 8 bytes of packet payload. It means, that precise relaying of
+ * ICMP in the real Internet is absolutely infeasible.
+ *
+ * Moreover, Cisco "wise men" put GRE key to the third word
+ * in GRE header. It makes impossible maintaining even soft
+ * state for keyed
+ * GRE tunnels with enabled checksum. Tell them "thank you".
+ *
+ * Well, I wonder, rfc1812 was written by Cisco employee,
+ * what the hell these idiots break standards established
+ * by themselves???
+ */
+
+ const int type = icmp_hdr(skb)->type;
+ const int code = icmp_hdr(skb)->code;
+ struct tnl_ptk_info tpi;
+ bool csum_err = false;
+ int i;
+
+ if (parse_gre_header(skb, &tpi, &csum_err)) {
+ if (!csum_err) /* ignore csum errors. */
+ return;
+ }
+
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
+ ipv4_update_pmtu(skb, dev_net(skb->dev), info,
+ skb->dev->ifindex, 0, IPPROTO_GRE, 0);
+ return;
+ }
+ if (type == ICMP_REDIRECT) {
+ ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, 0,
+ IPPROTO_GRE, 0);
+ return;
+ }
+
+ rcu_read_lock();
+ for (i = 0; i < GRE_IP_PROTO_MAX; i++) {
+ struct gre_cisco_protocol *proto;
+
+ proto = rcu_dereference(gre_cisco_proto_list[i]);
+ if (!proto)
+ continue;
+
+ if (proto->err_handler(skb, info, &tpi) == PACKET_RCVD)
+ goto out;
+
+ }
+out:
+ rcu_read_unlock();
+}
+
+static int gre_rcv(struct sk_buff *skb)
+{
+ const struct gre_protocol *proto;
+ u8 ver;
+ int ret;
+
+ if (!pskb_may_pull(skb, 12))
+ goto drop;
+
+ ver = skb->data[1]&0x7f;
+ if (ver >= GREPROTO_MAX)
+ goto drop;
+
+ rcu_read_lock();
+ proto = rcu_dereference(gre_proto[ver]);
+ if (!proto || !proto->handler)
+ goto drop_unlock;
+ ret = proto->handler(skb);
+ rcu_read_unlock();
+ return ret;
+
+drop_unlock:
+ rcu_read_unlock();
+drop:
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
+
+static void gre_err(struct sk_buff *skb, u32 info)
+{
+ const struct gre_protocol *proto;
+ const struct iphdr *iph = (const struct iphdr *)skb->data;
+ u8 ver = skb->data[(iph->ihl<<2) + 1]&0x7f;
+
+ if (ver >= GREPROTO_MAX)
+ return;
+
+ rcu_read_lock();
+ proto = rcu_dereference(gre_proto[ver]);
+ if (proto && proto->err_handler)
+ proto->err_handler(skb, info);
+ rcu_read_unlock();
+}
+
+static const struct net_protocol net_gre_protocol = {
+ .handler = gre_rcv,
+ .err_handler = gre_err,
+ .netns_ok = 1,
+};
+
+static const struct gre_protocol ipgre_protocol = {
+ .handler = gre_cisco_rcv,
+ .err_handler = gre_cisco_err,
+};
+
+int gre_cisco_register(struct gre_cisco_protocol *newp)
+{
+ struct gre_cisco_protocol **proto = (struct gre_cisco_protocol **)
+ &gre_cisco_proto_list[newp->priority];
+
+ return (cmpxchg(proto, NULL, newp) == NULL) ? 0 : -EBUSY;
+}
+EXPORT_SYMBOL_GPL(gre_cisco_register);
+
+int gre_cisco_unregister(struct gre_cisco_protocol *del_proto)
+{
+ struct gre_cisco_protocol **proto = (struct gre_cisco_protocol **)
+ &gre_cisco_proto_list[del_proto->priority];
+ int ret;
+
+ ret = (cmpxchg(proto, del_proto, NULL) == del_proto) ? 0 : -EINVAL;
+
+ if (ret)
+ return ret;
+
+ synchronize_net();
+ return 0;
+}
+EXPORT_SYMBOL_GPL(gre_cisco_unregister);
+
+static int __init gre_init(void)
+{
+ pr_info("GRE over IPv4 demultiplexor driver\n");
+
+ if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) {
+ pr_err("can't add protocol\n");
+ goto err;
+ }
+
+ if (gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0) {
+ pr_info("%s: can't add ipgre handler\n", __func__);
+ goto err_gre;
+ }
+
+ if (gre_offload_init()) {
+ pr_err("can't add protocol offload\n");
+ goto err_gso;
+ }
+
+ return 0;
+err_gso:
+ gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
+err_gre:
+ inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
+err:
+ return -EAGAIN;
+}
+
+static void __exit gre_exit(void)
+{
+ gre_offload_exit();
+
+ gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
+ inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
+}
+
+module_init(gre_init);
+module_exit(gre_exit);
+
+MODULE_DESCRIPTION("GRE over IPv4 demultiplexer driver");
+MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)");
+MODULE_LICENSE("GPL");
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
new file mode 100644
index 000000000000..775d5b532ece
--- /dev/null
+++ b/net/ipv4/gre_offload.c
@@ -0,0 +1,127 @@
+/*
+ * IPV4 GSO/GRO offload support
+ * Linux INET implementation
+ *
+ * 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.
+ *
+ * GRE GSO support
+ */
+
+#include <linux/skbuff.h>
+#include <net/protocol.h>
+#include <net/gre.h>
+
+static int gre_gso_send_check(struct sk_buff *skb)
+{
+ if (!skb->encapsulation)
+ return -EINVAL;
+ return 0;
+}
+
+static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ netdev_features_t enc_features;
+ int ghl = GRE_HEADER_SECTION;
+ struct gre_base_hdr *greh;
+ int mac_len = skb->mac_len;
+ __be16 protocol = skb->protocol;
+ int tnl_hlen;
+ bool csum;
+
+ if (unlikely(skb_shinfo(skb)->gso_type &
+ ~(SKB_GSO_TCPV4 |
+ SKB_GSO_TCPV6 |
+ SKB_GSO_UDP |
+ SKB_GSO_DODGY |
+ SKB_GSO_TCP_ECN |
+ SKB_GSO_GRE)))
+ goto out;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
+ goto out;
+
+ greh = (struct gre_base_hdr *)skb_transport_header(skb);
+
+ if (greh->flags & GRE_KEY)
+ ghl += GRE_HEADER_SECTION;
+ if (greh->flags & GRE_SEQ)
+ ghl += GRE_HEADER_SECTION;
+ if (greh->flags & GRE_CSUM) {
+ ghl += GRE_HEADER_SECTION;
+ csum = true;
+ } else
+ csum = false;
+
+ /* setup inner skb. */
+ skb->protocol = greh->protocol;
+ skb->encapsulation = 0;
+
+ if (unlikely(!pskb_may_pull(skb, ghl)))
+ goto out;
+
+ __skb_pull(skb, ghl);
+ skb_reset_mac_header(skb);
+ skb_set_network_header(skb, skb_inner_network_offset(skb));
+ skb->mac_len = skb_inner_network_offset(skb);
+
+ /* segment inner packet. */
+ enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
+ segs = skb_mac_gso_segment(skb, enc_features);
+ if (!segs || IS_ERR(segs))
+ goto out;
+
+ skb = segs;
+ tnl_hlen = skb_tnl_header_len(skb);
+ do {
+ __skb_push(skb, ghl);
+ if (csum) {
+ __be32 *pcsum;
+
+ if (skb_has_shared_frag(skb)) {
+ int err;
+
+ err = __skb_linearize(skb);
+ if (err) {
+ kfree_skb_list(segs);
+ segs = ERR_PTR(err);
+ goto out;
+ }
+ }
+
+ greh = (struct gre_base_hdr *)(skb->data);
+ pcsum = (__be32 *)(greh + 1);
+ *pcsum = 0;
+ *(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0));
+ }
+ __skb_push(skb, tnl_hlen - ghl);
+
+ skb_reset_mac_header(skb);
+ skb_set_network_header(skb, mac_len);
+ skb->mac_len = mac_len;
+ skb->protocol = protocol;
+ } while ((skb = skb->next));
+out:
+ return segs;
+}
+
+static const struct net_offload gre_offload = {
+ .callbacks = {
+ .gso_send_check = gre_gso_send_check,
+ .gso_segment = gre_gso_segment,
+ },
+};
+
+int __init gre_offload_init(void)
+{
+ return inet_add_offload(&gre_offload, IPPROTO_GRE);
+}
+
+void __exit gre_offload_exit(void)
+{
+ inet_del_offload(&gre_offload, IPPROTO_GRE);
+}
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 76e10b47e053..5f7d11a45871 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -482,7 +482,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
{
struct iphdr *iph;
int room;
- struct icmp_bxm icmp_param;
+ struct icmp_bxm *icmp_param;
struct rtable *rt = skb_rtable(skb_in);
struct ipcm_cookie ipc;
struct flowi4 fl4;
@@ -503,7 +503,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
iph = ip_hdr(skb_in);
if ((u8 *)iph < skb_in->head ||
- (skb_in->network_header + sizeof(*iph)) > skb_in->tail)
+ (skb_network_header(skb_in) + sizeof(*iph)) >
+ skb_tail_pointer(skb_in))
goto out;
/*
@@ -557,9 +558,13 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
}
}
+ icmp_param = kmalloc(sizeof(*icmp_param), GFP_ATOMIC);
+ if (!icmp_param)
+ return;
+
sk = icmp_xmit_lock(net);
if (sk == NULL)
- return;
+ goto out_free;
/*
* Construct source address and options.
@@ -585,7 +590,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
IPTOS_PREC_INTERNETCONTROL) :
iph->tos;
- if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in))
+ if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb_in))
goto out_unlock;
@@ -593,19 +598,19 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
* Prepare data for ICMP header.
*/
- icmp_param.data.icmph.type = type;
- icmp_param.data.icmph.code = code;
- icmp_param.data.icmph.un.gateway = info;
- icmp_param.data.icmph.checksum = 0;
- icmp_param.skb = skb_in;
- icmp_param.offset = skb_network_offset(skb_in);
+ icmp_param->data.icmph.type = type;
+ icmp_param->data.icmph.code = code;
+ icmp_param->data.icmph.un.gateway = info;
+ icmp_param->data.icmph.checksum = 0;
+ icmp_param->skb = skb_in;
+ icmp_param->offset = skb_network_offset(skb_in);
inet_sk(sk)->tos = tos;
ipc.addr = iph->saddr;
- ipc.opt = &icmp_param.replyopts.opt;
+ ipc.opt = &icmp_param->replyopts.opt;
ipc.tx_flags = 0;
rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
- type, code, &icmp_param);
+ type, code, icmp_param);
if (IS_ERR(rt))
goto out_unlock;
@@ -617,19 +622,21 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
room = dst_mtu(&rt->dst);
if (room > 576)
room = 576;
- room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
+ room -= sizeof(struct iphdr) + icmp_param->replyopts.opt.opt.optlen;
room -= sizeof(struct icmphdr);
- icmp_param.data_len = skb_in->len - icmp_param.offset;
- if (icmp_param.data_len > room)
- icmp_param.data_len = room;
- icmp_param.head_len = sizeof(struct icmphdr);
+ icmp_param->data_len = skb_in->len - icmp_param->offset;
+ if (icmp_param->data_len > room)
+ icmp_param->data_len = room;
+ icmp_param->head_len = sizeof(struct icmphdr);
- icmp_push_reply(&icmp_param, &fl4, &ipc, &rt);
+ icmp_push_reply(icmp_param, &fl4, &ipc, &rt);
ende:
ip_rt_put(rt);
out_unlock:
icmp_xmit_unlock(sk);
+out_free:
+ kfree(icmp_param);
out:;
}
EXPORT_SYMBOL(icmp_send);
@@ -657,7 +664,8 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
}
/*
- * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, and ICMP_QUENCH.
+ * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and
+ * ICMP_PARAMETERPROB.
*/
static void icmp_unreach(struct sk_buff *skb)
@@ -939,7 +947,8 @@ error:
void icmp_err(struct sk_buff *skb, u32 info)
{
struct iphdr *iph = (struct iphdr *)skb->data;
- struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
+ int offset = iph->ihl<<2;
+ struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset);
int type = icmp_hdr(skb)->type;
int code = icmp_hdr(skb)->code;
struct net *net = dev_net(skb->dev);
@@ -949,7 +958,7 @@ void icmp_err(struct sk_buff *skb, u32 info)
* triggered by ICMP_ECHOREPLY which sent from kernel.
*/
if (icmph->type != ICMP_ECHOREPLY) {
- ping_err(skb, info);
+ ping_err(skb, offset, info);
return;
}
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index d8c232794bcb..cd71190d2962 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -363,7 +363,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
static int igmpv3_sendpack(struct sk_buff *skb)
{
struct igmphdr *pig = igmp_hdr(skb);
- const int igmplen = skb->tail - skb->transport_header;
+ const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb);
pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen);
@@ -1217,6 +1217,57 @@ static void igmp_group_added(struct ip_mc_list *im)
* Multicast list managers
*/
+static u32 ip_mc_hash(const struct ip_mc_list *im)
+{
+ return hash_32((__force u32)im->multiaddr, MC_HASH_SZ_LOG);
+}
+
+static void ip_mc_hash_add(struct in_device *in_dev,
+ struct ip_mc_list *im)
+{
+ struct ip_mc_list __rcu **mc_hash;
+ u32 hash;
+
+ mc_hash = rtnl_dereference(in_dev->mc_hash);
+ if (mc_hash) {
+ hash = ip_mc_hash(im);
+ im->next_hash = mc_hash[hash];
+ rcu_assign_pointer(mc_hash[hash], im);
+ return;
+ }
+
+ /* do not use a hash table for small number of items */
+ if (in_dev->mc_count < 4)
+ return;
+
+ mc_hash = kzalloc(sizeof(struct ip_mc_list *) << MC_HASH_SZ_LOG,
+ GFP_KERNEL);
+ if (!mc_hash)
+ return;
+
+ for_each_pmc_rtnl(in_dev, im) {
+ hash = ip_mc_hash(im);
+ im->next_hash = mc_hash[hash];
+ RCU_INIT_POINTER(mc_hash[hash], im);
+ }
+
+ rcu_assign_pointer(in_dev->mc_hash, mc_hash);
+}
+
+static void ip_mc_hash_remove(struct in_device *in_dev,
+ struct ip_mc_list *im)
+{
+ struct ip_mc_list __rcu **mc_hash = rtnl_dereference(in_dev->mc_hash);
+ struct ip_mc_list *aux;
+
+ if (!mc_hash)
+ return;
+ mc_hash += ip_mc_hash(im);
+ while ((aux = rtnl_dereference(*mc_hash)) != im)
+ mc_hash = &aux->next_hash;
+ *mc_hash = im->next_hash;
+}
+
/*
* A socket has joined a multicast group on device dev.
@@ -1258,6 +1309,8 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
in_dev->mc_count++;
rcu_assign_pointer(in_dev->mc_list, im);
+ ip_mc_hash_add(in_dev, im);
+
#ifdef CONFIG_IP_MULTICAST
igmpv3_del_delrec(in_dev, im->multiaddr);
#endif
@@ -1314,6 +1367,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr)
ip = &i->next_rcu) {
if (i->multiaddr == addr) {
if (--i->users == 0) {
+ ip_mc_hash_remove(in_dev, i);
*ip = i->next_rcu;
in_dev->mc_count--;
igmp_group_dropped(i);
@@ -1381,13 +1435,9 @@ void ip_mc_init_dev(struct in_device *in_dev)
{
ASSERT_RTNL();
- in_dev->mc_tomb = NULL;
#ifdef CONFIG_IP_MULTICAST
- in_dev->mr_gq_running = 0;
setup_timer(&in_dev->mr_gq_timer, igmp_gq_timer_expire,
(unsigned long)in_dev);
- in_dev->mr_ifc_count = 0;
- in_dev->mc_count = 0;
setup_timer(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire,
(unsigned long)in_dev);
in_dev->mr_qrv = IGMP_Unsolicited_Report_Count;
@@ -2321,12 +2371,25 @@ void ip_mc_drop_socket(struct sock *sk)
int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 proto)
{
struct ip_mc_list *im;
+ struct ip_mc_list __rcu **mc_hash;
struct ip_sf_list *psf;
int rv = 0;
- for_each_pmc_rcu(in_dev, im) {
- if (im->multiaddr == mc_addr)
- break;
+ mc_hash = rcu_dereference(in_dev->mc_hash);
+ if (mc_hash) {
+ u32 hash = hash_32((__force u32)mc_addr, MC_HASH_SZ_LOG);
+
+ for (im = rcu_dereference(mc_hash[hash]);
+ im != NULL;
+ im = rcu_dereference(im->next_hash)) {
+ if (im->multiaddr == mc_addr)
+ break;
+ }
+ } else {
+ for_each_pmc_rcu(in_dev, im) {
+ if (im->multiaddr == mc_addr)
+ break;
+ }
}
if (im && proto == IPPROTO_IGMP) {
rv = 1;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index cec539458307..c5313a9c019b 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -247,8 +247,6 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
{
struct inet_frag_bucket *hb;
struct inet_frag_queue *qp;
-#ifdef CONFIG_SMP
-#endif
unsigned int hash;
read_lock(&f->lock); /* Protects against hash rebuild */
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2a83591492dd..1f6eab66f7ce 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -121,103 +121,8 @@ static int ipgre_tunnel_init(struct net_device *dev);
static int ipgre_net_id __read_mostly;
static int gre_tap_net_id __read_mostly;
-static __sum16 check_checksum(struct sk_buff *skb)
-{
- __sum16 csum = 0;
-
- switch (skb->ip_summed) {
- case CHECKSUM_COMPLETE:
- csum = csum_fold(skb->csum);
-
- if (!csum)
- break;
- /* Fall through. */
-
- case CHECKSUM_NONE:
- skb->csum = 0;
- csum = __skb_checksum_complete(skb);
- skb->ip_summed = CHECKSUM_COMPLETE;
- break;
- }
-
- return csum;
-}
-
-static int ip_gre_calc_hlen(__be16 o_flags)
-{
- int addend = 4;
-
- if (o_flags&TUNNEL_CSUM)
- addend += 4;
- if (o_flags&TUNNEL_KEY)
- addend += 4;
- if (o_flags&TUNNEL_SEQ)
- addend += 4;
- return addend;
-}
-
-static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
- bool *csum_err, int *hdr_len)
-{
- unsigned int ip_hlen = ip_hdrlen(skb);
- const struct gre_base_hdr *greh;
- __be32 *options;
-
- if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr))))
- return -EINVAL;
-
- greh = (struct gre_base_hdr *)(skb_network_header(skb) + ip_hlen);
- if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING)))
- return -EINVAL;
-
- tpi->flags = gre_flags_to_tnl_flags(greh->flags);
- *hdr_len = ip_gre_calc_hlen(tpi->flags);
-
- if (!pskb_may_pull(skb, *hdr_len))
- return -EINVAL;
-
- greh = (struct gre_base_hdr *)(skb_network_header(skb) + ip_hlen);
-
- tpi->proto = greh->protocol;
-
- options = (__be32 *)(greh + 1);
- if (greh->flags & GRE_CSUM) {
- if (check_checksum(skb)) {
- *csum_err = true;
- return -EINVAL;
- }
- options++;
- }
-
- if (greh->flags & GRE_KEY) {
- tpi->key = *options;
- options++;
- } else
- tpi->key = 0;
-
- if (unlikely(greh->flags & GRE_SEQ)) {
- tpi->seq = *options;
- options++;
- } else
- tpi->seq = 0;
-
- /* WCCP version 1 and 2 protocol decoding.
- * - Change protocol to IP
- * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
- */
- if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) {
- tpi->proto = htons(ETH_P_IP);
- if ((*(u8 *)options & 0xF0) != 0x40) {
- *hdr_len += 4;
- if (!pskb_may_pull(skb, *hdr_len))
- return -EINVAL;
- }
- }
-
- return 0;
-}
-
-static void ipgre_err(struct sk_buff *skb, u32 info)
+static int ipgre_err(struct sk_buff *skb, u32 info,
+ const struct tnl_ptk_info *tpi)
{
/* All the routers (except for Linux) return only
@@ -239,26 +144,18 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
- struct tnl_ptk_info tpi;
- int hdr_len;
- bool csum_err = false;
-
- if (parse_gre_header(skb, &tpi, &csum_err, &hdr_len)) {
- if (!csum_err) /* ignore csum errors. */
- return;
- }
switch (type) {
default:
case ICMP_PARAMETERPROB:
- return;
+ return PACKET_RCVD;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
- return;
+ return PACKET_RCVD;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
@@ -269,138 +166,61 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
- return;
+ return PACKET_RCVD;
break;
case ICMP_REDIRECT:
break;
}
- if (tpi.proto == htons(ETH_P_TEB))
+ if (tpi->proto == htons(ETH_P_TEB))
itn = net_generic(net, gre_tap_net_id);
else
itn = net_generic(net, ipgre_net_id);
iph = (const struct iphdr *)skb->data;
- t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi.flags,
- iph->daddr, iph->saddr, tpi.key);
+ t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags,
+ iph->daddr, iph->saddr, tpi->key);
if (t == NULL)
- return;
+ return PACKET_REJECT;
- if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
- ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- t->parms.link, 0, IPPROTO_GRE, 0);
- return;
- }
- if (type == ICMP_REDIRECT) {
- ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
- IPPROTO_GRE, 0);
- return;
- }
if (t->parms.iph.daddr == 0 ||
ipv4_is_multicast(t->parms.iph.daddr))
- return;
+ return PACKET_RCVD;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
- return;
+ return PACKET_RCVD;
if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
t->err_count++;
else
t->err_count = 1;
t->err_time = jiffies;
+ return PACKET_RCVD;
}
-static int ipgre_rcv(struct sk_buff *skb)
+static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
{
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn;
const struct iphdr *iph;
struct ip_tunnel *tunnel;
- struct tnl_ptk_info tpi;
- int hdr_len;
- bool csum_err = false;
-
- if (parse_gre_header(skb, &tpi, &csum_err, &hdr_len) < 0)
- goto drop;
- if (tpi.proto == htons(ETH_P_TEB))
+ if (tpi->proto == htons(ETH_P_TEB))
itn = net_generic(net, gre_tap_net_id);
else
itn = net_generic(net, ipgre_net_id);
iph = ip_hdr(skb);
- tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi.flags,
- iph->saddr, iph->daddr, tpi.key);
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags,
+ iph->saddr, iph->daddr, tpi->key);
if (tunnel) {
- ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
- return 0;
- }
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
-drop:
- kfree_skb(skb);
- return 0;
-}
-
-static struct sk_buff *handle_offloads(struct ip_tunnel *tunnel, struct sk_buff *skb)
-{
- int err;
-
- if (skb_is_gso(skb)) {
- err = skb_unclone(skb, GFP_ATOMIC);
- if (unlikely(err))
- goto error;
- skb_shinfo(skb)->gso_type |= SKB_GSO_GRE;
- return skb;
- } else if (skb->ip_summed == CHECKSUM_PARTIAL &&
- tunnel->parms.o_flags&TUNNEL_CSUM) {
- err = skb_checksum_help(skb);
- if (unlikely(err))
- goto error;
- } else if (skb->ip_summed != CHECKSUM_PARTIAL)
- skb->ip_summed = CHECKSUM_NONE;
-
- return skb;
-
-error:
- kfree_skb(skb);
- return ERR_PTR(err);
-}
-
-static struct sk_buff *gre_build_header(struct sk_buff *skb,
- const struct tnl_ptk_info *tpi,
- int hdr_len)
-{
- struct gre_base_hdr *greh;
-
- skb_push(skb, hdr_len);
-
- greh = (struct gre_base_hdr *)skb->data;
- greh->flags = tnl_flags_to_gre_flags(tpi->flags);
- greh->protocol = tpi->proto;
-
- if (tpi->flags&(TUNNEL_KEY|TUNNEL_CSUM|TUNNEL_SEQ)) {
- __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
-
- if (tpi->flags&TUNNEL_SEQ) {
- *ptr = tpi->seq;
- ptr--;
- }
- if (tpi->flags&TUNNEL_KEY) {
- *ptr = tpi->key;
- ptr--;
- }
- if (tpi->flags&TUNNEL_CSUM &&
- !(skb_shinfo(skb)->gso_type & SKB_GSO_GRE)) {
- *(__sum16 *)ptr = 0;
- *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0,
- skb->len, 0));
- }
+ ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error);
+ return PACKET_RCVD;
}
-
- return skb;
+ return PACKET_REJECT;
}
static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
@@ -410,11 +230,6 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
struct ip_tunnel *tunnel = netdev_priv(dev);
struct tnl_ptk_info tpi;
- if (likely(!skb->encapsulation)) {
- skb_reset_inner_headers(skb);
- skb->encapsulation = 1;
- }
-
tpi.flags = tunnel->parms.o_flags;
tpi.proto = proto;
tpi.key = tunnel->parms.o_key;
@@ -423,13 +238,9 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
tpi.seq = htonl(tunnel->o_seqno);
/* Push GRE header. */
- skb = gre_build_header(skb, &tpi, tunnel->hlen);
- if (unlikely(!skb)) {
- dev->stats.tx_dropped++;
- return;
- }
+ gre_build_header(skb, &tpi, tunnel->hlen);
- ip_tunnel_xmit(skb, dev, tnl_params);
+ ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol);
}
static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
@@ -438,7 +249,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tnl_params;
- skb = handle_offloads(tunnel, skb);
+ skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM));
if (IS_ERR(skb))
goto out;
@@ -477,7 +288,7 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- skb = handle_offloads(tunnel, skb);
+ skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM));
if (IS_ERR(skb))
goto out;
@@ -503,10 +314,11 @@ static int ipgre_tunnel_ioctl(struct net_device *dev,
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
return -EFAULT;
- 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))) {
- return -EINVAL;
+ 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)))
+ return -EINVAL;
}
p.i_flags = gre_flags_to_tnl_flags(p.i_flags);
p.o_flags = gre_flags_to_tnl_flags(p.o_flags);
@@ -708,9 +520,10 @@ static int ipgre_tunnel_init(struct net_device *dev)
return ip_tunnel_init(dev);
}
-static const struct gre_protocol ipgre_protocol = {
- .handler = ipgre_rcv,
- .err_handler = ipgre_err,
+static struct gre_cisco_protocol ipgre_protocol = {
+ .handler = ipgre_rcv,
+ .err_handler = ipgre_err,
+ .priority = 0,
};
static int __net_init ipgre_init_net(struct net *net)
@@ -978,7 +791,7 @@ static int __init ipgre_init(void)
if (err < 0)
goto pnet_tap_faied;
- err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO);
+ err = gre_cisco_register(&ipgre_protocol);
if (err < 0) {
pr_info("%s: can't add protocol\n", __func__);
goto add_proto_failed;
@@ -997,7 +810,7 @@ static int __init ipgre_init(void)
tap_ops_failed:
rtnl_link_unregister(&ipgre_link_ops);
rtnl_link_failed:
- gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
+ gre_cisco_unregister(&ipgre_protocol);
add_proto_failed:
unregister_pernet_device(&ipgre_tap_net_ops);
pnet_tap_faied:
@@ -1009,8 +822,7 @@ static void __exit ipgre_fini(void)
{
rtnl_link_unregister(&ipgre_tap_ops);
rtnl_link_unregister(&ipgre_link_ops);
- if (gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0)
- pr_info("%s: can't remove protocol\n", __func__);
+ gre_cisco_unregister(&ipgre_protocol);
unregister_pernet_device(&ipgre_tap_net_ops);
unregister_pernet_device(&ipgre_net_ops);
}
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 7fa8f08fa7ae..945734b2f209 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -304,6 +304,7 @@ static struct net_device *__ip_tunnel_create(struct net *net,
tunnel = netdev_priv(dev);
tunnel->parms = *parms;
+ tunnel->net = net;
err = register_netdevice(dev);
if (err)
@@ -408,13 +409,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
const struct iphdr *iph = ip_hdr(skb);
int err;
- secpath_reset(skb);
-
- skb->protocol = tpi->proto;
-
- skb->mac_header = skb->network_header;
- __pskb_pull(skb, tunnel->hlen);
- skb_postpull_rcsum(skb, skb_transport_header(skb), tunnel->hlen);
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
/* Looped back packet, drop it! */
@@ -442,23 +436,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
tunnel->i_seqno = ntohl(tpi->seq) + 1;
}
- /* Warning: All skb pointers will be invalidated! */
- if (tunnel->dev->type == ARPHRD_ETHER) {
- if (!pskb_may_pull(skb, ETH_HLEN)) {
- tunnel->dev->stats.rx_length_errors++;
- tunnel->dev->stats.rx_errors++;
- goto drop;
- }
-
- iph = ip_hdr(skb);
- skb->protocol = eth_type_trans(skb, tunnel->dev);
- skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
- }
-
- skb->pkt_type = PACKET_HOST;
- __skb_tunnel_rx(skb, tunnel->dev);
-
- skb_reset_network_header(skb);
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
if (log_ecn_error)
@@ -477,6 +454,15 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
+ if (tunnel->net != dev_net(tunnel->dev))
+ skb_scrub_packet(skb);
+
+ if (tunnel->dev->type == ARPHRD_ETHER) {
+ skb->protocol = eth_type_trans(skb, tunnel->dev);
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+ } else {
+ skb->dev = tunnel->dev;
+ }
gro_cells_receive(&tunnel->gro_cells, skb);
return 0;
@@ -486,24 +472,69 @@ drop:
}
EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
+static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
+ struct rtable *rt, __be16 df)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ int pkt_size = skb->len - tunnel->hlen;
+ int mtu;
+
+ if (df)
+ mtu = dst_mtu(&rt->dst) - dev->hard_header_len
+ - sizeof(struct iphdr) - tunnel->hlen;
+ else
+ mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+
+ if (skb_dst(skb))
+ skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+
+ if (skb->protocol == htons(ETH_P_IP)) {
+ if (!skb_is_gso(skb) &&
+ (df & htons(IP_DF)) && mtu < pkt_size) {
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
+ return -E2BIG;
+ }
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (skb->protocol == htons(ETH_P_IPV6)) {
+ struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
+
+ if (rt6 && mtu < dst_mtu(skb_dst(skb)) &&
+ mtu >= IPV6_MIN_MTU) {
+ if ((tunnel->parms.iph.daddr &&
+ !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
+ rt6->rt6i_dst.plen == 128) {
+ rt6->rt6i_flags |= RTF_MODIFIED;
+ dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
+ }
+ }
+
+ if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
+ mtu < pkt_size) {
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ return -E2BIG;
+ }
+ }
+#endif
+ return 0;
+}
+
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
- const struct iphdr *tnl_params)
+ const struct iphdr *tnl_params, const u8 protocol)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *inner_iph;
- struct iphdr *iph;
struct flowi4 fl4;
u8 tos, ttl;
__be16 df;
struct rtable *rt; /* Route to the other host */
- struct net_device *tdev; /* Device to other host */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst;
- int mtu;
+ int err;
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
- memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
dst = tnl_params->daddr;
if (dst == 0) {
/* NBMA tunnel */
@@ -561,8 +592,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
}
- rt = ip_route_output_tunnel(dev_net(dev), &fl4,
- tunnel->parms.iph.protocol,
+ rt = ip_route_output_tunnel(tunnel->net, &fl4,
+ protocol,
dst, tnl_params->saddr,
tunnel->parms.o_key,
RT_TOS(tos),
@@ -571,58 +602,19 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
dev->stats.tx_carrier_errors++;
goto tx_error;
}
- tdev = rt->dst.dev;
-
- if (tdev == dev) {
+ if (rt->dst.dev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
- df = tnl_params->frag_off;
-
- if (df)
- mtu = dst_mtu(&rt->dst) - dev->hard_header_len
- - sizeof(struct iphdr);
- else
- mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
-
- if (skb_dst(skb))
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-
- if (skb->protocol == htons(ETH_P_IP)) {
- df |= (inner_iph->frag_off&htons(IP_DF));
-
- if (!skb_is_gso(skb) &&
- (inner_iph->frag_off&htons(IP_DF)) &&
- mtu < ntohs(inner_iph->tot_len)) {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
- ip_rt_put(rt);
- goto tx_error;
- }
+ if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
+ ip_rt_put(rt);
+ goto tx_error;
}
-#if IS_ENABLED(CONFIG_IPV6)
- else if (skb->protocol == htons(ETH_P_IPV6)) {
- struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
-
- if (rt6 && mtu < dst_mtu(skb_dst(skb)) &&
- mtu >= IPV6_MIN_MTU) {
- if ((tunnel->parms.iph.daddr &&
- !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
- rt6->rt6i_dst.plen == 128) {
- rt6->rt6i_flags |= RTF_MODIFIED;
- dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
- }
- }
- if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
- mtu < skb->len) {
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- ip_rt_put(rt);
- goto tx_error;
- }
- }
-#endif
+ if (tunnel->net != dev_net(dev))
+ skb_scrub_packet(skb);
if (tunnel->err_count > 0) {
if (time_before(jiffies,
@@ -646,8 +638,12 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
ttl = ip4_dst_hoplimit(&rt->dst);
}
- max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr)
- + rt->dst.header_len;
+ df = tnl_params->frag_off;
+ if (skb->protocol == htons(ETH_P_IP))
+ df |= (inner_iph->frag_off&htons(IP_DF));
+
+ max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
+ + rt->dst.header_len;
if (max_headroom > dev->needed_headroom) {
dev->needed_headroom = max_headroom;
if (skb_cow_head(skb, dev->needed_headroom)) {
@@ -657,27 +653,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
}
}
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
- /* Push down and install the IP header. */
- skb_push(skb, sizeof(struct iphdr));
- skb_reset_network_header(skb);
-
- iph = ip_hdr(skb);
- inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+ err = iptunnel_xmit(dev_net(dev), rt, skb,
+ fl4.saddr, fl4.daddr, protocol,
+ ip_tunnel_ecn_encap(tos, inner_iph, skb), ttl, df);
+ iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
- iph->version = 4;
- iph->ihl = sizeof(struct iphdr) >> 2;
- iph->frag_off = df;
- iph->protocol = tnl_params->protocol;
- iph->tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
- iph->daddr = fl4.daddr;
- iph->saddr = fl4.saddr;
- iph->ttl = ttl;
- tunnel_ip_select_ident(skb, inner_iph, &rt->dst);
-
- iptunnel_xmit(skb, dev);
return;
#if IS_ENABLED(CONFIG_IPV6)
@@ -926,6 +906,7 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
if (ip_tunnel_find(itn, p, dev->type))
return -EEXIST;
+ nt->net = net;
nt->parms = *p;
err = register_netdevice(dev);
if (err)
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
new file mode 100644
index 000000000000..7167b08977df
--- /dev/null
+++ b/net/ipv4/ip_tunnel_core.c
@@ -0,0 +1,122 @@
+/*
+ * Copyright (c) 2013 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/in.h>
+#include <linux/if_arp.h>
+#include <linux/mroute.h>
+#include <linux/init.h>
+#include <linux/in6.h>
+#include <linux/inetdevice.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/protocol.h>
+#include <net/ip_tunnels.h>
+#include <net/arp.h>
+#include <net/checksum.h>
+#include <net/dsfield.h>
+#include <net/inet_ecn.h>
+#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
+
+int iptunnel_xmit(struct net *net, struct rtable *rt,
+ struct sk_buff *skb,
+ __be32 src, __be32 dst, __u8 proto,
+ __u8 tos, __u8 ttl, __be16 df)
+{
+ int pkt_len = skb->len;
+ struct iphdr *iph;
+ int err;
+
+ nf_reset(skb);
+ secpath_reset(skb);
+ skb->rxhash = 0;
+ skb_dst_drop(skb);
+ skb_dst_set(skb, &rt->dst);
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+
+ /* Push down and install the IP header. */
+ __skb_push(skb, sizeof(struct iphdr));
+ skb_reset_network_header(skb);
+
+ iph = ip_hdr(skb);
+
+ iph->version = 4;
+ iph->ihl = sizeof(struct iphdr) >> 2;
+ iph->frag_off = df;
+ iph->protocol = proto;
+ iph->tos = tos;
+ iph->daddr = dst;
+ iph->saddr = src;
+ iph->ttl = ttl;
+ tunnel_ip_select_ident(skb,
+ (const struct iphdr *)skb_inner_network_header(skb),
+ &rt->dst);
+
+ err = ip_local_out(skb);
+ if (unlikely(net_xmit_eval(err)))
+ pkt_len = 0;
+ return pkt_len;
+}
+EXPORT_SYMBOL_GPL(iptunnel_xmit);
+
+int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
+{
+ if (unlikely(!pskb_may_pull(skb, hdr_len)))
+ return -ENOMEM;
+
+ skb_pull_rcsum(skb, hdr_len);
+
+ if (inner_proto == htons(ETH_P_TEB)) {
+ struct ethhdr *eh = (struct ethhdr *)skb->data;
+
+ if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
+ return -ENOMEM;
+
+ if (likely(ntohs(eh->h_proto) >= ETH_P_802_3_MIN))
+ skb->protocol = eh->h_proto;
+ else
+ skb->protocol = htons(ETH_P_802_2);
+
+ } else {
+ skb->protocol = inner_proto;
+ }
+
+ nf_reset(skb);
+ secpath_reset(skb);
+ if (!skb->l4_rxhash)
+ skb->rxhash = 0;
+ skb_dst_drop(skb);
+ skb->vlan_tci = 0;
+ skb_set_queue_mapping(skb, 0);
+ skb->pkt_type = PACKET_HOST;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iptunnel_pull_header);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index c118f6b576bb..17cc0ffa8c0d 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -606,17 +606,10 @@ static int __net_init vti_fb_tunnel_init(struct net_device *dev)
struct iphdr *iph = &tunnel->parms.iph;
struct vti_net *ipn = net_generic(dev_net(dev), vti_net_id);
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
-
iph->version = 4;
iph->protocol = IPPROTO_IPIP;
iph->ihl = 5;
- dev->tstats = alloc_percpu(struct pcpu_tstats);
- if (!dev->tstats)
- return -ENOMEM;
-
dev_hold(dev);
rcu_assign_pointer(ipn->tunnels_wc[0], tunnel);
return 0;
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 59cb8c769056..826be4cb482a 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -47,12 +47,9 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info)
if (!x)
return;
- if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
- atomic_inc(&flow_cache_genid);
- rt_genid_bump(net);
-
+ if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
- } else
+ else
ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 77bfcce64fe5..51fc2a1dcdd3 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -188,8 +188,12 @@ static int ipip_rcv(struct sk_buff *skb)
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
struct ip_tunnel *tunnel;
- const struct iphdr *iph = ip_hdr(skb);
+ const struct iphdr *iph;
+ if (iptunnel_pull_header(skb, 0, tpi.proto))
+ goto drop;
+
+ iph = ip_hdr(skb);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
if (tunnel) {
@@ -222,7 +226,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
skb->encapsulation = 1;
}
- ip_tunnel_xmit(skb, dev, tiph);
+ ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
return NETDEV_TX_OK;
tx_error:
@@ -240,11 +244,13 @@ ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
return -EFAULT;
- if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
- p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
- return -EINVAL;
- if (p.i_key || p.o_key || p.i_flags || p.o_flags)
- return -EINVAL;
+ if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
+ if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
+ p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
+ return -EINVAL;
+ }
+
+ p.i_key = p.o_key = p.i_flags = p.o_flags = 0;
if (p.iph.ttl)
p.iph.frag_off |= htons(IP_DF);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d9610ae7855..132a09664704 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -980,7 +980,7 @@ static int ipmr_cache_report(struct mr_table *mrt,
/* Copy the IP header */
- skb->network_header = skb->tail;
+ skb_set_network_header(skb, skb->len);
skb_put(skb, ihl);
skb_copy_to_linear_data(skb, pkt->data, ihl);
ip_hdr(skb)->protocol = 0; /* Flag to the kernel this is a route add */
@@ -1609,7 +1609,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct mr_table *mrt;
struct vif_device *v;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index e7916c193932..4e9028017428 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -111,7 +111,7 @@ config IP_NF_TARGET_REJECT
To compile it as a module, choose M here. If unsure, say N.
config IP_NF_TARGET_ULOG
- tristate "ULOG target support"
+ tristate "ULOG target support (obsolete)"
default m if NETFILTER_ADVANCED=n
---help---
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index 5d5d4d1be9c2..30e4de940567 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -108,7 +108,7 @@ static int masq_device_event(struct notifier_block *this,
unsigned long event,
void *ptr)
{
- const struct net_device *dev = ptr;
+ const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
if (event == NETDEV_DOWN) {
@@ -129,7 +129,10 @@ static int masq_inet_event(struct notifier_block *this,
void *ptr)
{
struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
- return masq_device_event(this, event, dev);
+ struct netdev_notifier_info info;
+
+ netdev_notifier_info_init(&info, dev);
+ return masq_device_event(this, event, &info);
}
static struct notifier_block masq_dev_notifier = {
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index 32b0e978c8e0..cbc22158af49 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -331,6 +331,12 @@ static int ulog_tg_check(const struct xt_tgchk_param *par)
{
const struct ipt_ulog_info *loginfo = par->targinfo;
+ if (!par->net->xt.ulog_warn_deprecated) {
+ pr_info("ULOG is deprecated and it will be removed soon, "
+ "use NFLOG instead\n");
+ par->net->xt.ulog_warn_deprecated = true;
+ }
+
if (loginfo->prefix[sizeof(loginfo->prefix) - 1] != '\0') {
pr_debug("prefix not null-terminated\n");
return -EINVAL;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 567d84168bd2..0a2e0e3e95ba 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -223,7 +223,7 @@ static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = {
static int log_invalid_proto_min = 0;
static int log_invalid_proto_max = 255;
-static ctl_table ip_ct_sysctl_table[] = {
+static struct ctl_table ip_ct_sysctl_table[] = {
{
.procname = "ip_conntrack_max",
.maxlen = sizeof(int),
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 7d93d62cd5fd..746427c9e719 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -33,7 +33,6 @@
#include <linux/netdevice.h>
#include <net/snmp.h>
#include <net/ip.h>
-#include <net/ipv6.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
@@ -46,8 +45,18 @@
#include <net/inet_common.h>
#include <net/checksum.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <linux/in6.h>
+#include <linux/icmpv6.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/transp_v6.h>
+#endif
-static struct ping_table ping_table;
+
+struct ping_table ping_table;
+struct pingv6_ops pingv6_ops;
+EXPORT_SYMBOL_GPL(pingv6_ops);
static u16 ping_port_rover;
@@ -58,6 +67,7 @@ static inline int ping_hashfn(struct net *net, unsigned int num, unsigned int ma
pr_debug("hash(%d) = %d\n", num, res);
return res;
}
+EXPORT_SYMBOL_GPL(ping_hash);
static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
struct net *net, unsigned int num)
@@ -65,7 +75,7 @@ static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)];
}
-static int ping_v4_get_port(struct sock *sk, unsigned short ident)
+int ping_get_port(struct sock *sk, unsigned short ident)
{
struct hlist_nulls_node *node;
struct hlist_nulls_head *hlist;
@@ -103,6 +113,10 @@ next_port:
ping_portaddr_for_each_entry(sk2, node, hlist) {
isk2 = inet_sk(sk2);
+ /* BUG? Why is this reuse and not reuseaddr? ping.c
+ * doesn't turn off SO_REUSEADDR, and it doesn't expect
+ * that other ping processes can steal its packets.
+ */
if ((isk2->inet_num == ident) &&
(sk2 != sk) &&
(!sk2->sk_reuse || !sk->sk_reuse))
@@ -125,17 +139,18 @@ fail:
write_unlock_bh(&ping_table.lock);
return 1;
}
+EXPORT_SYMBOL_GPL(ping_get_port);
-static void ping_v4_hash(struct sock *sk)
+void ping_hash(struct sock *sk)
{
- pr_debug("ping_v4_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
+ pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
BUG(); /* "Please do not press this button again." */
}
-static void ping_v4_unhash(struct sock *sk)
+void ping_unhash(struct sock *sk)
{
struct inet_sock *isk = inet_sk(sk);
- pr_debug("ping_v4_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+ pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
if (sk_hashed(sk)) {
write_lock_bh(&ping_table.lock);
hlist_nulls_del(&sk->sk_nulls_node);
@@ -146,31 +161,61 @@ static void ping_v4_unhash(struct sock *sk)
write_unlock_bh(&ping_table.lock);
}
}
+EXPORT_SYMBOL_GPL(ping_unhash);
-static struct sock *ping_v4_lookup(struct net *net, __be32 saddr, __be32 daddr,
- u16 ident, int dif)
+static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
{
struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident);
struct sock *sk = NULL;
struct inet_sock *isk;
struct hlist_nulls_node *hnode;
+ int dif = skb->dev->ifindex;
+
+ if (skb->protocol == htons(ETH_P_IP)) {
+ pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
+ (int)ident, &ip_hdr(skb)->daddr, dif);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n",
+ (int)ident, &ipv6_hdr(skb)->daddr, dif);
+#endif
+ }
- pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
- (int)ident, &daddr, dif);
read_lock_bh(&ping_table.lock);
ping_portaddr_for_each_entry(sk, hnode, hslot) {
isk = inet_sk(sk);
- pr_debug("found: %p: num = %d, daddr = %pI4, dif = %d\n", sk,
- (int)isk->inet_num, &isk->inet_rcv_saddr,
- sk->sk_bound_dev_if);
-
pr_debug("iterate\n");
if (isk->inet_num != ident)
continue;
- if (isk->inet_rcv_saddr && isk->inet_rcv_saddr != daddr)
- continue;
+
+ if (skb->protocol == htons(ETH_P_IP) &&
+ sk->sk_family == AF_INET) {
+ pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk,
+ (int) isk->inet_num, &isk->inet_rcv_saddr,
+ sk->sk_bound_dev_if);
+
+ if (isk->inet_rcv_saddr &&
+ isk->inet_rcv_saddr != ip_hdr(skb)->daddr)
+ continue;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (skb->protocol == htons(ETH_P_IPV6) &&
+ sk->sk_family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk,
+ (int) isk->inet_num,
+ &inet6_sk(sk)->rcv_saddr,
+ sk->sk_bound_dev_if);
+
+ if (!ipv6_addr_any(&np->rcv_saddr) &&
+ !ipv6_addr_equal(&np->rcv_saddr,
+ &ipv6_hdr(skb)->daddr))
+ continue;
+#endif
+ }
+
if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
continue;
@@ -200,7 +245,7 @@ static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
}
-static int ping_init_sock(struct sock *sk)
+int ping_init_sock(struct sock *sk)
{
struct net *net = sock_net(sk);
kgid_t group = current_egid();
@@ -225,8 +270,9 @@ static int ping_init_sock(struct sock *sk)
return -EACCES;
}
+EXPORT_SYMBOL_GPL(ping_init_sock);
-static void ping_close(struct sock *sk, long timeout)
+void ping_close(struct sock *sk, long timeout)
{
pr_debug("ping_close(sk=%p,sk->num=%u)\n",
inet_sk(sk), inet_sk(sk)->inet_num);
@@ -234,36 +280,122 @@ static void ping_close(struct sock *sk, long timeout)
sk_common_release(sk);
}
+EXPORT_SYMBOL_GPL(ping_close);
+
+/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */
+static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
+ struct sockaddr *uaddr, int addr_len) {
+ struct net *net = sock_net(sk);
+ if (sk->sk_family == AF_INET) {
+ struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
+ int chk_addr_ret;
+
+ if (addr_len < sizeof(*addr))
+ return -EINVAL;
+
+ pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
+ sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
+
+ chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);
+
+ if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
+ chk_addr_ret = RTN_LOCAL;
+
+ if ((sysctl_ip_nonlocal_bind == 0 &&
+ isk->freebind == 0 && isk->transparent == 0 &&
+ chk_addr_ret != RTN_LOCAL) ||
+ chk_addr_ret == RTN_MULTICAST ||
+ chk_addr_ret == RTN_BROADCAST)
+ return -EADDRNOTAVAIL;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (sk->sk_family == AF_INET6) {
+ struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr;
+ int addr_type, scoped, has_addr;
+ struct net_device *dev = NULL;
+
+ if (addr_len < sizeof(*addr))
+ return -EINVAL;
+
+ pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
+ sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));
+
+ addr_type = ipv6_addr_type(&addr->sin6_addr);
+ scoped = __ipv6_addr_needs_scope_id(addr_type);
+ if ((addr_type != IPV6_ADDR_ANY &&
+ !(addr_type & IPV6_ADDR_UNICAST)) ||
+ (scoped && !addr->sin6_scope_id))
+ return -EINVAL;
+
+ rcu_read_lock();
+ if (addr->sin6_scope_id) {
+ dev = dev_get_by_index_rcu(net, addr->sin6_scope_id);
+ if (!dev) {
+ rcu_read_unlock();
+ return -ENODEV;
+ }
+ }
+ has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev,
+ scoped);
+ rcu_read_unlock();
+
+ if (!(isk->freebind || isk->transparent || has_addr ||
+ addr_type == IPV6_ADDR_ANY))
+ return -EADDRNOTAVAIL;
+
+ if (scoped)
+ sk->sk_bound_dev_if = addr->sin6_scope_id;
+#endif
+ } else {
+ return -EAFNOSUPPORT;
+ }
+ return 0;
+}
+
+static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
+{
+ if (saddr->sa_family == AF_INET) {
+ struct inet_sock *isk = inet_sk(sk);
+ struct sockaddr_in *addr = (struct sockaddr_in *) saddr;
+ isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (saddr->sa_family == AF_INET6) {
+ struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr;
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ np->rcv_saddr = np->saddr = addr->sin6_addr;
+#endif
+ }
+}
+static void ping_clear_saddr(struct sock *sk, int dif)
+{
+ sk->sk_bound_dev_if = dif;
+ if (sk->sk_family == AF_INET) {
+ struct inet_sock *isk = inet_sk(sk);
+ isk->inet_rcv_saddr = isk->inet_saddr = 0;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (sk->sk_family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr));
+ memset(&np->saddr, 0, sizeof(np->saddr));
+#endif
+ }
+}
/*
* We need our own bind because there are no privileged id's == local ports.
* Moreover, we don't allow binding to multi- and broadcast addresses.
*/
-static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
- struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
struct inet_sock *isk = inet_sk(sk);
unsigned short snum;
- int chk_addr_ret;
int err;
+ int dif = sk->sk_bound_dev_if;
- if (addr_len < sizeof(struct sockaddr_in))
- return -EINVAL;
-
- pr_debug("ping_v4_bind(sk=%p,sa_addr=%08x,sa_port=%d)\n",
- sk, addr->sin_addr.s_addr, ntohs(addr->sin_port));
-
- chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
- if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
- chk_addr_ret = RTN_LOCAL;
-
- if ((sysctl_ip_nonlocal_bind == 0 &&
- isk->freebind == 0 && isk->transparent == 0 &&
- chk_addr_ret != RTN_LOCAL) ||
- chk_addr_ret == RTN_MULTICAST ||
- chk_addr_ret == RTN_BROADCAST)
- return -EADDRNOTAVAIL;
+ err = ping_check_bind_addr(sk, isk, uaddr, addr_len);
+ if (err)
+ return err;
lock_sock(sk);
@@ -272,42 +404,50 @@ static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
goto out;
err = -EADDRINUSE;
- isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
- snum = ntohs(addr->sin_port);
- if (ping_v4_get_port(sk, snum) != 0) {
- isk->inet_saddr = isk->inet_rcv_saddr = 0;
+ ping_set_saddr(sk, uaddr);
+ snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port);
+ if (ping_get_port(sk, snum) != 0) {
+ ping_clear_saddr(sk, dif);
goto out;
}
- pr_debug("after bind(): num = %d, daddr = %pI4, dif = %d\n",
+ pr_debug("after bind(): num = %d, dif = %d\n",
(int)isk->inet_num,
- &isk->inet_rcv_saddr,
(int)sk->sk_bound_dev_if);
err = 0;
- if (isk->inet_rcv_saddr)
+ if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) ||
+ (sk->sk_family == AF_INET6 &&
+ !ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)))
sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
+
if (snum)
sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
isk->inet_sport = htons(isk->inet_num);
isk->inet_daddr = 0;
isk->inet_dport = 0;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6)
+ memset(&inet6_sk(sk)->daddr, 0, sizeof(inet6_sk(sk)->daddr));
+#endif
+
sk_dst_reset(sk);
out:
release_sock(sk);
pr_debug("ping_v4_bind -> %d\n", err);
return err;
}
+EXPORT_SYMBOL_GPL(ping_bind);
/*
* Is this a supported type of ICMP message?
*/
-static inline int ping_supported(int type, int code)
+static inline int ping_supported(int family, int type, int code)
{
- if (type == ICMP_ECHO && code == 0)
- return 1;
- return 0;
+ return (family == AF_INET && type == ICMP_ECHO && code == 0) ||
+ (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0);
}
/*
@@ -315,30 +455,42 @@ static inline int ping_supported(int type, int code)
* sort of error condition.
*/
-static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
-
-void ping_err(struct sk_buff *skb, u32 info)
+void ping_err(struct sk_buff *skb, int offset, u32 info)
{
- struct iphdr *iph = (struct iphdr *)skb->data;
- struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
+ int family;
+ struct icmphdr *icmph;
struct inet_sock *inet_sock;
- int type = icmp_hdr(skb)->type;
- int code = icmp_hdr(skb)->code;
+ int type;
+ int code;
struct net *net = dev_net(skb->dev);
struct sock *sk;
int harderr;
int err;
+ if (skb->protocol == htons(ETH_P_IP)) {
+ family = AF_INET;
+ type = icmp_hdr(skb)->type;
+ code = icmp_hdr(skb)->code;
+ icmph = (struct icmphdr *)(skb->data + offset);
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ family = AF_INET6;
+ type = icmp6_hdr(skb)->icmp6_type;
+ code = icmp6_hdr(skb)->icmp6_code;
+ icmph = (struct icmphdr *) (skb->data + offset);
+ } else {
+ BUG();
+ }
+
/* We assume the packet has already been checked by icmp_unreach */
- if (!ping_supported(icmph->type, icmph->code))
+ if (!ping_supported(family, icmph->type, icmph->code))
return;
- pr_debug("ping_err(type=%04x,code=%04x,id=%04x,seq=%04x)\n", type,
- code, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence));
+ pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n",
+ skb->protocol, type, code, ntohs(icmph->un.echo.id),
+ ntohs(icmph->un.echo.sequence));
- sk = ping_v4_lookup(net, iph->daddr, iph->saddr,
- ntohs(icmph->un.echo.id), skb->dev->ifindex);
+ sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
if (sk == NULL) {
pr_debug("no socket, dropping\n");
return; /* No socket for error */
@@ -349,72 +501,83 @@ void ping_err(struct sk_buff *skb, u32 info)
harderr = 0;
inet_sock = inet_sk(sk);
- switch (type) {
- default:
- case ICMP_TIME_EXCEEDED:
- err = EHOSTUNREACH;
- break;
- case ICMP_SOURCE_QUENCH:
- /* This is not a real error but ping wants to see it.
- * Report it with some fake errno. */
- err = EREMOTEIO;
- break;
- case ICMP_PARAMETERPROB:
- err = EPROTO;
- harderr = 1;
- break;
- case ICMP_DEST_UNREACH:
- if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
- ipv4_sk_update_pmtu(skb, sk, info);
- if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
- err = EMSGSIZE;
- harderr = 1;
- break;
+ if (skb->protocol == htons(ETH_P_IP)) {
+ switch (type) {
+ default:
+ case ICMP_TIME_EXCEEDED:
+ err = EHOSTUNREACH;
+ break;
+ case ICMP_SOURCE_QUENCH:
+ /* This is not a real error but ping wants to see it.
+ * Report it with some fake errno.
+ */
+ err = EREMOTEIO;
+ break;
+ case ICMP_PARAMETERPROB:
+ err = EPROTO;
+ harderr = 1;
+ break;
+ case ICMP_DEST_UNREACH:
+ if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
+ ipv4_sk_update_pmtu(skb, sk, info);
+ if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
+ err = EMSGSIZE;
+ harderr = 1;
+ break;
+ }
+ goto out;
}
- goto out;
- }
- err = EHOSTUNREACH;
- if (code <= NR_ICMP_UNREACH) {
- harderr = icmp_err_convert[code].fatal;
- err = icmp_err_convert[code].errno;
+ err = EHOSTUNREACH;
+ if (code <= NR_ICMP_UNREACH) {
+ harderr = icmp_err_convert[code].fatal;
+ err = icmp_err_convert[code].errno;
+ }
+ break;
+ case ICMP_REDIRECT:
+ /* See ICMP_SOURCE_QUENCH */
+ ipv4_sk_redirect(skb, sk);
+ err = EREMOTEIO;
+ break;
}
- break;
- case ICMP_REDIRECT:
- /* See ICMP_SOURCE_QUENCH */
- ipv4_sk_redirect(skb, sk);
- err = EREMOTEIO;
- break;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ harderr = pingv6_ops.icmpv6_err_convert(type, code, &err);
+#endif
}
/*
* RFC1122: OK. Passes ICMP errors back to application, as per
* 4.1.3.3.
*/
- if (!inet_sock->recverr) {
+ if ((family == AF_INET && !inet_sock->recverr) ||
+ (family == AF_INET6 && !inet6_sk(sk)->recverr)) {
if (!harderr || sk->sk_state != TCP_ESTABLISHED)
goto out;
} else {
- ip_icmp_error(sk, skb, err, 0 /* no remote port */,
- info, (u8 *)icmph);
+ if (family == AF_INET) {
+ ip_icmp_error(sk, skb, err, 0 /* no remote port */,
+ info, (u8 *)icmph);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ pingv6_ops.ipv6_icmp_error(sk, skb, err, 0,
+ info, (u8 *)icmph);
+#endif
+ }
}
sk->sk_err = err;
sk->sk_error_report(sk);
out:
sock_put(sk);
}
+EXPORT_SYMBOL_GPL(ping_err);
/*
- * Copy and checksum an ICMP Echo packet from user space into a buffer.
+ * Copy and checksum an ICMP Echo packet from user space into a buffer
+ * starting from the payload.
*/
-struct pingfakehdr {
- struct icmphdr icmph;
- struct iovec *iov;
- __wsum wcheck;
-};
-
-static int ping_getfrag(void *from, char *to,
- int offset, int fraglen, int odd, struct sk_buff *skb)
+int ping_getfrag(void *from, char *to,
+ int offset, int fraglen, int odd, struct sk_buff *skb)
{
struct pingfakehdr *pfh = (struct pingfakehdr *)from;
@@ -425,20 +588,33 @@ static int ping_getfrag(void *from, char *to,
pfh->iov, 0, fraglen - sizeof(struct icmphdr),
&pfh->wcheck))
return -EFAULT;
+ } else if (offset < sizeof(struct icmphdr)) {
+ BUG();
+ } else {
+ if (csum_partial_copy_fromiovecend
+ (to, pfh->iov, offset - sizeof(struct icmphdr),
+ fraglen, &pfh->wcheck))
+ return -EFAULT;
+ }
- return 0;
+#if IS_ENABLED(CONFIG_IPV6)
+ /* For IPv6, checksum each skb as we go along, as expected by
+ * icmpv6_push_pending_frames. For IPv4, accumulate the checksum in
+ * wcheck, it will be finalized in ping_v4_push_pending_frames.
+ */
+ if (pfh->family == AF_INET6) {
+ skb->csum = pfh->wcheck;
+ skb->ip_summed = CHECKSUM_NONE;
+ pfh->wcheck = 0;
}
- if (offset < sizeof(struct icmphdr))
- BUG();
- if (csum_partial_copy_fromiovecend
- (to, pfh->iov, offset - sizeof(struct icmphdr),
- fraglen, &pfh->wcheck))
- return -EFAULT;
+#endif
+
return 0;
}
+EXPORT_SYMBOL_GPL(ping_getfrag);
-static int ping_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
- struct flowi4 *fl4)
+static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
+ struct flowi4 *fl4)
{
struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
@@ -450,24 +626,9 @@ static int ping_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
return ip_push_pending_frames(sk, fl4);
}
-static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- size_t len)
-{
- struct net *net = sock_net(sk);
- struct flowi4 fl4;
- struct inet_sock *inet = inet_sk(sk);
- struct ipcm_cookie ipc;
- struct icmphdr user_icmph;
- struct pingfakehdr pfh;
- struct rtable *rt = NULL;
- struct ip_options_data opt_copy;
- int free = 0;
- __be32 saddr, daddr, faddr;
- u8 tos;
- int err;
-
- pr_debug("ping_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
-
+int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+ void *user_icmph, size_t icmph_len) {
+ u8 type, code;
if (len > 0xFFFF)
return -EMSGSIZE;
@@ -482,15 +643,53 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
/*
* Fetch the ICMP header provided by the userland.
- * iovec is modified!
+ * iovec is modified! The ICMP header is consumed.
*/
-
- if (memcpy_fromiovec((u8 *)&user_icmph, msg->msg_iov,
- sizeof(struct icmphdr)))
+ if (memcpy_fromiovec(user_icmph, msg->msg_iov, icmph_len))
return -EFAULT;
- if (!ping_supported(user_icmph.type, user_icmph.code))
+
+ if (family == AF_INET) {
+ type = ((struct icmphdr *) user_icmph)->type;
+ code = ((struct icmphdr *) user_icmph)->code;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ type = ((struct icmp6hdr *) user_icmph)->icmp6_type;
+ code = ((struct icmp6hdr *) user_icmph)->icmp6_code;
+#endif
+ } else {
+ BUG();
+ }
+
+ if (!ping_supported(family, type, code))
return -EINVAL;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ping_common_sendmsg);
+
+int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len)
+{
+ struct net *net = sock_net(sk);
+ struct flowi4 fl4;
+ struct inet_sock *inet = inet_sk(sk);
+ struct ipcm_cookie ipc;
+ struct icmphdr user_icmph;
+ struct pingfakehdr pfh;
+ struct rtable *rt = NULL;
+ struct ip_options_data opt_copy;
+ int free = 0;
+ __be32 saddr, daddr, faddr;
+ u8 tos;
+ int err;
+
+ pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
+
+ err = ping_common_sendmsg(AF_INET, msg, len, &user_icmph,
+ sizeof(user_icmph));
+ if (err)
+ return err;
+
/*
* Get and verify the address.
*/
@@ -595,13 +794,14 @@ back_from_confirm:
pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence;
pfh.iov = msg->msg_iov;
pfh.wcheck = 0;
+ pfh.family = AF_INET;
err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len,
0, &ipc, &rt, msg->msg_flags);
if (err)
ip_flush_pending_frames(sk);
else
- err = ping_push_pending_frames(sk, &pfh, &fl4);
+ err = ping_v4_push_pending_frames(sk, &pfh, &fl4);
release_sock(sk);
out:
@@ -622,11 +822,13 @@ do_confirm:
goto out;
}
-static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- size_t len, int noblock, int flags, int *addr_len)
+int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len, int noblock, int flags, int *addr_len)
{
struct inet_sock *isk = inet_sk(sk);
- struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+ int family = sk->sk_family;
+ struct sockaddr_in *sin;
+ struct sockaddr_in6 *sin6;
struct sk_buff *skb;
int copied, err;
@@ -636,11 +838,22 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (flags & MSG_OOB)
goto out;
- if (addr_len)
- *addr_len = sizeof(*sin);
+ if (addr_len) {
+ if (family == AF_INET)
+ *addr_len = sizeof(*sin);
+ else if (family == AF_INET6 && addr_len)
+ *addr_len = sizeof(*sin6);
+ }
- if (flags & MSG_ERRQUEUE)
- return ip_recv_error(sk, msg, len);
+ if (flags & MSG_ERRQUEUE) {
+ if (family == AF_INET) {
+ return ip_recv_error(sk, msg, len);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ return pingv6_ops.ipv6_recv_error(sk, msg, len);
+#endif
+ }
+ }
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
@@ -659,15 +872,40 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
sock_recv_timestamp(msg, sk, skb);
- /* Copy the address. */
- if (sin) {
+ /* Copy the address and add cmsg data. */
+ if (family == AF_INET) {
+ sin = (struct sockaddr_in *) msg->msg_name;
sin->sin_family = AF_INET;
sin->sin_port = 0 /* skb->h.uh->source */;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+
+ if (isk->cmsg_flags)
+ ip_cmsg_recv(msg, skb);
+
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6hdr *ip6 = ipv6_hdr(skb);
+ sin6 = (struct sockaddr_in6 *) msg->msg_name;
+ sin6->sin6_family = AF_INET6;
+ sin6->sin6_port = 0;
+ sin6->sin6_addr = ip6->saddr;
+
+ sin6->sin6_flowinfo = 0;
+ if (np->sndflow)
+ sin6->sin6_flowinfo = ip6_flowinfo(ip6);
+
+ sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
+ IP6CB(skb)->iif);
+
+ if (inet6_sk(sk)->rxopt.all)
+ pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb);
+#endif
+ } else {
+ BUG();
}
- if (isk->cmsg_flags)
- ip_cmsg_recv(msg, skb);
+
err = copied;
done:
@@ -676,8 +914,9 @@ out:
pr_debug("ping_recvmsg -> %d\n", err);
return err;
}
+EXPORT_SYMBOL_GPL(ping_recvmsg);
-static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n",
inet_sk(sk), inet_sk(sk)->inet_num, skb);
@@ -688,6 +927,7 @@ static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
}
return 0;
}
+EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
/*
@@ -698,10 +938,7 @@ void ping_rcv(struct sk_buff *skb)
{
struct sock *sk;
struct net *net = dev_net(skb->dev);
- struct iphdr *iph = ip_hdr(skb);
struct icmphdr *icmph = icmp_hdr(skb);
- __be32 saddr = iph->saddr;
- __be32 daddr = iph->daddr;
/* We assume the packet has already been checked by icmp_rcv */
@@ -711,8 +948,7 @@ void ping_rcv(struct sk_buff *skb)
/* Push ICMP header back */
skb_push(skb, skb->data - (u8 *)icmph);
- sk = ping_v4_lookup(net, saddr, daddr, ntohs(icmph->un.echo.id),
- skb->dev->ifindex);
+ sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
if (sk != NULL) {
pr_debug("rcv on socket %p\n", sk);
ping_queue_rcv_skb(sk, skb_get(skb));
@@ -723,6 +959,7 @@ void ping_rcv(struct sk_buff *skb)
/* We're called from icmp_rcv(). kfree_skb() is done there. */
}
+EXPORT_SYMBOL_GPL(ping_rcv);
struct proto ping_prot = {
.name = "PING",
@@ -733,14 +970,14 @@ struct proto ping_prot = {
.disconnect = udp_disconnect,
.setsockopt = ip_setsockopt,
.getsockopt = ip_getsockopt,
- .sendmsg = ping_sendmsg,
+ .sendmsg = ping_v4_sendmsg,
.recvmsg = ping_recvmsg,
.bind = ping_bind,
.backlog_rcv = ping_queue_rcv_skb,
.release_cb = ip4_datagram_release_cb,
- .hash = ping_v4_hash,
- .unhash = ping_v4_unhash,
- .get_port = ping_v4_get_port,
+ .hash = ping_hash,
+ .unhash = ping_unhash,
+ .get_port = ping_get_port,
.obj_size = sizeof(struct inet_sock),
};
EXPORT_SYMBOL(ping_prot);
@@ -764,7 +1001,8 @@ static struct sock *ping_get_first(struct seq_file *seq, int start)
continue;
sk_nulls_for_each(sk, node, hslot) {
- if (net_eq(sock_net(sk), net))
+ if (net_eq(sock_net(sk), net) &&
+ sk->sk_family == state->family)
goto found;
}
}
@@ -797,17 +1035,24 @@ static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos)
return pos ? NULL : sk;
}
-static void *ping_seq_start(struct seq_file *seq, loff_t *pos)
+void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family)
{
struct ping_iter_state *state = seq->private;
state->bucket = 0;
+ state->family = family;
read_lock_bh(&ping_table.lock);
return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
}
+EXPORT_SYMBOL_GPL(ping_seq_start);
+
+static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ return ping_seq_start(seq, pos, AF_INET);
+}
-static void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct sock *sk;
@@ -819,13 +1064,15 @@ static void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
++*pos;
return sk;
}
+EXPORT_SYMBOL_GPL(ping_seq_next);
-static void ping_seq_stop(struct seq_file *seq, void *v)
+void ping_seq_stop(struct seq_file *seq, void *v)
{
read_unlock_bh(&ping_table.lock);
}
+EXPORT_SYMBOL_GPL(ping_seq_stop);
-static void ping_format_sock(struct sock *sp, struct seq_file *f,
+static void ping_v4_format_sock(struct sock *sp, struct seq_file *f,
int bucket, int *len)
{
struct inet_sock *inet = inet_sk(sp);
@@ -846,7 +1093,7 @@ static void ping_format_sock(struct sock *sp, struct seq_file *f,
atomic_read(&sp->sk_drops), len);
}
-static int ping_seq_show(struct seq_file *seq, void *v)
+static int ping_v4_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN)
seq_printf(seq, "%-127s\n",
@@ -857,72 +1104,86 @@ static int ping_seq_show(struct seq_file *seq, void *v)
struct ping_iter_state *state = seq->private;
int len;
- ping_format_sock(v, seq, state->bucket, &len);
+ ping_v4_format_sock(v, seq, state->bucket, &len);
seq_printf(seq, "%*s\n", 127 - len, "");
}
return 0;
}
-static const struct seq_operations ping_seq_ops = {
- .show = ping_seq_show,
- .start = ping_seq_start,
+static const struct seq_operations ping_v4_seq_ops = {
+ .show = ping_v4_seq_show,
+ .start = ping_v4_seq_start,
.next = ping_seq_next,
.stop = ping_seq_stop,
};
static int ping_seq_open(struct inode *inode, struct file *file)
{
- return seq_open_net(inode, file, &ping_seq_ops,
+ struct ping_seq_afinfo *afinfo = PDE_DATA(inode);
+ return seq_open_net(inode, file, &afinfo->seq_ops,
sizeof(struct ping_iter_state));
}
-static const struct file_operations ping_seq_fops = {
+const struct file_operations ping_seq_fops = {
.open = ping_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_net,
};
+EXPORT_SYMBOL_GPL(ping_seq_fops);
+
+static struct ping_seq_afinfo ping_v4_seq_afinfo = {
+ .name = "icmp",
+ .family = AF_INET,
+ .seq_fops = &ping_seq_fops,
+ .seq_ops = {
+ .start = ping_v4_seq_start,
+ .show = ping_v4_seq_show,
+ .next = ping_seq_next,
+ .stop = ping_seq_stop,
+ },
+};
-static int ping_proc_register(struct net *net)
+int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo)
{
struct proc_dir_entry *p;
- int rc = 0;
-
- p = proc_create("icmp", S_IRUGO, net->proc_net, &ping_seq_fops);
+ p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
+ afinfo->seq_fops, afinfo);
if (!p)
- rc = -ENOMEM;
- return rc;
+ return -ENOMEM;
+ return 0;
}
+EXPORT_SYMBOL_GPL(ping_proc_register);
-static void ping_proc_unregister(struct net *net)
+void ping_proc_unregister(struct net *net, struct ping_seq_afinfo *afinfo)
{
- remove_proc_entry("icmp", net->proc_net);
+ remove_proc_entry(afinfo->name, net->proc_net);
}
+EXPORT_SYMBOL_GPL(ping_proc_unregister);
-
-static int __net_init ping_proc_init_net(struct net *net)
+static int __net_init ping_v4_proc_init_net(struct net *net)
{
- return ping_proc_register(net);
+ return ping_proc_register(net, &ping_v4_seq_afinfo);
}
-static void __net_exit ping_proc_exit_net(struct net *net)
+static void __net_exit ping_v4_proc_exit_net(struct net *net)
{
- ping_proc_unregister(net);
+ ping_proc_unregister(net, &ping_v4_seq_afinfo);
}
-static struct pernet_operations ping_net_ops = {
- .init = ping_proc_init_net,
- .exit = ping_proc_exit_net,
+static struct pernet_operations ping_v4_net_ops = {
+ .init = ping_v4_proc_init_net,
+ .exit = ping_v4_proc_exit_net,
};
int __init ping_proc_init(void)
{
- return register_pernet_subsys(&ping_net_ops);
+ return register_pernet_subsys(&ping_v4_net_ops);
}
void ping_proc_exit(void)
{
- unregister_pernet_subsys(&ping_net_ops);
+ unregister_pernet_subsys(&ping_v4_net_ops);
}
#endif
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 2a5bf86d2415..6577a1149a47 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -273,6 +273,7 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
+ SNMP_MIB_ITEM("LowLatencyRxPackets", LINUX_MIB_LOWLATENCYRXPACKETS),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d35bbf0cf404..a9a54a236832 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -565,10 +565,25 @@ static inline void rt_free(struct rtable *rt)
static DEFINE_SPINLOCK(fnhe_lock);
+static void fnhe_flush_routes(struct fib_nh_exception *fnhe)
+{
+ struct rtable *rt;
+
+ rt = rcu_dereference(fnhe->fnhe_rth_input);
+ if (rt) {
+ RCU_INIT_POINTER(fnhe->fnhe_rth_input, NULL);
+ rt_free(rt);
+ }
+ rt = rcu_dereference(fnhe->fnhe_rth_output);
+ if (rt) {
+ RCU_INIT_POINTER(fnhe->fnhe_rth_output, NULL);
+ rt_free(rt);
+ }
+}
+
static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
{
struct fib_nh_exception *fnhe, *oldest;
- struct rtable *orig;
oldest = rcu_dereference(hash->chain);
for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe;
@@ -576,11 +591,7 @@ static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp))
oldest = fnhe;
}
- orig = rcu_dereference(oldest->fnhe_rth);
- if (orig) {
- RCU_INIT_POINTER(oldest->fnhe_rth, NULL);
- rt_free(orig);
- }
+ fnhe_flush_routes(oldest);
return oldest;
}
@@ -594,11 +605,25 @@ static inline u32 fnhe_hashfun(__be32 daddr)
return hval & (FNHE_HASH_SIZE - 1);
}
+static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe)
+{
+ rt->rt_pmtu = fnhe->fnhe_pmtu;
+ rt->dst.expires = fnhe->fnhe_expires;
+
+ if (fnhe->fnhe_gw) {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ rt->rt_gateway = fnhe->fnhe_gw;
+ rt->rt_uses_gateway = 1;
+ }
+}
+
static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
u32 pmtu, unsigned long expires)
{
struct fnhe_hash_bucket *hash;
struct fib_nh_exception *fnhe;
+ struct rtable *rt;
+ unsigned int i;
int depth;
u32 hval = fnhe_hashfun(daddr);
@@ -627,8 +652,15 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
fnhe->fnhe_gw = gw;
if (pmtu) {
fnhe->fnhe_pmtu = pmtu;
- fnhe->fnhe_expires = expires;
+ fnhe->fnhe_expires = max(1UL, expires);
}
+ /* Update all cached dsts too */
+ rt = rcu_dereference(fnhe->fnhe_rth_input);
+ if (rt)
+ fill_route_from_fnhe(rt, fnhe);
+ rt = rcu_dereference(fnhe->fnhe_rth_output);
+ if (rt)
+ fill_route_from_fnhe(rt, fnhe);
} else {
if (depth > FNHE_RECLAIM_DEPTH)
fnhe = fnhe_oldest(hash);
@@ -640,10 +672,27 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
fnhe->fnhe_next = hash->chain;
rcu_assign_pointer(hash->chain, fnhe);
}
+ fnhe->fnhe_genid = fnhe_genid(dev_net(nh->nh_dev));
fnhe->fnhe_daddr = daddr;
fnhe->fnhe_gw = gw;
fnhe->fnhe_pmtu = pmtu;
fnhe->fnhe_expires = expires;
+
+ /* Exception created; mark the cached routes for the nexthop
+ * stale, so anyone caching it rechecks if this exception
+ * applies to them.
+ */
+ rt = rcu_dereference(nh->nh_rth_input);
+ if (rt)
+ rt->dst.obsolete = DST_OBSOLETE_KILL;
+
+ for_each_possible_cpu(i) {
+ struct rtable __rcu **prt;
+ prt = per_cpu_ptr(nh->nh_pcpu_rth_output, i);
+ rt = rcu_dereference(*prt);
+ if (rt)
+ rt->dst.obsolete = DST_OBSOLETE_KILL;
+ }
}
fnhe->fnhe_stamp = jiffies;
@@ -922,12 +971,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
- if (!rt->rt_pmtu) {
- dst->obsolete = DST_OBSOLETE_KILL;
- } else {
- rt->rt_pmtu = mtu;
- dst->expires = max(1UL, jiffies + ip_rt_mtu_expires);
- }
+ if (rt->rt_pmtu == mtu &&
+ time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2))
+ return;
rcu_read_lock();
if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) {
@@ -1068,11 +1114,11 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
* into this function always.
*
- * When a PMTU/redirect information update invalidates a
- * route, this is indicated by setting obsolete to
- * DST_OBSOLETE_KILL.
+ * When a PMTU/redirect information update invalidates a route,
+ * this is indicated by setting obsolete to DST_OBSOLETE_KILL or
+ * DST_OBSOLETE_DEAD by dst_free().
*/
- if (dst->obsolete == DST_OBSOLETE_KILL || rt_is_expired(rt))
+ if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt))
return NULL;
return dst;
}
@@ -1214,34 +1260,36 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
spin_lock_bh(&fnhe_lock);
if (daddr == fnhe->fnhe_daddr) {
- struct rtable *orig = rcu_dereference(fnhe->fnhe_rth);
- if (orig && rt_is_expired(orig)) {
+ struct rtable __rcu **porig;
+ struct rtable *orig;
+ int genid = fnhe_genid(dev_net(rt->dst.dev));
+
+ if (rt_is_input_route(rt))
+ porig = &fnhe->fnhe_rth_input;
+ else
+ porig = &fnhe->fnhe_rth_output;
+ orig = rcu_dereference(*porig);
+
+ if (fnhe->fnhe_genid != genid) {
+ fnhe->fnhe_genid = genid;
fnhe->fnhe_gw = 0;
fnhe->fnhe_pmtu = 0;
fnhe->fnhe_expires = 0;
+ fnhe_flush_routes(fnhe);
+ orig = NULL;
}
- if (fnhe->fnhe_pmtu) {
- unsigned long expires = fnhe->fnhe_expires;
- unsigned long diff = expires - jiffies;
-
- if (time_before(jiffies, expires)) {
- rt->rt_pmtu = fnhe->fnhe_pmtu;
- dst_set_expires(&rt->dst, diff);
- }
- }
- if (fnhe->fnhe_gw) {
- rt->rt_flags |= RTCF_REDIRECTED;
- rt->rt_gateway = fnhe->fnhe_gw;
- rt->rt_uses_gateway = 1;
- } else if (!rt->rt_gateway)
+ fill_route_from_fnhe(rt, fnhe);
+ if (!rt->rt_gateway)
rt->rt_gateway = daddr;
- rcu_assign_pointer(fnhe->fnhe_rth, rt);
- if (orig)
- rt_free(orig);
+ if (!(rt->dst.flags & DST_NOCACHE)) {
+ rcu_assign_pointer(*porig, rt);
+ if (orig)
+ rt_free(orig);
+ ret = true;
+ }
fnhe->fnhe_stamp = jiffies;
- ret = true;
}
spin_unlock_bh(&fnhe_lock);
@@ -1473,6 +1521,7 @@ static int __mkroute_input(struct sk_buff *skb,
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos)
{
+ struct fib_nh_exception *fnhe;
struct rtable *rth;
int err;
struct in_device *out_dev;
@@ -1519,8 +1568,13 @@ static int __mkroute_input(struct sk_buff *skb,
}
}
+ fnhe = find_exception(&FIB_RES_NH(*res), daddr);
if (do_cache) {
- rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+ if (fnhe != NULL)
+ rth = rcu_dereference(fnhe->fnhe_rth_input);
+ else
+ rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
goto out;
@@ -1548,7 +1602,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
- rt_set_nexthop(rth, daddr, res, NULL, res->fi, res->type, itag);
+ rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag);
skb_dst_set(skb, &rth->dst);
out:
err = 0;
@@ -1863,7 +1917,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
fnhe = find_exception(nh, fl4->daddr);
if (fnhe)
- prth = &fnhe->fnhe_rth;
+ prth = &fnhe->fnhe_rth_output;
else {
if (unlikely(fl4->flowi4_flags &
FLOWI_FLAG_KNOWN_NH &&
@@ -2429,19 +2483,22 @@ static int ip_rt_gc_interval __read_mostly = 60 * HZ;
static int ip_rt_gc_min_interval __read_mostly = HZ / 2;
static int ip_rt_gc_elasticity __read_mostly = 8;
-static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
+static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
+ struct net *net = (struct net *)__ctl->extra1;
+
if (write) {
- rt_cache_flush((struct net *)__ctl->extra1);
+ rt_cache_flush(net);
+ fnhe_genid_bump(net);
return 0;
}
return -EINVAL;
}
-static ctl_table ipv4_route_table[] = {
+static struct ctl_table ipv4_route_table[] = {
{
.procname = "gc_thresh",
.data = &ipv4_dst_ops.gc_thresh,
@@ -2609,6 +2666,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = {
static __net_init int rt_genid_init(struct net *net)
{
atomic_set(&net->rt_genid, 0);
+ atomic_set(&net->fnhe_genid, 0);
get_random_bytes(&net->ipv4.dev_addr_genid,
sizeof(net->ipv4.dev_addr_genid));
return 0;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index fa2f63fc453b..b2c123c44d69 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -49,13 +49,13 @@ static void set_local_port_range(int range[2])
}
/* Validate changes from /proc interface. */
-static int ipv4_local_port_range(ctl_table *table, int write,
+static int ipv4_local_port_range(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
int ret;
int range[2];
- ctl_table tmp = {
+ struct ctl_table tmp = {
.data = &range,
.maxlen = sizeof(range),
.mode = table->mode,
@@ -100,7 +100,7 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
}
/* Validate changes from /proc interface. */
-static int ipv4_ping_group_range(ctl_table *table, int write,
+static int ipv4_ping_group_range(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
@@ -108,7 +108,7 @@ static int ipv4_ping_group_range(ctl_table *table, int write,
int ret;
gid_t urange[2];
kgid_t low, high;
- ctl_table tmp = {
+ struct ctl_table tmp = {
.data = &urange,
.maxlen = sizeof(urange),
.mode = table->mode,
@@ -135,11 +135,11 @@ static int ipv4_ping_group_range(ctl_table *table, int write,
return ret;
}
-static int proc_tcp_congestion_control(ctl_table *ctl, int write,
+static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
char val[TCP_CA_NAME_MAX];
- ctl_table tbl = {
+ struct ctl_table tbl = {
.data = val,
.maxlen = TCP_CA_NAME_MAX,
};
@@ -153,12 +153,12 @@ static int proc_tcp_congestion_control(ctl_table *ctl, int write,
return ret;
}
-static int proc_tcp_available_congestion_control(ctl_table *ctl,
+static int proc_tcp_available_congestion_control(struct ctl_table *ctl,
int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, };
+ struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, };
int ret;
tbl.data = kmalloc(tbl.maxlen, GFP_USER);
@@ -170,12 +170,12 @@ static int proc_tcp_available_congestion_control(ctl_table *ctl,
return ret;
}
-static int proc_allowed_congestion_control(ctl_table *ctl,
+static int proc_allowed_congestion_control(struct ctl_table *ctl,
int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX };
+ struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX };
int ret;
tbl.data = kmalloc(tbl.maxlen, GFP_USER);
@@ -190,7 +190,7 @@ static int proc_allowed_congestion_control(ctl_table *ctl,
return ret;
}
-static int ipv4_tcp_mem(ctl_table *ctl, int write,
+static int ipv4_tcp_mem(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
@@ -201,7 +201,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write,
struct mem_cgroup *memcg;
#endif
- ctl_table tmp = {
+ struct ctl_table tmp = {
.data = &vec,
.maxlen = sizeof(vec),
.mode = ctl->mode,
@@ -233,10 +233,11 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write,
return 0;
}
-static int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer,
- size_t *lenp, loff_t *ppos)
+static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
{
- ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
+ struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
struct tcp_fastopen_context *ctxt;
int ret;
u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ab450c099aa4..15cbfa94bd8e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -279,6 +279,7 @@
#include <asm/uaccess.h>
#include <asm/ioctls.h>
+#include <net/ll_poll.h>
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
@@ -436,6 +437,8 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
struct sock *sk = sock->sk;
const struct tcp_sock *tp = tcp_sk(sk);
+ sock_rps_record_flow(sk);
+
sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
@@ -1551,6 +1554,10 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
struct sk_buff *skb;
u32 urg_hole = 0;
+ if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
+ (sk->sk_state == TCP_ESTABLISHED))
+ sk_busy_loop(sk, nonblock);
+
lock_sock(sk);
err = -ENOTCONN;
@@ -2875,249 +2882,9 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
EXPORT_SYMBOL(compat_tcp_getsockopt);
#endif
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
- netdev_features_t features)
-{
- struct sk_buff *segs = ERR_PTR(-EINVAL);
- struct tcphdr *th;
- unsigned int thlen;
- unsigned int seq;
- __be32 delta;
- unsigned int oldlen;
- unsigned int mss;
- struct sk_buff *gso_skb = skb;
- __sum16 newcheck;
- bool ooo_okay, copy_destructor;
-
- if (!pskb_may_pull(skb, sizeof(*th)))
- goto out;
-
- th = tcp_hdr(skb);
- thlen = th->doff * 4;
- if (thlen < sizeof(*th))
- goto out;
-
- if (!pskb_may_pull(skb, thlen))
- goto out;
-
- oldlen = (u16)~skb->len;
- __skb_pull(skb, thlen);
-
- mss = skb_shinfo(skb)->gso_size;
- if (unlikely(skb->len <= mss))
- goto out;
-
- if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
- /* Packet is from an untrusted source, reset gso_segs. */
- int type = skb_shinfo(skb)->gso_type;
-
- if (unlikely(type &
- ~(SKB_GSO_TCPV4 |
- SKB_GSO_DODGY |
- SKB_GSO_TCP_ECN |
- SKB_GSO_TCPV6 |
- SKB_GSO_GRE |
- SKB_GSO_UDP_TUNNEL |
- 0) ||
- !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
- goto out;
-
- skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
-
- segs = NULL;
- goto out;
- }
-
- copy_destructor = gso_skb->destructor == tcp_wfree;
- ooo_okay = gso_skb->ooo_okay;
- /* All segments but the first should have ooo_okay cleared */
- skb->ooo_okay = 0;
-
- segs = skb_segment(skb, features);
- if (IS_ERR(segs))
- goto out;
-
- /* Only first segment might have ooo_okay set */
- segs->ooo_okay = ooo_okay;
-
- delta = htonl(oldlen + (thlen + mss));
-
- skb = segs;
- th = tcp_hdr(skb);
- seq = ntohl(th->seq);
-
- newcheck = ~csum_fold((__force __wsum)((__force u32)th->check +
- (__force u32)delta));
-
- do {
- th->fin = th->psh = 0;
- th->check = newcheck;
-
- if (skb->ip_summed != CHECKSUM_PARTIAL)
- th->check =
- csum_fold(csum_partial(skb_transport_header(skb),
- thlen, skb->csum));
-
- seq += mss;
- if (copy_destructor) {
- skb->destructor = gso_skb->destructor;
- skb->sk = gso_skb->sk;
- /* {tcp|sock}_wfree() use exact truesize accounting :
- * sum(skb->truesize) MUST be exactly be gso_skb->truesize
- * So we account mss bytes of 'true size' for each segment.
- * The last segment will contain the remaining.
- */
- skb->truesize = mss;
- gso_skb->truesize -= mss;
- }
- skb = skb->next;
- th = tcp_hdr(skb);
-
- th->seq = htonl(seq);
- th->cwr = 0;
- } while (skb->next);
-
- /* Following permits TCP Small Queues to work well with GSO :
- * The callback to TCP stack will be called at the time last frag
- * is freed at TX completion, and not right now when gso_skb
- * is freed by GSO engine
- */
- if (copy_destructor) {
- swap(gso_skb->sk, skb->sk);
- swap(gso_skb->destructor, skb->destructor);
- swap(gso_skb->truesize, skb->truesize);
- }
-
- delta = htonl(oldlen + (skb->tail - skb->transport_header) +
- skb->data_len);
- th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
- (__force u32)delta));
- if (skb->ip_summed != CHECKSUM_PARTIAL)
- th->check = csum_fold(csum_partial(skb_transport_header(skb),
- thlen, skb->csum));
-
-out:
- return segs;
-}
-EXPORT_SYMBOL(tcp_tso_segment);
-
-struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
-{
- struct sk_buff **pp = NULL;
- struct sk_buff *p;
- struct tcphdr *th;
- struct tcphdr *th2;
- unsigned int len;
- unsigned int thlen;
- __be32 flags;
- unsigned int mss = 1;
- unsigned int hlen;
- unsigned int off;
- int flush = 1;
- int i;
-
- off = skb_gro_offset(skb);
- hlen = off + sizeof(*th);
- th = skb_gro_header_fast(skb, off);
- if (skb_gro_header_hard(skb, hlen)) {
- th = skb_gro_header_slow(skb, hlen, off);
- if (unlikely(!th))
- goto out;
- }
-
- thlen = th->doff * 4;
- if (thlen < sizeof(*th))
- goto out;
-
- hlen = off + thlen;
- if (skb_gro_header_hard(skb, hlen)) {
- th = skb_gro_header_slow(skb, hlen, off);
- if (unlikely(!th))
- goto out;
- }
-
- skb_gro_pull(skb, thlen);
-
- len = skb_gro_len(skb);
- flags = tcp_flag_word(th);
-
- for (; (p = *head); head = &p->next) {
- if (!NAPI_GRO_CB(p)->same_flow)
- continue;
-
- th2 = tcp_hdr(p);
-
- if (*(u32 *)&th->source ^ *(u32 *)&th2->source) {
- NAPI_GRO_CB(p)->same_flow = 0;
- continue;
- }
-
- goto found;
- }
-
- goto out_check_final;
-
-found:
- flush = NAPI_GRO_CB(p)->flush;
- flush |= (__force int)(flags & TCP_FLAG_CWR);
- flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
- ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
- flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
- for (i = sizeof(*th); i < thlen; i += 4)
- flush |= *(u32 *)((u8 *)th + i) ^
- *(u32 *)((u8 *)th2 + i);
-
- mss = skb_shinfo(p)->gso_size;
-
- flush |= (len - 1) >= mss;
- flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
-
- if (flush || skb_gro_receive(head, skb)) {
- mss = 1;
- goto out_check_final;
- }
-
- p = *head;
- th2 = tcp_hdr(p);
- tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
-
-out_check_final:
- flush = len < mss;
- flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH |
- TCP_FLAG_RST | TCP_FLAG_SYN |
- TCP_FLAG_FIN));
-
- if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
- pp = head;
-
-out:
- NAPI_GRO_CB(skb)->flush |= flush;
-
- return pp;
-}
-EXPORT_SYMBOL(tcp_gro_receive);
-
-int tcp_gro_complete(struct sk_buff *skb)
-{
- struct tcphdr *th = tcp_hdr(skb);
-
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct tcphdr, check);
- skb->ip_summed = CHECKSUM_PARTIAL;
-
- skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
-
- if (th->cwr)
- skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
-
- return 0;
-}
-EXPORT_SYMBOL(tcp_gro_complete);
-
#ifdef CONFIG_TCP_MD5SIG
-static unsigned long tcp_md5sig_users;
-static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool;
-static DEFINE_SPINLOCK(tcp_md5sig_pool_lock);
+static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly;
+static DEFINE_MUTEX(tcp_md5sig_mutex);
static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
{
@@ -3132,30 +2899,14 @@ static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
free_percpu(pool);
}
-void tcp_free_md5sig_pool(void)
-{
- struct tcp_md5sig_pool __percpu *pool = NULL;
-
- spin_lock_bh(&tcp_md5sig_pool_lock);
- if (--tcp_md5sig_users == 0) {
- pool = tcp_md5sig_pool;
- tcp_md5sig_pool = NULL;
- }
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- if (pool)
- __tcp_free_md5sig_pool(pool);
-}
-EXPORT_SYMBOL(tcp_free_md5sig_pool);
-
-static struct tcp_md5sig_pool __percpu *
-__tcp_alloc_md5sig_pool(struct sock *sk)
+static void __tcp_alloc_md5sig_pool(void)
{
int cpu;
struct tcp_md5sig_pool __percpu *pool;
pool = alloc_percpu(struct tcp_md5sig_pool);
if (!pool)
- return NULL;
+ return;
for_each_possible_cpu(cpu) {
struct crypto_hash *hash;
@@ -3166,53 +2917,27 @@ __tcp_alloc_md5sig_pool(struct sock *sk)
per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash;
}
- return pool;
+ /* before setting tcp_md5sig_pool, we must commit all writes
+ * to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool()
+ */
+ smp_wmb();
+ tcp_md5sig_pool = pool;
+ return;
out_free:
__tcp_free_md5sig_pool(pool);
- return NULL;
}
-struct tcp_md5sig_pool __percpu *tcp_alloc_md5sig_pool(struct sock *sk)
+bool tcp_alloc_md5sig_pool(void)
{
- struct tcp_md5sig_pool __percpu *pool;
- bool alloc = false;
-
-retry:
- spin_lock_bh(&tcp_md5sig_pool_lock);
- pool = tcp_md5sig_pool;
- if (tcp_md5sig_users++ == 0) {
- alloc = true;
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- } else if (!pool) {
- tcp_md5sig_users--;
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- cpu_relax();
- goto retry;
- } else
- spin_unlock_bh(&tcp_md5sig_pool_lock);
-
- if (alloc) {
- /* we cannot hold spinlock here because this may sleep. */
- struct tcp_md5sig_pool __percpu *p;
-
- p = __tcp_alloc_md5sig_pool(sk);
- spin_lock_bh(&tcp_md5sig_pool_lock);
- if (!p) {
- tcp_md5sig_users--;
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- return NULL;
- }
- pool = tcp_md5sig_pool;
- if (pool) {
- /* oops, it has already been assigned. */
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- __tcp_free_md5sig_pool(p);
- } else {
- tcp_md5sig_pool = pool = p;
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- }
+ if (unlikely(!tcp_md5sig_pool)) {
+ mutex_lock(&tcp_md5sig_mutex);
+
+ if (!tcp_md5sig_pool)
+ __tcp_alloc_md5sig_pool();
+
+ mutex_unlock(&tcp_md5sig_mutex);
}
- return pool;
+ return tcp_md5sig_pool != NULL;
}
EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
@@ -3229,28 +2954,15 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
struct tcp_md5sig_pool __percpu *p;
local_bh_disable();
-
- spin_lock(&tcp_md5sig_pool_lock);
- p = tcp_md5sig_pool;
+ p = ACCESS_ONCE(tcp_md5sig_pool);
if (p)
- tcp_md5sig_users++;
- spin_unlock(&tcp_md5sig_pool_lock);
-
- if (p)
- return this_cpu_ptr(p);
+ return __this_cpu_ptr(p);
local_bh_enable();
return NULL;
}
EXPORT_SYMBOL(tcp_get_md5sig_pool);
-void tcp_put_md5sig_pool(void)
-{
- local_bh_enable();
- tcp_free_md5sig_pool();
-}
-EXPORT_SYMBOL(tcp_put_md5sig_pool);
-
int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
const struct tcphdr *th)
{
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9c6225780bd5..28af45abe062 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -347,24 +347,13 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
}
/* 3. Tuning rcvbuf, when connection enters established state. */
-
static void tcp_fixup_rcvbuf(struct sock *sk)
{
u32 mss = tcp_sk(sk)->advmss;
- u32 icwnd = TCP_DEFAULT_INIT_RCVWND;
int rcvmem;
- /* Limit to 10 segments if mss <= 1460,
- * or 14600/mss segments, with a minimum of two segments.
- */
- if (mss > 1460)
- icwnd = max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
-
- rcvmem = SKB_TRUESIZE(mss + MAX_TCP_HEADER);
- while (tcp_win_from_space(rcvmem) < mss)
- rcvmem += 128;
-
- rcvmem *= icwnd;
+ rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER) *
+ tcp_default_init_rwnd(mss);
if (sk->sk_rcvbuf < rcvmem)
sk->sk_rcvbuf = min(rcvmem, sysctl_tcp_rmem[2]);
@@ -1257,8 +1246,6 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
if (skb == tp->retransmit_skb_hint)
tp->retransmit_skb_hint = prev;
- if (skb == tp->scoreboard_skb_hint)
- tp->scoreboard_skb_hint = prev;
if (skb == tp->lost_skb_hint) {
tp->lost_skb_hint = prev;
tp->lost_cnt_hint -= tcp_skb_pcount(prev);
@@ -1966,20 +1953,6 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag)
return true;
}
-static inline int tcp_skb_timedout(const struct sock *sk,
- const struct sk_buff *skb)
-{
- return tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto;
-}
-
-static inline int tcp_head_timedout(const struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
-
- return tp->packets_out &&
- tcp_skb_timedout(sk, tcp_write_queue_head(sk));
-}
-
/* Linux NewReno/SACK/FACK/ECN state machine.
* --------------------------------------
*
@@ -2086,12 +2059,6 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
if (tcp_dupack_heuristics(tp) > tp->reordering)
return true;
- /* Trick#3 : when we use RFC2988 timer restart, fast
- * retransmit can be triggered by timeout of queue head.
- */
- if (tcp_is_fack(tp) && tcp_head_timedout(sk))
- return true;
-
/* Trick#4: It is still not OK... But will it be useful to delay
* recovery more?
*/
@@ -2128,44 +2095,6 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
return false;
}
-/* New heuristics: it is possible only after we switched to restart timer
- * each time when something is ACKed. Hence, we can detect timed out packets
- * during fast retransmit without falling to slow start.
- *
- * Usefulness of this as is very questionable, since we should know which of
- * the segments is the next to timeout which is relatively expensive to find
- * in general case unless we add some data structure just for that. The
- * current approach certainly won't find the right one too often and when it
- * finally does find _something_ it usually marks large part of the window
- * right away (because a retransmission with a larger timestamp blocks the
- * loop from advancing). -ij
- */
-static void tcp_timeout_skbs(struct sock *sk)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb;
-
- if (!tcp_is_fack(tp) || !tcp_head_timedout(sk))
- return;
-
- skb = tp->scoreboard_skb_hint;
- if (tp->scoreboard_skb_hint == NULL)
- skb = tcp_write_queue_head(sk);
-
- tcp_for_write_queue_from(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
- if (!tcp_skb_timedout(sk, skb))
- break;
-
- tcp_skb_mark_lost(tp, skb);
- }
-
- tp->scoreboard_skb_hint = skb;
-
- tcp_verify_left_out(tp);
-}
-
/* Detect loss in event "A" above by marking head of queue up as lost.
* For FACK or non-SACK(Reno) senders, the first "packets" number of segments
* are considered lost. For RFC3517 SACK, a segment is considered lost if it
@@ -2251,8 +2180,6 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit)
else if (fast_rexmit)
tcp_mark_head_lost(sk, 1, 1);
}
-
- tcp_timeout_skbs(sk);
}
/* CWND moderation, preventing bursts due to too big ACKs
@@ -2307,10 +2234,22 @@ static void DBGUNDO(struct sock *sk, const char *msg)
#define DBGUNDO(x...) do { } while (0)
#endif
-static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
+static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
{
struct tcp_sock *tp = tcp_sk(sk);
+ if (unmark_loss) {
+ struct sk_buff *skb;
+
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
+ TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
+ }
+ tp->lost_out = 0;
+ tcp_clear_all_retrans_hints(tp);
+ }
+
if (tp->prior_ssthresh) {
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -2319,7 +2258,7 @@ static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
else
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1);
- if (undo_ssthresh && tp->prior_ssthresh > tp->snd_ssthresh) {
+ if (tp->prior_ssthresh > tp->snd_ssthresh) {
tp->snd_ssthresh = tp->prior_ssthresh;
TCP_ECN_withdraw_cwr(tp);
}
@@ -2327,6 +2266,7 @@ static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
}
tp->snd_cwnd_stamp = tcp_time_stamp;
+ tp->undo_marker = 0;
}
static inline bool tcp_may_undo(const struct tcp_sock *tp)
@@ -2346,14 +2286,13 @@ static bool tcp_try_undo_recovery(struct sock *sk)
* or our original transmission succeeded.
*/
DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
- tcp_undo_cwr(sk, true);
+ tcp_undo_cwnd_reduction(sk, false);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
mib_idx = LINUX_MIB_TCPLOSSUNDO;
else
mib_idx = LINUX_MIB_TCPFULLUNDO;
NET_INC_STATS_BH(sock_net(sk), mib_idx);
- tp->undo_marker = 0;
}
if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
/* Hold old state until something *above* high_seq
@@ -2367,16 +2306,17 @@ static bool tcp_try_undo_recovery(struct sock *sk)
}
/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */
-static void tcp_try_undo_dsack(struct sock *sk)
+static bool tcp_try_undo_dsack(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tp->undo_marker && !tp->undo_retrans) {
DBGUNDO(sk, "D-SACK");
- tcp_undo_cwr(sk, true);
- tp->undo_marker = 0;
+ tcp_undo_cwnd_reduction(sk, false);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
+ return true;
}
+ return false;
}
/* We can clear retrans_stamp when there are no retransmissions in the
@@ -2408,60 +2348,20 @@ static bool tcp_any_retrans_done(const struct sock *sk)
return false;
}
-/* Undo during fast recovery after partial ACK. */
-
-static int tcp_try_undo_partial(struct sock *sk, int acked)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- /* Partial ACK arrived. Force Hoe's retransmit. */
- int failed = tcp_is_reno(tp) || (tcp_fackets_out(tp) > tp->reordering);
-
- if (tcp_may_undo(tp)) {
- /* Plain luck! Hole if filled with delayed
- * packet, rather than with a retransmit.
- */
- if (!tcp_any_retrans_done(sk))
- tp->retrans_stamp = 0;
-
- tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
-
- DBGUNDO(sk, "Hoe");
- tcp_undo_cwr(sk, false);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
-
- /* So... Do not make Hoe's retransmit yet.
- * If the first packet was delayed, the rest
- * ones are most probably delayed as well.
- */
- failed = 0;
- }
- return failed;
-}
-
/* Undo during loss recovery after partial ACK or using F-RTO. */
static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
{
struct tcp_sock *tp = tcp_sk(sk);
if (frto_undo || tcp_may_undo(tp)) {
- struct sk_buff *skb;
- tcp_for_write_queue(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
- }
-
- tcp_clear_all_retrans_hints(tp);
+ tcp_undo_cwnd_reduction(sk, true);
DBGUNDO(sk, "partial loss");
- tp->lost_out = 0;
- tcp_undo_cwr(sk, true);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO);
if (frto_undo)
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
- tp->undo_marker = 0;
if (frto_undo || tcp_is_sack(tp))
tcp_set_ca_state(sk, TCP_CA_Open);
return true;
@@ -2494,12 +2394,14 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh)
TCP_ECN_queue_cwr(tp);
}
-static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked,
+static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked,
int fast_rexmit)
{
struct tcp_sock *tp = tcp_sk(sk);
int sndcnt = 0;
int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp);
+ int newly_acked_sacked = prior_unsacked -
+ (tp->packets_out - tp->sacked_out);
tp->prr_delivered += newly_acked_sacked;
if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) {
@@ -2556,7 +2458,7 @@ static void tcp_try_keep_open(struct sock *sk)
}
}
-static void tcp_try_to_open(struct sock *sk, int flag, int newly_acked_sacked)
+static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -2573,7 +2475,7 @@ static void tcp_try_to_open(struct sock *sk, int flag, int newly_acked_sacked)
if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
tcp_moderate_cwnd(tp);
} else {
- tcp_cwnd_reduction(sk, newly_acked_sacked, 0);
+ tcp_cwnd_reduction(sk, prior_unsacked, 0);
}
}
@@ -2731,6 +2633,40 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
tcp_xmit_retransmit_queue(sk);
}
+/* Undo during fast recovery after partial ACK. */
+static bool tcp_try_undo_partial(struct sock *sk, const int acked,
+ const int prior_unsacked)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tp->undo_marker && tcp_packet_delayed(tp)) {
+ /* Plain luck! Hole if filled with delayed
+ * packet, rather than with a retransmit.
+ */
+ tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
+
+ /* We are getting evidence that the reordering degree is higher
+ * than we realized. If there are no retransmits out then we
+ * can undo. Otherwise we clock out new packets but do not
+ * mark more packets lost or retransmit more.
+ */
+ if (tp->retrans_out) {
+ tcp_cwnd_reduction(sk, prior_unsacked, 0);
+ return true;
+ }
+
+ if (!tcp_any_retrans_done(sk))
+ tp->retrans_stamp = 0;
+
+ DBGUNDO(sk, "partial recovery");
+ tcp_undo_cwnd_reduction(sk, true);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
+ tcp_try_keep_open(sk);
+ return true;
+ }
+ return false;
+}
+
/* Process an event, which can update packets-in-flight not trivially.
* Main goal of this function is to calculate new estimate for left_out,
* taking into account both packets sitting in receiver's buffer and
@@ -2742,15 +2678,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
* It does _not_ decide what to send, it is made in function
* tcp_xmit_retransmit_queue().
*/
-static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
- int prior_sacked, int prior_packets,
+static void tcp_fastretrans_alert(struct sock *sk, const int acked,
+ const int prior_unsacked,
bool is_dupack, int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
+ bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
(tcp_fackets_out(tp) > tp->reordering));
- int newly_acked_sacked = 0;
int fast_rexmit = 0;
if (WARN_ON(!tp->packets_out && tp->sacked_out))
@@ -2802,10 +2737,17 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
if (!(flag & FLAG_SND_UNA_ADVANCED)) {
if (tcp_is_reno(tp) && is_dupack)
tcp_add_reno_sack(sk);
- } else
- do_lost = tcp_try_undo_partial(sk, pkts_acked);
- newly_acked_sacked = prior_packets - tp->packets_out +
- tp->sacked_out - prior_sacked;
+ } else {
+ if (tcp_try_undo_partial(sk, acked, prior_unsacked))
+ return;
+ /* Partial ACK arrived. Force fast retransmit. */
+ do_lost = tcp_is_reno(tp) ||
+ tcp_fackets_out(tp) > tp->reordering;
+ }
+ if (tcp_try_undo_dsack(sk)) {
+ tcp_try_keep_open(sk);
+ return;
+ }
break;
case TCP_CA_Loss:
tcp_process_loss(sk, flag, is_dupack);
@@ -2819,14 +2761,12 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
if (is_dupack)
tcp_add_reno_sack(sk);
}
- newly_acked_sacked = prior_packets - tp->packets_out +
- tp->sacked_out - prior_sacked;
if (icsk->icsk_ca_state <= TCP_CA_Disorder)
tcp_try_undo_dsack(sk);
if (!tcp_time_to_recover(sk, flag)) {
- tcp_try_to_open(sk, flag, newly_acked_sacked);
+ tcp_try_to_open(sk, flag, prior_unsacked);
return;
}
@@ -2846,9 +2786,9 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
fast_rexmit = 1;
}
- if (do_lost || (tcp_is_fack(tp) && tcp_head_timedout(sk)))
+ if (do_lost)
tcp_update_scoreboard(sk, fast_rexmit);
- tcp_cwnd_reduction(sk, newly_acked_sacked, fast_rexmit);
+ tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit);
tcp_xmit_retransmit_queue(sk);
}
@@ -3079,7 +3019,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
tcp_unlink_write_queue(skb, sk);
sk_wmem_free_skb(sk, skb);
- tp->scoreboard_skb_hint = NULL;
if (skb == tp->retransmit_skb_hint)
tp->retransmit_skb_hint = NULL;
if (skb == tp->lost_skb_hint)
@@ -3333,9 +3272,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
u32 prior_in_flight;
u32 prior_fackets;
int prior_packets = tp->packets_out;
- int prior_sacked = tp->sacked_out;
- int pkts_acked = 0;
- int previous_packets_out = 0;
+ const int prior_unsacked = tp->packets_out - tp->sacked_out;
+ int acked = 0; /* Number of packets newly acked */
/* If the ack is older than previous acks
* then we can probably ignore it.
@@ -3410,18 +3348,17 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
goto no_queue;
/* See if we can take anything off of the retransmit queue. */
- previous_packets_out = tp->packets_out;
+ acked = tp->packets_out;
flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
-
- pkts_acked = previous_packets_out - tp->packets_out;
+ acked -= tp->packets_out;
if (tcp_ack_is_dubious(sk, flag)) {
/* Advance CWND, if state allows this. */
if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, prior_in_flight);
is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
- tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
- prior_packets, is_dupack, flag);
+ tcp_fastretrans_alert(sk, acked, prior_unsacked,
+ is_dupack, flag);
} else {
if (flag & FLAG_DATA_ACKED)
tcp_cong_avoid(sk, ack, prior_in_flight);
@@ -3443,8 +3380,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
no_queue:
/* If data was DSACKed, see if we can undo a cwnd reduction. */
if (flag & FLAG_DSACKING_ACK)
- tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
- prior_packets, is_dupack, flag);
+ tcp_fastretrans_alert(sk, acked, prior_unsacked,
+ is_dupack, flag);
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
* it needs to be for normal retransmission.
@@ -3466,8 +3403,8 @@ old_ack:
*/
if (TCP_SKB_CB(skb)->sacked) {
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
- tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
- prior_packets, is_dupack, flag);
+ tcp_fastretrans_alert(sk, acked, prior_unsacked,
+ is_dupack, flag);
}
SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
@@ -3780,6 +3717,7 @@ void tcp_reset(struct sock *sk)
static void tcp_fin(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ const struct dst_entry *dst;
inet_csk_schedule_ack(sk);
@@ -3791,7 +3729,9 @@ static void tcp_fin(struct sock *sk)
case TCP_ESTABLISHED:
/* Move to CLOSE_WAIT */
tcp_set_state(sk, TCP_CLOSE_WAIT);
- inet_csk(sk)->icsk_ack.pingpong = 1;
+ dst = __sk_dst_get(sk);
+ if (!dst || !dst_metric(dst, RTAX_QUICKACK))
+ inet_csk(sk)->icsk_ack.pingpong = 1;
break;
case TCP_CLOSE_WAIT:
@@ -5601,6 +5541,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
struct inet_connection_sock *icsk = inet_csk(sk);
struct request_sock *req;
int queued = 0;
+ bool acceptable;
tp->rx_opt.saw_tstamp = 0;
@@ -5671,157 +5612,147 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
return 0;
/* step 5: check the ACK field */
- if (true) {
- int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
- FLAG_UPDATE_TS_RECENT) > 0;
-
- switch (sk->sk_state) {
- case TCP_SYN_RECV:
- if (acceptable) {
- /* Once we leave TCP_SYN_RECV, we no longer
- * need req so release it.
- */
- if (req) {
- tcp_synack_rtt_meas(sk, req);
- tp->total_retrans = req->num_retrans;
-
- reqsk_fastopen_remove(sk, req, false);
- } else {
- /* Make sure socket is routed, for
- * correct metrics.
- */
- icsk->icsk_af_ops->rebuild_header(sk);
- tcp_init_congestion_control(sk);
+ acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
+ FLAG_UPDATE_TS_RECENT) > 0;
- tcp_mtup_init(sk);
- tcp_init_buffer_space(sk);
- tp->copied_seq = tp->rcv_nxt;
- }
- smp_mb();
- tcp_set_state(sk, TCP_ESTABLISHED);
- sk->sk_state_change(sk);
-
- /* Note, that this wakeup is only for marginal
- * crossed SYN case. Passively open sockets
- * are not waked up, because sk->sk_sleep ==
- * NULL and sk->sk_socket == NULL.
- */
- if (sk->sk_socket)
- sk_wake_async(sk,
- SOCK_WAKE_IO, POLL_OUT);
-
- tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
- tp->snd_wnd = ntohs(th->window) <<
- tp->rx_opt.snd_wscale;
- tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
-
- if (tp->rx_opt.tstamp_ok)
- tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
-
- if (req) {
- /* Re-arm the timer because data may
- * have been sent out. This is similar
- * to the regular data transmission case
- * when new data has just been ack'ed.
- *
- * (TFO) - we could try to be more
- * aggressive and retranmitting any data
- * sooner based on when they were sent
- * out.
- */
- tcp_rearm_rto(sk);
- } else
- tcp_init_metrics(sk);
+ switch (sk->sk_state) {
+ case TCP_SYN_RECV:
+ if (!acceptable)
+ return 1;
- /* Prevent spurious tcp_cwnd_restart() on
- * first data packet.
- */
- tp->lsndtime = tcp_time_stamp;
+ /* Once we leave TCP_SYN_RECV, we no longer need req
+ * so release it.
+ */
+ if (req) {
+ tcp_synack_rtt_meas(sk, req);
+ tp->total_retrans = req->num_retrans;
- tcp_initialize_rcv_mss(sk);
- tcp_fast_path_on(tp);
- } else {
- return 1;
- }
- break;
+ reqsk_fastopen_remove(sk, req, false);
+ } else {
+ /* Make sure socket is routed, for correct metrics. */
+ icsk->icsk_af_ops->rebuild_header(sk);
+ tcp_init_congestion_control(sk);
+
+ tcp_mtup_init(sk);
+ tcp_init_buffer_space(sk);
+ tp->copied_seq = tp->rcv_nxt;
+ }
+ smp_mb();
+ tcp_set_state(sk, TCP_ESTABLISHED);
+ sk->sk_state_change(sk);
+
+ /* Note, that this wakeup is only for marginal crossed SYN case.
+ * Passively open sockets are not waked up, because
+ * sk->sk_sleep == NULL and sk->sk_socket == NULL.
+ */
+ if (sk->sk_socket)
+ sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
+
+ tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
+ tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
+ tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
- case TCP_FIN_WAIT1:
- /* If we enter the TCP_FIN_WAIT1 state and we are a
- * Fast Open socket and this is the first acceptable
- * ACK we have received, this would have acknowledged
- * our SYNACK so stop the SYNACK timer.
+ if (tp->rx_opt.tstamp_ok)
+ tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
+
+ if (req) {
+ /* Re-arm the timer because data may have been sent out.
+ * This is similar to the regular data transmission case
+ * when new data has just been ack'ed.
+ *
+ * (TFO) - we could try to be more aggressive and
+ * retransmitting any data sooner based on when they
+ * are sent out.
*/
- if (req != NULL) {
- /* Return RST if ack_seq is invalid.
- * Note that RFC793 only says to generate a
- * DUPACK for it but for TCP Fast Open it seems
- * better to treat this case like TCP_SYN_RECV
- * above.
- */
- if (!acceptable)
- return 1;
- /* We no longer need the request sock. */
- reqsk_fastopen_remove(sk, req, false);
- tcp_rearm_rto(sk);
- }
- if (tp->snd_una == tp->write_seq) {
- struct dst_entry *dst;
-
- tcp_set_state(sk, TCP_FIN_WAIT2);
- sk->sk_shutdown |= SEND_SHUTDOWN;
-
- dst = __sk_dst_get(sk);
- if (dst)
- dst_confirm(dst);
-
- if (!sock_flag(sk, SOCK_DEAD))
- /* Wake up lingering close() */
- sk->sk_state_change(sk);
- else {
- int tmo;
-
- if (tp->linger2 < 0 ||
- (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
- after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) {
- tcp_done(sk);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
- return 1;
- }
+ tcp_rearm_rto(sk);
+ } else
+ tcp_init_metrics(sk);
- tmo = tcp_fin_time(sk);
- if (tmo > TCP_TIMEWAIT_LEN) {
- inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
- } else if (th->fin || sock_owned_by_user(sk)) {
- /* Bad case. We could lose such FIN otherwise.
- * It is not a big problem, but it looks confusing
- * and not so rare event. We still can lose it now,
- * if it spins in bh_lock_sock(), but it is really
- * marginal case.
- */
- inet_csk_reset_keepalive_timer(sk, tmo);
- } else {
- tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
- goto discard;
- }
- }
- }
- break;
+ /* Prevent spurious tcp_cwnd_restart() on first data packet */
+ tp->lsndtime = tcp_time_stamp;
- case TCP_CLOSING:
- if (tp->snd_una == tp->write_seq) {
- tcp_time_wait(sk, TCP_TIME_WAIT, 0);
- goto discard;
- }
+ tcp_initialize_rcv_mss(sk);
+ tcp_fast_path_on(tp);
+ break;
+
+ case TCP_FIN_WAIT1: {
+ struct dst_entry *dst;
+ int tmo;
+
+ /* If we enter the TCP_FIN_WAIT1 state and we are a
+ * Fast Open socket and this is the first acceptable
+ * ACK we have received, this would have acknowledged
+ * our SYNACK so stop the SYNACK timer.
+ */
+ if (req != NULL) {
+ /* Return RST if ack_seq is invalid.
+ * Note that RFC793 only says to generate a
+ * DUPACK for it but for TCP Fast Open it seems
+ * better to treat this case like TCP_SYN_RECV
+ * above.
+ */
+ if (!acceptable)
+ return 1;
+ /* We no longer need the request sock. */
+ reqsk_fastopen_remove(sk, req, false);
+ tcp_rearm_rto(sk);
+ }
+ if (tp->snd_una != tp->write_seq)
break;
- case TCP_LAST_ACK:
- if (tp->snd_una == tp->write_seq) {
- tcp_update_metrics(sk);
- tcp_done(sk);
- goto discard;
- }
+ tcp_set_state(sk, TCP_FIN_WAIT2);
+ sk->sk_shutdown |= SEND_SHUTDOWN;
+
+ dst = __sk_dst_get(sk);
+ if (dst)
+ dst_confirm(dst);
+
+ if (!sock_flag(sk, SOCK_DEAD)) {
+ /* Wake up lingering close() */
+ sk->sk_state_change(sk);
break;
}
+
+ if (tp->linger2 < 0 ||
+ (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
+ after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) {
+ tcp_done(sk);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
+ return 1;
+ }
+
+ tmo = tcp_fin_time(sk);
+ if (tmo > TCP_TIMEWAIT_LEN) {
+ inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
+ } else if (th->fin || sock_owned_by_user(sk)) {
+ /* Bad case. We could lose such FIN otherwise.
+ * It is not a big problem, but it looks confusing
+ * and not so rare event. We still can lose it now,
+ * if it spins in bh_lock_sock(), but it is really
+ * marginal case.
+ */
+ inet_csk_reset_keepalive_timer(sk, tmo);
+ } else {
+ tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
+ goto discard;
+ }
+ break;
+ }
+
+ case TCP_CLOSING:
+ if (tp->snd_una == tp->write_seq) {
+ tcp_time_wait(sk, TCP_TIME_WAIT, 0);
+ goto discard;
+ }
+ break;
+
+ case TCP_LAST_ACK:
+ if (tp->snd_una == tp->write_seq) {
+ tcp_update_metrics(sk);
+ tcp_done(sk);
+ goto discard;
+ }
+ break;
}
/* step 6: check the URG bit */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7999fc55c83b..35675e46aff8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -75,6 +75,7 @@
#include <net/netdma.h>
#include <net/secure_seq.h>
#include <net/tcp_memcontrol.h>
+#include <net/ll_poll.h>
#include <linux/inet.h>
#include <linux/ipv6.h>
@@ -545,8 +546,7 @@ out:
sock_put(sk);
}
-static void __tcp_v4_send_check(struct sk_buff *skb,
- __be32 saddr, __be32 daddr)
+void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr)
{
struct tcphdr *th = tcp_hdr(skb);
@@ -571,23 +571,6 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_v4_send_check);
-int tcp_v4_gso_send_check(struct sk_buff *skb)
-{
- const struct iphdr *iph;
- struct tcphdr *th;
-
- if (!pskb_may_pull(skb, sizeof(*th)))
- return -EINVAL;
-
- iph = ip_hdr(skb);
- th = tcp_hdr(skb);
-
- th->check = 0;
- skb->ip_summed = CHECKSUM_PARTIAL;
- __tcp_v4_send_check(skb, iph->saddr, iph->daddr);
- return 0;
-}
-
/*
* This routine will send an RST to the other tcp.
*
@@ -1026,7 +1009,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
key = sock_kmalloc(sk, sizeof(*key), gfp);
if (!key)
return -ENOMEM;
- if (hlist_empty(&md5sig->head) && !tcp_alloc_md5sig_pool(sk)) {
+ if (!tcp_alloc_md5sig_pool()) {
sock_kfree_s(sk, key, sizeof(*key));
return -ENOMEM;
}
@@ -1044,9 +1027,7 @@ EXPORT_SYMBOL(tcp_md5_do_add);
int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
{
- struct tcp_sock *tp = tcp_sk(sk);
struct tcp_md5sig_key *key;
- struct tcp_md5sig_info *md5sig;
key = tcp_md5_do_lookup(sk, addr, family);
if (!key)
@@ -1054,10 +1035,6 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
hlist_del_rcu(&key->node);
atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
kfree_rcu(key, rcu);
- md5sig = rcu_dereference_protected(tp->md5sig_info,
- sock_owned_by_user(sk));
- if (hlist_empty(&md5sig->head))
- tcp_free_md5sig_pool();
return 0;
}
EXPORT_SYMBOL(tcp_md5_do_del);
@@ -1071,8 +1048,6 @@ static void tcp_clear_md5_list(struct sock *sk)
md5sig = rcu_dereference_protected(tp->md5sig_info, 1);
- if (!hlist_empty(&md5sig->head))
- tcp_free_md5sig_pool();
hlist_for_each_entry_safe(key, n, &md5sig->head, node) {
hlist_del_rcu(&key->node);
atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
@@ -2019,6 +1994,7 @@ process:
if (sk_filter(sk, skb))
goto discard_and_relse;
+ sk_mark_ll(sk, skb);
skb->dev = NULL;
bh_lock_sock_nested(sk);
@@ -2803,52 +2779,6 @@ void tcp4_proc_exit(void)
}
#endif /* CONFIG_PROC_FS */
-struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
-{
- const struct iphdr *iph = skb_gro_network_header(skb);
- __wsum wsum;
- __sum16 sum;
-
- switch (skb->ip_summed) {
- case CHECKSUM_COMPLETE:
- if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
- skb->csum)) {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- break;
- }
-flush:
- NAPI_GRO_CB(skb)->flush = 1;
- return NULL;
-
- case CHECKSUM_NONE:
- wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
- skb_gro_len(skb), IPPROTO_TCP, 0);
- sum = csum_fold(skb_checksum(skb,
- skb_gro_offset(skb),
- skb_gro_len(skb),
- wsum));
- if (sum)
- goto flush;
-
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- break;
- }
-
- return tcp_gro_receive(head, skb);
-}
-
-int tcp4_gro_complete(struct sk_buff *skb)
-{
- const struct iphdr *iph = ip_hdr(skb);
- struct tcphdr *th = tcp_hdr(skb);
-
- th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
- iph->saddr, iph->daddr, 0);
- skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
-
- return tcp_gro_complete(skb);
-}
-
struct proto tcp_prot = {
.name = "TCP",
.owner = THIS_MODULE,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 0f0178827259..ab1c08658528 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -317,7 +317,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
key = tp->af_specific->md5_lookup(sk, sk);
if (key != NULL) {
tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
- if (tcptw->tw_md5_key && tcp_alloc_md5sig_pool(sk) == NULL)
+ if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool())
BUG();
}
} while (0);
@@ -358,10 +358,8 @@ void tcp_twsk_destructor(struct sock *sk)
#ifdef CONFIG_TCP_MD5SIG
struct tcp_timewait_sock *twsk = tcp_twsk(sk);
- if (twsk->tw_md5_key) {
- tcp_free_md5sig_pool();
+ if (twsk->tw_md5_key)
kfree_rcu(twsk->tw_md5_key, rcu);
- }
#endif
}
EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
new file mode 100644
index 000000000000..3a7525e6c086
--- /dev/null
+++ b/net/ipv4/tcp_offload.c
@@ -0,0 +1,332 @@
+/*
+ * IPV4 GSO/GRO offload support
+ * Linux INET implementation
+ *
+ * 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.
+ *
+ * TCPv4 GSO/GRO support
+ */
+
+#include <linux/skbuff.h>
+#include <net/tcp.h>
+#include <net/protocol.h>
+
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ struct tcphdr *th;
+ unsigned int thlen;
+ unsigned int seq;
+ __be32 delta;
+ unsigned int oldlen;
+ unsigned int mss;
+ struct sk_buff *gso_skb = skb;
+ __sum16 newcheck;
+ bool ooo_okay, copy_destructor;
+
+ if (!pskb_may_pull(skb, sizeof(*th)))
+ goto out;
+
+ th = tcp_hdr(skb);
+ thlen = th->doff * 4;
+ if (thlen < sizeof(*th))
+ goto out;
+
+ if (!pskb_may_pull(skb, thlen))
+ goto out;
+
+ oldlen = (u16)~skb->len;
+ __skb_pull(skb, thlen);
+
+ mss = tcp_skb_mss(skb);
+ if (unlikely(skb->len <= mss))
+ goto out;
+
+ if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
+ /* Packet is from an untrusted source, reset gso_segs. */
+ int type = skb_shinfo(skb)->gso_type;
+
+ if (unlikely(type &
+ ~(SKB_GSO_TCPV4 |
+ SKB_GSO_DODGY |
+ SKB_GSO_TCP_ECN |
+ SKB_GSO_TCPV6 |
+ SKB_GSO_GRE |
+ SKB_GSO_MPLS |
+ SKB_GSO_UDP_TUNNEL |
+ 0) ||
+ !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
+ goto out;
+
+ skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
+
+ segs = NULL;
+ goto out;
+ }
+
+ copy_destructor = gso_skb->destructor == tcp_wfree;
+ ooo_okay = gso_skb->ooo_okay;
+ /* All segments but the first should have ooo_okay cleared */
+ skb->ooo_okay = 0;
+
+ segs = skb_segment(skb, features);
+ if (IS_ERR(segs))
+ goto out;
+
+ /* Only first segment might have ooo_okay set */
+ segs->ooo_okay = ooo_okay;
+
+ delta = htonl(oldlen + (thlen + mss));
+
+ skb = segs;
+ th = tcp_hdr(skb);
+ seq = ntohl(th->seq);
+
+ newcheck = ~csum_fold((__force __wsum)((__force u32)th->check +
+ (__force u32)delta));
+
+ do {
+ th->fin = th->psh = 0;
+ th->check = newcheck;
+
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ th->check =
+ csum_fold(csum_partial(skb_transport_header(skb),
+ thlen, skb->csum));
+
+ seq += mss;
+ if (copy_destructor) {
+ skb->destructor = gso_skb->destructor;
+ skb->sk = gso_skb->sk;
+ /* {tcp|sock}_wfree() use exact truesize accounting :
+ * sum(skb->truesize) MUST be exactly be gso_skb->truesize
+ * So we account mss bytes of 'true size' for each segment.
+ * The last segment will contain the remaining.
+ */
+ skb->truesize = mss;
+ gso_skb->truesize -= mss;
+ }
+ skb = skb->next;
+ th = tcp_hdr(skb);
+
+ th->seq = htonl(seq);
+ th->cwr = 0;
+ } while (skb->next);
+
+ /* Following permits TCP Small Queues to work well with GSO :
+ * The callback to TCP stack will be called at the time last frag
+ * is freed at TX completion, and not right now when gso_skb
+ * is freed by GSO engine
+ */
+ if (copy_destructor) {
+ swap(gso_skb->sk, skb->sk);
+ swap(gso_skb->destructor, skb->destructor);
+ swap(gso_skb->truesize, skb->truesize);
+ }
+
+ delta = htonl(oldlen + (skb_tail_pointer(skb) -
+ skb_transport_header(skb)) +
+ skb->data_len);
+ th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
+ (__force u32)delta));
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ th->check = csum_fold(csum_partial(skb_transport_header(skb),
+ thlen, skb->csum));
+out:
+ return segs;
+}
+EXPORT_SYMBOL(tcp_tso_segment);
+
+struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+ struct sk_buff **pp = NULL;
+ struct sk_buff *p;
+ struct tcphdr *th;
+ struct tcphdr *th2;
+ unsigned int len;
+ unsigned int thlen;
+ __be32 flags;
+ unsigned int mss = 1;
+ unsigned int hlen;
+ unsigned int off;
+ int flush = 1;
+ int i;
+
+ off = skb_gro_offset(skb);
+ hlen = off + sizeof(*th);
+ th = skb_gro_header_fast(skb, off);
+ if (skb_gro_header_hard(skb, hlen)) {
+ th = skb_gro_header_slow(skb, hlen, off);
+ if (unlikely(!th))
+ goto out;
+ }
+
+ thlen = th->doff * 4;
+ if (thlen < sizeof(*th))
+ goto out;
+
+ hlen = off + thlen;
+ if (skb_gro_header_hard(skb, hlen)) {
+ th = skb_gro_header_slow(skb, hlen, off);
+ if (unlikely(!th))
+ goto out;
+ }
+
+ skb_gro_pull(skb, thlen);
+
+ len = skb_gro_len(skb);
+ flags = tcp_flag_word(th);
+
+ for (; (p = *head); head = &p->next) {
+ if (!NAPI_GRO_CB(p)->same_flow)
+ continue;
+
+ th2 = tcp_hdr(p);
+
+ if (*(u32 *)&th->source ^ *(u32 *)&th2->source) {
+ NAPI_GRO_CB(p)->same_flow = 0;
+ continue;
+ }
+
+ goto found;
+ }
+
+ goto out_check_final;
+
+found:
+ flush = NAPI_GRO_CB(p)->flush;
+ flush |= (__force int)(flags & TCP_FLAG_CWR);
+ flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
+ ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
+ flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
+ for (i = sizeof(*th); i < thlen; i += 4)
+ flush |= *(u32 *)((u8 *)th + i) ^
+ *(u32 *)((u8 *)th2 + i);
+
+ mss = tcp_skb_mss(p);
+
+ flush |= (len - 1) >= mss;
+ flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
+
+ if (flush || skb_gro_receive(head, skb)) {
+ mss = 1;
+ goto out_check_final;
+ }
+
+ p = *head;
+ th2 = tcp_hdr(p);
+ tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
+
+out_check_final:
+ flush = len < mss;
+ flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH |
+ TCP_FLAG_RST | TCP_FLAG_SYN |
+ TCP_FLAG_FIN));
+
+ if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
+ pp = head;
+
+out:
+ NAPI_GRO_CB(skb)->flush |= flush;
+
+ return pp;
+}
+EXPORT_SYMBOL(tcp_gro_receive);
+
+int tcp_gro_complete(struct sk_buff *skb)
+{
+ struct tcphdr *th = tcp_hdr(skb);
+
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct tcphdr, check);
+ skb->ip_summed = CHECKSUM_PARTIAL;
+
+ skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+ if (th->cwr)
+ skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+
+ return 0;
+}
+EXPORT_SYMBOL(tcp_gro_complete);
+
+static int tcp_v4_gso_send_check(struct sk_buff *skb)
+{
+ const struct iphdr *iph;
+ struct tcphdr *th;
+
+ if (!pskb_may_pull(skb, sizeof(*th)))
+ return -EINVAL;
+
+ iph = ip_hdr(skb);
+ th = tcp_hdr(skb);
+
+ th->check = 0;
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ __tcp_v4_send_check(skb, iph->saddr, iph->daddr);
+ return 0;
+}
+
+static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+ const struct iphdr *iph = skb_gro_network_header(skb);
+ __wsum wsum;
+ __sum16 sum;
+
+ switch (skb->ip_summed) {
+ case CHECKSUM_COMPLETE:
+ if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
+ skb->csum)) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ break;
+ }
+flush:
+ NAPI_GRO_CB(skb)->flush = 1;
+ return NULL;
+
+ case CHECKSUM_NONE:
+ wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
+ skb_gro_len(skb), IPPROTO_TCP, 0);
+ sum = csum_fold(skb_checksum(skb,
+ skb_gro_offset(skb),
+ skb_gro_len(skb),
+ wsum));
+ if (sum)
+ goto flush;
+
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ break;
+ }
+
+ return tcp_gro_receive(head, skb);
+}
+
+static int tcp4_gro_complete(struct sk_buff *skb)
+{
+ const struct iphdr *iph = ip_hdr(skb);
+ struct tcphdr *th = tcp_hdr(skb);
+
+ th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
+ iph->saddr, iph->daddr, 0);
+ skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+
+ return tcp_gro_complete(skb);
+}
+
+static const struct net_offload tcpv4_offload = {
+ .callbacks = {
+ .gso_send_check = tcp_v4_gso_send_check,
+ .gso_segment = tcp_tso_segment,
+ .gro_receive = tcp4_gro_receive,
+ .gro_complete = tcp4_gro_complete,
+ },
+};
+
+int __init tcpv4_offload_init(void)
+{
+ return inet_add_offload(&tcpv4_offload, IPPROTO_TCP);
+}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ec335fabd5cc..3d609490f118 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -160,6 +160,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
{
struct inet_connection_sock *icsk = inet_csk(sk);
const u32 now = tcp_time_stamp;
+ const struct dst_entry *dst = __sk_dst_get(sk);
if (sysctl_tcp_slow_start_after_idle &&
(!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto))
@@ -170,8 +171,9 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
/* If it is a reply for ato after last received
* packet, enter pingpong mode.
*/
- if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
- icsk->icsk_ack.pingpong = 1;
+ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato &&
+ (!dst || !dst_metric(dst, RTAX_QUICKACK)))
+ icsk->icsk_ack.pingpong = 1;
}
/* Account for an ACK we sent. */
@@ -181,6 +183,21 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
+
+u32 tcp_default_init_rwnd(u32 mss)
+{
+ /* Initial receive window should be twice of TCP_INIT_CWND to
+ * enable proper sending of new unsent data during fast recovery
+ * (RFC 3517, Section 4, NextSeg() rule (2)). Further place a
+ * limit when mss is larger than 1460.
+ */
+ u32 init_rwnd = TCP_INIT_CWND * 2;
+
+ if (mss > 1460)
+ init_rwnd = max((1460 * init_rwnd) / mss, 2U);
+ return init_rwnd;
+}
+
/* Determine a window scaling and initial window to offer.
* Based on the assumption that the given amount of space
* will be offered. Store the results in the tp structure.
@@ -230,22 +247,10 @@ void tcp_select_initial_window(int __space, __u32 mss,
}
}
- /* Set initial window to a value enough for senders starting with
- * initial congestion window of TCP_DEFAULT_INIT_RCVWND. Place
- * a limit on the initial window when mss is larger than 1460.
- */
if (mss > (1 << *rcv_wscale)) {
- int init_cwnd = TCP_DEFAULT_INIT_RCVWND;
- if (mss > 1460)
- init_cwnd =
- max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
- /* when initializing use the value from init_rcv_wnd
- * rather than the default from above
- */
- if (init_rcv_wnd)
- *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
- else
- *rcv_wnd = min(*rcv_wnd, init_cwnd * mss);
+ if (!init_rcv_wnd) /* Use default unless specified otherwise */
+ init_rcv_wnd = tcp_default_init_rwnd(mss);
+ *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
}
/* Set the clamp no higher than max representable value */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0bf5d399a03c..6b270e53c207 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -109,6 +109,7 @@
#include <trace/events/udp.h>
#include <linux/static_key.h>
#include <trace/events/skb.h>
+#include <net/ll_poll.h>
#include "udp_impl.h"
struct udp_table udp_table __read_mostly;
@@ -429,7 +430,7 @@ begin:
reuseport = sk->sk_reuseport;
if (reuseport) {
hash = inet_ehashfn(net, daddr, hnum,
- saddr, htons(sport));
+ saddr, sport);
matches = 1;
}
} else if (score == badness && reuseport) {
@@ -510,7 +511,7 @@ begin:
reuseport = sk->sk_reuseport;
if (reuseport) {
hash = inet_ehashfn(net, daddr, hnum,
- saddr, htons(sport));
+ saddr, sport);
matches = 1;
}
} else if (score == badness && reuseport) {
@@ -799,7 +800,7 @@ send:
/*
* Push out all pending data as one UDP datagram. Socket is locked.
*/
-static int udp_push_pending_frames(struct sock *sk)
+int udp_push_pending_frames(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
@@ -818,6 +819,7 @@ out:
up->pending = 0;
return err;
}
+EXPORT_SYMBOL(udp_push_pending_frames);
int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len)
@@ -1709,7 +1711,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk != NULL) {
- int ret = udp_queue_rcv_skb(sk, skb);
+ int ret;
+
+ sk_mark_ll(sk, skb);
+ ret = udp_queue_rcv_skb(sk, skb);
sock_put(sk);
/* a return value > 0 means to resubmit the input, but
@@ -1967,6 +1972,8 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
unsigned int mask = datagram_poll(file, sock, wait);
struct sock *sk = sock->sk;
+ sock_rps_record_flow(sk);
+
/* Check for false positives due to checksum errors */
if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
!(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk))
@@ -2284,29 +2291,8 @@ void __init udp_init(void)
sysctl_udp_wmem_min = SK_MEM_QUANTUM;
}
-int udp4_ufo_send_check(struct sk_buff *skb)
-{
- if (!pskb_may_pull(skb, sizeof(struct udphdr)))
- return -EINVAL;
-
- if (likely(!skb->encapsulation)) {
- const struct iphdr *iph;
- struct udphdr *uh;
-
- iph = ip_hdr(skb);
- uh = udp_hdr(skb);
-
- uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
- IPPROTO_UDP, 0);
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct udphdr, check);
- skb->ip_summed = CHECKSUM_PARTIAL;
- }
- return 0;
-}
-
-static struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
- netdev_features_t features)
+struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
int mac_len = skb->mac_len;
@@ -2365,53 +2351,3 @@ static struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
out:
return segs;
}
-
-struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
- netdev_features_t features)
-{
- struct sk_buff *segs = ERR_PTR(-EINVAL);
- unsigned int mss;
- mss = skb_shinfo(skb)->gso_size;
- if (unlikely(skb->len <= mss))
- goto out;
-
- if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
- /* Packet is from an untrusted source, reset gso_segs. */
- int type = skb_shinfo(skb)->gso_type;
-
- if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
- SKB_GSO_UDP_TUNNEL |
- SKB_GSO_GRE) ||
- !(type & (SKB_GSO_UDP))))
- goto out;
-
- skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
-
- segs = NULL;
- goto out;
- }
-
- /* Fragment the skb. IP headers of the fragments are updated in
- * inet_gso_segment()
- */
- if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL)
- segs = skb_udp_tunnel_segment(skb, features);
- else {
- int offset;
- __wsum csum;
-
- /* Do software UFO. Complete and fill in the UDP checksum as
- * HW cannot do checksum of UDP packets sent as multiple
- * IP fragments.
- */
- offset = skb_checksum_start_offset(skb);
- csum = skb_checksum(skb, offset, skb->len - offset, 0);
- offset += skb->csum_offset;
- *(__sum16 *)(skb->data + offset) = csum_fold(csum);
- skb->ip_summed = CHECKSUM_NONE;
-
- segs = skb_segment(skb, features);
- }
-out:
- return segs;
-}
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
new file mode 100644
index 000000000000..f35eccaa855e
--- /dev/null
+++ b/net/ipv4/udp_offload.c
@@ -0,0 +1,100 @@
+/*
+ * IPV4 GSO/GRO offload support
+ * Linux INET implementation
+ *
+ * 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.
+ *
+ * UDPv4 GSO support
+ */
+
+#include <linux/skbuff.h>
+#include <net/udp.h>
+#include <net/protocol.h>
+
+static int udp4_ufo_send_check(struct sk_buff *skb)
+{
+ if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+ return -EINVAL;
+
+ if (likely(!skb->encapsulation)) {
+ const struct iphdr *iph;
+ struct udphdr *uh;
+
+ iph = ip_hdr(skb);
+ uh = udp_hdr(skb);
+
+ uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
+ IPPROTO_UDP, 0);
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ }
+
+ return 0;
+}
+
+static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ unsigned int mss;
+
+ mss = skb_shinfo(skb)->gso_size;
+ if (unlikely(skb->len <= mss))
+ goto out;
+
+ if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
+ /* Packet is from an untrusted source, reset gso_segs. */
+ int type = skb_shinfo(skb)->gso_type;
+
+ if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
+ SKB_GSO_UDP_TUNNEL |
+ SKB_GSO_GRE | SKB_GSO_MPLS) ||
+ !(type & (SKB_GSO_UDP))))
+ goto out;
+
+ skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
+
+ segs = NULL;
+ goto out;
+ }
+
+ /* Fragment the skb. IP headers of the fragments are updated in
+ * inet_gso_segment()
+ */
+ if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL)
+ segs = skb_udp_tunnel_segment(skb, features);
+ else {
+ int offset;
+ __wsum csum;
+
+ /* Do software UFO. Complete and fill in the UDP checksum as
+ * HW cannot do checksum of UDP packets sent as multiple
+ * IP fragments.
+ */
+ offset = skb_checksum_start_offset(skb);
+ csum = skb_checksum(skb, offset, skb->len - offset, 0);
+ offset += skb->csum_offset;
+ *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+ skb->ip_summed = CHECKSUM_NONE;
+
+ segs = skb_segment(skb, features);
+ }
+out:
+ return segs;
+}
+
+static const struct net_offload udpv4_offload = {
+ .callbacks = {
+ .gso_send_check = udp4_ufo_send_check,
+ .gso_segment = udp4_ufo_fragment,
+ },
+};
+
+int __init udpv4_offload_init(void)
+{
+ return inet_add_offload(&udpv4_offload, IPPROTO_UDP);
+}
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index 05a5df2febc9..06347dbd32c1 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -63,7 +63,7 @@ static int xfrm_tunnel_err(struct sk_buff *skb, u32 info)
static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = {
.handler = xfrm_tunnel_rcv,
.err_handler = xfrm_tunnel_err,
- .priority = 2,
+ .priority = 3,
};
#if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 9af088d2cdaa..470a9c008e9b 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_IPV6) += ipv6.o
ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
addrlabel.o \
route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
- raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o \
+ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \
exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o
ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4ab4c38958c6..cfdcf7b2daf6 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -253,37 +253,32 @@ static inline bool addrconf_qdisc_ok(const struct net_device *dev)
return !qdisc_tx_is_noop(dev);
}
-static void addrconf_del_timer(struct inet6_ifaddr *ifp)
+static void addrconf_del_rs_timer(struct inet6_dev *idev)
{
- if (del_timer(&ifp->timer))
+ if (del_timer(&idev->rs_timer))
+ __in6_dev_put(idev);
+}
+
+static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp)
+{
+ if (del_timer(&ifp->dad_timer))
__in6_ifa_put(ifp);
}
-enum addrconf_timer_t {
- AC_NONE,
- AC_DAD,
- AC_RS,
-};
+static void addrconf_mod_rs_timer(struct inet6_dev *idev,
+ unsigned long when)
+{
+ if (!timer_pending(&idev->rs_timer))
+ in6_dev_hold(idev);
+ mod_timer(&idev->rs_timer, jiffies + when);
+}
-static void addrconf_mod_timer(struct inet6_ifaddr *ifp,
- enum addrconf_timer_t what,
- unsigned long when)
+static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp,
+ unsigned long when)
{
- if (!del_timer(&ifp->timer))
+ if (!timer_pending(&ifp->dad_timer))
in6_ifa_hold(ifp);
-
- switch (what) {
- case AC_DAD:
- ifp->timer.function = addrconf_dad_timer;
- break;
- case AC_RS:
- ifp->timer.function = addrconf_rs_timer;
- break;
- default:
- break;
- }
- ifp->timer.expires = jiffies + when;
- add_timer(&ifp->timer);
+ mod_timer(&ifp->dad_timer, jiffies + when);
}
static int snmp6_alloc_dev(struct inet6_dev *idev)
@@ -326,6 +321,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev)
WARN_ON(!list_empty(&idev->addr_list));
WARN_ON(idev->mc_list != NULL);
+ WARN_ON(timer_pending(&idev->rs_timer));
#ifdef NET_REFCNT_DEBUG
pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL");
@@ -357,7 +353,8 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
rwlock_init(&ndev->lock);
ndev->dev = dev;
INIT_LIST_HEAD(&ndev->addr_list);
-
+ setup_timer(&ndev->rs_timer, addrconf_rs_timer,
+ (unsigned long)ndev);
memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf));
ndev->cnf.mtu6 = dev->mtu;
ndev->cnf.sysctl = NULL;
@@ -776,7 +773,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
in6_dev_put(ifp->idev);
- if (del_timer(&ifp->timer))
+ if (del_timer(&ifp->dad_timer))
pr_notice("Timer is still running, when freeing ifa=%p\n", ifp);
if (ifp->state != INET6_IFADDR_STATE_DEAD) {
@@ -869,9 +866,9 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
spin_lock_init(&ifa->lock);
spin_lock_init(&ifa->state_lock);
- init_timer(&ifa->timer);
+ setup_timer(&ifa->dad_timer, addrconf_dad_timer,
+ (unsigned long)ifa);
INIT_HLIST_NODE(&ifa->addr_lst);
- ifa->timer.data = (unsigned long) ifa;
ifa->scope = scope;
ifa->prefix_len = pfxlen;
ifa->flags = flags | IFA_F_TENTATIVE;
@@ -994,7 +991,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
}
write_unlock_bh(&idev->lock);
- addrconf_del_timer(ifp);
+ addrconf_del_dad_timer(ifp);
ipv6_ifa_notify(RTM_DELADDR, ifp);
@@ -1126,8 +1123,7 @@ retry:
ift = !max_addresses ||
ipv6_count_addresses(idev) < max_addresses ?
- ipv6_add_addr(idev, &addr, tmp_plen,
- ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK,
+ ipv6_add_addr(idev, &addr, tmp_plen, ipv6_addr_scope(&addr),
addr_flags) : NULL;
if (IS_ERR_OR_NULL(ift)) {
in6_ifa_put(ifp);
@@ -1448,6 +1444,23 @@ try_nextdev:
}
EXPORT_SYMBOL(ipv6_dev_get_saddr);
+int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
+ unsigned char banned_flags)
+{
+ struct inet6_ifaddr *ifp;
+ int err = -EADDRNOTAVAIL;
+
+ list_for_each_entry(ifp, &idev->addr_list, if_list) {
+ if (ifp->scope == IFA_LINK &&
+ !(ifp->flags & banned_flags)) {
+ *addr = ifp->addr;
+ err = 0;
+ break;
+ }
+ }
+ return err;
+}
+
int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
unsigned char banned_flags)
{
@@ -1457,17 +1470,8 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
rcu_read_lock();
idev = __in6_dev_get(dev);
if (idev) {
- struct inet6_ifaddr *ifp;
-
read_lock_bh(&idev->lock);
- list_for_each_entry(ifp, &idev->addr_list, if_list) {
- if (ifp->scope == IFA_LINK &&
- !(ifp->flags & banned_flags)) {
- *addr = ifp->addr;
- err = 0;
- break;
- }
- }
+ err = __ipv6_get_lladdr(idev, addr, banned_flags);
read_unlock_bh(&idev->lock);
}
rcu_read_unlock();
@@ -1581,7 +1585,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
{
if (ifp->flags&IFA_F_PERMANENT) {
spin_lock_bh(&ifp->lock);
- addrconf_del_timer(ifp);
+ addrconf_del_dad_timer(ifp);
ifp->flags |= IFA_F_TENTATIVE;
if (dad_failed)
ifp->flags |= IFA_F_DADFAILED;
@@ -2402,6 +2406,7 @@ err_exit:
* Manual configuration of address on an interface
*/
static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx,
+ const struct in6_addr *peer_pfx,
unsigned int plen, __u8 ifa_flags, __u32 prefered_lft,
__u32 valid_lft)
{
@@ -2457,6 +2462,8 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *p
ifp->valid_lft = valid_lft;
ifp->prefered_lft = prefered_lft;
ifp->tstamp = jiffies;
+ if (peer_pfx)
+ ifp->peer_addr = *peer_pfx;
spin_unlock_bh(&ifp->lock);
addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
@@ -2500,12 +2507,6 @@ static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *p
read_unlock_bh(&idev->lock);
ipv6_del_addr(ifp);
-
- /* If the last address is deleted administratively,
- disable IPv6 on this interface.
- */
- if (list_empty(&idev->addr_list))
- addrconf_ifdown(idev->dev, 1);
return 0;
}
}
@@ -2526,7 +2527,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg)
return -EFAULT;
rtnl_lock();
- err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr,
+ err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL,
ireq.ifr6_prefixlen, IFA_F_PERMANENT,
INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
rtnl_unlock();
@@ -2761,8 +2762,6 @@ static void addrconf_gre_config(struct net_device *dev)
struct inet6_dev *idev;
struct in6_addr addr;
- pr_info("%s(%s)\n", __func__, dev->name);
-
ASSERT_RTNL();
if ((idev = ipv6_find_idev(dev)) == NULL) {
@@ -2829,9 +2828,9 @@ static void addrconf_ip6_tnl_config(struct net_device *dev)
}
static int addrconf_notify(struct notifier_block *this, unsigned long event,
- void *data)
+ void *ptr)
{
- struct net_device *dev = (struct net_device *) data;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct inet6_dev *idev = __in6_dev_get(dev);
int run_pending = 0;
int err;
@@ -3039,7 +3038,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
hlist_for_each_entry_rcu(ifa, h, addr_lst) {
if (ifa->idev == idev) {
hlist_del_init_rcu(&ifa->addr_lst);
- addrconf_del_timer(ifa);
+ addrconf_del_dad_timer(ifa);
goto restart;
}
}
@@ -3048,6 +3047,8 @@ static int addrconf_ifdown(struct net_device *dev, int how)
write_lock_bh(&idev->lock);
+ addrconf_del_rs_timer(idev);
+
/* Step 2: clear flags for stateless addrconf */
if (!how)
idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);
@@ -3077,7 +3078,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
while (!list_empty(&idev->addr_list)) {
ifa = list_first_entry(&idev->addr_list,
struct inet6_ifaddr, if_list);
- addrconf_del_timer(ifa);
+ addrconf_del_dad_timer(ifa);
list_del(&ifa->if_list);
@@ -3119,10 +3120,10 @@ static int addrconf_ifdown(struct net_device *dev, int how)
static void addrconf_rs_timer(unsigned long data)
{
- struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data;
- struct inet6_dev *idev = ifp->idev;
+ struct inet6_dev *idev = (struct inet6_dev *)data;
+ struct in6_addr lladdr;
- read_lock(&idev->lock);
+ write_lock(&idev->lock);
if (idev->dead || !(idev->if_flags & IF_READY))
goto out;
@@ -3133,18 +3134,19 @@ static void addrconf_rs_timer(unsigned long data)
if (idev->if_flags & IF_RA_RCVD)
goto out;
- spin_lock(&ifp->lock);
- if (ifp->probes++ < idev->cnf.rtr_solicits) {
- /* The wait after the last probe can be shorter */
- addrconf_mod_timer(ifp, AC_RS,
- (ifp->probes == idev->cnf.rtr_solicits) ?
- idev->cnf.rtr_solicit_delay :
- idev->cnf.rtr_solicit_interval);
- spin_unlock(&ifp->lock);
+ if (idev->rs_probes++ < idev->cnf.rtr_solicits) {
+ if (!__ipv6_get_lladdr(idev, &lladdr, IFA_F_TENTATIVE))
+ ndisc_send_rs(idev->dev, &lladdr,
+ &in6addr_linklocal_allrouters);
+ else
+ goto out;
- ndisc_send_rs(idev->dev, &ifp->addr, &in6addr_linklocal_allrouters);
+ /* The wait after the last probe can be shorter */
+ addrconf_mod_rs_timer(idev, (idev->rs_probes ==
+ idev->cnf.rtr_solicits) ?
+ idev->cnf.rtr_solicit_delay :
+ idev->cnf.rtr_solicit_interval);
} else {
- spin_unlock(&ifp->lock);
/*
* Note: we do not support deprecated "all on-link"
* assumption any longer.
@@ -3153,8 +3155,8 @@ static void addrconf_rs_timer(unsigned long data)
}
out:
- read_unlock(&idev->lock);
- in6_ifa_put(ifp);
+ write_unlock(&idev->lock);
+ in6_dev_put(idev);
}
/*
@@ -3170,8 +3172,8 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp)
else
rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1);
- ifp->probes = idev->cnf.dad_transmits;
- addrconf_mod_timer(ifp, AC_DAD, rand_num);
+ ifp->dad_probes = idev->cnf.dad_transmits;
+ addrconf_mod_dad_timer(ifp, rand_num);
}
static void addrconf_dad_start(struct inet6_ifaddr *ifp)
@@ -3232,40 +3234,40 @@ static void addrconf_dad_timer(unsigned long data)
struct inet6_dev *idev = ifp->idev;
struct in6_addr mcaddr;
- if (!ifp->probes && addrconf_dad_end(ifp))
+ if (!ifp->dad_probes && addrconf_dad_end(ifp))
goto out;
- read_lock(&idev->lock);
+ write_lock(&idev->lock);
if (idev->dead || !(idev->if_flags & IF_READY)) {
- read_unlock(&idev->lock);
+ write_unlock(&idev->lock);
goto out;
}
spin_lock(&ifp->lock);
if (ifp->state == INET6_IFADDR_STATE_DEAD) {
spin_unlock(&ifp->lock);
- read_unlock(&idev->lock);
+ write_unlock(&idev->lock);
goto out;
}
- if (ifp->probes == 0) {
+ if (ifp->dad_probes == 0) {
/*
* DAD was successful
*/
ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
spin_unlock(&ifp->lock);
- read_unlock(&idev->lock);
+ write_unlock(&idev->lock);
addrconf_dad_completed(ifp);
goto out;
}
- ifp->probes--;
- addrconf_mod_timer(ifp, AC_DAD, ifp->idev->nd_parms->retrans_time);
+ ifp->dad_probes--;
+ addrconf_mod_dad_timer(ifp, ifp->idev->nd_parms->retrans_time);
spin_unlock(&ifp->lock);
- read_unlock(&idev->lock);
+ write_unlock(&idev->lock);
/* send a neighbour solicitation for our addr */
addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
@@ -3277,6 +3279,10 @@ out:
static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
{
struct net_device *dev = ifp->idev->dev;
+ struct in6_addr lladdr;
+ bool send_rs, send_mld;
+
+ addrconf_del_dad_timer(ifp);
/*
* Configure the address for reception. Now it is valid.
@@ -3288,22 +3294,41 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
router advertisements, start sending router solicitations.
*/
- if (ipv6_accept_ra(ifp->idev) &&
- ifp->idev->cnf.rtr_solicits > 0 &&
- (dev->flags&IFF_LOOPBACK) == 0 &&
- (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) {
+ read_lock_bh(&ifp->idev->lock);
+ spin_lock(&ifp->lock);
+ send_mld = ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL &&
+ ifp->idev->valid_ll_addr_cnt == 1;
+ send_rs = send_mld &&
+ ipv6_accept_ra(ifp->idev) &&
+ ifp->idev->cnf.rtr_solicits > 0 &&
+ (dev->flags&IFF_LOOPBACK) == 0;
+ spin_unlock(&ifp->lock);
+ read_unlock_bh(&ifp->idev->lock);
+
+ /* While dad is in progress mld report's source address is in6_addrany.
+ * Resend with proper ll now.
+ */
+ if (send_mld)
+ ipv6_mc_dad_complete(ifp->idev);
+
+ if (send_rs) {
/*
* If a host as already performed a random delay
* [...] as part of DAD [...] there is no need
* to delay again before sending the first RS
*/
- ndisc_send_rs(ifp->idev->dev, &ifp->addr, &in6addr_linklocal_allrouters);
+ if (ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE))
+ return;
+ ndisc_send_rs(dev, &lladdr, &in6addr_linklocal_allrouters);
- spin_lock_bh(&ifp->lock);
- ifp->probes = 1;
+ write_lock_bh(&ifp->idev->lock);
+ spin_lock(&ifp->lock);
+ ifp->idev->rs_probes = 1;
ifp->idev->if_flags |= IF_RS_SENT;
- addrconf_mod_timer(ifp, AC_RS, ifp->idev->cnf.rtr_solicit_interval);
- spin_unlock_bh(&ifp->lock);
+ addrconf_mod_rs_timer(ifp->idev,
+ ifp->idev->cnf.rtr_solicit_interval);
+ spin_unlock(&ifp->lock);
+ write_unlock_bh(&ifp->idev->lock);
}
}
@@ -3615,18 +3640,20 @@ restart:
rcu_read_unlock_bh();
}
-static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local)
+static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local,
+ struct in6_addr **peer_pfx)
{
struct in6_addr *pfx = NULL;
+ *peer_pfx = NULL;
+
if (addr)
pfx = nla_data(addr);
if (local) {
if (pfx && nla_memcmp(local, pfx, sizeof(*pfx)))
- pfx = NULL;
- else
- pfx = nla_data(local);
+ *peer_pfx = pfx;
+ pfx = nla_data(local);
}
return pfx;
@@ -3644,7 +3671,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
struct net *net = sock_net(skb->sk);
struct ifaddrmsg *ifm;
struct nlattr *tb[IFA_MAX+1];
- struct in6_addr *pfx;
+ struct in6_addr *pfx, *peer_pfx;
int err;
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
@@ -3652,7 +3679,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
return err;
ifm = nlmsg_data(nlh);
- pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]);
+ pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx);
if (pfx == NULL)
return -EINVAL;
@@ -3710,7 +3737,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
struct net *net = sock_net(skb->sk);
struct ifaddrmsg *ifm;
struct nlattr *tb[IFA_MAX+1];
- struct in6_addr *pfx;
+ struct in6_addr *pfx, *peer_pfx;
struct inet6_ifaddr *ifa;
struct net_device *dev;
u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME;
@@ -3722,7 +3749,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
return err;
ifm = nlmsg_data(nlh);
- pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]);
+ pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx);
if (pfx == NULL)
return -EINVAL;
@@ -3750,7 +3777,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
* It would be best to check for !NLM_F_CREATE here but
* userspace alreay relies on not having to provide this.
*/
- return inet6_addr_add(net, ifm->ifa_index, pfx,
+ return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx,
ifm->ifa_prefixlen, ifa_flags,
preferred_lft, valid_lft);
}
@@ -3807,6 +3834,7 @@ static inline int rt_scope(int ifa_scope)
static inline int inet6_ifaddr_msgsize(void)
{
return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
+ + nla_total_size(16) /* IFA_LOCAL */
+ nla_total_size(16) /* IFA_ADDRESS */
+ nla_total_size(sizeof(struct ifa_cacheinfo));
}
@@ -3845,13 +3873,22 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
valid = INFINITY_LIFE_TIME;
}
- if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0 ||
- put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) {
- nlmsg_cancel(skb, nlh);
- return -EMSGSIZE;
- }
+ if (!ipv6_addr_any(&ifa->peer_addr)) {
+ if (nla_put(skb, IFA_LOCAL, 16, &ifa->addr) < 0 ||
+ nla_put(skb, IFA_ADDRESS, 16, &ifa->peer_addr) < 0)
+ goto error;
+ } else
+ if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0)
+ goto error;
+
+ if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0)
+ goto error;
return nlmsg_end(skb, nlh);
+
+error:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
}
static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
@@ -4051,7 +4088,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh)
struct net *net = sock_net(in_skb->sk);
struct ifaddrmsg *ifm;
struct nlattr *tb[IFA_MAX+1];
- struct in6_addr *addr = NULL;
+ struct in6_addr *addr = NULL, *peer;
struct net_device *dev = NULL;
struct inet6_ifaddr *ifa;
struct sk_buff *skb;
@@ -4061,7 +4098,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh)
if (err < 0)
goto errout;
- addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]);
+ addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer);
if (addr == NULL) {
err = -EINVAL;
goto errout;
@@ -4339,8 +4376,11 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
write_lock_bh(&idev->lock);
- if (update_rs)
+ if (update_rs) {
idev->if_flags |= IF_RS_SENT;
+ idev->rs_probes = 1;
+ addrconf_mod_rs_timer(idev, idev->cnf.rtr_solicit_interval);
+ }
/* Well, that's kinda nasty ... */
list_for_each_entry(ifp, &idev->addr_list, if_list) {
@@ -4353,6 +4393,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
}
write_unlock_bh(&idev->lock);
+ addrconf_verify(0);
return 0;
}
@@ -4550,6 +4591,19 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
}
+static void update_valid_ll_addr_cnt(struct inet6_ifaddr *ifp, int count)
+{
+ write_lock_bh(&ifp->idev->lock);
+ spin_lock(&ifp->lock);
+ if (((ifp->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|
+ IFA_F_DADFAILED)) == IFA_F_PERMANENT) &&
+ (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL))
+ ifp->idev->valid_ll_addr_cnt += count;
+ WARN_ON(ifp->idev->valid_ll_addr_cnt < 0);
+ spin_unlock(&ifp->lock);
+ write_unlock_bh(&ifp->idev->lock);
+}
+
static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
{
struct net *net = dev_net(ifp->idev->dev);
@@ -4558,6 +4612,8 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
switch (event) {
case RTM_NEWADDR:
+ update_valid_ll_addr_cnt(ifp, 1);
+
/*
* If the address was optimistic
* we inserted the route at the start of
@@ -4568,11 +4624,28 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
ip6_ins_rt(ifp->rt);
if (ifp->idev->cnf.forwarding)
addrconf_join_anycast(ifp);
+ if (!ipv6_addr_any(&ifp->peer_addr))
+ addrconf_prefix_route(&ifp->peer_addr, 128,
+ ifp->idev->dev, 0, 0);
break;
case RTM_DELADDR:
+ update_valid_ll_addr_cnt(ifp, -1);
+
if (ifp->idev->cnf.forwarding)
addrconf_leave_anycast(ifp);
addrconf_leave_solict(ifp->idev, &ifp->addr);
+ if (!ipv6_addr_any(&ifp->peer_addr)) {
+ struct rt6_info *rt;
+ struct net_device *dev = ifp->idev->dev;
+
+ rt = rt6_lookup(dev_net(dev), &ifp->peer_addr, NULL,
+ dev->ifindex, 1);
+ if (rt) {
+ dst_hold(&rt->dst);
+ if (ip6_del_rt(rt))
+ dst_free(&rt->dst);
+ }
+ }
dst_hold(&ifp->rt->dst);
if (ip6_del_rt(ifp->rt))
@@ -4593,13 +4666,13 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
#ifdef CONFIG_SYSCTL
static
-int addrconf_sysctl_forward(ctl_table *ctl, int write,
+int addrconf_sysctl_forward(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int *valp = ctl->data;
int val = *valp;
loff_t pos = *ppos;
- ctl_table lctl;
+ struct ctl_table lctl;
int ret;
/*
@@ -4620,13 +4693,16 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write,
static void dev_disable_change(struct inet6_dev *idev)
{
+ struct netdev_notifier_info info;
+
if (!idev || !idev->dev)
return;
+ netdev_notifier_info_init(&info, idev->dev);
if (idev->cnf.disable_ipv6)
- addrconf_notify(NULL, NETDEV_DOWN, idev->dev);
+ addrconf_notify(NULL, NETDEV_DOWN, &info);
else
- addrconf_notify(NULL, NETDEV_UP, idev->dev);
+ addrconf_notify(NULL, NETDEV_UP, &info);
}
static void addrconf_disable_change(struct net *net, __s32 newf)
@@ -4675,13 +4751,13 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
}
static
-int addrconf_sysctl_disable(ctl_table *ctl, int write,
+int addrconf_sysctl_disable(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int *valp = ctl->data;
int val = *valp;
loff_t pos = *ppos;
- ctl_table lctl;
+ struct ctl_table lctl;
int ret;
/*
@@ -4703,7 +4779,7 @@ int addrconf_sysctl_disable(ctl_table *ctl, int write,
static struct addrconf_sysctl_table
{
struct ctl_table_header *sysctl_header;
- ctl_table addrconf_vars[DEVCONF_MAX+1];
+ struct ctl_table addrconf_vars[DEVCONF_MAX+1];
} addrconf_sysctl __read_mostly = {
.sysctl_header = NULL,
.addrconf_vars = {
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 72104562c864..d2f87427244b 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -5,6 +5,7 @@
#include <linux/export.h>
#include <net/ipv6.h>
+#include <net/addrconf.h>
#define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index ab5c7ad482cd..a5ac969aeefe 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -49,6 +49,7 @@
#include <net/udp.h>
#include <net/udplite.h>
#include <net/tcp.h>
+#include <net/ping.h>
#include <net/protocol.h>
#include <net/inet_common.h>
#include <net/route.h>
@@ -840,6 +841,9 @@ static int __init inet6_init(void)
if (err)
goto out_unregister_udplite_proto;
+ err = proto_register(&pingv6_prot, 1);
+ if (err)
+ goto out_unregister_ping_proto;
/* We MUST register RAW sockets before we create the ICMP6,
* IGMP6, or NDISC control sockets.
@@ -930,6 +934,10 @@ static int __init inet6_init(void)
if (err)
goto ipv6_packet_fail;
+ err = pingv6_init();
+ if (err)
+ goto pingv6_fail;
+
#ifdef CONFIG_SYSCTL
err = ipv6_sysctl_register();
if (err)
@@ -942,6 +950,8 @@ out:
sysctl_fail:
ipv6_packet_cleanup();
#endif
+pingv6_fail:
+ pingv6_exit();
ipv6_packet_fail:
tcpv6_exit();
tcpv6_fail:
@@ -985,6 +995,8 @@ register_pernet_fail:
rtnl_unregister_all(PF_INET6);
out_sock_register_fail:
rawv6_exit();
+out_unregister_ping_proto:
+ proto_unregister(&pingv6_prot);
out_unregister_raw_proto:
proto_unregister(&rawv6_prot);
out_unregister_udplite_proto:
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 4b56cbbc7890..197e6f4a2b74 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -879,3 +879,30 @@ exit_f:
return err;
}
EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl);
+
+void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
+ __u16 srcp, __u16 destp, int bucket)
+{
+ struct ipv6_pinfo *np = inet6_sk(sp);
+ const struct in6_addr *dest, *src;
+
+ dest = &np->daddr;
+ src = &np->rcv_saddr;
+ seq_printf(seq,
+ "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
+ "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n",
+ bucket,
+ src->s6_addr32[0], src->s6_addr32[1],
+ src->s6_addr32[2], src->s6_addr32[3], srcp,
+ dest->s6_addr32[0], dest->s6_addr32[1],
+ dest->s6_addr32[2], dest->s6_addr32[3], destp,
+ sp->sk_state,
+ sk_wmem_alloc_get(sp),
+ sk_rmem_alloc_get(sp),
+ 0, 0L, 0,
+ from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
+ 0,
+ sock_i_ino(sp),
+ atomic_read(&sp->sk_refcnt), sp,
+ atomic_read(&sp->sk_drops));
+}
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index c5e83fae4df4..140748debc4a 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -115,7 +115,7 @@ EXPORT_SYMBOL(ipv6_skip_exthdr);
int ipv6_find_tlv(struct sk_buff *skb, int offset, int type)
{
const unsigned char *nh = skb_network_header(skb);
- int packet_len = skb->tail - skb->network_header;
+ int packet_len = skb_tail_pointer(skb) - skb_network_header(skb);
struct ipv6_opt_hdr *hdr;
int len;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index b4ff0a42b8c7..7cfc8d284870 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -57,6 +57,7 @@
#include <net/ipv6.h>
#include <net/ip6_checksum.h>
+#include <net/ping.h>
#include <net/protocol.h>
#include <net/raw.h>
#include <net/rawv6.h>
@@ -84,12 +85,18 @@ static inline struct sock *icmpv6_sk(struct net *net)
static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
+ /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
+ struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset);
struct net *net = dev_net(skb->dev);
if (type == ICMPV6_PKT_TOOBIG)
ip6_update_pmtu(skb, net, info, 0, 0);
else if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, 0, 0);
+
+ if (!(type & ICMPV6_INFOMSG_MASK))
+ if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
+ ping_err(skb, offset, info);
}
static int icmpv6_rcv(struct sk_buff *skb);
@@ -224,7 +231,8 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset)
return (*op & 0xC0) == 0x80;
}
-static int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len)
+int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
+ struct icmp6hdr *thdr, int len)
{
struct sk_buff *skb;
struct icmp6hdr *icmp6h;
@@ -307,8 +315,8 @@ static void mip6_addr_swap(struct sk_buff *skb)
static inline void mip6_addr_swap(struct sk_buff *skb) {}
#endif
-static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
- struct sock *sk, struct flowi6 *fl6)
+struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
+ struct sock *sk, struct flowi6 *fl6)
{
struct dst_entry *dst, *dst2;
struct flowi6 fl2;
@@ -391,7 +399,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
int err = 0;
if ((u8 *)hdr < skb->head ||
- (skb->network_header + sizeof(*hdr)) > skb->tail)
+ (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb))
return;
/*
@@ -697,7 +705,8 @@ static int icmpv6_rcv(struct sk_buff *skb)
skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len,
IPPROTO_ICMPV6, 0));
if (__skb_checksum_complete(skb)) {
- LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%pI6 > %pI6]\n",
+ LIMIT_NETDEBUG(KERN_DEBUG
+ "ICMPv6 checksum failed [%pI6c > %pI6c]\n",
saddr, daddr);
goto csum_error;
}
@@ -718,7 +727,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
break;
case ICMPV6_ECHO_REPLY:
- /* we couldn't care less */
+ ping_rcv(skb);
break;
case ICMPV6_PKT_TOOBIG:
@@ -967,7 +976,7 @@ int icmpv6_err_convert(u8 type, u8 code, int *err)
EXPORT_SYMBOL(icmpv6_err_convert);
#ifdef CONFIG_SYSCTL
-ctl_table ipv6_icmp_table_template[] = {
+struct ctl_table ipv6_icmp_table_template[] = {
{
.procname = "ratelimit",
.data = &init_net.ipv6.sysctl.icmpv6_time,
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 71b766ee821d..a263b990ee11 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -98,6 +98,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
SKB_GSO_UDP_TUNNEL |
+ SKB_GSO_MPLS |
SKB_GSO_TCPV6 |
0)))
goto out;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d5d20cde8d92..6e3ddf806ec2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1098,11 +1098,12 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
}
-static void ip6_append_data_mtu(int *mtu,
+static void ip6_append_data_mtu(unsigned int *mtu,
int *maxfraglen,
unsigned int fragheaderlen,
struct sk_buff *skb,
- struct rt6_info *rt)
+ struct rt6_info *rt,
+ bool pmtuprobe)
{
if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
if (skb == NULL) {
@@ -1114,7 +1115,9 @@ static void ip6_append_data_mtu(int *mtu,
* this fragment is not first, the headers
* space is regarded as data space.
*/
- *mtu = dst_mtu(rt->dst.path);
+ *mtu = min(*mtu, pmtuprobe ?
+ rt->dst.dev->mtu :
+ dst_mtu(rt->dst.path));
}
*maxfraglen = ((*mtu - fragheaderlen) & ~7)
+ fragheaderlen - sizeof(struct frag_hdr);
@@ -1131,11 +1134,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_cork *cork;
struct sk_buff *skb, *skb_prev = NULL;
- unsigned int maxfraglen, fragheaderlen;
+ unsigned int maxfraglen, fragheaderlen, mtu;
int exthdrlen;
int dst_exthdrlen;
int hh_len;
- int mtu;
int copy;
int err;
int offset = 0;
@@ -1292,7 +1294,9 @@ alloc_new_skb:
/* update mtu and maxfraglen if necessary */
if (skb == NULL || skb_prev == NULL)
ip6_append_data_mtu(&mtu, &maxfraglen,
- fragheaderlen, skb, rt);
+ fragheaderlen, skb, rt,
+ np->pmtudisc ==
+ IPV6_PMTUDISC_PROBE);
skb_prev = skb;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 241fb8ad9fcf..583e8d435f9a 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1319,7 +1319,7 @@ static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc,
static int ip6mr_device_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct mr6_table *mrt;
struct mif_device *v;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index bfa6cc36ef2a..99cd65c715cd 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -999,6 +999,14 @@ static void mld_ifc_start_timer(struct inet6_dev *idev, int delay)
in6_dev_hold(idev);
}
+static void mld_dad_start_timer(struct inet6_dev *idev, int delay)
+{
+ int tv = net_random() % delay;
+
+ if (!mod_timer(&idev->mc_dad_timer, jiffies+tv+2))
+ in6_dev_hold(idev);
+}
+
/*
* IGMP handling (alias multicast ICMPv6 messages)
*/
@@ -1343,8 +1351,9 @@ static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb,
hdr->daddr = *daddr;
}
-static struct sk_buff *mld_newpack(struct net_device *dev, int size)
+static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size)
{
+ struct net_device *dev = idev->dev;
struct net *net = dev_net(dev);
struct sock *sk = net->ipv6.igmp_sk;
struct sk_buff *skb;
@@ -1369,7 +1378,7 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size)
skb_reserve(skb, hlen);
- if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) {
+ if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
/* <draft-ietf-magma-mld-source-05.txt>:
* use unspecified address as the source address
* when a valid link-local address is not available.
@@ -1409,8 +1418,9 @@ static void mld_sendpack(struct sk_buff *skb)
idev = __in6_dev_get(skb->dev);
IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
- payload_len = (skb->tail - skb->network_header) - sizeof(*pip6);
- mldlen = skb->tail - skb->transport_header;
+ payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) -
+ sizeof(*pip6);
+ mldlen = skb_tail_pointer(skb) - skb_transport_header(skb);
pip6->payload_len = htons(payload_len);
pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen,
@@ -1465,7 +1475,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
struct mld2_grec *pgr;
if (!skb)
- skb = mld_newpack(dev, dev->mtu);
+ skb = mld_newpack(pmc->idev, dev->mtu);
if (!skb)
return NULL;
pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec));
@@ -1485,7 +1495,8 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
int type, int gdeleted, int sdeleted)
{
- struct net_device *dev = pmc->idev->dev;
+ struct inet6_dev *idev = pmc->idev;
+ struct net_device *dev = idev->dev;
struct mld2_report *pmr;
struct mld2_grec *pgr = NULL;
struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list;
@@ -1514,7 +1525,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(dev, dev->mtu);
+ skb = mld_newpack(idev, dev->mtu);
}
}
first = 1;
@@ -1541,7 +1552,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(dev, dev->mtu);
+ skb = mld_newpack(idev, dev->mtu);
first = 1;
scount = 0;
}
@@ -1596,8 +1607,8 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc)
struct sk_buff *skb = NULL;
int type;
+ read_lock_bh(&idev->lock);
if (!pmc) {
- read_lock_bh(&idev->lock);
for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
if (pmc->mca_flags & MAF_NOREPORT)
continue;
@@ -1609,7 +1620,6 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc)
skb = add_grec(skb, pmc, type, 0, 0);
spin_unlock_bh(&pmc->mca_lock);
}
- read_unlock_bh(&idev->lock);
} else {
spin_lock_bh(&pmc->mca_lock);
if (pmc->mca_sfcount[MCAST_EXCLUDE])
@@ -1619,6 +1629,7 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc)
skb = add_grec(skb, pmc, type, 0, 0);
spin_unlock_bh(&pmc->mca_lock);
}
+ read_unlock_bh(&idev->lock);
if (skb)
mld_sendpack(skb);
}
@@ -1814,6 +1825,46 @@ err_out:
goto out;
}
+static void mld_resend_report(struct inet6_dev *idev)
+{
+ if (MLD_V1_SEEN(idev)) {
+ struct ifmcaddr6 *mcaddr;
+ read_lock_bh(&idev->lock);
+ for (mcaddr = idev->mc_list; mcaddr; mcaddr = mcaddr->next) {
+ if (!(mcaddr->mca_flags & MAF_NOREPORT))
+ igmp6_send(&mcaddr->mca_addr, idev->dev,
+ ICMPV6_MGM_REPORT);
+ }
+ read_unlock_bh(&idev->lock);
+ } else {
+ mld_send_report(idev, NULL);
+ }
+}
+
+void ipv6_mc_dad_complete(struct inet6_dev *idev)
+{
+ idev->mc_dad_count = idev->mc_qrv;
+ if (idev->mc_dad_count) {
+ mld_resend_report(idev);
+ idev->mc_dad_count--;
+ if (idev->mc_dad_count)
+ mld_dad_start_timer(idev, idev->mc_maxdelay);
+ }
+}
+
+static void mld_dad_timer_expire(unsigned long data)
+{
+ struct inet6_dev *idev = (struct inet6_dev *)data;
+
+ mld_resend_report(idev);
+ if (idev->mc_dad_count) {
+ idev->mc_dad_count--;
+ if (idev->mc_dad_count)
+ mld_dad_start_timer(idev, idev->mc_maxdelay);
+ }
+ __in6_dev_put(idev);
+}
+
static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode,
const struct in6_addr *psfsrc)
{
@@ -2231,6 +2282,8 @@ void ipv6_mc_down(struct inet6_dev *idev)
idev->mc_gq_running = 0;
if (del_timer(&idev->mc_gq_timer))
__in6_dev_put(idev);
+ if (del_timer(&idev->mc_dad_timer))
+ __in6_dev_put(idev);
for (i = idev->mc_list; i; i=i->next)
igmp6_group_dropped(i);
@@ -2267,6 +2320,8 @@ void ipv6_mc_init_dev(struct inet6_dev *idev)
idev->mc_ifc_count = 0;
setup_timer(&idev->mc_ifc_timer, mld_ifc_timer_expire,
(unsigned long)idev);
+ setup_timer(&idev->mc_dad_timer, mld_dad_timer_expire,
+ (unsigned long)idev);
idev->mc_qrv = MLD_QRV_DEFAULT;
idev->mc_maxdelay = IGMP6_UNSOLICITED_IVAL;
idev->mc_v1_seen = 0;
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index 0f9bdc5ee9f3..9ac01dc9402e 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -268,7 +268,8 @@ static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb,
struct ipv6_opt_hdr *exthdr =
(struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
const unsigned char *nh = skb_network_header(skb);
- unsigned int packet_len = skb->tail - skb->network_header;
+ unsigned int packet_len = skb_tail_pointer(skb) -
+ skb_network_header(skb);
int found_rhdr = 0;
*nexthdr = &ipv6_hdr(skb)->nexthdr;
@@ -404,7 +405,8 @@ static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb,
struct ipv6_opt_hdr *exthdr =
(struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
const unsigned char *nh = skb_network_header(skb);
- unsigned int packet_len = skb->tail - skb->network_header;
+ unsigned int packet_len = skb_tail_pointer(skb) -
+ skb_network_header(skb);
int found_rhdr = 0;
*nexthdr = &ipv6_hdr(skb)->nexthdr;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index ca4ffcc287f1..b3b5730b48c5 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -693,7 +693,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
u8 *lladdr = NULL;
- u32 ndoptlen = skb->tail - (skb->transport_header +
+ u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
offsetof(struct nd_msg, opt));
struct ndisc_options ndopts;
struct net_device *dev = skb->dev;
@@ -853,7 +853,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
u8 *lladdr = NULL;
- u32 ndoptlen = skb->tail - (skb->transport_header +
+ u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
offsetof(struct nd_msg, opt));
struct ndisc_options ndopts;
struct net_device *dev = skb->dev;
@@ -1069,7 +1069,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
__u8 * opt = (__u8 *)(ra_msg + 1);
- optlen = (skb->tail - skb->transport_header) - sizeof(struct ra_msg);
+ optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) -
+ sizeof(struct ra_msg);
if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) {
ND_PRINTK(2, warn, "RA: source address is not link-local\n");
@@ -1346,7 +1347,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb)
u8 *hdr;
struct ndisc_options ndopts;
struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb);
- u32 ndoptlen = skb->tail - (skb->transport_header +
+ u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
offsetof(struct rd_msg, opt));
#ifdef CONFIG_IPV6_NDISC_NODETYPE
@@ -1568,7 +1569,7 @@ int ndisc_rcv(struct sk_buff *skb)
static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct inet6_dev *idev;
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 60e9053bab05..47bff6107519 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -71,7 +71,7 @@ static int device_cmp(struct nf_conn *ct, void *ifindex)
static int masq_device_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
- const struct net_device *dev = ptr;
+ const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
if (event == NETDEV_DOWN)
@@ -89,8 +89,10 @@ static int masq_inet_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct inet6_ifaddr *ifa = ptr;
+ struct netdev_notifier_info info;
- return masq_device_event(this, event, ifa->idev->dev);
+ netdev_notifier_info_init(&info, ifa->idev->dev);
+ return masq_device_event(this, event, &info);
}
static struct notifier_block masq_inet_notifier = {
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index c2e73e647e44..ab92a3673fbb 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -40,7 +40,8 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
u16 offset = sizeof(struct ipv6hdr);
struct ipv6_opt_hdr *exthdr =
(struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
- unsigned int packet_len = skb->tail - skb->network_header;
+ unsigned int packet_len = skb_tail_pointer(skb) -
+ skb_network_header(skb);
int found_rhdr = 0;
*nexthdr = &ipv6_hdr(skb)->nexthdr;
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
new file mode 100644
index 000000000000..18f19df4189f
--- /dev/null
+++ b/net/ipv6/ping.c
@@ -0,0 +1,277 @@
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * "Ping" sockets
+ *
+ * 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.
+ *
+ * Based on ipv4/ping.c code.
+ *
+ * Authors: Lorenzo Colitti (IPv6 support)
+ * Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6),
+ * Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32)
+ *
+ */
+
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/protocol.h>
+#include <net/udp.h>
+#include <net/transp_v6.h>
+#include <net/ping.h>
+
+struct proto pingv6_prot = {
+ .name = "PINGv6",
+ .owner = THIS_MODULE,
+ .init = ping_init_sock,
+ .close = ping_close,
+ .connect = ip6_datagram_connect,
+ .disconnect = udp_disconnect,
+ .setsockopt = ipv6_setsockopt,
+ .getsockopt = ipv6_getsockopt,
+ .sendmsg = ping_v6_sendmsg,
+ .recvmsg = ping_recvmsg,
+ .bind = ping_bind,
+ .backlog_rcv = ping_queue_rcv_skb,
+ .hash = ping_hash,
+ .unhash = ping_unhash,
+ .get_port = ping_get_port,
+ .obj_size = sizeof(struct raw6_sock),
+};
+EXPORT_SYMBOL_GPL(pingv6_prot);
+
+static struct inet_protosw pingv6_protosw = {
+ .type = SOCK_DGRAM,
+ .protocol = IPPROTO_ICMPV6,
+ .prot = &pingv6_prot,
+ .ops = &inet6_dgram_ops,
+ .no_check = UDP_CSUM_DEFAULT,
+ .flags = INET_PROTOSW_REUSE,
+};
+
+
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+{
+ return -EAFNOSUPPORT;
+}
+static int dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
+ struct sk_buff *skb)
+{
+ return -EAFNOSUPPORT;
+}
+static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err)
+{
+ return -EAFNOSUPPORT;
+}
+static void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
+ __be16 port, u32 info, u8 *payload) {}
+static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
+ const struct net_device *dev, int strict)
+{
+ return 0;
+}
+
+int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len)
+{
+ struct inet_sock *inet = inet_sk(sk);
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct icmp6hdr user_icmph;
+ int addr_type;
+ struct in6_addr *daddr;
+ int iif = 0;
+ struct flowi6 fl6;
+ int err;
+ int hlimit;
+ struct dst_entry *dst;
+ struct rt6_info *rt;
+ struct pingfakehdr pfh;
+
+ pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
+
+ err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph,
+ sizeof(user_icmph));
+ if (err)
+ return err;
+
+ if (msg->msg_name) {
+ struct sockaddr_in6 *u = (struct sockaddr_in6 *) msg->msg_name;
+ if (msg->msg_namelen < sizeof(struct sockaddr_in6) ||
+ u->sin6_family != AF_INET6) {
+ return -EINVAL;
+ }
+ if (sk->sk_bound_dev_if &&
+ sk->sk_bound_dev_if != u->sin6_scope_id) {
+ return -EINVAL;
+ }
+ daddr = &(u->sin6_addr);
+ iif = u->sin6_scope_id;
+ } else {
+ if (sk->sk_state != TCP_ESTABLISHED)
+ return -EDESTADDRREQ;
+ daddr = &np->daddr;
+ }
+
+ if (!iif)
+ iif = sk->sk_bound_dev_if;
+
+ addr_type = ipv6_addr_type(daddr);
+ if (__ipv6_addr_needs_scope_id(addr_type) && !iif)
+ return -EINVAL;
+ if (addr_type & IPV6_ADDR_MAPPED)
+ return -EINVAL;
+
+ /* TODO: use ip6_datagram_send_ctl to get options from cmsg */
+
+ memset(&fl6, 0, sizeof(fl6));
+
+ fl6.flowi6_proto = IPPROTO_ICMPV6;
+ fl6.saddr = np->saddr;
+ fl6.daddr = *daddr;
+ fl6.fl6_icmp_type = user_icmph.icmp6_type;
+ fl6.fl6_icmp_code = user_icmph.icmp6_code;
+ security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+ if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+ fl6.flowi6_oif = np->mcast_oif;
+ else if (!fl6.flowi6_oif)
+ fl6.flowi6_oif = np->ucast_oif;
+
+ dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, 1);
+ if (IS_ERR(dst))
+ return PTR_ERR(dst);
+ rt = (struct rt6_info *) dst;
+
+ np = inet6_sk(sk);
+ if (!np)
+ return -EBADF;
+
+ if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+ fl6.flowi6_oif = np->mcast_oif;
+ else if (!fl6.flowi6_oif)
+ fl6.flowi6_oif = np->ucast_oif;
+
+ pfh.icmph.type = user_icmph.icmp6_type;
+ pfh.icmph.code = user_icmph.icmp6_code;
+ pfh.icmph.checksum = 0;
+ pfh.icmph.un.echo.id = inet->inet_sport;
+ pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
+ pfh.iov = msg->msg_iov;
+ pfh.wcheck = 0;
+ pfh.family = AF_INET6;
+
+ if (ipv6_addr_is_multicast(&fl6.daddr))
+ hlimit = np->mcast_hops;
+ else
+ hlimit = np->hop_limit;
+ if (hlimit < 0)
+ hlimit = ip6_dst_hoplimit(dst);
+
+ lock_sock(sk);
+ err = ip6_append_data(sk, ping_getfrag, &pfh, len,
+ 0, hlimit,
+ np->tclass, NULL, &fl6, rt,
+ MSG_DONTWAIT, np->dontfrag);
+
+ if (err) {
+ ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev,
+ ICMP6_MIB_OUTERRORS);
+ ip6_flush_pending_frames(sk);
+ } else {
+ err = icmpv6_push_pending_frames(sk, &fl6,
+ (struct icmp6hdr *) &pfh.icmph,
+ len);
+ }
+ release_sock(sk);
+
+ if (err)
+ return err;
+
+ return len;
+}
+
+#ifdef CONFIG_PROC_FS
+static void *ping_v6_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ return ping_seq_start(seq, pos, AF_INET6);
+}
+
+static int ping_v6_seq_show(struct seq_file *seq, void *v)
+{
+ if (v == SEQ_START_TOKEN) {
+ seq_puts(seq, IPV6_SEQ_DGRAM_HEADER);
+ } else {
+ int bucket = ((struct ping_iter_state *) seq->private)->bucket;
+ struct inet_sock *inet = inet_sk(v);
+ __u16 srcp = ntohs(inet->inet_sport);
+ __u16 destp = ntohs(inet->inet_dport);
+ ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket);
+ }
+ return 0;
+}
+
+static struct ping_seq_afinfo ping_v6_seq_afinfo = {
+ .name = "icmp6",
+ .family = AF_INET6,
+ .seq_fops = &ping_seq_fops,
+ .seq_ops = {
+ .start = ping_v6_seq_start,
+ .show = ping_v6_seq_show,
+ .next = ping_seq_next,
+ .stop = ping_seq_stop,
+ },
+};
+
+static int __net_init ping_v6_proc_init_net(struct net *net)
+{
+ return ping_proc_register(net, &ping_v6_seq_afinfo);
+}
+
+static void __net_init ping_v6_proc_exit_net(struct net *net)
+{
+ return ping_proc_unregister(net, &ping_v6_seq_afinfo);
+}
+
+static struct pernet_operations ping_v6_net_ops = {
+ .init = ping_v6_proc_init_net,
+ .exit = ping_v6_proc_exit_net,
+};
+#endif
+
+int __init pingv6_init(void)
+{
+#ifdef CONFIG_PROC_FS
+ int ret = register_pernet_subsys(&ping_v6_net_ops);
+ if (ret)
+ return ret;
+#endif
+ pingv6_ops.ipv6_recv_error = ipv6_recv_error;
+ pingv6_ops.ip6_datagram_recv_ctl = ip6_datagram_recv_ctl;
+ pingv6_ops.icmpv6_err_convert = icmpv6_err_convert;
+ pingv6_ops.ipv6_icmp_error = ipv6_icmp_error;
+ pingv6_ops.ipv6_chk_addr = ipv6_chk_addr;
+ return inet6_register_protosw(&pingv6_protosw);
+}
+
+/* This never gets called because it's not possible to unload the ipv6 module,
+ * but just in case.
+ */
+void pingv6_exit(void)
+{
+ pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error;
+ pingv6_ops.ip6_datagram_recv_ctl = dummy_ip6_datagram_recv_ctl;
+ pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert;
+ pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error;
+ pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr;
+#ifdef CONFIG_PROC_FS
+ unregister_pernet_subsys(&ping_v6_net_ops);
+#endif
+ inet6_unregister_protosw(&pingv6_protosw);
+}
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index eedff8ccded5..c45f7a5c36e9 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1132,7 +1132,8 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
spin_lock_bh(&sk->sk_receive_queue.lock);
skb = skb_peek(&sk->sk_receive_queue);
if (skb != NULL)
- amount = skb->tail - skb->transport_header;
+ amount = skb_tail_pointer(skb) -
+ skb_transport_header(skb);
spin_unlock_bh(&sk->sk_receive_queue.lock);
return put_user(amount, (int __user *)arg);
}
@@ -1226,45 +1227,16 @@ struct proto rawv6_prot = {
};
#ifdef CONFIG_PROC_FS
-static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
-{
- struct ipv6_pinfo *np = inet6_sk(sp);
- const struct in6_addr *dest, *src;
- __u16 destp, srcp;
-
- dest = &np->daddr;
- src = &np->rcv_saddr;
- destp = 0;
- srcp = inet_sk(sp)->inet_num;
- seq_printf(seq,
- "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
- "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n",
- i,
- src->s6_addr32[0], src->s6_addr32[1],
- src->s6_addr32[2], src->s6_addr32[3], srcp,
- dest->s6_addr32[0], dest->s6_addr32[1],
- dest->s6_addr32[2], dest->s6_addr32[3], destp,
- sp->sk_state,
- sk_wmem_alloc_get(sp),
- sk_rmem_alloc_get(sp),
- 0, 0L, 0,
- from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
- 0,
- sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops));
-}
-
static int raw6_seq_show(struct seq_file *seq, void *v)
{
- if (v == SEQ_START_TOKEN)
- seq_printf(seq,
- " sl "
- "local_address "
- "remote_address "
- "st tx_queue rx_queue tr tm->when retrnsmt"
- " uid timeout inode ref pointer drops\n");
- else
- raw6_sock_seq_show(seq, v, raw_seq_private(seq)->bucket);
+ if (v == SEQ_START_TOKEN) {
+ seq_puts(seq, IPV6_SEQ_DGRAM_HEADER);
+ } else {
+ struct sock *sp = v;
+ __u16 srcp = inet_sk(sp)->inet_num;
+ ip6_dgram_sock_seq_show(seq, v, srcp, 0,
+ raw_seq_private(seq)->bucket);
+ }
return 0;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ad0aa6b0b86a..bd5fd7054031 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -83,6 +83,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
+static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct net *net,
@@ -394,7 +395,8 @@ static int rt6_info_hash_nhsfn(unsigned int candidate_count,
}
static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
- struct flowi6 *fl6)
+ struct flowi6 *fl6, int oif,
+ int strict)
{
struct rt6_info *sibling, *next_sibling;
int route_choosen;
@@ -408,6 +410,8 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
&match->rt6i_siblings, rt6i_siblings) {
route_choosen--;
if (route_choosen == 0) {
+ if (rt6_score_route(sibling, oif, strict) < 0)
+ break;
match = sibling;
break;
}
@@ -547,6 +551,8 @@ static inline bool rt6_check_neigh(struct rt6_info *rt)
ret = true;
#endif
read_unlock(&neigh->lock);
+ } else if (IS_ENABLED(CONFIG_IPV6_ROUTER_PREF)) {
+ ret = true;
}
rcu_read_unlock_bh();
@@ -743,7 +749,7 @@ restart:
rt = fn->leaf;
rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags);
if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
- rt = rt6_multipath_select(rt, fl6);
+ rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags);
BACKTRACK(net, &fl6->saddr);
out:
dst_use(&rt->dst, jiffies);
@@ -875,8 +881,8 @@ restart_2:
restart:
rt = rt6_select(fn, oif, strict | reachable);
- if (rt->rt6i_nsiblings && oif == 0)
- rt = rt6_multipath_select(rt, fl6);
+ if (rt->rt6i_nsiblings)
+ rt = rt6_multipath_select(rt, fl6, oif, strict | reachable);
BACKTRACK(net, &fl6->saddr);
if (rt == net->ipv6.ip6_null_entry ||
rt->rt6i_flags & RTF_CACHE)
@@ -1649,7 +1655,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
int optlen, on_link;
u8 *lladdr;
- optlen = skb->tail - skb->transport_header;
+ optlen = skb_tail_pointer(skb) - skb_transport_header(skb);
optlen -= sizeof(*msg);
if (optlen < 0) {
@@ -2681,9 +2687,9 @@ errout:
}
static int ip6_route_dev_notify(struct notifier_block *this,
- unsigned long event, void *data)
+ unsigned long event, void *ptr)
{
- struct net_device *dev = (struct net_device *)data;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) {
@@ -2790,7 +2796,7 @@ static const struct file_operations rt6_stats_seq_fops = {
#ifdef CONFIG_SYSCTL
static
-int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write,
+int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct net *net;
@@ -2805,7 +2811,7 @@ int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write,
return 0;
}
-ctl_table ipv6_route_table_template[] = {
+struct ctl_table ipv6_route_table_template[] = {
{
.procname = "flush",
.data = &init_net.ipv6.sysctl.flush_delay,
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 335363478bbf..a3437a4cd07e 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -466,14 +466,14 @@ isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t)
static void ipip6_tunnel_uninit(struct net_device *dev)
{
- struct net *net = dev_net(dev);
- struct sit_net *sitn = net_generic(net, sit_net_id);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct sit_net *sitn = net_generic(tunnel->net, sit_net_id);
if (dev == sitn->fb_tunnel_dev) {
RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL);
} else {
- ipip6_tunnel_unlink(sitn, netdev_priv(dev));
- ipip6_tunnel_del_prl(netdev_priv(dev), NULL);
+ ipip6_tunnel_unlink(sitn, tunnel);
+ ipip6_tunnel_del_prl(tunnel, NULL);
}
dev_put(dev);
}
@@ -577,6 +577,10 @@ static int ipip6_rcv(struct sk_buff *skb)
if (tunnel != NULL) {
struct pcpu_tstats *tstats;
+ if (tunnel->parms.iph.protocol != IPPROTO_IPV6 &&
+ tunnel->parms.iph.protocol != 0)
+ goto out;
+
secpath_reset(skb);
skb->mac_header = skb->network_header;
skb_reset_network_header(skb);
@@ -589,7 +593,7 @@ static int ipip6_rcv(struct sk_buff *skb)
tunnel->dev->stats.rx_errors++;
goto out;
}
- } else {
+ } else if (!(tunnel->dev->flags&IFF_POINTOPOINT)) {
if (is_spoofed_6rd(tunnel, iph->saddr,
&ipv6_hdr(skb)->saddr) ||
is_spoofed_6rd(tunnel, iph->daddr,
@@ -617,6 +621,8 @@ static int ipip6_rcv(struct sk_buff *skb)
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
+ if (tunnel->net != dev_net(tunnel->dev))
+ skb_scrub_packet(skb);
netif_rx(skb);
return 0;
@@ -629,6 +635,40 @@ out:
return 0;
}
+static const struct tnl_ptk_info tpi = {
+ /* no tunnel info required for ipip. */
+ .proto = htons(ETH_P_IP),
+};
+
+static int ipip_rcv(struct sk_buff *skb)
+{
+ const struct iphdr *iph;
+ struct ip_tunnel *tunnel;
+
+ if (iptunnel_pull_header(skb, 0, tpi.proto))
+ goto drop;
+
+ iph = ip_hdr(skb);
+
+ tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
+ iph->saddr, iph->daddr);
+ if (tunnel != NULL) {
+ if (tunnel->parms.iph.protocol != IPPROTO_IPIP &&
+ tunnel->parms.iph.protocol != 0)
+ goto drop;
+
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+ return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
+ }
+
+ return 1;
+
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+
/*
* If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function
* stores the embedded IPv4 address in v4dst and returns true.
@@ -690,13 +730,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
__be16 df = tiph->frag_off;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
- struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
struct flowi4 fl4;
int mtu;
const struct in6_addr *addr6;
int addr_type;
+ u8 ttl;
+ int err;
if (skb->protocol != htons(ETH_P_IPV6))
goto tx_error;
@@ -764,7 +805,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
goto tx_error;
}
- rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
+ rt = ip_route_output_ports(tunnel->net, &fl4, NULL,
dst, tiph->saddr,
0, 0,
IPPROTO_IPV6, RT_TOS(tos),
@@ -819,6 +860,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
tunnel->err_count = 0;
}
+ if (tunnel->net != dev_net(dev))
+ skb_scrub_packet(skb);
+
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
@@ -839,34 +883,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
skb = new_skb;
iph6 = ipv6_hdr(skb);
}
-
- skb->transport_header = skb->network_header;
- skb_push(skb, sizeof(struct iphdr));
- skb_reset_network_header(skb);
- memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- IPCB(skb)->flags = 0;
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
- /*
- * Push down and install the IPIP header.
- */
-
- iph = ip_hdr(skb);
- iph->version = 4;
- iph->ihl = sizeof(struct iphdr)>>2;
- iph->frag_off = df;
- iph->protocol = IPPROTO_IPV6;
- iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
- iph->daddr = fl4.daddr;
- iph->saddr = fl4.saddr;
-
- if ((iph->ttl = tiph->ttl) == 0)
- iph->ttl = iph6->hop_limit;
-
- skb->ip_summed = CHECKSUM_NONE;
- ip_select_ident(iph, skb_dst(skb), NULL);
- iptunnel_xmit(skb, dev);
+ ttl = tiph->ttl;
+ if (ttl == 0)
+ ttl = iph6->hop_limit;
+ tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
+
+ err = iptunnel_xmit(dev_net(dev), rt, skb, fl4.saddr, fl4.daddr,
+ IPPROTO_IPV6, tos, ttl, df);
+ iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
return NETDEV_TX_OK;
tx_error_icmp:
@@ -877,6 +901,43 @@ tx_error:
return NETDEV_TX_OK;
}
+static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ const struct iphdr *tiph = &tunnel->parms.iph;
+
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
+ }
+
+ ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP);
+ return NETDEV_TX_OK;
+}
+
+static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ ipip_tunnel_xmit(skb, dev);
+ break;
+ case htons(ETH_P_IPV6):
+ ipip6_tunnel_xmit(skb, dev);
+ break;
+ default:
+ goto tx_err;
+ }
+
+ return NETDEV_TX_OK;
+
+tx_err:
+ dev->stats.tx_errors++;
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+
+}
+
static void ipip6_tunnel_bind_dev(struct net_device *dev)
{
struct net_device *tdev = NULL;
@@ -888,7 +949,8 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
iph = &tunnel->parms.iph;
if (iph->daddr) {
- struct rtable *rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
+ struct rtable *rt = ip_route_output_ports(tunnel->net, &fl4,
+ NULL,
iph->daddr, iph->saddr,
0, 0,
IPPROTO_IPV6,
@@ -903,7 +965,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
}
if (!tdev && tunnel->parms.link)
- tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
+ tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);
if (tdev) {
dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
@@ -916,7 +978,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
{
- struct net *net = dev_net(t->dev);
+ struct net *net = t->net;
struct sit_net *sitn = net_generic(net, sit_net_id);
ipip6_tunnel_unlink(sitn, t);
@@ -1027,7 +1089,11 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
goto done;
err = -EINVAL;
- if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPV6 ||
+ if (p.iph.protocol != IPPROTO_IPV6 &&
+ p.iph.protocol != IPPROTO_IPIP &&
+ p.iph.protocol != 0)
+ goto done;
+ if (p.iph.version != 4 ||
p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
goto done;
if (p.iph.ttl)
@@ -1164,7 +1230,7 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu)
static const struct net_device_ops ipip6_netdev_ops = {
.ndo_uninit = ipip6_tunnel_uninit,
- .ndo_start_xmit = ipip6_tunnel_xmit,
+ .ndo_start_xmit = sit_tunnel_xmit,
.ndo_do_ioctl = ipip6_tunnel_ioctl,
.ndo_change_mtu = ipip6_tunnel_change_mtu,
.ndo_get_stats64 = ip_tunnel_get_stats64,
@@ -1188,7 +1254,6 @@ static void ipip6_tunnel_setup(struct net_device *dev)
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
dev->iflink = 0;
dev->addr_len = 4;
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->features |= NETIF_F_LLTX;
}
@@ -1197,6 +1262,7 @@ static int ipip6_tunnel_init(struct net_device *dev)
struct ip_tunnel *tunnel = netdev_priv(dev);
tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
@@ -1217,6 +1283,7 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
struct sit_net *sitn = net_generic(net, sit_net_id);
tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
iph->version = 4;
@@ -1232,6 +1299,22 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
return 0;
}
+static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+ u8 proto;
+
+ if (!data || !data[IFLA_IPTUN_PROTO])
+ return 0;
+
+ proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
+ if (proto != IPPROTO_IPV6 &&
+ proto != IPPROTO_IPIP &&
+ proto != 0)
+ return -EINVAL;
+
+ return 0;
+}
+
static void ipip6_netlink_parms(struct nlattr *data[],
struct ip_tunnel_parm *parms)
{
@@ -1268,6 +1351,10 @@ static void ipip6_netlink_parms(struct nlattr *data[],
if (data[IFLA_IPTUN_FLAGS])
parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]);
+
+ if (data[IFLA_IPTUN_PROTO])
+ parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]);
+
}
#ifdef CONFIG_IPV6_SIT_6RD
@@ -1339,9 +1426,9 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
- struct ip_tunnel *t;
+ struct ip_tunnel *t = netdev_priv(dev);
struct ip_tunnel_parm p;
- struct net *net = dev_net(dev);
+ struct net *net = t->net;
struct sit_net *sitn = net_generic(net, sit_net_id);
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel_6rd ip6rd;
@@ -1391,6 +1478,8 @@ static size_t ipip6_get_size(const struct net_device *dev)
nla_total_size(1) +
/* IFLA_IPTUN_FLAGS */
nla_total_size(2) +
+ /* IFLA_IPTUN_PROTO */
+ nla_total_size(1) +
#ifdef CONFIG_IPV6_SIT_6RD
/* IFLA_IPTUN_6RD_PREFIX */
nla_total_size(sizeof(struct in6_addr)) +
@@ -1416,6 +1505,7 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) ||
nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
!!(parm->iph.frag_off & htons(IP_DF))) ||
+ nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) ||
nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags))
goto nla_put_failure;
@@ -1445,6 +1535,7 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = {
[IFLA_IPTUN_TOS] = { .type = NLA_U8 },
[IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 },
[IFLA_IPTUN_FLAGS] = { .type = NLA_U16 },
+ [IFLA_IPTUN_PROTO] = { .type = NLA_U8 },
#ifdef CONFIG_IPV6_SIT_6RD
[IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) },
[IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 },
@@ -1459,6 +1550,7 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = {
.policy = ipip6_policy,
.priv_size = sizeof(struct ip_tunnel),
.setup = ipip6_tunnel_setup,
+ .validate = ipip6_validate,
.newlink = ipip6_newlink,
.changelink = ipip6_changelink,
.get_size = ipip6_get_size,
@@ -1471,10 +1563,22 @@ static struct xfrm_tunnel sit_handler __read_mostly = {
.priority = 1,
};
+static struct xfrm_tunnel ipip_handler __read_mostly = {
+ .handler = ipip_rcv,
+ .err_handler = ipip6_err,
+ .priority = 2,
+};
+
static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head)
{
+ struct net *net = dev_net(sitn->fb_tunnel_dev);
+ struct net_device *dev, *aux;
int prio;
+ for_each_netdev_safe(net, dev, aux)
+ if (dev->rtnl_link_ops == &sit_link_ops)
+ unregister_netdevice_queue(dev, head);
+
for (prio = 1; prio < 4; prio++) {
int h;
for (h = 0; h < HASH_SIZE; h++) {
@@ -1482,7 +1586,12 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea
t = rtnl_dereference(sitn->tunnels[prio][h]);
while (t != NULL) {
- unregister_netdevice_queue(t->dev, head);
+ /* If dev is in the same netns, it has already
+ * been added to the list by the previous loop.
+ */
+ if (dev_net(t->dev) != net)
+ unregister_netdevice_queue(t->dev,
+ head);
t = rtnl_dereference(t->next);
}
}
@@ -1507,6 +1616,10 @@ static int __net_init sit_init_net(struct net *net)
goto err_alloc_dev;
}
dev_net_set(sitn->fb_tunnel_dev, net);
+ /* FB netdevice is special: we have one, and only one per netns.
+ * Allowing to move it to another netns is clearly unsafe.
+ */
+ sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
if (err)
@@ -1553,6 +1666,7 @@ static void __exit sit_cleanup(void)
{
rtnl_link_unregister(&sit_link_ops);
xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
unregister_pernet_device(&sit_net_ops);
rcu_barrier(); /* Wait for completion of call_rcu()'s */
@@ -1569,9 +1683,14 @@ static int __init sit_init(void)
return err;
err = xfrm4_tunnel_register(&sit_handler, AF_INET6);
if (err < 0) {
- pr_info("%s: can't add protocol\n", __func__);
+ pr_info("%s: can't register ip6ip4\n", __func__);
goto xfrm_tunnel_failed;
}
+ err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+ if (err < 0) {
+ pr_info("%s: can't register ip4ip4\n", __func__);
+ goto xfrm_tunnel4_failed;
+ }
err = rtnl_link_register(&sit_link_ops);
if (err < 0)
goto rtnl_link_failed;
@@ -1580,6 +1699,8 @@ out:
return err;
rtnl_link_failed:
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+xfrm_tunnel4_failed:
xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
xfrm_tunnel_failed:
unregister_pernet_device(&sit_net_ops);
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index e85c48bd404f..107b2f1d90ae 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -16,7 +16,7 @@
#include <net/addrconf.h>
#include <net/inet_frag.h>
-static ctl_table ipv6_table_template[] = {
+static struct ctl_table ipv6_table_template[] = {
{
.procname = "bindv6only",
.data = &init_net.ipv6.sysctl.bindv6only,
@@ -27,7 +27,7 @@ static ctl_table ipv6_table_template[] = {
{ }
};
-static ctl_table ipv6_rotable[] = {
+static struct ctl_table ipv6_rotable[] = {
{
.procname = "mld_max_msf",
.data = &sysctl_mld_max_msf,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 0a17ed9eaf39..5cffa5c3e6b8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -63,6 +63,7 @@
#include <net/inet_common.h>
#include <net/secure_seq.h>
#include <net/tcp_memcontrol.h>
+#include <net/ll_poll.h>
#include <asm/uaccess.h>
@@ -1498,6 +1499,7 @@ process:
if (sk_filter(sk, skb))
goto discard_and_relse;
+ sk_mark_ll(sk, skb);
skb->dev = NULL;
bh_lock_sock_nested(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 42923b14dfa6..b6f31437a1f8 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -46,6 +46,7 @@
#include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <net/inet6_hashtables.h>
+#include <net/ll_poll.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
@@ -841,7 +842,10 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
*/
sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk != NULL) {
- int ret = udpv6_queue_rcv_skb(sk, skb);
+ int ret;
+
+ sk_mark_ll(sk, skb);
+ ret = udpv6_queue_rcv_skb(sk, skb);
sock_put(sk);
/* a return value > 0 means to resubmit the input, but
@@ -955,11 +959,16 @@ static int udp_v6_push_pending_frames(struct sock *sk)
struct udphdr *uh;
struct udp_sock *up = udp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
- struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
+ struct flowi6 *fl6;
int err = 0;
int is_udplite = IS_UDPLITE(sk);
__wsum csum = 0;
+ if (up->pending == AF_INET)
+ return udp_push_pending_frames(sk);
+
+ fl6 = &inet->cork.fl.u.ip6;
+
/* Grab the skbuff where UDP header space exists. */
if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
goto out;
@@ -1359,48 +1368,17 @@ static const struct inet6_protocol udpv6_protocol = {
/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS
-
-static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket)
-{
- struct inet_sock *inet = inet_sk(sp);
- struct ipv6_pinfo *np = inet6_sk(sp);
- const struct in6_addr *dest, *src;
- __u16 destp, srcp;
-
- dest = &np->daddr;
- src = &np->rcv_saddr;
- destp = ntohs(inet->inet_dport);
- srcp = ntohs(inet->inet_sport);
- seq_printf(seq,
- "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
- "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n",
- bucket,
- src->s6_addr32[0], src->s6_addr32[1],
- src->s6_addr32[2], src->s6_addr32[3], srcp,
- dest->s6_addr32[0], dest->s6_addr32[1],
- dest->s6_addr32[2], dest->s6_addr32[3], destp,
- sp->sk_state,
- sk_wmem_alloc_get(sp),
- sk_rmem_alloc_get(sp),
- 0, 0L, 0,
- from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
- 0,
- sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp,
- atomic_read(&sp->sk_drops));
-}
-
int udp6_seq_show(struct seq_file *seq, void *v)
{
- if (v == SEQ_START_TOKEN)
- seq_printf(seq,
- " sl "
- "local_address "
- "remote_address "
- "st tx_queue rx_queue tr tm->when retrnsmt"
- " uid timeout inode ref pointer drops\n");
- else
- udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket);
+ if (v == SEQ_START_TOKEN) {
+ seq_puts(seq, IPV6_SEQ_DGRAM_HEADER);
+ } else {
+ int bucket = ((struct udp_iter_state *)seq->private)->bucket;
+ struct inet_sock *inet = inet_sk(v);
+ __u16 srcp = ntohs(inet->inet_sport);
+ __u16 destp = ntohs(inet->inet_dport);
+ ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket);
+ }
return 0;
}
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index d3cfaf9c7a08..5d1b8d7ac993 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -64,7 +64,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
if (unlikely(type & ~(SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_UDP_TUNNEL |
- SKB_GSO_GRE) ||
+ SKB_GSO_GRE |
+ SKB_GSO_MPLS) ||
!(type & (SKB_GSO_UDP))))
goto out;
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index f547a47d381c..7a1e0fc1bd4d 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -330,7 +330,7 @@ static __inline__ void __ipxitf_put(struct ipx_interface *intrfc)
static int ipxitf_device_event(struct notifier_block *notifier,
unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct ipx_interface *i, *tmp;
if (!net_eq(dev_net(dev), &init_net))
diff --git a/net/irda/irsysctl.c b/net/irda/irsysctl.c
index de73f6496db5..d6a59651767a 100644
--- a/net/irda/irsysctl.c
+++ b/net/irda/irsysctl.c
@@ -73,7 +73,7 @@ static int min_lap_keepalive_time = 100; /* 100us */
/* For other sysctl, I've no idea of the range. Maybe Dag could help
* us on that - Jean II */
-static int do_devname(ctl_table *table, int write,
+static int do_devname(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
@@ -90,7 +90,7 @@ static int do_devname(ctl_table *table, int write,
}
-static int do_discovery(ctl_table *table, int write,
+static int do_discovery(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
@@ -111,7 +111,7 @@ static int do_discovery(ctl_table *table, int write,
}
/* One file */
-static ctl_table irda_table[] = {
+static struct ctl_table irda_table[] = {
{
.procname = "discovery",
.data = &sysctl_discovery,
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index ae691651b721..168aff5e60de 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -2293,7 +2293,7 @@ out_unlock:
static int afiucv_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
- struct net_device *event_dev = (struct net_device *)ptr;
+ struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
struct sock *sk;
struct iucv_sock *iucv;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6984c3a353cd..feae495a0a30 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -414,10 +414,7 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *
if (L2TP_SKB_CB(skb)->has_seq) {
/* Bump our Nr */
session->nr++;
- if (tunnel->version == L2TP_HDR_VER_2)
- session->nr &= 0xffff;
- else
- session->nr &= 0xffffff;
+ session->nr &= session->nr_max;
l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated nr to %hu\n",
session->name, session->nr);
@@ -542,6 +539,84 @@ static inline int l2tp_verify_udp_checksum(struct sock *sk,
return __skb_checksum_complete(skb);
}
+static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr)
+{
+ u32 nws;
+
+ if (nr >= session->nr)
+ nws = nr - session->nr;
+ else
+ nws = (session->nr_max + 1) - (session->nr - nr);
+
+ return nws < session->nr_window_size;
+}
+
+/* If packet has sequence numbers, queue it if acceptable. Returns 0 if
+ * acceptable, else non-zero.
+ */
+static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb)
+{
+ if (!l2tp_seq_check_rx_window(session, L2TP_SKB_CB(skb)->ns)) {
+ /* Packet sequence number is outside allowed window.
+ * Discard it.
+ */
+ l2tp_dbg(session, L2TP_MSG_SEQ,
+ "%s: pkt %u len %d discarded, outside window, nr=%u\n",
+ session->name, L2TP_SKB_CB(skb)->ns,
+ L2TP_SKB_CB(skb)->length, session->nr);
+ goto discard;
+ }
+
+ if (session->reorder_timeout != 0) {
+ /* Packet reordering enabled. Add skb to session's
+ * reorder queue, in order of ns.
+ */
+ l2tp_recv_queue_skb(session, skb);
+ goto out;
+ }
+
+ /* Packet reordering disabled. Discard out-of-sequence packets, while
+ * tracking the number if in-sequence packets after the first OOS packet
+ * is seen. After nr_oos_count_max in-sequence packets, reset the
+ * sequence number to re-enable packet reception.
+ */
+ if (L2TP_SKB_CB(skb)->ns == session->nr) {
+ skb_queue_tail(&session->reorder_q, skb);
+ } else {
+ u32 nr_oos = L2TP_SKB_CB(skb)->ns;
+ u32 nr_next = (session->nr_oos + 1) & session->nr_max;
+
+ if (nr_oos == nr_next)
+ session->nr_oos_count++;
+ else
+ session->nr_oos_count = 0;
+
+ session->nr_oos = nr_oos;
+ if (session->nr_oos_count > session->nr_oos_count_max) {
+ session->reorder_skip = 1;
+ l2tp_dbg(session, L2TP_MSG_SEQ,
+ "%s: %d oos packets received. Resetting sequence numbers\n",
+ session->name, session->nr_oos_count);
+ }
+ if (!session->reorder_skip) {
+ atomic_long_inc(&session->stats.rx_seq_discards);
+ l2tp_dbg(session, L2TP_MSG_SEQ,
+ "%s: oos pkt %u len %d discarded, waiting for %u, reorder_q_len=%d\n",
+ session->name, L2TP_SKB_CB(skb)->ns,
+ L2TP_SKB_CB(skb)->length, session->nr,
+ skb_queue_len(&session->reorder_q));
+ goto discard;
+ }
+ skb_queue_tail(&session->reorder_q, skb);
+ }
+
+out:
+ return 0;
+
+discard:
+ return 1;
+}
+
/* Do receive processing of L2TP data frames. We handle both L2TPv2
* and L2TPv3 data frames here.
*
@@ -757,26 +832,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
* enabled. Saved L2TP protocol info is stored in skb->sb[].
*/
if (L2TP_SKB_CB(skb)->has_seq) {
- if (session->reorder_timeout != 0) {
- /* Packet reordering enabled. Add skb to session's
- * reorder queue, in order of ns.
- */
- l2tp_recv_queue_skb(session, skb);
- } else {
- /* Packet reordering disabled. Discard out-of-sequence
- * packets
- */
- if (L2TP_SKB_CB(skb)->ns != session->nr) {
- atomic_long_inc(&session->stats.rx_seq_discards);
- l2tp_dbg(session, L2TP_MSG_SEQ,
- "%s: oos pkt %u len %d discarded, waiting for %u, reorder_q_len=%d\n",
- session->name, L2TP_SKB_CB(skb)->ns,
- L2TP_SKB_CB(skb)->length, session->nr,
- skb_queue_len(&session->reorder_q));
- goto discard;
- }
- skb_queue_tail(&session->reorder_q, skb);
- }
+ if (l2tp_recv_data_seq(session, skb))
+ goto discard;
} else {
/* No sequence numbers. Add the skb to the tail of the
* reorder queue. This ensures that it will be
@@ -1812,6 +1869,15 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
session->session_id = session_id;
session->peer_session_id = peer_session_id;
session->nr = 0;
+ if (tunnel->version == L2TP_HDR_VER_2)
+ session->nr_max = 0xffff;
+ else
+ session->nr_max = 0xffffff;
+ session->nr_window_size = session->nr_max / 2;
+ session->nr_oos_count_max = 4;
+
+ /* Use NR of first received packet */
+ session->reorder_skip = 1;
sprintf(&session->name[0], "sess %u/%u",
tunnel->tunnel_id, session->session_id);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 485a490fd990..66a559b104b6 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -102,6 +102,11 @@ struct l2tp_session {
u32 nr; /* session NR state (receive) */
u32 ns; /* session NR state (send) */
struct sk_buff_head reorder_q; /* receive reorder queue */
+ u32 nr_max; /* max NR. Depends on tunnel */
+ u32 nr_window_size; /* NR window size */
+ u32 nr_oos; /* NR of last OOS packet */
+ int nr_oos_count; /* For OOS recovery */
+ int nr_oos_count_max;
struct hlist_node hlist; /* Hash list node */
atomic_t ref_count;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 8dec6876dc50..5ebee2ded9e9 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1793,7 +1793,8 @@ static const struct proto_ops pppol2tp_ops = {
static const struct pppox_proto pppol2tp_proto = {
.create = pppol2tp_create,
- .ioctl = pppol2tp_ioctl
+ .ioctl = pppol2tp_ioctl,
+ .owner = THIS_MODULE,
};
#ifdef CONFIG_L2TP_V3
diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c
index 0785e95c9924..be7614b9ed27 100644
--- a/net/mac80211/aes_ccm.c
+++ b/net/mac80211/aes_ccm.c
@@ -85,7 +85,7 @@ void ieee80211_aes_ccm_encrypt(struct crypto_cipher *tfm, u8 *scratch,
*cpos++ = *pos++ ^ e[i];
}
- for (i = 0; i < CCMP_MIC_LEN; i++)
+ for (i = 0; i < IEEE80211_CCMP_MIC_LEN; i++)
mic[i] = b[i] ^ s_0[i];
}
@@ -123,7 +123,7 @@ int ieee80211_aes_ccm_decrypt(struct crypto_cipher *tfm, u8 *scratch,
crypto_cipher_encrypt_one(tfm, a, a);
}
- for (i = 0; i < CCMP_MIC_LEN; i++) {
+ for (i = 0; i < IEEE80211_CCMP_MIC_LEN; i++) {
if ((mic[i] ^ s_0[i]) != a[i])
return -1;
}
@@ -138,7 +138,7 @@ struct crypto_cipher *ieee80211_aes_key_setup_encrypt(const u8 key[])
tfm = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
if (!IS_ERR(tfm))
- crypto_cipher_setkey(tfm, key, ALG_CCMP_KEY_LEN);
+ crypto_cipher_setkey(tfm, key, WLAN_KEY_LEN_CCMP);
return tfm;
}
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 4fdb306e42e0..8184d121ff09 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -73,16 +73,19 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
struct ieee80211_local *local = sdata->local;
if (ieee80211_sdata_running(sdata)) {
+ u32 mask = MONITOR_FLAG_COOK_FRAMES |
+ MONITOR_FLAG_ACTIVE;
+
/*
- * Prohibit MONITOR_FLAG_COOK_FRAMES to be
- * changed while the interface is up.
+ * Prohibit MONITOR_FLAG_COOK_FRAMES and
+ * MONITOR_FLAG_ACTIVE to be changed while the
+ * interface is up.
* Else we would need to add a lot of cruft
* to update everything:
* cooked_mntrs, monitor and all fif_* counters
* reconfigure hardware
*/
- if ((*flags & MONITOR_FLAG_COOK_FRAMES) !=
- (sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES))
+ if ((*flags & mask) != (sdata->u.mntr_flags & mask))
return -EBUSY;
ieee80211_adjust_monitor_flags(sdata, -1);
@@ -444,7 +447,7 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
struct ieee80211_local *local = sdata->local;
struct timespec uptime;
u64 packets = 0;
- int ac;
+ int i, ac;
sinfo->generation = sdata->local->sta_generation;
@@ -488,6 +491,17 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
sinfo->signal = (s8)sta->last_signal;
sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal);
}
+ if (sta->chains) {
+ sinfo->filled |= STATION_INFO_CHAIN_SIGNAL |
+ STATION_INFO_CHAIN_SIGNAL_AVG;
+
+ sinfo->chains = sta->chains;
+ for (i = 0; i < ARRAY_SIZE(sinfo->chain_signal); i++) {
+ sinfo->chain_signal[i] = sta->chain_signal_last[i];
+ sinfo->chain_signal_avg[i] =
+ (s8) -ewma_read(&sta->chain_signal_avg[i]);
+ }
+ }
sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate);
sta_set_rate_info_rx(sta, &sinfo->rxrate);
@@ -728,7 +742,7 @@ static void ieee80211_get_et_strings(struct wiphy *wiphy,
if (sset == ETH_SS_STATS) {
sz_sta_stats = sizeof(ieee80211_gstrings_sta_stats);
- memcpy(data, *ieee80211_gstrings_sta_stats, sz_sta_stats);
+ memcpy(data, ieee80211_gstrings_sta_stats, sz_sta_stats);
}
drv_get_et_strings(sdata, sset, &(data[sz_sta_stats]));
}
@@ -1741,6 +1755,7 @@ static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh,
ifmsh->mesh_pp_id = setup->path_sel_proto;
ifmsh->mesh_pm_id = setup->path_metric;
ifmsh->user_mpm = setup->user_mpm;
+ ifmsh->mesh_auth_id = setup->auth_id;
ifmsh->security = IEEE80211_MESH_SEC_NONE;
if (setup->is_authenticated)
ifmsh->security |= IEEE80211_MESH_SEC_AUTHED;
@@ -1750,6 +1765,7 @@ static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh,
/* mcast rate setting in Mesh Node */
memcpy(sdata->vif.bss_conf.mcast_rate, setup->mcast_rate,
sizeof(setup->mcast_rate));
+ sdata->vif.bss_conf.basic_rates = setup->basic_rates;
sdata->vif.bss_conf.beacon_int = setup->beacon_interval;
sdata->vif.bss_conf.dtim_period = setup->dtim_period;
@@ -1862,6 +1878,8 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy,
if (_chg_mesh_attr(NL80211_MESHCONF_AWAKE_WINDOW, mask))
conf->dot11MeshAwakeWindowDuration =
nconf->dot11MeshAwakeWindowDuration;
+ if (_chg_mesh_attr(NL80211_MESHCONF_PLINK_TIMEOUT, mask))
+ conf->plink_timeout = nconf->plink_timeout;
ieee80211_mbss_info_change_notify(sdata, BSS_CHANGED_BEACON);
return 0;
}
@@ -2312,7 +2330,7 @@ int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata,
enum ieee80211_smps_mode old_req;
int err;
- lockdep_assert_held(&sdata->u.mgd.mtx);
+ lockdep_assert_held(&sdata->wdev.mtx);
old_req = sdata->u.mgd.req_smps;
sdata->u.mgd.req_smps = smps_mode;
@@ -2369,9 +2387,9 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
local->dynamic_ps_forced_timeout = timeout;
/* no change, but if automatic follow powersave */
- mutex_lock(&sdata->u.mgd.mtx);
+ sdata_lock(sdata);
__ieee80211_request_smps(sdata, sdata->u.mgd.req_smps);
- mutex_unlock(&sdata->u.mgd.mtx);
+ sdata_unlock(sdata);
if (local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS)
ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS);
@@ -2809,7 +2827,8 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
!rcu_access_pointer(sdata->bss->beacon))
need_offchan = true;
if (!ieee80211_is_action(mgmt->frame_control) ||
- mgmt->u.action.category == WLAN_CATEGORY_PUBLIC)
+ mgmt->u.action.category == WLAN_CATEGORY_PUBLIC ||
+ mgmt->u.action.category == WLAN_CATEGORY_SELF_PROTECTED)
break;
rcu_read_lock();
sta = sta_info_get(sdata, mgmt->da);
@@ -2829,6 +2848,12 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
return -EOPNOTSUPP;
}
+ /* configurations requiring offchan cannot work if no channel has been
+ * specified
+ */
+ if (need_offchan && !chan)
+ return -EINVAL;
+
mutex_lock(&local->mtx);
/* Check if the operating channel is the requested channel */
@@ -2838,10 +2863,15 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
rcu_read_lock();
chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
- if (chanctx_conf)
- need_offchan = chan != chanctx_conf->def.chan;
- else
+ if (chanctx_conf) {
+ need_offchan = chan && (chan != chanctx_conf->def.chan);
+ } else if (!chan) {
+ ret = -EINVAL;
+ rcu_read_unlock();
+ goto out_unlock;
+ } else {
need_offchan = true;
+ }
rcu_read_unlock();
}
@@ -2901,19 +2931,8 @@ static void ieee80211_mgmt_frame_register(struct wiphy *wiphy,
u16 frame_type, bool reg)
{
struct ieee80211_local *local = wiphy_priv(wiphy);
- struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
switch (frame_type) {
- case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH:
- if (sdata->vif.type == NL80211_IFTYPE_ADHOC) {
- struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
-
- if (reg)
- ifibss->auth_frame_registrations++;
- else
- ifibss->auth_frame_registrations--;
- }
- break;
case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ:
if (reg)
local->probe_req_reg++;
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 14abcf44f974..cafe614ef93d 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -228,9 +228,9 @@ static int ieee80211_set_smps(struct ieee80211_sub_if_data *sdata,
if (sdata->vif.type != NL80211_IFTYPE_STATION)
return -EOPNOTSUPP;
- mutex_lock(&sdata->u.mgd.mtx);
+ sdata_lock(sdata);
err = __ieee80211_request_smps(sdata, smps_mode);
- mutex_unlock(&sdata->u.mgd.mtx);
+ sdata_unlock(sdata);
return err;
}
@@ -313,16 +313,16 @@ static ssize_t ieee80211_if_parse_tkip_mic_test(
case NL80211_IFTYPE_STATION:
fc |= cpu_to_le16(IEEE80211_FCTL_TODS);
/* BSSID SA DA */
- mutex_lock(&sdata->u.mgd.mtx);
+ sdata_lock(sdata);
if (!sdata->u.mgd.associated) {
- mutex_unlock(&sdata->u.mgd.mtx);
+ sdata_unlock(sdata);
dev_kfree_skb(skb);
return -ENOTCONN;
}
memcpy(hdr->addr1, sdata->u.mgd.associated->bssid, ETH_ALEN);
memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN);
memcpy(hdr->addr3, addr, ETH_ALEN);
- mutex_unlock(&sdata->u.mgd.mtx);
+ sdata_unlock(sdata);
break;
default:
dev_kfree_skb(skb);
@@ -471,6 +471,8 @@ __IEEE80211_IF_FILE_W(tsf);
IEEE80211_IF_FILE(peer, u.wds.remote_addr, MAC);
#ifdef CONFIG_MAC80211_MESH
+IEEE80211_IF_FILE(estab_plinks, u.mesh.estab_plinks, ATOMIC);
+
/* Mesh stats attributes */
IEEE80211_IF_FILE(fwded_mcast, u.mesh.mshstats.fwded_mcast, DEC);
IEEE80211_IF_FILE(fwded_unicast, u.mesh.mshstats.fwded_unicast, DEC);
@@ -480,7 +482,6 @@ IEEE80211_IF_FILE(dropped_frames_congestion,
u.mesh.mshstats.dropped_frames_congestion, DEC);
IEEE80211_IF_FILE(dropped_frames_no_route,
u.mesh.mshstats.dropped_frames_no_route, DEC);
-IEEE80211_IF_FILE(estab_plinks, u.mesh.estab_plinks, ATOMIC);
/* Mesh parameters */
IEEE80211_IF_FILE(dot11MeshMaxRetries,
@@ -583,6 +584,7 @@ static void add_wds_files(struct ieee80211_sub_if_data *sdata)
static void add_mesh_files(struct ieee80211_sub_if_data *sdata)
{
DEBUGFS_ADD_MODE(tsf, 0600);
+ DEBUGFS_ADD_MODE(estab_plinks, 0400);
}
static void add_mesh_stats(struct ieee80211_sub_if_data *sdata)
@@ -598,7 +600,6 @@ static void add_mesh_stats(struct ieee80211_sub_if_data *sdata)
MESHSTATS_ADD(dropped_frames_ttl);
MESHSTATS_ADD(dropped_frames_no_route);
MESHSTATS_ADD(dropped_frames_congestion);
- MESHSTATS_ADD(estab_plinks);
#undef MESHSTATS_ADD
}
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 169664c122e2..b931c96a596f 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -146,7 +146,8 @@ static inline int drv_add_interface(struct ieee80211_local *local,
if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
(sdata->vif.type == NL80211_IFTYPE_MONITOR &&
- !(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF))))
+ !(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF) &&
+ !(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE))))
return -EINVAL;
trace_drv_add_interface(local, sdata);
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index af8cee06e4f3..f83534f6a2ee 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -281,13 +281,14 @@ void ieee80211_ba_session_work(struct work_struct *work)
sta, tid, WLAN_BACK_RECIPIENT,
WLAN_REASON_UNSPECIFIED, true);
+ spin_lock_bh(&sta->lock);
+
tid_tx = sta->ampdu_mlme.tid_start_tx[tid];
if (tid_tx) {
/*
* Assign it over to the normal tid_tx array
* where it "goes live".
*/
- spin_lock_bh(&sta->lock);
sta->ampdu_mlme.tid_start_tx[tid] = NULL;
/* could there be a race? */
@@ -300,6 +301,7 @@ void ieee80211_ba_session_work(struct work_struct *work)
ieee80211_tx_ba_session_handle_start(sta, tid);
continue;
}
+ spin_unlock_bh(&sta->lock);
tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
if (tid_tx && test_and_clear_bit(HT_AGG_STATE_WANT_STOP,
@@ -429,9 +431,9 @@ void ieee80211_request_smps_work(struct work_struct *work)
container_of(work, struct ieee80211_sub_if_data,
u.mgd.request_smps_work);
- mutex_lock(&sdata->u.mgd.mtx);
+ sdata_lock(sdata);
__ieee80211_request_smps(sdata, sdata->u.mgd.driver_smps_mode);
- mutex_unlock(&sdata->u.mgd.mtx);
+ sdata_unlock(sdata);
}
void ieee80211_request_smps(struct ieee80211_vif *vif,
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 170f9a7fa319..ea7b9c2c7e66 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -54,7 +54,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
struct beacon_data *presp;
int frame_len;
- lockdep_assert_held(&ifibss->mtx);
+ sdata_assert_lock(sdata);
/* Reset own TSF to allow time synchronization work. */
drv_reset_tsf(local, sdata);
@@ -74,14 +74,14 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
}
presp = rcu_dereference_protected(ifibss->presp,
- lockdep_is_held(&ifibss->mtx));
+ lockdep_is_held(&sdata->wdev.mtx));
rcu_assign_pointer(ifibss->presp, NULL);
if (presp)
kfree_rcu(presp, rcu_head);
sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0;
- cfg80211_chandef_create(&chandef, chan, ifibss->channel_type);
+ chandef = ifibss->chandef;
if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef)) {
chandef.width = NL80211_CHAN_WIDTH_20;
chandef.center_freq1 = chan->center_freq;
@@ -176,6 +176,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
/* add HT capability and information IEs */
if (chandef.width != NL80211_CHAN_WIDTH_20_NOHT &&
+ chandef.width != NL80211_CHAN_WIDTH_5 &&
+ chandef.width != NL80211_CHAN_WIDTH_10 &&
sband->ht_cap.ht_supported) {
pos = ieee80211_ie_build_ht_cap(pos, &sband->ht_cap,
sband->ht_cap.cap);
@@ -263,7 +265,7 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
const struct cfg80211_bss_ies *ies;
u64 tsf;
- lockdep_assert_held(&sdata->u.ibss.mtx);
+ sdata_assert_lock(sdata);
if (beacon_int < 10)
beacon_int = 10;
@@ -298,8 +300,7 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
tsf, false);
}
-static struct sta_info *ieee80211_ibss_finish_sta(struct sta_info *sta,
- bool auth)
+static struct sta_info *ieee80211_ibss_finish_sta(struct sta_info *sta)
__acquires(RCU)
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
@@ -321,26 +322,19 @@ static struct sta_info *ieee80211_ibss_finish_sta(struct sta_info *sta,
/* If it fails, maybe we raced another insertion? */
if (sta_info_insert_rcu(sta))
return sta_info_get(sdata, addr);
- if (auth && !sdata->u.ibss.auth_frame_registrations) {
- ibss_dbg(sdata,
- "TX Auth SA=%pM DA=%pM BSSID=%pM (auth_transaction=1)\n",
- sdata->vif.addr, addr, sdata->u.ibss.bssid);
- ieee80211_send_auth(sdata, 1, WLAN_AUTH_OPEN, 0, NULL, 0,
- addr, sdata->u.ibss.bssid, NULL, 0, 0, 0);
- }
return sta;
}
static struct sta_info *
-ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata,
- const u8 *bssid, const u8 *addr,
- u32 supp_rates, bool auth)
+ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, const u8 *bssid,
+ const u8 *addr, u32 supp_rates)
__acquires(RCU)
{
struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
struct ieee80211_local *local = sdata->local;
struct sta_info *sta;
struct ieee80211_chanctx_conf *chanctx_conf;
+ struct ieee80211_supported_band *sband;
int band;
/*
@@ -380,10 +374,11 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata,
sta->last_rx = jiffies;
/* make sure mandatory rates are always added */
+ sband = local->hw.wiphy->bands[band];
sta->sta.supp_rates[band] = supp_rates |
- ieee80211_mandatory_rates(local, band);
+ ieee80211_mandatory_rates(sband);
- return ieee80211_ibss_finish_sta(sta, auth);
+ return ieee80211_ibss_finish_sta(sta);
}
static void ieee80211_rx_mgmt_deauth_ibss(struct ieee80211_sub_if_data *sdata,
@@ -405,10 +400,8 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata,
size_t len)
{
u16 auth_alg, auth_transaction;
- struct sta_info *sta;
- u8 deauth_frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
- lockdep_assert_held(&sdata->u.ibss.mtx);
+ sdata_assert_lock(sdata);
if (len < 24 + 6)
return;
@@ -423,22 +416,6 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata,
if (auth_alg != WLAN_AUTH_OPEN || auth_transaction != 1)
return;
- sta_info_destroy_addr(sdata, mgmt->sa);
- sta = ieee80211_ibss_add_sta(sdata, mgmt->bssid, mgmt->sa, 0, false);
- rcu_read_unlock();
-
- /*
- * if we have any problem in allocating the new station, we reply with a
- * DEAUTH frame to tell the other end that we had a problem
- */
- if (!sta) {
- ieee80211_send_deauth_disassoc(sdata, sdata->u.ibss.bssid,
- IEEE80211_STYPE_DEAUTH,
- WLAN_REASON_UNSPECIFIED, true,
- deauth_frame_buf);
- return;
- }
-
/*
* IEEE 802.11 standard does not require authentication in IBSS
* networks and most implementations do not seem to use it.
@@ -492,7 +469,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
prev_rates = sta->sta.supp_rates[band];
/* make sure mandatory rates are always added */
sta->sta.supp_rates[band] = supp_rates |
- ieee80211_mandatory_rates(local, band);
+ ieee80211_mandatory_rates(sband);
if (sta->sta.supp_rates[band] != prev_rates) {
ibss_dbg(sdata,
@@ -504,7 +481,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
} else {
rcu_read_unlock();
sta = ieee80211_ibss_add_sta(sdata, mgmt->bssid,
- mgmt->sa, supp_rates, true);
+ mgmt->sa, supp_rates);
}
}
@@ -512,7 +489,9 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
set_sta_flag(sta, WLAN_STA_WME);
if (sta && elems->ht_operation && elems->ht_cap_elem &&
- sdata->u.ibss.channel_type != NL80211_CHAN_NO_HT) {
+ sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT &&
+ sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_5 &&
+ sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_10) {
/* we both use HT */
struct ieee80211_ht_cap htcap_ie;
struct cfg80211_chan_def chandef;
@@ -527,8 +506,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
* fall back to HT20 if we don't use or use
* the other extension channel
*/
- if (cfg80211_get_chandef_type(&chandef) !=
- sdata->u.ibss.channel_type)
+ if (chandef.center_freq1 !=
+ sdata->u.ibss.chandef.center_freq1)
htcap_ie.cap_info &=
cpu_to_le16(~IEEE80211_HT_CAP_SUP_WIDTH_20_40);
@@ -567,7 +546,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
/* different channel */
if (sdata->u.ibss.fixed_channel &&
- sdata->u.ibss.channel != cbss->channel)
+ sdata->u.ibss.chandef.chan != cbss->channel)
goto put_bss;
/* different SSID */
@@ -608,7 +587,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
ieee80211_sta_join_ibss(sdata, bss);
supp_rates = ieee80211_sta_get_rates(local, elems, band, NULL);
ieee80211_ibss_add_sta(sdata, mgmt->bssid, mgmt->sa,
- supp_rates, true);
+ supp_rates);
rcu_read_unlock();
}
@@ -624,6 +603,7 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
struct sta_info *sta;
struct ieee80211_chanctx_conf *chanctx_conf;
+ struct ieee80211_supported_band *sband;
int band;
/*
@@ -658,8 +638,9 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata,
sta->last_rx = jiffies;
/* make sure mandatory rates are always added */
+ sband = local->hw.wiphy->bands[band];
sta->sta.supp_rates[band] = supp_rates |
- ieee80211_mandatory_rates(local, band);
+ ieee80211_mandatory_rates(sband);
spin_lock(&ifibss->incomplete_lock);
list_add(&sta->list, &ifibss->incomplete_stations);
@@ -673,7 +654,7 @@ static int ieee80211_sta_active_ibss(struct ieee80211_sub_if_data *sdata)
int active = 0;
struct sta_info *sta;
- lockdep_assert_held(&sdata->u.ibss.mtx);
+ sdata_assert_lock(sdata);
rcu_read_lock();
@@ -699,7 +680,7 @@ static void ieee80211_sta_merge_ibss(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
- lockdep_assert_held(&ifibss->mtx);
+ sdata_assert_lock(sdata);
mod_timer(&ifibss->timer,
round_jiffies(jiffies + IEEE80211_IBSS_MERGE_INTERVAL));
@@ -730,7 +711,7 @@ static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata)
u16 capability;
int i;
- lockdep_assert_held(&ifibss->mtx);
+ sdata_assert_lock(sdata);
if (ifibss->fixed_bssid) {
memcpy(bssid, ifibss->bssid, ETH_ALEN);
@@ -755,7 +736,7 @@ static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata)
sdata->drop_unencrypted = 0;
__ieee80211_sta_join_ibss(sdata, bssid, sdata->vif.bss_conf.beacon_int,
- ifibss->channel, ifibss->basic_rates,
+ ifibss->chandef.chan, ifibss->basic_rates,
capability, 0, true);
}
@@ -773,7 +754,7 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata)
int active_ibss;
u16 capability;
- lockdep_assert_held(&ifibss->mtx);
+ sdata_assert_lock(sdata);
active_ibss = ieee80211_sta_active_ibss(sdata);
ibss_dbg(sdata, "sta_find_ibss (active_ibss=%d)\n", active_ibss);
@@ -787,7 +768,7 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata)
if (ifibss->fixed_bssid)
bssid = ifibss->bssid;
if (ifibss->fixed_channel)
- chan = ifibss->channel;
+ chan = ifibss->chandef.chan;
if (!is_zero_ether_addr(ifibss->bssid))
bssid = ifibss->bssid;
cbss = cfg80211_get_bss(local->hw.wiphy, chan, bssid,
@@ -843,10 +824,10 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata,
struct beacon_data *presp;
u8 *pos, *end;
- lockdep_assert_held(&ifibss->mtx);
+ sdata_assert_lock(sdata);
presp = rcu_dereference_protected(ifibss->presp,
- lockdep_is_held(&ifibss->mtx));
+ lockdep_is_held(&sdata->wdev.mtx));
if (ifibss->state != IEEE80211_IBSS_MLME_JOINED ||
len < 24 + 2 || !presp)
@@ -930,7 +911,7 @@ void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
mgmt = (struct ieee80211_mgmt *) skb->data;
fc = le16_to_cpu(mgmt->frame_control);
- mutex_lock(&sdata->u.ibss.mtx);
+ sdata_lock(sdata);
if (!sdata->u.ibss.ssid_len)
goto mgmt_out; /* not ready to merge yet */
@@ -953,7 +934,7 @@ void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
}
mgmt_out:
- mutex_unlock(&sdata->u.ibss.mtx);
+ sdata_unlock(sdata);
}
void ieee80211_ibss_work(struct ieee80211_sub_if_data *sdata)
@@ -961,7 +942,7 @@ void ieee80211_ibss_work(struct ieee80211_sub_if_data *sdata)
struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
struct sta_info *sta;
- mutex_lock(&ifibss->mtx);
+ sdata_lock(sdata);
/*
* Work could be scheduled after scan or similar
@@ -978,7 +959,7 @@ void ieee80211_ibss_work(struct ieee80211_sub_if_data *sdata)
list_del(&sta->list);
spin_unlock_bh(&ifibss->incomplete_lock);
- ieee80211_ibss_finish_sta(sta, true);
+ ieee80211_ibss_finish_sta(sta);
rcu_read_unlock();
spin_lock_bh(&ifibss->incomplete_lock);
}
@@ -997,7 +978,7 @@ void ieee80211_ibss_work(struct ieee80211_sub_if_data *sdata)
}
out:
- mutex_unlock(&ifibss->mtx);
+ sdata_unlock(sdata);
}
static void ieee80211_ibss_timer(unsigned long data)
@@ -1014,7 +995,6 @@ void ieee80211_ibss_setup_sdata(struct ieee80211_sub_if_data *sdata)
setup_timer(&ifibss->timer, ieee80211_ibss_timer,
(unsigned long) sdata);
- mutex_init(&ifibss->mtx);
INIT_LIST_HEAD(&ifibss->incomplete_stations);
spin_lock_init(&ifibss->incomplete_lock);
}
@@ -1041,8 +1021,6 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
{
u32 changed = 0;
- mutex_lock(&sdata->u.ibss.mtx);
-
if (params->bssid) {
memcpy(sdata->u.ibss.bssid, params->bssid, ETH_ALEN);
sdata->u.ibss.fixed_bssid = true;
@@ -1057,9 +1035,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
sdata->vif.bss_conf.beacon_int = params->beacon_interval;
- sdata->u.ibss.channel = params->chandef.chan;
- sdata->u.ibss.channel_type =
- cfg80211_get_chandef_type(&params->chandef);
+ sdata->u.ibss.chandef = params->chandef;
sdata->u.ibss.fixed_channel = params->channel_fixed;
if (params->ie) {
@@ -1075,8 +1051,6 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
memcpy(sdata->u.ibss.ssid, params->ssid, params->ssid_len);
sdata->u.ibss.ssid_len = params->ssid_len;
- mutex_unlock(&sdata->u.ibss.mtx);
-
/*
* 802.11n-2009 9.13.3.1: In an IBSS, the HT Protection field is
* reserved, but an HT STA shall protect HT transmissions as though
@@ -1112,8 +1086,6 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata)
struct sta_info *sta;
struct beacon_data *presp;
- mutex_lock(&sdata->u.ibss.mtx);
-
active_ibss = ieee80211_sta_active_ibss(sdata);
if (!active_ibss && !is_zero_ether_addr(ifibss->bssid)) {
@@ -1122,7 +1094,7 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata)
if (ifibss->privacy)
capability |= WLAN_CAPABILITY_PRIVACY;
- cbss = cfg80211_get_bss(local->hw.wiphy, ifibss->channel,
+ cbss = cfg80211_get_bss(local->hw.wiphy, ifibss->chandef.chan,
ifibss->bssid, ifibss->ssid,
ifibss->ssid_len, WLAN_CAPABILITY_IBSS |
WLAN_CAPABILITY_PRIVACY,
@@ -1157,7 +1129,7 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata)
/* remove beacon */
kfree(sdata->u.ibss.ie);
presp = rcu_dereference_protected(ifibss->presp,
- lockdep_is_held(&sdata->u.ibss.mtx));
+ lockdep_is_held(&sdata->wdev.mtx));
RCU_INIT_POINTER(sdata->u.ibss.presp, NULL);
sdata->vif.bss_conf.ibss_joined = false;
sdata->vif.bss_conf.ibss_creator = false;
@@ -1173,7 +1145,5 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata)
del_timer_sync(&sdata->u.ibss.timer);
- mutex_unlock(&sdata->u.ibss.mtx);
-
return 0;
}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 9ca8e3278cc0..8412a303993a 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -94,6 +94,7 @@ struct ieee80211_bss {
#define IEEE80211_MAX_SUPP_RATES 32
u8 supp_rates[IEEE80211_MAX_SUPP_RATES];
size_t supp_rates_len;
+ struct ieee80211_rate *beacon_rate;
/*
* During association, we save an ERP value from a probe response so
@@ -366,7 +367,7 @@ struct ieee80211_mgd_assoc_data {
u8 ssid_len;
u8 supp_rates_len;
bool wmm, uapsd;
- bool have_beacon, need_beacon;
+ bool need_beacon;
bool synced;
bool timeout_started;
@@ -394,7 +395,6 @@ struct ieee80211_if_managed {
bool nullfunc_failed;
bool connection_loss;
- struct mutex mtx;
struct cfg80211_bss *associated;
struct ieee80211_mgd_auth_data *auth_data;
struct ieee80211_mgd_assoc_data *assoc_data;
@@ -405,6 +405,7 @@ struct ieee80211_if_managed {
bool powersave; /* powersave requested for this iface */
bool broken_ap; /* AP is broken -- turn off powersave */
+ bool have_beacon;
u8 dtim_period;
enum ieee80211_smps_mode req_smps, /* requested smps mode */
driver_smps_mode; /* smps mode request */
@@ -488,8 +489,6 @@ struct ieee80211_if_managed {
struct ieee80211_if_ibss {
struct timer_list timer;
- struct mutex mtx;
-
unsigned long last_scan_completed;
u32 basic_rates;
@@ -499,14 +498,12 @@ struct ieee80211_if_ibss {
bool privacy;
bool control_port;
- unsigned int auth_frame_registrations;
u8 bssid[ETH_ALEN] __aligned(2);
u8 ssid[IEEE80211_MAX_SSID_LEN];
u8 ssid_len, ie_len;
u8 *ie;
- struct ieee80211_channel *channel;
- enum nl80211_channel_type channel_type;
+ struct cfg80211_chan_def chandef;
unsigned long ibss_join_req;
/* probe response/beacon for IBSS */
@@ -545,6 +542,7 @@ struct ieee80211_if_mesh {
struct timer_list mesh_path_root_timer;
unsigned long wrkq_flags;
+ unsigned long mbss_changed;
u8 mesh_id[IEEE80211_MAX_MESH_ID_LEN];
size_t mesh_id_len;
@@ -580,8 +578,6 @@ struct ieee80211_if_mesh {
bool accepting_plinks;
int num_gates;
struct beacon_data __rcu *beacon;
- /* just protects beacon updates for now */
- struct mutex mtx;
const u8 *ie;
u8 ie_len;
enum {
@@ -778,6 +774,26 @@ struct ieee80211_sub_if_data *vif_to_sdata(struct ieee80211_vif *p)
return container_of(p, struct ieee80211_sub_if_data, vif);
}
+static inline void sdata_lock(struct ieee80211_sub_if_data *sdata)
+ __acquires(&sdata->wdev.mtx)
+{
+ mutex_lock(&sdata->wdev.mtx);
+ __acquire(&sdata->wdev.mtx);
+}
+
+static inline void sdata_unlock(struct ieee80211_sub_if_data *sdata)
+ __releases(&sdata->wdev.mtx)
+{
+ mutex_unlock(&sdata->wdev.mtx);
+ __release(&sdata->wdev.mtx);
+}
+
+static inline void
+sdata_assert_lock(struct ieee80211_sub_if_data *sdata)
+{
+ lockdep_assert_held(&sdata->wdev.mtx);
+}
+
static inline enum ieee80211_band
ieee80211_get_sdata_band(struct ieee80211_sub_if_data *sdata)
{
@@ -1507,9 +1523,6 @@ static inline void ieee802_11_parse_elems(const u8 *start, size_t len,
ieee802_11_parse_elems_crc(start, len, action, elems, 0, 0);
}
-u32 ieee80211_mandatory_rates(struct ieee80211_local *local,
- enum ieee80211_band band);
-
void ieee80211_dynamic_ps_enable_work(struct work_struct *work);
void ieee80211_dynamic_ps_disable_work(struct work_struct *work);
void ieee80211_dynamic_ps_timer(unsigned long data);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 98d20c0f6fed..cc117591f678 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -159,7 +159,8 @@ static int ieee80211_change_mtu(struct net_device *dev, int new_mtu)
return 0;
}
-static int ieee80211_verify_mac(struct ieee80211_sub_if_data *sdata, u8 *addr)
+static int ieee80211_verify_mac(struct ieee80211_sub_if_data *sdata, u8 *addr,
+ bool check_dup)
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_sub_if_data *iter;
@@ -180,13 +181,16 @@ static int ieee80211_verify_mac(struct ieee80211_sub_if_data *sdata, u8 *addr)
((u64)m[2] << 3*8) | ((u64)m[3] << 2*8) |
((u64)m[4] << 1*8) | ((u64)m[5] << 0*8);
+ if (!check_dup)
+ return ret;
mutex_lock(&local->iflist_mtx);
list_for_each_entry(iter, &local->interfaces, list) {
if (iter == sdata)
continue;
- if (iter->vif.type == NL80211_IFTYPE_MONITOR)
+ if (iter->vif.type == NL80211_IFTYPE_MONITOR &&
+ !(iter->u.mntr_flags & MONITOR_FLAG_ACTIVE))
continue;
m = iter->vif.addr;
@@ -208,12 +212,17 @@ static int ieee80211_change_mac(struct net_device *dev, void *addr)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct sockaddr *sa = addr;
+ bool check_dup = true;
int ret;
if (ieee80211_sdata_running(sdata))
return -EBUSY;
- ret = ieee80211_verify_mac(sdata, sa->sa_data);
+ if (sdata->vif.type == NL80211_IFTYPE_MONITOR &&
+ !(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE))
+ check_dup = false;
+
+ ret = ieee80211_verify_mac(sdata, sa->sa_data, check_dup);
if (ret)
return ret;
@@ -545,7 +554,11 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
break;
}
- if (local->monitors == 0 && local->open_count == 0) {
+ if (sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE) {
+ res = drv_add_interface(local, sdata);
+ if (res)
+ goto err_stop;
+ } else if (local->monitors == 0 && local->open_count == 0) {
res = ieee80211_add_virtual_monitor(local);
if (res)
goto err_stop;
@@ -923,7 +936,11 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
mutex_lock(&local->mtx);
ieee80211_recalc_idle(local);
mutex_unlock(&local->mtx);
- break;
+
+ if (!(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE))
+ break;
+
+ /* fall through */
default:
if (going_down)
drv_remove_interface(local, sdata);
@@ -1072,7 +1089,7 @@ static const struct net_device_ops ieee80211_monitorif_ops = {
.ndo_start_xmit = ieee80211_monitor_start_xmit,
.ndo_set_rx_mode = ieee80211_set_multicast_list,
.ndo_change_mtu = ieee80211_change_mtu,
- .ndo_set_mac_address = eth_mac_addr,
+ .ndo_set_mac_address = ieee80211_change_mac,
.ndo_select_queue = ieee80211_monitor_select_queue,
};
@@ -1747,10 +1764,9 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local)
}
static int netdev_notify(struct notifier_block *nb,
- unsigned long state,
- void *ndev)
+ unsigned long state, void *ptr)
{
- struct net_device *dev = ndev;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct ieee80211_sub_if_data *sdata;
if (state != NETDEV_CHANGENAME)
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 67059b88fea5..e39cc91d0cf1 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -335,12 +335,12 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
switch (cipher) {
case WLAN_CIPHER_SUITE_WEP40:
case WLAN_CIPHER_SUITE_WEP104:
- key->conf.iv_len = WEP_IV_LEN;
- key->conf.icv_len = WEP_ICV_LEN;
+ key->conf.iv_len = IEEE80211_WEP_IV_LEN;
+ key->conf.icv_len = IEEE80211_WEP_ICV_LEN;
break;
case WLAN_CIPHER_SUITE_TKIP:
- key->conf.iv_len = TKIP_IV_LEN;
- key->conf.icv_len = TKIP_ICV_LEN;
+ key->conf.iv_len = IEEE80211_TKIP_IV_LEN;
+ key->conf.icv_len = IEEE80211_TKIP_ICV_LEN;
if (seq) {
for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
key->u.tkip.rx[i].iv32 =
@@ -352,13 +352,13 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
spin_lock_init(&key->u.tkip.txlock);
break;
case WLAN_CIPHER_SUITE_CCMP:
- key->conf.iv_len = CCMP_HDR_LEN;
- key->conf.icv_len = CCMP_MIC_LEN;
+ key->conf.iv_len = IEEE80211_CCMP_HDR_LEN;
+ key->conf.icv_len = IEEE80211_CCMP_MIC_LEN;
if (seq) {
for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++)
- for (j = 0; j < CCMP_PN_LEN; j++)
+ for (j = 0; j < IEEE80211_CCMP_PN_LEN; j++)
key->u.ccmp.rx_pn[i][j] =
- seq[CCMP_PN_LEN - j - 1];
+ seq[IEEE80211_CCMP_PN_LEN - j - 1];
}
/*
* Initialize AES key state here as an optimization so that
@@ -375,9 +375,9 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
key->conf.iv_len = 0;
key->conf.icv_len = sizeof(struct ieee80211_mmie);
if (seq)
- for (j = 0; j < CMAC_PN_LEN; j++)
+ for (j = 0; j < IEEE80211_CMAC_PN_LEN; j++)
key->u.aes_cmac.rx_pn[j] =
- seq[CMAC_PN_LEN - j - 1];
+ seq[IEEE80211_CMAC_PN_LEN - j - 1];
/*
* Initialize AES key state here as an optimization so that
* it does not need to be initialized for every packet.
@@ -740,13 +740,13 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf,
pn = key->u.ccmp.rx_pn[IEEE80211_NUM_TIDS];
else
pn = key->u.ccmp.rx_pn[tid];
- memcpy(seq->ccmp.pn, pn, CCMP_PN_LEN);
+ memcpy(seq->ccmp.pn, pn, IEEE80211_CCMP_PN_LEN);
break;
case WLAN_CIPHER_SUITE_AES_CMAC:
if (WARN_ON(tid != 0))
return;
pn = key->u.aes_cmac.rx_pn;
- memcpy(seq->aes_cmac.pn, pn, CMAC_PN_LEN);
+ memcpy(seq->aes_cmac.pn, pn, IEEE80211_CMAC_PN_LEN);
break;
}
}
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index e8de3e6d7804..036d57e76a5e 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -19,17 +19,6 @@
#define NUM_DEFAULT_KEYS 4
#define NUM_DEFAULT_MGMT_KEYS 2
-#define WEP_IV_LEN 4
-#define WEP_ICV_LEN 4
-#define ALG_CCMP_KEY_LEN 16
-#define CCMP_HDR_LEN 8
-#define CCMP_MIC_LEN 8
-#define CCMP_TK_LEN 16
-#define CCMP_PN_LEN 6
-#define TKIP_IV_LEN 8
-#define TKIP_ICV_LEN 4
-#define CMAC_PN_LEN 6
-
struct ieee80211_local;
struct ieee80211_sub_if_data;
struct sta_info;
@@ -93,13 +82,13 @@ struct ieee80211_key {
* frames and the last counter is used with Robust
* Management frames.
*/
- u8 rx_pn[IEEE80211_NUM_TIDS + 1][CCMP_PN_LEN];
+ u8 rx_pn[IEEE80211_NUM_TIDS + 1][IEEE80211_CCMP_PN_LEN];
struct crypto_cipher *tfm;
u32 replays; /* dot11RSNAStatsCCMPReplays */
} ccmp;
struct {
atomic64_t tx_pn;
- u8 rx_pn[CMAC_PN_LEN];
+ u8 rx_pn[IEEE80211_CMAC_PN_LEN];
struct crypto_cipher *tfm;
u32 replays; /* dot11RSNAStatsCMACReplays */
u32 icverrors; /* dot11RSNAStatsCMACICVErrors */
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 8eae74ac4e1e..091088ac7890 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -331,7 +331,7 @@ static int ieee80211_ifa_changed(struct notifier_block *nb,
return NOTIFY_DONE;
ifmgd = &sdata->u.mgd;
- mutex_lock(&ifmgd->mtx);
+ sdata_lock(sdata);
/* Copy the addresses to the bss_conf list */
ifa = idev->ifa_list;
@@ -349,7 +349,7 @@ static int ieee80211_ifa_changed(struct notifier_block *nb,
ieee80211_bss_info_change_notify(sdata,
BSS_CHANGED_ARP_FILTER);
- mutex_unlock(&ifmgd->mtx);
+ sdata_unlock(sdata);
return NOTIFY_DONE;
}
@@ -686,8 +686,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
return -EINVAL;
#ifdef CONFIG_PM
- if ((hw->wiphy->wowlan.flags || hw->wiphy->wowlan.n_patterns) &&
- (!local->ops->suspend || !local->ops->resume))
+ if (hw->wiphy->wowlan && (!local->ops->suspend || !local->ops->resume))
return -EINVAL;
#endif
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 6952760881c8..447f41bbe744 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -271,8 +271,7 @@ int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata,
*pos++ = ifmsh->mesh_auth_id;
/* Mesh Formation Info - number of neighbors */
neighbors = atomic_read(&ifmsh->estab_plinks);
- /* Number of neighbor mesh STAs or 15 whichever is smaller */
- neighbors = (neighbors > 15) ? 15 : neighbors;
+ neighbors = min_t(int, neighbors, IEEE80211_MAX_MESH_PEERINGS);
*pos++ = neighbors << 1;
/* Mesh capability */
*pos = IEEE80211_MESHCONF_CAPAB_FORWARDING;
@@ -417,7 +416,9 @@ int mesh_add_ht_cap_ie(struct ieee80211_sub_if_data *sdata,
sband = local->hw.wiphy->bands[band];
if (!sband->ht_cap.ht_supported ||
- sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT)
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10)
return 0;
if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_ht_cap))
@@ -573,7 +574,7 @@ static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata)
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
u32 changed;
- ieee80211_sta_expire(sdata, IEEE80211_MESH_PEER_INACTIVITY_LIMIT);
+ ieee80211_sta_expire(sdata, ifmsh->mshcfg.plink_timeout * HZ);
mesh_path_expire(sdata);
changed = mesh_accept_plinks_update(sdata);
@@ -697,38 +698,38 @@ out_free:
}
static int
-ieee80211_mesh_rebuild_beacon(struct ieee80211_if_mesh *ifmsh)
+ieee80211_mesh_rebuild_beacon(struct ieee80211_sub_if_data *sdata)
{
struct beacon_data *old_bcn;
int ret;
- mutex_lock(&ifmsh->mtx);
-
- old_bcn = rcu_dereference_protected(ifmsh->beacon,
- lockdep_is_held(&ifmsh->mtx));
- ret = ieee80211_mesh_build_beacon(ifmsh);
+ old_bcn = rcu_dereference_protected(sdata->u.mesh.beacon,
+ lockdep_is_held(&sdata->wdev.mtx));
+ ret = ieee80211_mesh_build_beacon(&sdata->u.mesh);
if (ret)
/* just reuse old beacon */
- goto out;
+ return ret;
if (old_bcn)
kfree_rcu(old_bcn, rcu_head);
-out:
- mutex_unlock(&ifmsh->mtx);
- return ret;
+ return 0;
}
void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata,
u32 changed)
{
- if (sdata->vif.bss_conf.enable_beacon &&
- (changed & (BSS_CHANGED_BEACON |
- BSS_CHANGED_HT |
- BSS_CHANGED_BASIC_RATES |
- BSS_CHANGED_BEACON_INT)))
- if (ieee80211_mesh_rebuild_beacon(&sdata->u.mesh))
- return;
- ieee80211_bss_info_change_notify(sdata, changed);
+ struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+ unsigned long bits = changed;
+ u32 bit;
+
+ if (!bits)
+ return;
+
+ /* if we race with running work, worst case this work becomes a noop */
+ for_each_set_bit(bit, &bits, sizeof(changed) * BITS_PER_BYTE)
+ set_bit(bit, &ifmsh->mbss_changed);
+ set_bit(MESH_WORK_MBSS_CHANGED, &ifmsh->wrkq_flags);
+ ieee80211_queue_work(&sdata->local->hw, &sdata->work);
}
int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata)
@@ -740,7 +741,6 @@ int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata)
BSS_CHANGED_HT |
BSS_CHANGED_BASIC_RATES |
BSS_CHANGED_BEACON_INT;
- enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
local->fif_other_bss++;
/* mesh ifaces must set allmulti to forward mcast traffic */
@@ -748,7 +748,6 @@ int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata)
ieee80211_configure_filter(local);
ifmsh->mesh_cc_id = 0; /* Disabled */
- ifmsh->mesh_auth_id = 0; /* Disabled */
/* register sync ops from extensible synchronization framework */
ifmsh->sync_ops = ieee80211_mesh_sync_ops_get(ifmsh->mesh_sp_id);
ifmsh->adjusting_tbtt = false;
@@ -759,8 +758,6 @@ int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata)
sdata->vif.bss_conf.ht_operation_mode =
ifmsh->mshcfg.ht_opmode;
sdata->vif.bss_conf.enable_beacon = true;
- sdata->vif.bss_conf.basic_rates =
- ieee80211_mandatory_rates(local, band);
changed |= ieee80211_mps_local_status_update(sdata);
@@ -788,12 +785,10 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata)
sdata->vif.bss_conf.enable_beacon = false;
clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state);
ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED);
- mutex_lock(&ifmsh->mtx);
bcn = rcu_dereference_protected(ifmsh->beacon,
- lockdep_is_held(&ifmsh->mtx));
+ lockdep_is_held(&sdata->wdev.mtx));
rcu_assign_pointer(ifmsh->beacon, NULL);
kfree_rcu(bcn, rcu_head);
- mutex_unlock(&ifmsh->mtx);
/* flush STAs and mpaths on this iface */
sta_info_flush(sdata);
@@ -806,14 +801,10 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata)
del_timer_sync(&sdata->u.mesh.housekeeping_timer);
del_timer_sync(&sdata->u.mesh.mesh_path_root_timer);
del_timer_sync(&sdata->u.mesh.mesh_path_timer);
- /*
- * If the timer fired while we waited for it, it will have
- * requeued the work. Now the work will be running again
- * but will not rearm the timer again because it checks
- * whether the interface is running, which, at this point,
- * it no longer is.
- */
- cancel_work_sync(&sdata->work);
+
+ /* clear any mesh work (for next join) we may have accrued */
+ ifmsh->wrkq_flags = 0;
+ ifmsh->mbss_changed = 0;
local->fif_other_bss--;
atomic_dec(&local->iff_allmultis);
@@ -954,6 +945,12 @@ void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
struct ieee80211_mgmt *mgmt;
u16 stype;
+ sdata_lock(sdata);
+
+ /* mesh already went down */
+ if (!sdata->wdev.mesh_id_len)
+ goto out;
+
rx_status = IEEE80211_SKB_RXCB(skb);
mgmt = (struct ieee80211_mgmt *) skb->data;
stype = le16_to_cpu(mgmt->frame_control) & IEEE80211_FCTL_STYPE;
@@ -971,12 +968,42 @@ void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
ieee80211_mesh_rx_mgmt_action(sdata, mgmt, skb->len, rx_status);
break;
}
+out:
+ sdata_unlock(sdata);
+}
+
+static void mesh_bss_info_changed(struct ieee80211_sub_if_data *sdata)
+{
+ struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+ u32 bit, changed = 0;
+
+ for_each_set_bit(bit, &ifmsh->mbss_changed,
+ sizeof(changed) * BITS_PER_BYTE) {
+ clear_bit(bit, &ifmsh->mbss_changed);
+ changed |= BIT(bit);
+ }
+
+ if (sdata->vif.bss_conf.enable_beacon &&
+ (changed & (BSS_CHANGED_BEACON |
+ BSS_CHANGED_HT |
+ BSS_CHANGED_BASIC_RATES |
+ BSS_CHANGED_BEACON_INT)))
+ if (ieee80211_mesh_rebuild_beacon(sdata))
+ return;
+
+ ieee80211_bss_info_change_notify(sdata, changed);
}
void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+ sdata_lock(sdata);
+
+ /* mesh already went down */
+ if (!sdata->wdev.mesh_id_len)
+ goto out;
+
if (ifmsh->preq_queue_len &&
time_after(jiffies,
ifmsh->last_preq + msecs_to_jiffies(ifmsh->mshcfg.dot11MeshHWMPpreqMinInterval)))
@@ -996,6 +1023,11 @@ void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata)
if (test_and_clear_bit(MESH_WORK_DRIFT_ADJUST, &ifmsh->wrkq_flags))
mesh_sync_adjust_tbtt(sdata);
+
+ if (test_and_clear_bit(MESH_WORK_MBSS_CHANGED, &ifmsh->wrkq_flags))
+ mesh_bss_info_changed(sdata);
+out:
+ sdata_unlock(sdata);
}
void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local)
@@ -1041,7 +1073,6 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata)
spin_lock_init(&ifmsh->mesh_preq_queue_lock);
spin_lock_init(&ifmsh->sync_offset_lock);
RCU_INIT_POINTER(ifmsh->beacon, NULL);
- mutex_init(&ifmsh->mtx);
sdata->vif.bss_conf.bssid = zero_addr;
}
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index da158774eebb..2bc7fd2f787d 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -58,6 +58,7 @@ enum mesh_path_flags {
* @MESH_WORK_ROOT: the mesh root station needs to send a frame
* @MESH_WORK_DRIFT_ADJUST: time to compensate for clock drift relative to other
* mesh nodes
+ * @MESH_WORK_MBSS_CHANGED: rebuild beacon and notify driver of BSS changes
*/
enum mesh_deferred_task_flags {
MESH_WORK_HOUSEKEEPING,
@@ -65,6 +66,7 @@ enum mesh_deferred_task_flags {
MESH_WORK_GROW_MPP_TABLE,
MESH_WORK_ROOT,
MESH_WORK_DRIFT_ADJUST,
+ MESH_WORK_MBSS_CHANGED,
};
/**
@@ -188,7 +190,6 @@ struct mesh_rmc {
u32 idx_mask;
};
-#define IEEE80211_MESH_PEER_INACTIVITY_LIMIT (1800 * HZ)
#define IEEE80211_MESH_HOUSEKEEPING_INTERVAL (60 * HZ)
#define MESH_PATH_EXPIRE (600 * HZ)
@@ -324,14 +325,14 @@ static inline
u32 mesh_plink_inc_estab_count(struct ieee80211_sub_if_data *sdata)
{
atomic_inc(&sdata->u.mesh.estab_plinks);
- return mesh_accept_plinks_update(sdata);
+ return mesh_accept_plinks_update(sdata) | BSS_CHANGED_BEACON;
}
static inline
u32 mesh_plink_dec_estab_count(struct ieee80211_sub_if_data *sdata)
{
atomic_dec(&sdata->u.mesh.estab_plinks);
- return mesh_accept_plinks_update(sdata);
+ return mesh_accept_plinks_update(sdata) | BSS_CHANGED_BEACON;
}
static inline int mesh_plink_free_count(struct ieee80211_sub_if_data *sdata)
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 09bebed99416..02c05fa15c20 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -154,8 +154,14 @@ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata)
u16 ht_opmode;
bool non_ht_sta = false, ht20_sta = false;
- if (sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT)
+ switch (sdata->vif.bss_conf.chandef.width) {
+ case NL80211_CHAN_WIDTH_20_NOHT:
+ case NL80211_CHAN_WIDTH_5:
+ case NL80211_CHAN_WIDTH_10:
return 0;
+ default:
+ break;
+ }
rcu_read_lock();
list_for_each_entry_rcu(sta, &local->sta_list, list) {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 741448b30825..ae31968d42d3 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -91,41 +91,6 @@ MODULE_PARM_DESC(probe_wait_ms,
#define IEEE80211_SIGNAL_AVE_MIN_COUNT 4
/*
- * All cfg80211 functions have to be called outside a locked
- * section so that they can acquire a lock themselves... This
- * is much simpler than queuing up things in cfg80211, but we
- * do need some indirection for that here.
- */
-enum rx_mgmt_action {
- /* no action required */
- RX_MGMT_NONE,
-
- /* caller must call cfg80211_send_deauth() */
- RX_MGMT_CFG80211_DEAUTH,
-
- /* caller must call cfg80211_send_disassoc() */
- RX_MGMT_CFG80211_DISASSOC,
-
- /* caller must call cfg80211_send_rx_auth() */
- RX_MGMT_CFG80211_RX_AUTH,
-
- /* caller must call cfg80211_send_rx_assoc() */
- RX_MGMT_CFG80211_RX_ASSOC,
-
- /* caller must call cfg80211_send_assoc_timeout() */
- RX_MGMT_CFG80211_ASSOC_TIMEOUT,
-
- /* used when a processed beacon causes a deauth */
- RX_MGMT_CFG80211_TX_DEAUTH,
-};
-
-/* utils */
-static inline void ASSERT_MGD_MTX(struct ieee80211_if_managed *ifmgd)
-{
- lockdep_assert_held(&ifmgd->mtx);
-}
-
-/*
* We can have multiple work items (and connection probing)
* scheduling this timer, but we need to take care to only
* reschedule it when it should fire _earlier_ than it was
@@ -135,13 +100,14 @@ static inline void ASSERT_MGD_MTX(struct ieee80211_if_managed *ifmgd)
* has happened -- the work that runs from this timer will
* do that.
*/
-static void run_again(struct ieee80211_if_managed *ifmgd, unsigned long timeout)
+static void run_again(struct ieee80211_sub_if_data *sdata,
+ unsigned long timeout)
{
- ASSERT_MGD_MTX(ifmgd);
+ sdata_assert_lock(sdata);
- if (!timer_pending(&ifmgd->timer) ||
- time_before(timeout, ifmgd->timer.expires))
- mod_timer(&ifmgd->timer, timeout);
+ if (!timer_pending(&sdata->u.mgd.timer) ||
+ time_before(timeout, sdata->u.mgd.timer.expires))
+ mod_timer(&sdata->u.mgd.timer, timeout);
}
void ieee80211_sta_reset_beacon_monitor(struct ieee80211_sub_if_data *sdata)
@@ -224,6 +190,12 @@ static u32 chandef_downgrade(struct cfg80211_chan_def *c)
c->width = NL80211_CHAN_WIDTH_20_NOHT;
ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT;
break;
+ case NL80211_CHAN_WIDTH_5:
+ case NL80211_CHAN_WIDTH_10:
+ WARN_ON_ONCE(1);
+ /* keep c->width */
+ ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT;
+ break;
}
WARN_ON_ONCE(!cfg80211_chandef_valid(c));
@@ -652,7 +624,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
struct ieee80211_channel *chan;
u32 rates = 0;
- lockdep_assert_held(&ifmgd->mtx);
+ sdata_assert_lock(sdata);
rcu_read_lock();
chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
@@ -914,6 +886,10 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local,
IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT |
IEEE80211_TX_INTFL_OFFCHAN_TX_OK;
+
+ if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
+ IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
+
if (ifmgd->flags & (IEEE80211_STA_BEACON_POLL |
IEEE80211_STA_CONNECTION_POLL))
IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_USE_MINRATE;
@@ -962,7 +938,7 @@ static void ieee80211_chswitch_work(struct work_struct *work)
if (!ieee80211_sdata_running(sdata))
return;
- mutex_lock(&ifmgd->mtx);
+ sdata_lock(sdata);
if (!ifmgd->associated)
goto out;
@@ -985,7 +961,7 @@ static void ieee80211_chswitch_work(struct work_struct *work)
IEEE80211_QUEUE_STOP_REASON_CSA);
out:
ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED;
- mutex_unlock(&ifmgd->mtx);
+ sdata_unlock(sdata);
}
void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success)
@@ -1036,7 +1012,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
const struct ieee80211_ht_operation *ht_oper;
int secondary_channel_offset = -1;
- ASSERT_MGD_MTX(ifmgd);
+ sdata_assert_lock(sdata);
if (!cbss)
return;
@@ -1390,6 +1366,9 @@ static bool ieee80211_powersave_allowed(struct ieee80211_sub_if_data *sdata)
IEEE80211_STA_CONNECTION_POLL))
return false;
+ if (!mgd->have_beacon)
+ return false;
+
rcu_read_lock();
sta = sta_info_get(sdata, mgd->bssid);
if (sta)
@@ -1798,7 +1777,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata,
ieee80211_led_assoc(local, 1);
- if (sdata->u.mgd.assoc_data->have_beacon) {
+ if (sdata->u.mgd.have_beacon) {
/*
* If the AP is buggy we may get here with no DTIM period
* known, so assume it's 1 which is the only safe assumption
@@ -1806,8 +1785,10 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata,
* probably just won't work at all.
*/
bss_conf->dtim_period = sdata->u.mgd.dtim_period ?: 1;
- bss_info_changed |= BSS_CHANGED_DTIM_PERIOD;
+ bss_conf->beacon_rate = bss->beacon_rate;
+ bss_info_changed |= BSS_CHANGED_BEACON_INFO;
} else {
+ bss_conf->beacon_rate = NULL;
bss_conf->dtim_period = 0;
}
@@ -1842,7 +1823,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
u32 changed = 0;
- ASSERT_MGD_MTX(ifmgd);
+ sdata_assert_lock(sdata);
if (WARN_ON_ONCE(tx && !frame_buf))
return;
@@ -1930,6 +1911,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
del_timer_sync(&sdata->u.mgd.chswitch_timer);
sdata->vif.bss_conf.dtim_period = 0;
+ sdata->vif.bss_conf.beacon_rate = NULL;
+
+ ifmgd->have_beacon = false;
ifmgd->flags = 0;
ieee80211_vif_release_channel(sdata);
@@ -2051,7 +2035,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
}
ifmgd->probe_timeout = jiffies + msecs_to_jiffies(probe_wait_ms);
- run_again(ifmgd, ifmgd->probe_timeout);
+ run_again(sdata, ifmgd->probe_timeout);
if (sdata->local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
ieee80211_flush_queues(sdata->local, sdata);
}
@@ -2065,7 +2049,7 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata,
if (!ieee80211_sdata_running(sdata))
return;
- mutex_lock(&ifmgd->mtx);
+ sdata_lock(sdata);
if (!ifmgd->associated)
goto out;
@@ -2119,7 +2103,7 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata,
ifmgd->probe_send_count = 0;
ieee80211_mgd_probe_ap_send(sdata);
out:
- mutex_unlock(&ifmgd->mtx);
+ sdata_unlock(sdata);
}
struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
@@ -2135,7 +2119,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION))
return NULL;
- ASSERT_MGD_MTX(ifmgd);
+ sdata_assert_lock(sdata);
if (ifmgd->associated)
cbss = ifmgd->associated;
@@ -2168,9 +2152,9 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
- mutex_lock(&ifmgd->mtx);
+ sdata_lock(sdata);
if (!ifmgd->associated) {
- mutex_unlock(&ifmgd->mtx);
+ sdata_unlock(sdata);
return;
}
@@ -2181,13 +2165,10 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
ieee80211_wake_queues_by_reason(&sdata->local->hw,
IEEE80211_MAX_QUEUE_MAP,
IEEE80211_QUEUE_STOP_REASON_CSA);
- mutex_unlock(&ifmgd->mtx);
- /*
- * must be outside lock due to cfg80211,
- * but that's not a problem.
- */
- cfg80211_send_deauth(sdata->dev, frame_buf, IEEE80211_DEAUTH_FRAME_LEN);
+ cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
+ IEEE80211_DEAUTH_FRAME_LEN);
+ sdata_unlock(sdata);
}
static void ieee80211_beacon_connection_loss_work(struct work_struct *work)
@@ -2254,7 +2235,7 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata,
{
struct ieee80211_mgd_auth_data *auth_data = sdata->u.mgd.auth_data;
- lockdep_assert_held(&sdata->u.mgd.mtx);
+ sdata_assert_lock(sdata);
if (!assoc) {
sta_info_destroy_addr(sdata, auth_data->bss->bssid);
@@ -2295,27 +2276,26 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata,
auth_data->key_idx, tx_flags);
}
-static enum rx_mgmt_action __must_check
-ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
- struct ieee80211_mgmt *mgmt, size_t len)
+static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_mgmt *mgmt, size_t len)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
u8 bssid[ETH_ALEN];
u16 auth_alg, auth_transaction, status_code;
struct sta_info *sta;
- lockdep_assert_held(&ifmgd->mtx);
+ sdata_assert_lock(sdata);
if (len < 24 + 6)
- return RX_MGMT_NONE;
+ return;
if (!ifmgd->auth_data || ifmgd->auth_data->done)
- return RX_MGMT_NONE;
+ return;
memcpy(bssid, ifmgd->auth_data->bss->bssid, ETH_ALEN);
if (!ether_addr_equal(bssid, mgmt->bssid))
- return RX_MGMT_NONE;
+ return;
auth_alg = le16_to_cpu(mgmt->u.auth.auth_alg);
auth_transaction = le16_to_cpu(mgmt->u.auth.auth_transaction);
@@ -2327,14 +2307,15 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
mgmt->sa, auth_alg, ifmgd->auth_data->algorithm,
auth_transaction,
ifmgd->auth_data->expected_transaction);
- return RX_MGMT_NONE;
+ return;
}
if (status_code != WLAN_STATUS_SUCCESS) {
sdata_info(sdata, "%pM denied authentication (status %d)\n",
mgmt->sa, status_code);
ieee80211_destroy_auth_data(sdata, false);
- return RX_MGMT_CFG80211_RX_AUTH;
+ cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
+ return;
}
switch (ifmgd->auth_data->algorithm) {
@@ -2347,20 +2328,20 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
if (ifmgd->auth_data->expected_transaction != 4) {
ieee80211_auth_challenge(sdata, mgmt, len);
/* need another frame */
- return RX_MGMT_NONE;
+ return;
}
break;
default:
WARN_ONCE(1, "invalid auth alg %d",
ifmgd->auth_data->algorithm);
- return RX_MGMT_NONE;
+ return;
}
sdata_info(sdata, "authenticated\n");
ifmgd->auth_data->done = true;
ifmgd->auth_data->timeout = jiffies + IEEE80211_AUTH_WAIT_ASSOC;
ifmgd->auth_data->timeout_started = true;
- run_again(ifmgd, ifmgd->auth_data->timeout);
+ run_again(sdata, ifmgd->auth_data->timeout);
if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE &&
ifmgd->auth_data->expected_transaction != 2) {
@@ -2368,7 +2349,8 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
* Report auth frame to user space for processing since another
* round of Authentication frames is still needed.
*/
- return RX_MGMT_CFG80211_RX_AUTH;
+ cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
+ return;
}
/* move station state to auth */
@@ -2384,30 +2366,29 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
}
mutex_unlock(&sdata->local->sta_mtx);
- return RX_MGMT_CFG80211_RX_AUTH;
+ cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
+ return;
out_err:
mutex_unlock(&sdata->local->sta_mtx);
/* ignore frame -- wait for timeout */
- return RX_MGMT_NONE;
}
-static enum rx_mgmt_action __must_check
-ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata,
- struct ieee80211_mgmt *mgmt, size_t len)
+static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_mgmt *mgmt, size_t len)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
const u8 *bssid = NULL;
u16 reason_code;
- lockdep_assert_held(&ifmgd->mtx);
+ sdata_assert_lock(sdata);
if (len < 24 + 2)
- return RX_MGMT_NONE;
+ return;
if (!ifmgd->associated ||
!ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid))
- return RX_MGMT_NONE;
+ return;
bssid = ifmgd->associated->bssid;
@@ -2418,25 +2399,24 @@ ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata,
ieee80211_set_disassoc(sdata, 0, 0, false, NULL);
- return RX_MGMT_CFG80211_DEAUTH;
+ cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
}
-static enum rx_mgmt_action __must_check
-ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata,
- struct ieee80211_mgmt *mgmt, size_t len)
+static void ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_mgmt *mgmt, size_t len)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
u16 reason_code;
- lockdep_assert_held(&ifmgd->mtx);
+ sdata_assert_lock(sdata);
if (len < 24 + 2)
- return RX_MGMT_NONE;
+ return;
if (!ifmgd->associated ||
!ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid))
- return RX_MGMT_NONE;
+ return;
reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code);
@@ -2445,7 +2425,7 @@ ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata,
ieee80211_set_disassoc(sdata, 0, 0, false, NULL);
- return RX_MGMT_CFG80211_DISASSOC;
+ cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
}
static void ieee80211_get_rates(struct ieee80211_supported_band *sband,
@@ -2495,7 +2475,7 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
{
struct ieee80211_mgd_assoc_data *assoc_data = sdata->u.mgd.assoc_data;
- lockdep_assert_held(&sdata->u.mgd.mtx);
+ sdata_assert_lock(sdata);
if (!assoc) {
sta_info_destroy_addr(sdata, assoc_data->bss->bssid);
@@ -2749,10 +2729,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
return ret;
}
-static enum rx_mgmt_action __must_check
-ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
- struct ieee80211_mgmt *mgmt, size_t len,
- struct cfg80211_bss **bss)
+static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_mgmt *mgmt,
+ size_t len)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data;
@@ -2760,13 +2739,14 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
struct ieee802_11_elems elems;
u8 *pos;
bool reassoc;
+ struct cfg80211_bss *bss;
- lockdep_assert_held(&ifmgd->mtx);
+ sdata_assert_lock(sdata);
if (!assoc_data)
- return RX_MGMT_NONE;
+ return;
if (!ether_addr_equal(assoc_data->bss->bssid, mgmt->bssid))
- return RX_MGMT_NONE;
+ return;
/*
* AssocResp and ReassocResp have identical structure, so process both
@@ -2774,7 +2754,7 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
*/
if (len < 24 + 6)
- return RX_MGMT_NONE;
+ return;
reassoc = ieee80211_is_reassoc_req(mgmt->frame_control);
capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info);
@@ -2801,22 +2781,22 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
assoc_data->timeout = jiffies + msecs_to_jiffies(ms);
assoc_data->timeout_started = true;
if (ms > IEEE80211_ASSOC_TIMEOUT)
- run_again(ifmgd, assoc_data->timeout);
- return RX_MGMT_NONE;
+ run_again(sdata, assoc_data->timeout);
+ return;
}
- *bss = assoc_data->bss;
+ bss = assoc_data->bss;
if (status_code != WLAN_STATUS_SUCCESS) {
sdata_info(sdata, "%pM denied association (code=%d)\n",
mgmt->sa, status_code);
ieee80211_destroy_assoc_data(sdata, false);
} else {
- if (!ieee80211_assoc_success(sdata, *bss, mgmt, len)) {
+ if (!ieee80211_assoc_success(sdata, bss, mgmt, len)) {
/* oops -- internal error -- send timeout for now */
ieee80211_destroy_assoc_data(sdata, false);
- cfg80211_put_bss(sdata->local->hw.wiphy, *bss);
- return RX_MGMT_CFG80211_ASSOC_TIMEOUT;
+ cfg80211_assoc_timeout(sdata->dev, bss);
+ return;
}
sdata_info(sdata, "associated\n");
@@ -2828,7 +2808,7 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
ieee80211_destroy_assoc_data(sdata, true);
}
- return RX_MGMT_CFG80211_RX_ASSOC;
+ cfg80211_rx_assoc_resp(sdata->dev, bss, (u8 *)mgmt, len);
}
static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
@@ -2840,23 +2820,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
int freq;
struct ieee80211_bss *bss;
struct ieee80211_channel *channel;
- bool need_ps = false;
-
- lockdep_assert_held(&sdata->u.mgd.mtx);
- if ((sdata->u.mgd.associated &&
- ether_addr_equal(mgmt->bssid, sdata->u.mgd.associated->bssid)) ||
- (sdata->u.mgd.assoc_data &&
- ether_addr_equal(mgmt->bssid,
- sdata->u.mgd.assoc_data->bss->bssid))) {
- /* not previously set so we may need to recalc */
- need_ps = sdata->u.mgd.associated && !sdata->u.mgd.dtim_period;
-
- if (elems->tim && !elems->parse_error) {
- const struct ieee80211_tim_ie *tim_ie = elems->tim;
- sdata->u.mgd.dtim_period = tim_ie->dtim_period;
- }
- }
+ sdata_assert_lock(sdata);
if (elems->ds_params)
freq = ieee80211_channel_to_frequency(elems->ds_params[0],
@@ -2871,19 +2836,15 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems,
channel);
- if (bss)
+ if (bss) {
ieee80211_rx_bss_put(local, bss);
+ sdata->vif.bss_conf.beacon_rate = bss->beacon_rate;
+ }
if (!sdata->u.mgd.associated ||
!ether_addr_equal(mgmt->bssid, sdata->u.mgd.associated->bssid))
return;
- if (need_ps) {
- mutex_lock(&local->iflist_mtx);
- ieee80211_recalc_ps(local, -1);
- mutex_unlock(&local->iflist_mtx);
- }
-
ieee80211_sta_process_chanswitch(sdata, rx_status->mactime,
elems, true);
@@ -2901,7 +2862,7 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata,
ifmgd = &sdata->u.mgd;
- ASSERT_MGD_MTX(ifmgd);
+ sdata_assert_lock(sdata);
if (!ether_addr_equal(mgmt->da, sdata->vif.addr))
return; /* ignore ProbeResp to foreign address */
@@ -2926,7 +2887,7 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata,
ifmgd->auth_data->tries = 0;
ifmgd->auth_data->timeout = jiffies;
ifmgd->auth_data->timeout_started = true;
- run_again(ifmgd, ifmgd->auth_data->timeout);
+ run_again(sdata, ifmgd->auth_data->timeout);
}
}
@@ -2951,10 +2912,9 @@ static const u64 care_about_ies =
(1ULL << WLAN_EID_HT_CAPABILITY) |
(1ULL << WLAN_EID_HT_OPERATION);
-static enum rx_mgmt_action
-ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
- struct ieee80211_mgmt *mgmt, size_t len,
- u8 *deauth_buf, struct ieee80211_rx_status *rx_status)
+static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_mgmt *mgmt, size_t len,
+ struct ieee80211_rx_status *rx_status)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf;
@@ -2969,24 +2929,25 @@ ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
u8 erp_value = 0;
u32 ncrc;
u8 *bssid;
+ u8 deauth_buf[IEEE80211_DEAUTH_FRAME_LEN];
- lockdep_assert_held(&ifmgd->mtx);
+ sdata_assert_lock(sdata);
/* Process beacon from the current BSS */
baselen = (u8 *) mgmt->u.beacon.variable - (u8 *) mgmt;
if (baselen > len)
- return RX_MGMT_NONE;
+ return;
rcu_read_lock();
chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
if (!chanctx_conf) {
rcu_read_unlock();
- return RX_MGMT_NONE;
+ return;
}
if (rx_status->freq != chanctx_conf->def.chan->center_freq) {
rcu_read_unlock();
- return RX_MGMT_NONE;
+ return;
}
chan = chanctx_conf->def.chan;
rcu_read_unlock();
@@ -2997,7 +2958,11 @@ ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
len - baselen, false, &elems);
ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems);
- ifmgd->assoc_data->have_beacon = true;
+ if (elems.tim && !elems.parse_error) {
+ const struct ieee80211_tim_ie *tim_ie = elems.tim;
+ ifmgd->dtim_period = tim_ie->dtim_period;
+ }
+ ifmgd->have_beacon = true;
ifmgd->assoc_data->need_beacon = false;