aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorIngo Molnar <mingo@elte.hu>2009-03-30 23:53:32 +0200
committerIngo Molnar <mingo@elte.hu>2009-03-30 23:53:32 +0200
commit65fb0d23fcddd8697c871047b700c78817bdaa43 (patch)
tree119e6e5f276622c4c862f6c9b6d795264ba1603a /net
parent8c083f081d0014057901c68a0a3e0f8ca7ac8d23 (diff)
parentdfbbe89e197a77f2c8046a51c74e33e35f878080 (diff)
downloadlinux-2.6.38-lt-ux500-65fb0d23fcddd8697c871047b700c78817bdaa43.tar.gz
Merge branch 'linus' into cpumask-for-linus
Conflicts: arch/x86/kernel/cpu/common.c
Diffstat (limited to 'net')
-rw-r--r--net/802/psnap.c15
-rw-r--r--net/802/tr.c2
-rw-r--r--net/8021q/vlan.c4
-rw-r--r--net/8021q/vlan_core.c53
-rw-r--r--net/9p/trans_fd.c2
-rw-r--r--net/Kconfig18
-rw-r--r--net/Makefile1
-rw-r--r--net/appletalk/ddp.c16
-rw-r--r--net/appletalk/dev.c10
-rw-r--r--net/atm/br2684.c58
-rw-r--r--net/atm/clip.c39
-rw-r--r--net/atm/lec.c66
-rw-r--r--net/atm/lec.h1
-rw-r--r--net/atm/mpc.c32
-rw-r--r--net/atm/mpc.h5
-rw-r--r--net/ax25/af_ax25.c9
-rw-r--r--net/ax25/ax25_iface.c13
-rw-r--r--net/bluetooth/af_bluetooth.c17
-rw-r--r--net/bluetooth/cmtp/core.c3
-rw-r--r--net/bluetooth/hci_conn.c64
-rw-r--r--net/bluetooth/hci_core.c3
-rw-r--r--net/bluetooth/hci_event.c26
-rw-r--r--net/bluetooth/hci_sysfs.c2
-rw-r--r--net/bluetooth/l2cap.c602
-rw-r--r--net/bluetooth/rfcomm/core.c179
-rw-r--r--net/bluetooth/rfcomm/sock.c189
-rw-r--r--net/bluetooth/rfcomm/tty.c5
-rw-r--r--net/bluetooth/sco.c57
-rw-r--r--net/bridge/br_if.c1
-rw-r--r--net/bridge/br_netfilter.c2
-rw-r--r--net/bridge/br_netlink.c3
-rw-r--r--net/bridge/netfilter/ebt_log.c2
-rw-r--r--net/bridge/netfilter/ebt_ulog.c14
-rw-r--r--net/bridge/netfilter/ebtable_broute.c1
-rw-r--r--net/bridge/netfilter/ebtable_filter.c1
-rw-r--r--net/bridge/netfilter/ebtable_nat.c1
-rw-r--r--net/can/af_can.c5
-rw-r--r--net/can/raw.c3
-rw-r--r--net/compat.c19
-rw-r--r--net/core/Makefile3
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dev.c268
-rw-r--r--net/core/drop_monitor.c263
-rw-r--r--net/core/ethtool.c58
-rw-r--r--net/core/fib_rules.c3
-rw-r--r--net/core/neighbour.c15
-rw-r--r--net/core/net-sysfs.c2
-rw-r--r--net/core/net-traces.c29
-rw-r--r--net/core/pktgen.c18
-rw-r--r--net/core/rtnetlink.c9
-rw-r--r--net/core/skbuff.c235
-rw-r--r--net/core/sock.c95
-rw-r--r--net/core/sysctl_net_core.c1
-rw-r--r--net/core/utils.c1
-rw-r--r--net/dccp/ackvec.h3
-rw-r--r--net/dccp/dccp.h26
-rw-r--r--net/dccp/feat.c232
-rw-r--r--net/dccp/feat.h21
-rw-r--r--net/dccp/minisocks.c11
-rw-r--r--net/dccp/options.c8
-rw-r--r--net/dccp/output.c37
-rw-r--r--net/dccp/proto.c2
-rw-r--r--net/dccp/sysctl.c43
-rw-r--r--net/decnet/af_decnet.c25
-rw-r--r--net/decnet/dn_dev.c6
-rw-r--r--net/decnet/dn_route.c8
-rw-r--r--net/decnet/dn_table.c3
-rw-r--r--net/decnet/sysctl_net_decnet.c2
-rw-r--r--net/dsa/Kconfig6
-rw-r--r--net/dsa/dsa.c177
-rw-r--r--net/dsa/dsa_priv.h97
-rw-r--r--net/dsa/mv88e6060.c12
-rw-r--r--net/dsa/mv88e6123_61_65.c92
-rw-r--r--net/dsa/mv88e6131.c98
-rw-r--r--net/dsa/slave.c34
-rw-r--r--net/dsa/tag_dsa.c34
-rw-r--r--net/dsa/tag_edsa.c34
-rw-r--r--net/dsa/tag_trailer.c14
-rw-r--r--net/econet/af_econet.c4
-rw-r--r--net/ipv4/Kconfig52
-rw-r--r--net/ipv4/af_inet.c28
-rw-r--r--net/ipv4/arp.c13
-rw-r--r--net/ipv4/cipso_ipv4.c130
-rw-r--r--net/ipv4/devinet.c12
-rw-r--r--net/ipv4/fib_frontend.c2
-rw-r--r--net/ipv4/fib_semantics.c5
-rw-r--r--net/ipv4/icmp.c2
-rw-r--r--net/ipv4/inet_connection_sock.c42
-rw-r--r--net/ipv4/inet_fragment.c1
-rw-r--r--net/ipv4/inet_hashtables.c12
-rw-r--r--net/ipv4/ip_fragment.c3
-rw-r--r--net/ipv4/ip_gre.c136
-rw-r--r--net/ipv4/ip_output.c6
-rw-r--r--net/ipv4/ipconfig.c8
-rw-r--r--net/ipv4/ipip.c7
-rw-r--r--net/ipv4/ipmr.c464
-rw-r--r--net/ipv4/netfilter/Kconfig30
-rw-r--r--net/ipv4/netfilter/Makefile2
-rw-r--r--net/ipv4/netfilter/arp_tables.c155
-rw-r--r--net/ipv4/netfilter/arptable_filter.c2
-rw-r--r--net/ipv4/netfilter/ip_queue.c2
-rw-r--r--net/ipv4/netfilter/ip_tables.c138
-rw-r--r--net/ipv4/netfilter/ipt_LOG.c2
-rw-r--r--net/ipv4/netfilter/ipt_TTL.c97
-rw-r--r--net/ipv4/netfilter/ipt_ULOG.c2
-rw-r--r--net/ipv4/netfilter/ipt_ttl.c63
-rw-r--r--net/ipv4/netfilter/iptable_filter.c1
-rw-r--r--net/ipv4/netfilter/iptable_mangle.c1
-rw-r--r--net/ipv4/netfilter/iptable_raw.c1
-rw-r--r--net/ipv4/netfilter/iptable_security.c1
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c10
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c63
-rw-r--r--net/ipv4/netfilter/nf_conntrack_proto_icmp.c6
-rw-r--r--net/ipv4/netfilter/nf_nat_core.c2
-rw-r--r--net/ipv4/netfilter/nf_nat_rule.c1
-rw-r--r--net/ipv4/netfilter/nf_nat_snmp_basic.c4
-rw-r--r--net/ipv4/proc.c4
-rw-r--r--net/ipv4/raw.c1
-rw-r--r--net/ipv4/route.c15
-rw-r--r--net/ipv4/syncookies.c9
-rw-r--r--net/ipv4/tcp.c89
-rw-r--r--net/ipv4/tcp_bic.c11
-rw-r--r--net/ipv4/tcp_cong.c21
-rw-r--r--net/ipv4/tcp_cubic.c11
-rw-r--r--net/ipv4/tcp_htcp.c3
-rw-r--r--net/ipv4/tcp_input.c198
-rw-r--r--net/ipv4/tcp_ipv4.c18
-rw-r--r--net/ipv4/tcp_minisocks.c9
-rw-r--r--net/ipv4/tcp_output.c94
-rw-r--r--net/ipv4/tcp_probe.c5
-rw-r--r--net/ipv4/tcp_scalable.c10
-rw-r--r--net/ipv4/tcp_timer.c23
-rw-r--r--net/ipv4/tcp_veno.c7
-rw-r--r--net/ipv4/tcp_yeah.c9
-rw-r--r--net/ipv4/udp.c15
-rw-r--r--net/ipv4/xfrm4_policy.c2
-rw-r--r--net/ipv6/addrconf.c116
-rw-r--r--net/ipv6/af_inet6.c63
-rw-r--r--net/ipv6/ip6_input.c4
-rw-r--r--net/ipv6/ipv6_sockglue.c3
-rw-r--r--net/ipv6/ndisc.c22
-rw-r--r--net/ipv6/netfilter/Kconfig38
-rw-r--r--net/ipv6/netfilter/Makefile2
-rw-r--r--net/ipv6/netfilter/ip6_queue.c1
-rw-r--r--net/ipv6/netfilter/ip6_tables.c137
-rw-r--r--net/ipv6/netfilter/ip6t_HL.c95
-rw-r--r--net/ipv6/netfilter/ip6t_LOG.c2
-rw-r--r--net/ipv6/netfilter/ip6t_hl.c68
-rw-r--r--net/ipv6/netfilter/ip6table_filter.c1
-rw-r--r--net/ipv6/netfilter/ip6table_mangle.c1
-rw-r--r--net/ipv6/netfilter/ip6table_raw.c1
-rw-r--r--net/ipv6/netfilter/ip6table_security.c1
-rw-r--r--net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c7
-rw-r--r--net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c10
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c8
-rw-r--r--net/ipv6/reassembly.c7
-rw-r--r--net/ipv6/route.c9
-rw-r--r--net/ipv6/sit.c7
-rw-r--r--net/ipv6/tcp_ipv6.c8
-rw-r--r--net/ipv6/udp.c28
-rw-r--r--net/ipv6/xfrm6_policy.c2
-rw-r--r--net/ipv6/xfrm6_state.c2
-rw-r--r--net/ipx/af_ipx.c20
-rw-r--r--net/irda/irda_device.c5
-rw-r--r--net/irda/irlan/irlan_eth.c19
-rw-r--r--net/irda/irmod.c4
-rw-r--r--net/iucv/af_iucv.c3
-rw-r--r--net/key/af_key.c6
-rw-r--r--net/llc/af_llc.c6
-rw-r--r--net/llc/llc_conn.c3
-rw-r--r--net/llc/llc_core.c8
-rw-r--r--net/mac80211/Makefile6
-rw-r--r--net/mac80211/aes_cmac.c135
-rw-r--r--net/mac80211/aes_cmac.h19
-rw-r--r--net/mac80211/agg-rx.c310
-rw-r--r--net/mac80211/agg-tx.c695
-rw-r--r--net/mac80211/cfg.c237
-rw-r--r--net/mac80211/debugfs.c83
-rw-r--r--net/mac80211/debugfs_key.c79
-rw-r--r--net/mac80211/debugfs_key.h10
-rw-r--r--net/mac80211/debugfs_netdev.c48
-rw-r--r--net/mac80211/debugfs_sta.c5
-rw-r--r--net/mac80211/ht.c903
-rw-r--r--net/mac80211/ibss.c908
-rw-r--r--net/mac80211/ieee80211_i.h314
-rw-r--r--net/mac80211/iface.c168
-rw-r--r--net/mac80211/key.c115
-rw-r--r--net/mac80211/key.h16
-rw-r--r--net/mac80211/main.c185
-rw-r--r--net/mac80211/mesh.c15
-rw-r--r--net/mac80211/mesh.h10
-rw-r--r--net/mac80211/mesh_hwmp.c7
-rw-r--r--net/mac80211/mesh_plink.c38
-rw-r--r--net/mac80211/mlme.c2026
-rw-r--r--net/mac80211/pm.c179
-rw-r--r--net/mac80211/rate.c6
-rw-r--r--net/mac80211/rate.h16
-rw-r--r--net/mac80211/rx.c423
-rw-r--r--net/mac80211/scan.c763
-rw-r--r--net/mac80211/spectmgmt.c103
-rw-r--r--net/mac80211/sta_info.c45
-rw-r--r--net/mac80211/sta_info.h16
-rw-r--r--net/mac80211/tx.c675
-rw-r--r--net/mac80211/util.c243
-rw-r--r--net/mac80211/wep.c21
-rw-r--r--net/mac80211/wext.c492
-rw-r--r--net/mac80211/wme.c170
-rw-r--r--net/mac80211/wme.h6
-rw-r--r--net/mac80211/wpa.c180
-rw-r--r--net/mac80211/wpa.h5
-rw-r--r--net/netfilter/Kconfig63
-rw-r--r--net/netfilter/Makefile4
-rw-r--r--net/netfilter/core.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c4
-rw-r--r--net/netfilter/nf_conntrack_amanda.c4
-rw-r--r--net/netfilter/nf_conntrack_core.c141
-rw-r--r--net/netfilter/nf_conntrack_expect.c5
-rw-r--r--net/netfilter/nf_conntrack_h323_main.c8
-rw-r--r--net/netfilter/nf_conntrack_helper.c8
-rw-r--r--net/netfilter/nf_conntrack_netbios_ns.c2
-rw-r--r--net/netfilter/nf_conntrack_netlink.c252
-rw-r--r--net/netfilter/nf_conntrack_pptp.c4
-rw-r--r--net/netfilter/nf_conntrack_proto.c37
-rw-r--r--net/netfilter/nf_conntrack_proto_dccp.c154
-rw-r--r--net/netfilter/nf_conntrack_proto_generic.c2
-rw-r--r--net/netfilter/nf_conntrack_proto_gre.c1
-rw-r--r--net/netfilter/nf_conntrack_proto_sctp.c10
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c24
-rw-r--r--net/netfilter/nf_conntrack_proto_udp.c4
-rw-r--r--net/netfilter/nf_conntrack_proto_udplite.c1
-rw-r--r--net/netfilter/nf_conntrack_standalone.c57
-rw-r--r--net/netfilter/nf_log.c201
-rw-r--r--net/netfilter/nf_tproxy_core.c1
-rw-r--r--net/netfilter/nfnetlink.c6
-rw-r--r--net/netfilter/nfnetlink_log.c18
-rw-r--r--net/netfilter/x_tables.c26
-rw-r--r--net/netfilter/xt_HL.c171
-rw-r--r--net/netfilter/xt_LED.c161
-rw-r--r--net/netfilter/xt_cluster.c164
-rw-r--r--net/netfilter/xt_connlimit.c6
-rw-r--r--net/netfilter/xt_hashlimit.c7
-rw-r--r--net/netfilter/xt_hl.c108
-rw-r--r--net/netfilter/xt_limit.c40
-rw-r--r--net/netfilter/xt_physdev.c20
-rw-r--r--net/netfilter/xt_quota.c31
-rw-r--r--net/netfilter/xt_statistic.c28
-rw-r--r--net/netlabel/netlabel_kapi.c165
-rw-r--r--net/netlink/Makefile2
-rw-r--r--net/netlink/af_netlink.c88
-rw-r--r--net/netlink/attr.c473
-rw-r--r--net/netrom/af_netrom.c8
-rw-r--r--net/netrom/nr_dev.c26
-rw-r--r--net/packet/af_packet.c5
-rw-r--r--net/phonet/af_phonet.c34
-rw-r--r--net/phonet/pn_dev.c119
-rw-r--r--net/phonet/pn_netlink.c29
-rw-r--r--net/rds/Kconfig14
-rw-r--r--net/rds/Makefile14
-rw-r--r--net/rds/af_rds.c586
-rw-r--r--net/rds/bind.c199
-rw-r--r--net/rds/cong.c404
-rw-r--r--net/rds/connection.c487
-rw-r--r--net/rds/ib.c323
-rw-r--r--net/rds/ib.h367
-rw-r--r--net/rds/ib_cm.c726
-rw-r--r--net/rds/ib_rdma.c641
-rw-r--r--net/rds/ib_recv.c869
-rw-r--r--net/rds/ib_ring.c168
-rw-r--r--net/rds/ib_send.c874
-rw-r--r--net/rds/ib_stats.c95
-rw-r--r--net/rds/ib_sysctl.c137
-rw-r--r--net/rds/info.c241
-rw-r--r--net/rds/info.h30
-rw-r--r--net/rds/iw.c333
-rw-r--r--net/rds/iw.h395
-rw-r--r--net/rds/iw_cm.c750
-rw-r--r--net/rds/iw_rdma.c888
-rw-r--r--net/rds/iw_recv.c869
-rw-r--r--net/rds/iw_ring.c169
-rw-r--r--net/rds/iw_send.c975
-rw-r--r--net/rds/iw_stats.c95
-rw-r--r--net/rds/iw_sysctl.c137
-rw-r--r--net/rds/loop.c188
-rw-r--r--net/rds/loop.h9
-rw-r--r--net/rds/message.c402
-rw-r--r--net/rds/page.c221
-rw-r--r--net/rds/rdma.c679
-rw-r--r--net/rds/rdma.h84
-rw-r--r--net/rds/rdma_transport.c214
-rw-r--r--net/rds/rdma_transport.h28
-rw-r--r--net/rds/rds.h686
-rw-r--r--net/rds/recv.c542
-rw-r--r--net/rds/send.c1003
-rw-r--r--net/rds/stats.c148
-rw-r--r--net/rds/sysctl.c122
-rw-r--r--net/rds/threads.c265
-rw-r--r--net/rds/transport.c117
-rw-r--r--net/rose/af_rose.c7
-rw-r--r--net/rose/rose_dev.c22
-rw-r--r--net/sched/sch_api.c11
-rw-r--r--net/sched/sch_cbq.c7
-rw-r--r--net/sched/sch_drr.c7
-rw-r--r--net/sched/sch_hfsc.c13
-rw-r--r--net/sched/sch_htb.c49
-rw-r--r--net/sched/sch_multiq.c2
-rw-r--r--net/sched/sch_tbf.c9
-rw-r--r--net/sctp/debug.c4
-rw-r--r--net/sctp/endpointola.c3
-rw-r--r--net/sctp/input.c14
-rw-r--r--net/sctp/ipv6.c36
-rw-r--r--net/sctp/output.c21
-rw-r--r--net/sctp/outqueue.c6
-rw-r--r--net/sctp/protocol.c31
-rw-r--r--net/sctp/sm_make_chunk.c37
-rw-r--r--net/sctp/sm_sideeffect.c43
-rw-r--r--net/sctp/sm_statefuns.c6
-rw-r--r--net/sctp/socket.c216
-rw-r--r--net/sctp/transport.c9
-rw-r--r--net/socket.c95
-rw-r--r--net/sunrpc/rpc_pipe.c2
-rw-r--r--net/sunrpc/sched.c33
-rw-r--r--net/sunrpc/xprt.c2
-rw-r--r--net/sunrpc/xprtsock.c76
-rw-r--r--net/sysctl_net.c2
-rw-r--r--net/tipc/bcast.c4
-rw-r--r--net/tipc/bcast.h2
-rw-r--r--net/tipc/dbg.c2
-rw-r--r--net/tipc/node.c2
-rw-r--r--net/unix/af_unix.c3
-rw-r--r--net/wanrouter/wanmain.c8
-rw-r--r--net/wanrouter/wanproc.c2
-rw-r--r--net/wimax/op-msg.c9
-rw-r--r--net/wimax/stack.c12
-rw-r--r--net/wireless/Kconfig60
-rw-r--r--net/wireless/Makefile3
-rw-r--r--net/wireless/core.c162
-rw-r--r--net/wireless/core.h64
-rw-r--r--net/wireless/lib80211_crypt_ccmp.c2
-rw-r--r--net/wireless/lib80211_crypt_tkip.c4
-rw-r--r--net/wireless/mlme.c46
-rw-r--r--net/wireless/nl80211.c1335
-rw-r--r--net/wireless/nl80211.h31
-rw-r--r--net/wireless/reg.c1255
-rw-r--r--net/wireless/reg.h45
-rw-r--r--net/wireless/scan.c891
-rw-r--r--net/wireless/sysfs.c39
-rw-r--r--net/wireless/util.c2
-rw-r--r--net/wireless/wext-compat.c108
-rw-r--r--net/x25/af_x25.c21
-rw-r--r--net/xfrm/xfrm_state.c92
350 files changed, 31016 insertions, 8195 deletions
diff --git a/net/802/psnap.c b/net/802/psnap.c
index 70980baeb68..6fea0750662 100644
--- a/net/802/psnap.c
+++ b/net/802/psnap.c
@@ -29,7 +29,7 @@ static struct llc_sap *snap_sap;
/*
* Find a snap client by matching the 5 bytes.
*/
-static struct datalink_proto *find_snap_client(unsigned char *desc)
+static struct datalink_proto *find_snap_client(const unsigned char *desc)
{
struct datalink_proto *proto = NULL, *p;
@@ -51,7 +51,7 @@ static int snap_rcv(struct sk_buff *skb, struct net_device *dev,
int rc = 1;
struct datalink_proto *proto;
static struct packet_type snap_packet_type = {
- .type = __constant_htons(ETH_P_SNAP),
+ .type = cpu_to_be16(ETH_P_SNAP),
};
if (unlikely(!pskb_may_pull(skb, 5)))
@@ -95,15 +95,16 @@ static int snap_request(struct datalink_proto *dl,
EXPORT_SYMBOL(register_snap_client);
EXPORT_SYMBOL(unregister_snap_client);
-static char snap_err_msg[] __initdata =
+static const char snap_err_msg[] __initconst =
KERN_CRIT "SNAP - unable to register with 802.2\n";
static int __init snap_init(void)
{
snap_sap = llc_sap_open(0xAA, snap_rcv);
-
- if (!snap_sap)
+ if (!snap_sap) {
printk(snap_err_msg);
+ return -EBUSY;
+ }
return 0;
}
@@ -121,7 +122,7 @@ module_exit(snap_exit);
/*
* Register SNAP clients. We don't yet use this for IP.
*/
-struct datalink_proto *register_snap_client(unsigned char *desc,
+struct datalink_proto *register_snap_client(const unsigned char *desc,
int (*rcvfunc)(struct sk_buff *,
struct net_device *,
struct packet_type *,
@@ -136,7 +137,7 @@ struct datalink_proto *register_snap_client(unsigned char *desc,
proto = kmalloc(sizeof(*proto), GFP_ATOMIC);
if (proto) {
- memcpy(proto->type, desc,5);
+ memcpy(proto->type, desc, 5);
proto->rcvfunc = rcvfunc;
proto->header_length = 5 + 3; /* snap + 802.2 */
proto->request = snap_request;
diff --git a/net/802/tr.c b/net/802/tr.c
index f47ae289d83..e7eb13084d7 100644
--- a/net/802/tr.c
+++ b/net/802/tr.c
@@ -486,6 +486,7 @@ static struct rif_cache *rif_get_idx(loff_t pos)
}
static void *rif_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(&rif_lock)
{
spin_lock_irq(&rif_lock);
@@ -517,6 +518,7 @@ static void *rif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
}
static void rif_seq_stop(struct seq_file *seq, void *v)
+ __releases(&rif_lock)
{
spin_unlock_irq(&rif_lock);
}
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 41e8f65bd3f..2b7390e377b 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -51,8 +51,8 @@ const char vlan_version[] = DRV_VERSION;
static const char vlan_copyright[] = "Ben Greear <greearb@candelatech.com>";
static const char vlan_buggyright[] = "David S. Miller <davem@redhat.com>";
-static struct packet_type vlan_packet_type = {
- .type = __constant_htons(ETH_P_8021Q),
+static struct packet_type vlan_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_8021Q),
.func = vlan_skb_recv, /* VLAN receive method */
};
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 2886d2fb9ab..654e45f5719 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -89,38 +89,27 @@ static int vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp,
goto drop;
for (p = napi->gro_list; p; p = p->next) {
- NAPI_GRO_CB(p)->same_flow = p->dev == skb->dev;
+ NAPI_GRO_CB(p)->same_flow =
+ p->dev == skb->dev && !compare_ether_header(
+ skb_mac_header(p), skb_gro_mac_header(skb));
NAPI_GRO_CB(p)->flush = 0;
}
return dev_gro_receive(napi, skb);
drop:
- return 2;
+ return GRO_DROP;
}
int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
unsigned int vlan_tci, struct sk_buff *skb)
{
- int err = NET_RX_SUCCESS;
+ if (netpoll_rx_on(skb))
+ return vlan_hwaccel_receive_skb(skb, grp, vlan_tci);
- if (netpoll_receive_skb(skb))
- return NET_RX_DROP;
-
- switch (vlan_gro_common(napi, grp, vlan_tci, skb)) {
- case -1:
- return netif_receive_skb(skb);
+ skb_gro_reset_offset(skb);
- case 2:
- err = NET_RX_DROP;
- /* fall through */
-
- case 1:
- kfree_skb(skb);
- break;
- }
-
- return err;
+ return napi_skb_finish(vlan_gro_common(napi, grp, vlan_tci, skb), skb);
}
EXPORT_SYMBOL(vlan_gro_receive);
@@ -128,30 +117,14 @@ int vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
unsigned int vlan_tci, struct napi_gro_fraginfo *info)
{
struct sk_buff *skb = napi_fraginfo_skb(napi, info);
- int err = NET_RX_DROP;
if (!skb)
- goto out;
-
- if (netpoll_receive_skb(skb))
- goto out;
-
- err = NET_RX_SUCCESS;
-
- switch (vlan_gro_common(napi, grp, vlan_tci, skb)) {
- case -1:
- return netif_receive_skb(skb);
-
- case 2:
- err = NET_RX_DROP;
- /* fall through */
+ return NET_RX_DROP;
- case 1:
- napi_reuse_skb(napi, skb);
- break;
- }
+ if (netpoll_rx_on(skb))
+ return vlan_hwaccel_receive_skb(skb, grp, vlan_tci);
-out:
- return err;
+ return napi_frags_finish(napi, skb,
+ vlan_gro_common(napi, grp, vlan_tci, skb));
}
EXPORT_SYMBOL(vlan_gro_frags);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 1df0356f242..c613ed08a5e 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -417,7 +417,7 @@ static int p9_fd_write(struct p9_client *client, void *v, int len)
oldfs = get_fs();
set_fs(get_ds());
/* The cast to a user pointer is valid due to the set_fs() */
- ret = vfs_write(ts->wr, (void __user *)v, len, &ts->wr->f_pos);
+ ret = vfs_write(ts->wr, (__force void __user *)v, len, &ts->wr->f_pos);
set_fs(oldfs);
if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
diff --git a/net/Kconfig b/net/Kconfig
index cdb8fdef6c4..ec93e7e38b3 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -4,6 +4,7 @@
menuconfig NET
bool "Networking support"
+ select NLATTR
---help---
Unless you really know what you are doing, you should say Y here.
The reason is that some programs need kernel networking support even
@@ -24,9 +25,6 @@ if NET
menu "Networking options"
-config COMPAT_NET_DEV_OPS
- def_bool y
-
source "net/packet/Kconfig"
source "net/unix/Kconfig"
source "net/xfrm/Kconfig"
@@ -171,6 +169,7 @@ endif
source "net/dccp/Kconfig"
source "net/sctp/Kconfig"
+source "net/rds/Kconfig"
source "net/tipc/Kconfig"
source "net/atm/Kconfig"
source "net/802/Kconfig"
@@ -185,6 +184,7 @@ source "net/x25/Kconfig"
source "net/lapb/Kconfig"
source "net/econet/Kconfig"
source "net/wanrouter/Kconfig"
+source "net/phonet/Kconfig"
source "net/sched/Kconfig"
source "net/dcb/Kconfig"
@@ -220,6 +220,17 @@ config NET_TCPPROBE
To compile this code as a module, choose M here: the
module will be called tcp_probe.
+config NET_DROP_MONITOR
+ boolean "Network packet drop alerting service"
+ depends on INET && EXPERIMENTAL && TRACEPOINTS
+ ---help---
+ This feature provides an alerting service to userspace in the
+ event that packets are discarded in the network stack. Alerts
+ are broadcast via netlink socket to any listening user space
+ process. If you don't need network drop alerts, or if you are ok
+ just checking the various proc files and other utilities for
+ drop statistics, say N here.
+
endmenu
endmenu
@@ -229,7 +240,6 @@ source "net/can/Kconfig"
source "net/irda/Kconfig"
source "net/bluetooth/Kconfig"
source "net/rxrpc/Kconfig"
-source "net/phonet/Kconfig"
config FIB_RULES
bool
diff --git a/net/Makefile b/net/Makefile
index 0fcce89d716..9e00a55a901 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -49,6 +49,7 @@ obj-y += 8021q/
endif
obj-$(CONFIG_IP_DCCP) += dccp/
obj-$(CONFIG_IP_SCTP) += sctp/
+obj-$(CONFIG_RDS) += rds/
obj-y += wireless/
obj-$(CONFIG_MAC80211) += mac80211/
obj-$(CONFIG_TIPC) += tipc/
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 5abce07fb50..d6a9243641a 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1571,14 +1571,10 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
usat->sat_family != AF_APPLETALK)
return -EINVAL;
- /* netatalk doesn't implement this check */
+ /* netatalk didn't implement this check */
if (usat->sat_addr.s_node == ATADDR_BCAST &&
!sock_flag(sk, SOCK_BROADCAST)) {
- printk(KERN_INFO "SO_BROADCAST: Fix your netatalk as "
- "it will break before 2.2\n");
-#if 0
return -EPERM;
-#endif
}
} else {
if (sk->sk_state != TCP_ESTABLISHED)
@@ -1860,13 +1856,13 @@ static struct notifier_block ddp_notifier = {
.notifier_call = ddp_device_event,
};
-static struct packet_type ltalk_packet_type = {
- .type = __constant_htons(ETH_P_LOCALTALK),
+static struct packet_type ltalk_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_LOCALTALK),
.func = ltalk_rcv,
};
-static struct packet_type ppptalk_packet_type = {
- .type = __constant_htons(ETH_P_PPPTALK),
+static struct packet_type ppptalk_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_PPPTALK),
.func = atalk_rcv,
};
@@ -1877,7 +1873,7 @@ EXPORT_SYMBOL(aarp_send_ddp);
EXPORT_SYMBOL(atrtr_get_dev);
EXPORT_SYMBOL(atalk_find_dev_addr);
-static char atalk_err_snap[] __initdata =
+static const char atalk_err_snap[] __initconst =
KERN_CRIT "Unable to register DDP with SNAP.\n";
/* Called by proto.c on kernel start up */
diff --git a/net/appletalk/dev.c b/net/appletalk/dev.c
index d856a62ab50..72277d70c98 100644
--- a/net/appletalk/dev.c
+++ b/net/appletalk/dev.c
@@ -9,22 +9,20 @@
#include <linux/if_arp.h>
#include <linux/if_ltalk.h>
+#ifdef CONFIG_COMPAT_NET_DEV_OPS
static int ltalk_change_mtu(struct net_device *dev, int mtu)
{
return -EINVAL;
}
-
-static int ltalk_mac_addr(struct net_device *dev, void *addr)
-{
- return -EINVAL;
-}
+#endif
static void ltalk_setup(struct net_device *dev)
{
/* Fill in the fields of the device structure with localtalk-generic values. */
+#ifdef CONFIG_COMPAT_NET_DEV_OPS
dev->change_mtu = ltalk_change_mtu;
- dev->set_mac_address = ltalk_mac_addr;
+#endif
dev->type = ARPHRD_LOCALTLK;
dev->hard_header_len = LTALK_HLEN;
diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index ea9438fc685..334fcd4a4ea 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -83,7 +83,6 @@ struct br2684_dev {
struct list_head br2684_devs;
int number;
struct list_head brvccs; /* one device <=> one vcc (before xmas) */
- struct net_device_stats stats;
int mac_was_set;
enum br2684_payload payload;
};
@@ -148,9 +147,10 @@ static struct net_device *br2684_find_dev(const struct br2684_if_spec *s)
* the way for multiple vcc's per itf. Returns true if we can send,
* otherwise false
*/
-static int br2684_xmit_vcc(struct sk_buff *skb, struct br2684_dev *brdev,
+static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev,
struct br2684_vcc *brvcc)
{
+ struct br2684_dev *brdev = BRPRIV(dev);
struct atm_vcc *atmvcc;
int minheadroom = (brvcc->encaps == e_llc) ? 10 : 2;
@@ -211,8 +211,8 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct br2684_dev *brdev,
}
atomic_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc);
ATM_SKB(skb)->atm_options = atmvcc->atm_options;
- brdev->stats.tx_packets++;
- brdev->stats.tx_bytes += skb->len;
+ dev->stats.tx_packets++;
+ dev->stats.tx_bytes += skb->len;
atmvcc->send(atmvcc, skb);
return 1;
}
@@ -233,14 +233,14 @@ static int br2684_start_xmit(struct sk_buff *skb, struct net_device *dev)
brvcc = pick_outgoing_vcc(skb, brdev);
if (brvcc == NULL) {
pr_debug("no vcc attached to dev %s\n", dev->name);
- brdev->stats.tx_errors++;
- brdev->stats.tx_carrier_errors++;
+ dev->stats.tx_errors++;
+ dev->stats.tx_carrier_errors++;
/* netif_stop_queue(dev); */
dev_kfree_skb(skb);
read_unlock(&devs_lock);
return 0;
}
- if (!br2684_xmit_vcc(skb, brdev, brvcc)) {
+ if (!br2684_xmit_vcc(skb, dev, brvcc)) {
/*
* We should probably use netif_*_queue() here, but that
* involves added complication. We need to walk before
@@ -248,27 +248,20 @@ static int br2684_start_xmit(struct sk_buff *skb, struct net_device *dev)
*
* Don't free here! this pointer might be no longer valid!
*/
- brdev->stats.tx_errors++;
- brdev->stats.tx_fifo_errors++;
+ dev->stats.tx_errors++;
+ dev->stats.tx_fifo_errors++;
}
read_unlock(&devs_lock);
return 0;
}
-static struct net_device_stats *br2684_get_stats(struct net_device *dev)
-{
- pr_debug("br2684_get_stats\n");
- return &BRPRIV(dev)->stats;
-}
-
/*
* We remember when the MAC gets set, so we don't override it later with
* the ESI of the ATM card of the first VC
*/
-static int (*my_eth_mac_addr) (struct net_device *, void *);
static int br2684_mac_addr(struct net_device *dev, void *p)
{
- int err = my_eth_mac_addr(dev, p);
+ int err = eth_mac_addr(dev, p);
if (!err)
BRPRIV(dev)->mac_was_set = 1;
return err;
@@ -430,17 +423,17 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb)
/* sigh, interface is down? */
if (unlikely(!(net_dev->flags & IFF_UP)))
goto dropped;
- brdev->stats.rx_packets++;
- brdev->stats.rx_bytes += skb->len;
+ net_dev->stats.rx_packets++;
+ net_dev->stats.rx_bytes += skb->len;
memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data));
netif_rx(skb);
return;
dropped:
- brdev->stats.rx_dropped++;
+ net_dev->stats.rx_dropped++;
goto free_skb;
error:
- brdev->stats.rx_errors++;
+ net_dev->stats.rx_errors++;
free_skb:
dev_kfree_skb(skb);
return;
@@ -531,8 +524,8 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg)
skb->next = skb->prev = NULL;
br2684_push(atmvcc, skb);
- BRPRIV(skb->dev)->stats.rx_bytes -= skb->len;
- BRPRIV(skb->dev)->stats.rx_packets--;
+ skb->dev->stats.rx_bytes -= skb->len;
+ skb->dev->stats.rx_packets--;
skb = next;
}
@@ -544,17 +537,20 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg)
return err;
}
+static const struct net_device_ops br2684_netdev_ops = {
+ .ndo_start_xmit = br2684_start_xmit,
+ .ndo_set_mac_address = br2684_mac_addr,
+ .ndo_change_mtu = eth_change_mtu,
+ .ndo_validate_addr = eth_validate_addr,
+};
+
static void br2684_setup(struct net_device *netdev)
{
struct br2684_dev *brdev = BRPRIV(netdev);
ether_setup(netdev);
- brdev->net_dev = netdev;
- my_eth_mac_addr = netdev->set_mac_address;
- netdev->set_mac_address = br2684_mac_addr;
- netdev->hard_start_xmit = br2684_start_xmit;
- netdev->get_stats = br2684_get_stats;
+ netdev->netdev_ops = &br2684_netdev_ops;
INIT_LIST_HEAD(&brdev->brvccs);
}
@@ -565,10 +561,8 @@ static void br2684_setup_routed(struct net_device *netdev)
brdev->net_dev = netdev;
netdev->hard_header_len = 0;
- my_eth_mac_addr = netdev->set_mac_address;
- netdev->set_mac_address = br2684_mac_addr;
- netdev->hard_start_xmit = br2684_start_xmit;
- netdev->get_stats = br2684_get_stats;
+
+ netdev->netdev_ops = &br2684_netdev_ops;
netdev->addr_len = 0;
netdev->mtu = 1500;
netdev->type = ARPHRD_PPP;
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 2d33a83be79..3dc0a3a42a5 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -214,15 +214,15 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb)
skb->protocol = ((__be16 *) skb->data)[3];
skb_pull(skb, RFC1483LLC_LEN);
if (skb->protocol == htons(ETH_P_ARP)) {
- PRIV(skb->dev)->stats.rx_packets++;
- PRIV(skb->dev)->stats.rx_bytes += skb->len;
+ skb->dev->stats.rx_packets++;
+ skb->dev->stats.rx_bytes += skb->len;
clip_arp_rcv(skb);
return;
}
}
clip_vcc->last_use = jiffies;
- PRIV(skb->dev)->stats.rx_packets++;
- PRIV(skb->dev)->stats.rx_bytes += skb->len;
+ skb->dev->stats.rx_packets++;
+ skb->dev->stats.rx_bytes += skb->len;
memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data));
netif_rx(skb);
}
@@ -372,7 +372,7 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev)
if (!skb->dst) {
printk(KERN_ERR "clip_start_xmit: skb->dst == NULL\n");
dev_kfree_skb(skb);
- clip_priv->stats.tx_dropped++;
+ dev->stats.tx_dropped++;
return 0;
}
if (!skb->dst->neighbour) {
@@ -380,13 +380,13 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev)
skb->dst->neighbour = clip_find_neighbour(skb->dst, 1);
if (!skb->dst->neighbour) {
dev_kfree_skb(skb); /* lost that one */
- clip_priv->stats.tx_dropped++;
+ dev->stats.tx_dropped++;
return 0;
}
#endif
printk(KERN_ERR "clip_start_xmit: NO NEIGHBOUR !\n");
dev_kfree_skb(skb);
- clip_priv->stats.tx_dropped++;
+ dev->stats.tx_dropped++;
return 0;
}
entry = NEIGH2ENTRY(skb->dst->neighbour);
@@ -400,7 +400,7 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev)
skb_queue_tail(&entry->neigh->arp_queue, skb);
else {
dev_kfree_skb(skb);
- clip_priv->stats.tx_dropped++;
+ dev->stats.tx_dropped++;
}
return 0;
}
@@ -423,8 +423,8 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev)
printk(KERN_WARNING "clip_start_xmit: XOFF->XOFF transition\n");
return 0;
}
- clip_priv->stats.tx_packets++;
- clip_priv->stats.tx_bytes += skb->len;
+ dev->stats.tx_packets++;
+ dev->stats.tx_bytes += skb->len;
vcc->send(vcc, skb);
if (atm_may_send(vcc, 0)) {
entry->vccs->xoff = 0;
@@ -443,11 +443,6 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev)
return 0;
}
-static struct net_device_stats *clip_get_stats(struct net_device *dev)
-{
- return &PRIV(dev)->stats;
-}
-
static int clip_mkip(struct atm_vcc *vcc, int timeout)
{
struct clip_vcc *clip_vcc;
@@ -501,8 +496,8 @@ static int clip_mkip(struct atm_vcc *vcc, int timeout)
skb_get(skb);
clip_push(vcc, skb);
- PRIV(skb->dev)->stats.rx_packets--;
- PRIV(skb->dev)->stats.rx_bytes -= len;
+ skb->dev->stats.rx_packets--;
+ skb->dev->stats.rx_bytes -= len;
kfree_skb(skb);
}
@@ -557,11 +552,13 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
return error;
}
+static const struct net_device_ops clip_netdev_ops = {
+ .ndo_start_xmit = clip_start_xmit,
+};
+
static void clip_setup(struct net_device *dev)
{
- dev->hard_start_xmit = clip_start_xmit;
- /* sg_xmit ... */
- dev->get_stats = clip_get_stats;
+ dev->netdev_ops = &clip_netdev_ops;
dev->type = ARPHRD_ATM;
dev->hard_header_len = RFC1483LLC_LEN;
dev->mtu = RFC1626_MTU;
@@ -621,7 +618,7 @@ static int clip_device_event(struct notifier_block *this, unsigned long event,
}
/* ignore non-CLIP devices */
- if (dev->type != ARPHRD_ATM || dev->hard_start_xmit != clip_start_xmit)
+ if (dev->type != ARPHRD_ATM || dev->netdev_ops != &clip_netdev_ops)
return NOTIFY_DONE;
switch (event) {
diff --git a/net/atm/lec.c b/net/atm/lec.c
index e5e301550e8..199b6bb79f4 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -62,7 +62,6 @@ static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 };
static int lec_open(struct net_device *dev);
static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev);
static int lec_close(struct net_device *dev);
-static struct net_device_stats *lec_get_stats(struct net_device *dev);
static void lec_init(struct net_device *dev);
static struct lec_arp_table *lec_arp_find(struct lec_priv *priv,
const unsigned char *mac_addr);
@@ -218,28 +217,28 @@ static unsigned char *get_tr_dst(unsigned char *packet, unsigned char *rdesc)
static int lec_open(struct net_device *dev)
{
- struct lec_priv *priv = netdev_priv(dev);
-
netif_start_queue(dev);
- memset(&priv->stats, 0, sizeof(struct net_device_stats));
+ memset(&dev->stats, 0, sizeof(struct net_device_stats));
return 0;
}
-static __inline__ void
-lec_send(struct atm_vcc *vcc, struct sk_buff *skb, struct lec_priv *priv)
+static void
+lec_send(struct atm_vcc *vcc, struct sk_buff *skb)
{
+ struct net_device *dev = skb->dev;
+
ATM_SKB(skb)->vcc = vcc;
ATM_SKB(skb)->atm_options = vcc->atm_options;
atomic_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
if (vcc->send(vcc, skb) < 0) {
- priv->stats.tx_dropped++;
+ dev->stats.tx_dropped++;
return;
}
- priv->stats.tx_packets++;
- priv->stats.tx_bytes += skb->len;
+ dev->stats.tx_packets++;
+ dev->stats.tx_bytes += skb->len;
}
static void lec_tx_timeout(struct net_device *dev)
@@ -270,7 +269,7 @@ static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev)
pr_debug("lec_start_xmit called\n");
if (!priv->lecd) {
printk("%s:No lecd attached\n", dev->name);
- priv->stats.tx_errors++;
+ dev->stats.tx_errors++;
netif_stop_queue(dev);
return -EUNATCH;
}
@@ -345,7 +344,7 @@ static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev)
GFP_ATOMIC);
dev_kfree_skb(skb);
if (skb2 == NULL) {
- priv->stats.tx_dropped++;
+ dev->stats.tx_dropped++;
return 0;
}
skb = skb2;
@@ -380,7 +379,7 @@ static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev)
("%s:lec_start_xmit: tx queue full or no arp entry, dropping, ",
dev->name);
pr_debug("MAC address %pM\n", lec_h->h_dest);
- priv->stats.tx_dropped++;
+ dev->stats.tx_dropped++;
dev_kfree_skb(skb);
}
goto out;
@@ -392,10 +391,10 @@ static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev)
while (entry && (skb2 = skb_dequeue(&entry->tx_wait))) {
pr_debug("lec.c: emptying tx queue, ");
pr_debug("MAC address %pM\n", lec_h->h_dest);
- lec_send(vcc, skb2, priv);
+ lec_send(vcc, skb2);
}
- lec_send(vcc, skb, priv);
+ lec_send(vcc, skb);
if (!atm_may_send(vcc, 0)) {
struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc);
@@ -427,15 +426,6 @@ static int lec_close(struct net_device *dev)
return 0;
}
-/*
- * Get the current statistics.
- * This may be called with the card open or closed.
- */
-static struct net_device_stats *lec_get_stats(struct net_device *dev)
-{
- return &((struct lec_priv *)netdev_priv(dev))->stats;
-}
-
static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb)
{
unsigned long flags;
@@ -512,7 +502,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb)
priv->lane2_ops = NULL;
if (priv->lane_version > 1)
priv->lane2_ops = &lane2_ops;
- if (dev->change_mtu(dev, mesg->content.config.mtu))
+ if (dev_set_mtu(dev, mesg->content.config.mtu))
printk("%s: change_mtu to %d failed\n", dev->name,
mesg->content.config.mtu);
priv->is_proxy = mesg->content.config.is_proxy;
@@ -677,17 +667,19 @@ static void lec_set_multicast_list(struct net_device *dev)
return;
}
+static const struct net_device_ops lec_netdev_ops = {
+ .ndo_open = lec_open,
+ .ndo_stop = lec_close,
+ .ndo_start_xmit = lec_start_xmit,
+ .ndo_change_mtu = lec_change_mtu,
+ .ndo_tx_timeout = lec_tx_timeout,
+ .ndo_set_multicast_list = lec_set_multicast_list,
+};
+
+
static void lec_init(struct net_device *dev)
{
- dev->change_mtu = lec_change_mtu;
- dev->open = lec_open;
- dev->stop = lec_close;
- dev->hard_start_xmit = lec_start_xmit;
- dev->tx_timeout = lec_tx_timeout;
-
- dev->get_stats = lec_get_stats;
- dev->set_multicast_list = lec_set_multicast_list;
- dev->do_ioctl = NULL;
+ dev->netdev_ops = &lec_netdev_ops;
printk("%s: Initialized!\n", dev->name);
}
@@ -810,8 +802,8 @@ static void lec_push(struct atm_vcc *vcc, struct sk_buff *skb)
else
#endif
skb->protocol = eth_type_trans(skb, dev);
- priv->stats.rx_packets++;
- priv->stats.rx_bytes += skb->len;
+ dev->stats.rx_packets++;
+ dev->stats.rx_bytes += skb->len;
memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data));
netif_rx(skb);
}
@@ -1887,7 +1879,7 @@ restart:
lec_arp_hold(entry);
spin_unlock_irqrestore(&priv->lec_arp_lock, flags);
while ((skb = skb_dequeue(&entry->tx_wait)) != NULL)
- lec_send(vcc, skb, entry->priv);
+ lec_send(vcc, skb);
entry->last_used = jiffies;
entry->status = ESI_FORWARD_DIRECT;
lec_arp_put(entry);
@@ -2305,7 +2297,7 @@ restart:
lec_arp_hold(entry);
spin_unlock_irqrestore(&priv->lec_arp_lock, flags);
while ((skb = skb_dequeue(&entry->tx_wait)) != NULL)
- lec_send(vcc, skb, entry->priv);
+ lec_send(vcc, skb);
entry->last_used = jiffies;
entry->status = ESI_FORWARD_DIRECT;
lec_arp_put(entry);
diff --git a/net/atm/lec.h b/net/atm/lec.h
index 0d376682c1a..9d14d196cc1 100644
--- a/net/atm/lec.h
+++ b/net/atm/lec.h
@@ -69,7 +69,6 @@ struct lane2_ops {
#define LEC_ARP_TABLE_SIZE 16
struct lec_priv {
- struct net_device_stats stats;
unsigned short lecid; /* Lecid of this client */
struct hlist_head lec_arp_empty_ones;
/* Used for storing VCC's that don't have a MAC address attached yet */
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 039d5cc72c3..e5bf11453a1 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -286,33 +286,32 @@ static void start_mpc(struct mpoa_client *mpc, struct net_device *dev)
{
dprintk("mpoa: (%s) start_mpc:\n", mpc->dev->name);
- if (dev->hard_start_xmit == NULL) {
- printk("mpoa: (%s) start_mpc: dev->hard_start_xmit == NULL, not starting\n",
- dev->name);
- return;
+ if (!dev->netdev_ops)
+ printk("mpoa: (%s) start_mpc not starting\n", dev->name);
+ else {
+ mpc->old_ops = dev->netdev_ops;
+ mpc->new_ops = *mpc->old_ops;
+ mpc->new_ops.ndo_start_xmit = mpc_send_packet;
+ dev->netdev_ops = &mpc->new_ops;
}
- mpc->old_hard_start_xmit = dev->hard_start_xmit;
- dev->hard_start_xmit = mpc_send_packet;
-
- return;
}
static void stop_mpc(struct mpoa_client *mpc)
{
-
+ struct net_device *dev = mpc->dev;
dprintk("mpoa: (%s) stop_mpc:", mpc->dev->name);
/* Lets not nullify lec device's dev->hard_start_xmit */
- if (mpc->dev->hard_start_xmit != mpc_send_packet) {
+ if (dev->netdev_ops != &mpc->new_ops) {
dprintk(" mpc already stopped, not fatal\n");
return;
}
dprintk("\n");
- mpc->dev->hard_start_xmit = mpc->old_hard_start_xmit;
- mpc->old_hard_start_xmit = NULL;
- /* close_shortcuts(mpc); ??? FIXME */
- return;
+ dev->netdev_ops = mpc->old_ops;
+ mpc->old_ops = NULL;
+
+ /* close_shortcuts(mpc); ??? FIXME */
}
static const char *mpoa_device_type_string(char type) __attribute__ ((unused));
@@ -531,7 +530,6 @@ static int send_via_shortcut(struct sk_buff *skb, struct mpoa_client *mpc)
*/
static int mpc_send_packet(struct sk_buff *skb, struct net_device *dev)
{
- int retval;
struct mpoa_client *mpc;
struct ethhdr *eth;
int i = 0;
@@ -561,9 +559,7 @@ static int mpc_send_packet(struct sk_buff *skb, struct net_device *dev)
}
non_ip:
- retval = mpc->old_hard_start_xmit(skb,dev);
-
- return retval;
+ return mpc->old_ops->ndo_start_xmit(skb,dev);
}
static int atm_mpoa_vcc_attach(struct atm_vcc *vcc, void __user *arg)
diff --git a/net/atm/mpc.h b/net/atm/mpc.h
index 24c386c35f5..0919a88bbc7 100644
--- a/net/atm/mpc.h
+++ b/net/atm/mpc.h
@@ -15,7 +15,7 @@ struct mpoa_client {
struct mpoa_client *next;
struct net_device *dev; /* lec in question */
int dev_num; /* e.g. 2 for lec2 */
- int (*old_hard_start_xmit)(struct sk_buff *skb, struct net_device *dev);
+
struct atm_vcc *mpoad_vcc; /* control channel to mpoad */
uint8_t mps_ctrl_addr[ATM_ESA_LEN]; /* MPS control ATM address */
uint8_t our_ctrl_addr[ATM_ESA_LEN]; /* MPC's control ATM address */
@@ -31,6 +31,9 @@ struct mpoa_client {
uint8_t *mps_macs; /* array of MPS MAC addresses, >=1 */
int number_of_mps_macs; /* number of the above MAC addresses */
struct mpc_parameters parameters; /* parameters for this client */
+
+ const struct net_device_ops *old_ops;
+ struct net_device_ops new_ops;
};
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 00d9e5e1315..fd9d06f291d 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1529,10 +1529,8 @@ static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock,
dp = ax25->digipeat;
}
- SOCK_DEBUG(sk, "AX.25: sendto: Addresses built.\n");
-
/* Build a packet */
- SOCK_DEBUG(sk, "AX.25: sendto: building packet.\n");
+ SOCK_DEBUG(sk, "AX.25: sendto: Addresses built. Building packet.\n");
/* Assume the worst case */
size = len + ax25->ax25_dev->dev->hard_header_len;
@@ -1985,9 +1983,8 @@ static const struct proto_ops ax25_proto_ops = {
/*
* Called by socket.c on kernel start up
*/
-static struct packet_type ax25_packet_type = {
- .type = __constant_htons(ETH_P_AX25),
- .dev = NULL, /* All devices */
+static struct packet_type ax25_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_AX25),
.func = ax25_kiss_rcv,
};
diff --git a/net/ax25/ax25_iface.c b/net/ax25/ax25_iface.c
index 8443af57a37..71338f11210 100644
--- a/net/ax25/ax25_iface.c
+++ b/net/ax25/ax25_iface.c
@@ -61,27 +61,24 @@ void ax25_protocol_release(unsigned int pid)
write_lock_bh(&protocol_list_lock);
protocol = protocol_list;
- if (protocol == NULL) {
- write_unlock_bh(&protocol_list_lock);
- return;
- }
+ if (protocol == NULL)
+ goto out;
if (protocol->pid == pid) {
protocol_list = protocol->next;
- write_unlock_bh(&protocol_list_lock);
- return;
+ goto out;
}
while (protocol != NULL && protocol->next != NULL) {
if (protocol->next->pid == pid) {
s = protocol->next;
protocol->next = protocol->next->next;
- write_unlock_bh(&protocol_list_lock);
- return;
+ goto out;
}
protocol = protocol->next;
}
+out:
write_unlock_bh(&protocol_list_lock);
}
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 744ed3f07ef..02b9baa1930 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -41,14 +41,13 @@
#include <net/bluetooth/bluetooth.h>
-#define VERSION "2.14"
+#define VERSION "2.15"
/* Bluetooth sockets */
#define BT_MAX_PROTO 8
static struct net_proto_family *bt_proto[BT_MAX_PROTO];
static DEFINE_RWLOCK(bt_proto_lock);
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key bt_lock_key[BT_MAX_PROTO];
static const char *bt_key_strings[BT_MAX_PROTO] = {
"sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP",
@@ -86,11 +85,6 @@ static inline void bt_sock_reclassify_lock(struct socket *sock, int proto)
bt_slock_key_strings[proto], &bt_slock_key[proto],
bt_key_strings[proto], &bt_lock_key[proto]);
}
-#else
-static inline void bt_sock_reclassify_lock(struct socket *sock, int proto)
-{
-}
-#endif
int bt_sock_register(int proto, struct net_proto_family *ops)
{
@@ -217,7 +211,8 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock)
continue;
}
- if (sk->sk_state == BT_CONNECTED || !newsock) {
+ if (sk->sk_state == BT_CONNECTED || !newsock ||
+ bt_sk(parent)->defer_setup) {
bt_accept_unlink(sk);
if (newsock)
sock_graft(sk, newsock);
@@ -232,7 +227,7 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock)
EXPORT_SYMBOL(bt_accept_dequeue);
int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
- struct msghdr *msg, size_t len, int flags)
+ struct msghdr *msg, size_t len, int flags)
{
int noblock = flags & MSG_DONTWAIT;
struct sock *sk = sock->sk;
@@ -277,7 +272,9 @@ static inline unsigned int bt_accept_poll(struct sock *parent)
list_for_each_safe(p, n, &bt_sk(parent)->accept_q) {
sk = (struct sock *) list_entry(p, struct bt_sock, accept_q);
- if (sk->sk_state == BT_CONNECTED)
+ if (sk->sk_state == BT_CONNECTED ||
+ (bt_sk(parent)->defer_setup &&
+ sk->sk_state == BT_CONNECT2))
return POLLIN | POLLRDNORM;
}
diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c
index c9cac7719ef..0073ec8495d 100644
--- a/net/bluetooth/cmtp/core.c
+++ b/net/bluetooth/cmtp/core.c
@@ -126,8 +126,7 @@ static inline void cmtp_add_msgpart(struct cmtp_session *session, int id, const
session->reassembly[id] = nskb;
- if (skb)
- kfree_skb(skb);
+ kfree_skb(skb);
}
static inline int cmtp_recv_frame(struct cmtp_session *session, struct sk_buff *skb)
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index a4a789f24c8..1181db08d9d 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -123,6 +123,8 @@ void hci_add_sco(struct hci_conn *conn, __u16 handle)
conn->state = BT_CONNECT;
conn->out = 1;
+ conn->attempt++;
+
cp.handle = cpu_to_le16(handle);
cp.pkt_type = cpu_to_le16(conn->pkt_type);
@@ -139,6 +141,8 @@ void hci_setup_sync(struct hci_conn *conn, __u16 handle)
conn->state = BT_CONNECT;
conn->out = 1;
+ conn->attempt++;
+
cp.handle = cpu_to_le16(handle);
cp.pkt_type = cpu_to_le16(conn->pkt_type);
@@ -155,6 +159,7 @@ static void hci_conn_timeout(unsigned long arg)
{
struct hci_conn *conn = (void *) arg;
struct hci_dev *hdev = conn->hdev;
+ __u8 reason;
BT_DBG("conn %p state %d", conn, conn->state);
@@ -173,7 +178,8 @@ static void hci_conn_timeout(unsigned long arg)
break;
case BT_CONFIG:
case BT_CONNECTED:
- hci_acl_disconn(conn, 0x13);
+ reason = hci_proto_disconn_ind(conn);
+ hci_acl_disconn(conn, reason);
break;
default:
conn->state = BT_CLOSED;
@@ -216,12 +222,13 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
break;
case SCO_LINK:
if (lmp_esco_capable(hdev))
- conn->pkt_type = hdev->esco_type & SCO_ESCO_MASK;
+ conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) |
+ (hdev->esco_type & EDR_ESCO_MASK);
else
conn->pkt_type = hdev->pkt_type & SCO_PTYPE_MASK;
break;
case ESCO_LINK:
- conn->pkt_type = hdev->esco_type;
+ conn->pkt_type = hdev->esco_type & ~EDR_ESCO_MASK;
break;
}
@@ -280,6 +287,8 @@ int hci_conn_del(struct hci_conn *conn)
skb_queue_purge(&conn->data_q);
+ hci_conn_del_sysfs(conn);
+
return 0;
}
@@ -325,7 +334,7 @@ EXPORT_SYMBOL(hci_get_route);
/* Create SCO or ACL connection.
* Device _must_ be locked */
-struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 auth_type)
+struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 sec_level, __u8 auth_type)
{
struct hci_conn *acl;
struct hci_conn *sco;
@@ -340,6 +349,7 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8
hci_conn_hold(acl);
if (acl->state == BT_OPEN || acl->state == BT_CLOSED) {
+ acl->sec_level = sec_level;
acl->auth_type = auth_type;
hci_acl_connect(acl);
}
@@ -385,51 +395,59 @@ int hci_conn_check_link_mode(struct hci_conn *conn)
EXPORT_SYMBOL(hci_conn_check_link_mode);
/* Authenticate remote device */
-int hci_conn_auth(struct hci_conn *conn)
+static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
{
BT_DBG("conn %p", conn);
- if (conn->ssp_mode > 0 && conn->hdev->ssp_mode > 0) {
- if (!(conn->auth_type & 0x01)) {
- conn->auth_type |= 0x01;
- conn->link_mode &= ~HCI_LM_AUTH;
- }
- }
-
- if (conn->link_mode & HCI_LM_AUTH)
+ if (sec_level > conn->sec_level)
+ conn->sec_level = sec_level;
+ else if (conn->link_mode & HCI_LM_AUTH)
return 1;
+ conn->auth_type = auth_type;
+
if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->pend)) {
struct hci_cp_auth_requested cp;
cp.handle = cpu_to_le16(conn->handle);
hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED,
sizeof(cp), &cp);
}
+
return 0;
}
-EXPORT_SYMBOL(hci_conn_auth);
-/* Enable encryption */
-int hci_conn_encrypt(struct hci_conn *conn)
+/* Enable security */
+int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
{
BT_DBG("conn %p", conn);
+ if (sec_level == BT_SECURITY_SDP)
+ return 1;
+
+ if (sec_level == BT_SECURITY_LOW) {
+ if (conn->ssp_mode > 0 && conn->hdev->ssp_mode > 0)
+ return hci_conn_auth(conn, sec_level, auth_type);
+ else
+ return 1;
+ }
+
if (conn->link_mode & HCI_LM_ENCRYPT)
- return hci_conn_auth(conn);
+ return hci_conn_auth(conn, sec_level, auth_type);
if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend))
return 0;
- if (hci_conn_auth(conn)) {
+ if (hci_conn_auth(conn, sec_level, auth_type)) {
struct hci_cp_set_conn_encrypt cp;
cp.handle = cpu_to_le16(conn->handle);
cp.encrypt = 1;
hci_send_cmd(conn->hdev, HCI_OP_SET_CONN_ENCRYPT,
sizeof(cp), &cp);
}
+
return 0;
}
-EXPORT_SYMBOL(hci_conn_encrypt);
+EXPORT_SYMBOL(hci_conn_security);
/* Change link key */
int hci_conn_change_link_key(struct hci_conn *conn)
@@ -442,12 +460,13 @@ int hci_conn_change_link_key(struct hci_conn *conn)
hci_send_cmd(conn->hdev, HCI_OP_CHANGE_CONN_LINK_KEY,
sizeof(cp), &cp);
}
+
return 0;
}
EXPORT_SYMBOL(hci_conn_change_link_key);
/* Switch role */
-int hci_conn_switch_role(struct hci_conn *conn, uint8_t role)
+int hci_conn_switch_role(struct hci_conn *conn, __u8 role)
{
BT_DBG("conn %p", conn);
@@ -460,6 +479,7 @@ int hci_conn_switch_role(struct hci_conn *conn, uint8_t role)
cp.role = role;
hci_send_cmd(conn->hdev, HCI_OP_SWITCH_ROLE, sizeof(cp), &cp);
}
+
return 0;
}
EXPORT_SYMBOL(hci_conn_switch_role);
@@ -542,9 +562,7 @@ void hci_conn_hash_flush(struct hci_dev *hdev)
c->state = BT_CLOSED;
- hci_conn_del_sysfs(c);
-
- hci_proto_disconn_ind(c, 0x16);
+ hci_proto_disconn_cfm(c, 0x16);
hci_conn_del(c);
}
}
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index ba78cc1eb8d..cd061510b6b 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1565,8 +1565,7 @@ static void hci_cmd_task(unsigned long arg)
/* Send queued commands */
if (atomic_read(&hdev->cmd_cnt) && (skb = skb_dequeue(&hdev->cmd_q))) {
- if (hdev->sent_cmd)
- kfree_skb(hdev->sent_cmd);
+ kfree_skb(hdev->sent_cmd);
if ((hdev->sent_cmd = skb_clone(skb, GFP_ATOMIC))) {
atomic_dec(&hdev->cmd_cnt);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index f91ba690f5d..55534244c3a 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -484,6 +484,15 @@ static void hci_cc_read_local_features(struct hci_dev *hdev, struct sk_buff *skb
if (hdev->features[4] & LMP_EV5)
hdev->esco_type |= (ESCO_EV5);
+ if (hdev->features[5] & LMP_EDR_ESCO_2M)
+ hdev->esco_type |= (ESCO_2EV3);
+
+ if (hdev->features[5] & LMP_EDR_ESCO_3M)
+ hdev->esco_type |= (ESCO_3EV3);
+
+ if (hdev->features[5] & LMP_EDR_3S_ESCO)
+ hdev->esco_type |= (ESCO_2EV5 | ESCO_3EV5);
+
BT_DBG("%s features 0x%.2x%.2x%.2x%.2x%.2x%.2x%.2x%.2x", hdev->name,
hdev->features[0], hdev->features[1],
hdev->features[2], hdev->features[3],
@@ -914,7 +923,8 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s
if (ev->status) {
hci_proto_connect_cfm(conn, ev->status);
hci_conn_del(conn);
- }
+ } else if (ev->link_type != ACL_LINK)
+ hci_proto_connect_cfm(conn, ev->status);
unlock:
hci_dev_unlock(hdev);
@@ -1009,9 +1019,7 @@ static inline void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff
if (conn) {
conn->state = BT_CLOSED;
- hci_conn_del_sysfs(conn);
-
- hci_proto_disconn_ind(conn, ev->reason);
+ hci_proto_disconn_cfm(conn, ev->reason);
hci_conn_del(conn);
}
@@ -1600,7 +1608,8 @@ static inline void hci_remote_ext_features_evt(struct hci_dev *hdev, struct sk_b
if (conn->state == BT_CONFIG) {
if (!ev->status && hdev->ssp_mode > 0 &&
- conn->ssp_mode > 0 && conn->out) {
+ conn->ssp_mode > 0 && conn->out &&
+ conn->sec_level != BT_SECURITY_SDP) {
struct hci_cp_auth_requested cp;
cp.handle = ev->handle;
hci_send_cmd(hdev, HCI_OP_AUTH_REQUESTED,
@@ -1637,6 +1646,13 @@ static inline void hci_sync_conn_complete_evt(struct hci_dev *hdev, struct sk_bu
conn->type = SCO_LINK;
}
+ if (conn->out && ev->status == 0x1c && conn->attempt < 2) {
+ conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) |
+ (hdev->esco_type & EDR_ESCO_MASK);
+ hci_setup_sync(conn, conn->link->handle);
+ goto unlock;
+ }
+
if (!ev->status) {
conn->handle = __le16_to_cpu(ev->handle);
conn->state = BT_CONNECTED;
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index 1a1f916be44..ed82796d4a0 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -140,7 +140,7 @@ static void del_conn(struct work_struct *work)
dev = device_find_child(&conn->dev, NULL, __match_tty);
if (!dev)
break;
- device_move(dev, NULL);
+ device_move(dev, NULL, DPM_ORDER_DEV_LAST);
put_device(dev);
}
diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index b93748e224f..ca4d3b40d5c 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -50,9 +50,10 @@
#include <net/bluetooth/hci_core.h>
#include <net/bluetooth/l2cap.h>
-#define VERSION "2.11"
+#define VERSION "2.13"
-static u32 l2cap_feat_mask = 0x0000;
+static u32 l2cap_feat_mask = 0x0080;
+static u8 l2cap_fixed_chan[8] = { 0x02, };
static const struct proto_ops l2cap_sock_ops;
@@ -77,9 +78,10 @@ static void l2cap_sock_timeout(unsigned long arg)
bh_lock_sock(sk);
- if (sk->sk_state == BT_CONNECT &&
- (l2cap_pi(sk)->link_mode & (L2CAP_LM_AUTH |
- L2CAP_LM_ENCRYPT | L2CAP_LM_SECURE)))
+ if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONFIG)
+ reason = ECONNREFUSED;
+ else if (sk->sk_state == BT_CONNECT &&
+ l2cap_pi(sk)->sec_level != BT_SECURITY_SDP)
reason = ECONNREFUSED;
else
reason = ETIMEDOUT;
@@ -204,6 +206,8 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct sock *sk, struct so
BT_DBG("conn %p, psm 0x%2.2x, dcid 0x%4.4x", conn, l2cap_pi(sk)->psm, l2cap_pi(sk)->dcid);
+ conn->disc_reason = 0x13;
+
l2cap_pi(sk)->conn = conn;
if (sk->sk_type == SOCK_SEQPACKET) {
@@ -259,18 +263,35 @@ static void l2cap_chan_del(struct sock *sk, int err)
}
/* Service level security */
-static inline int l2cap_check_link_mode(struct sock *sk)
+static inline int l2cap_check_security(struct sock *sk)
{
struct l2cap_conn *conn = l2cap_pi(sk)->conn;
+ __u8 auth_type;
- if ((l2cap_pi(sk)->link_mode & L2CAP_LM_ENCRYPT) ||
- (l2cap_pi(sk)->link_mode & L2CAP_LM_SECURE))
- return hci_conn_encrypt(conn->hcon);
+ if (l2cap_pi(sk)->psm == cpu_to_le16(0x0001)) {
+ if (l2cap_pi(sk)->sec_level == BT_SECURITY_HIGH)
+ auth_type = HCI_AT_NO_BONDING_MITM;
+ else
+ auth_type = HCI_AT_NO_BONDING;
- if (l2cap_pi(sk)->link_mode & L2CAP_LM_AUTH)
- return hci_conn_auth(conn->hcon);
+ if (l2cap_pi(sk)->sec_level == BT_SECURITY_LOW)
+ l2cap_pi(sk)->sec_level = BT_SECURITY_SDP;
+ } else {
+ switch (l2cap_pi(sk)->sec_level) {
+ case BT_SECURITY_HIGH:
+ auth_type = HCI_AT_GENERAL_BONDING_MITM;
+ break;
+ case BT_SECURITY_MEDIUM:
+ auth_type = HCI_AT_GENERAL_BONDING;
+ break;
+ default:
+ auth_type = HCI_AT_NO_BONDING;
+ break;
+ }
+ }
- return 1;
+ return hci_conn_security(conn->hcon, l2cap_pi(sk)->sec_level,
+ auth_type);
}
static inline u8 l2cap_get_ident(struct l2cap_conn *conn)
@@ -312,7 +333,10 @@ static void l2cap_do_start(struct sock *sk)
struct l2cap_conn *conn = l2cap_pi(sk)->conn;
if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) {
- if (l2cap_check_link_mode(sk)) {
+ if (!(conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE))
+ return;
+
+ if (l2cap_check_security(sk)) {
struct l2cap_conn_req req;
req.scid = cpu_to_le16(l2cap_pi(sk)->scid);
req.psm = l2cap_pi(sk)->psm;
@@ -356,7 +380,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
}
if (sk->sk_state == BT_CONNECT) {
- if (l2cap_check_link_mode(sk)) {
+ if (l2cap_check_security(sk)) {
struct l2cap_conn_req req;
req.scid = cpu_to_le16(l2cap_pi(sk)->scid);
req.psm = l2cap_pi(sk)->psm;
@@ -371,10 +395,18 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
rsp.scid = cpu_to_le16(l2cap_pi(sk)->dcid);
rsp.dcid = cpu_to_le16(l2cap_pi(sk)->scid);
- if (l2cap_check_link_mode(sk)) {
- sk->sk_state = BT_CONFIG;
- rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS);
- rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
+ if (l2cap_check_security(sk)) {
+ if (bt_sk(sk)->defer_setup) {
+ struct sock *parent = bt_sk(sk)->parent;
+ rsp.result = cpu_to_le16(L2CAP_CR_PEND);
+ rsp.status = cpu_to_le16(L2CAP_CS_AUTHOR_PEND);
+ parent->sk_data_ready(parent, 0);
+
+ } else {
+ sk->sk_state = BT_CONFIG;
+ rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS);
+ rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
+ }
} else {
rsp.result = cpu_to_le16(L2CAP_CR_PEND);
rsp.status = cpu_to_le16(L2CAP_CS_AUTHEN_PEND);
@@ -426,7 +458,7 @@ static void l2cap_conn_unreliable(struct l2cap_conn *conn, int err)
read_lock(&l->lock);
for (sk = l->head; sk; sk = l2cap_pi(sk)->next_c) {
- if (l2cap_pi(sk)->link_mode & L2CAP_LM_RELIABLE)
+ if (l2cap_pi(sk)->force_reliable)
sk->sk_err = err;
}
@@ -437,6 +469,7 @@ static void l2cap_info_timeout(unsigned long arg)
{
struct l2cap_conn *conn = (void *) arg;
+ conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE;
conn->info_ident = 0;
l2cap_conn_start(conn);
@@ -470,6 +503,8 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status)
spin_lock_init(&conn->lock);
rwlock_init(&conn->chan_list.lock);
+ conn->disc_reason = 0x13;
+
return conn;
}
@@ -483,8 +518,7 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
BT_DBG("hcon %p conn %p, err %d", hcon, conn, err);
- if (conn->rx_skb)
- kfree_skb(conn->rx_skb);
+ kfree_skb(conn->rx_skb);
/* Kill channels */
while ((sk = conn->chan_list.head)) {
@@ -608,7 +642,6 @@ static void __l2cap_sock_close(struct sock *sk, int reason)
case BT_CONNECTED:
case BT_CONFIG:
- case BT_CONNECT2:
if (sk->sk_type == SOCK_SEQPACKET) {
struct l2cap_conn *conn = l2cap_pi(sk)->conn;
struct l2cap_disconn_req req;
@@ -624,6 +657,27 @@ static void __l2cap_sock_close(struct sock *sk, int reason)
l2cap_chan_del(sk, reason);
break;
+ case BT_CONNECT2:
+ if (sk->sk_type == SOCK_SEQPACKET) {
+ struct l2cap_conn *conn = l2cap_pi(sk)->conn;
+ struct l2cap_conn_rsp rsp;
+ __u16 result;
+
+ if (bt_sk(sk)->defer_setup)
+ result = L2CAP_CR_SEC_BLOCK;
+ else
+ result = L2CAP_CR_BAD_PSM;
+
+ rsp.scid = cpu_to_le16(l2cap_pi(sk)->dcid);
+ rsp.dcid = cpu_to_le16(l2cap_pi(sk)->scid);
+ rsp.result = cpu_to_le16(result);
+ rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
+ l2cap_send_cmd(conn, l2cap_pi(sk)->ident,
+ L2CAP_CONN_RSP, sizeof(rsp), &rsp);
+ } else
+ l2cap_chan_del(sk, reason);
+ break;
+
case BT_CONNECT:
case BT_DISCONN:
l2cap_chan_del(sk, reason);
@@ -653,13 +707,19 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
if (parent) {
sk->sk_type = parent->sk_type;
+ bt_sk(sk)->defer_setup = bt_sk(parent)->defer_setup;
+
pi->imtu = l2cap_pi(parent)->imtu;
pi->omtu = l2cap_pi(parent)->omtu;
- pi->link_mode = l2cap_pi(parent)->link_mode;
+ pi->sec_level = l2cap_pi(parent)->sec_level;
+ pi->role_switch = l2cap_pi(parent)->role_switch;
+ pi->force_reliable = l2cap_pi(parent)->force_reliable;
} else {
pi->imtu = L2CAP_DEFAULT_MTU;
pi->omtu = 0;
- pi->link_mode = 0;
+ pi->sec_level = BT_SECURITY_LOW;
+ pi->role_switch = 0;
+ pi->force_reliable = 0;
}
/* Default config options */
@@ -723,17 +783,24 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol)
return 0;
}
-static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
+static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
{
- struct sockaddr_l2 *la = (struct sockaddr_l2 *) addr;
struct sock *sk = sock->sk;
- int err = 0;
+ struct sockaddr_l2 la;
+ int len, err = 0;
- BT_DBG("sk %p, %s %d", sk, batostr(&la->l2_bdaddr), la->l2_psm);
+ BT_DBG("sk %p", sk);
if (!addr || addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ memset(&la, 0, sizeof(la));
+ len = min_t(unsigned int, sizeof(la), alen);
+ memcpy(&la, addr, len);
+
+ if (la.l2_cid)
+ return -EINVAL;
+
lock_sock(sk);
if (sk->sk_state != BT_OPEN) {
@@ -741,7 +808,7 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_
goto done;
}
- if (la->l2_psm && btohs(la->l2_psm) < 0x1001 &&
+ if (la.l2_psm && btohs(la.l2_psm) < 0x1001 &&
!capable(CAP_NET_BIND_SERVICE)) {
err = -EACCES;
goto done;
@@ -749,14 +816,17 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_
write_lock_bh(&l2cap_sk_list.lock);
- if (la->l2_psm && __l2cap_get_sock_by_addr(la->l2_psm, &la->l2_bdaddr)) {
+ if (la.l2_psm && __l2cap_get_sock_by_addr(la.l2_psm, &la.l2_bdaddr)) {
err = -EADDRINUSE;
} else {
/* Save source address */
- bacpy(&bt_sk(sk)->src, &la->l2_bdaddr);
- l2cap_pi(sk)->psm = la->l2_psm;
- l2cap_pi(sk)->sport = la->l2_psm;
+ bacpy(&bt_sk(sk)->src, &la.l2_bdaddr);
+ l2cap_pi(sk)->psm = la.l2_psm;
+ l2cap_pi(sk)->sport = la.l2_psm;
sk->sk_state = BT_BOUND;
+
+ if (btohs(la.l2_psm) == 0x0001 || btohs(la.l2_psm) == 0x0003)
+ l2cap_pi(sk)->sec_level = BT_SECURITY_SDP;
}
write_unlock_bh(&l2cap_sk_list.lock);
@@ -776,7 +846,8 @@ static int l2cap_do_connect(struct sock *sk)
__u8 auth_type;
int err = 0;
- BT_DBG("%s -> %s psm 0x%2.2x", batostr(src), batostr(dst), l2cap_pi(sk)->psm);
+ BT_DBG("%s -> %s psm 0x%2.2x", batostr(src), batostr(dst),
+ l2cap_pi(sk)->psm);
if (!(hdev = hci_get_route(dst, src)))
return -EHOSTUNREACH;
@@ -785,21 +856,42 @@ static int l2cap_do_connect(struct sock *sk)
err = -ENOMEM;
- if (l2cap_pi(sk)->link_mode & L2CAP_LM_AUTH ||
- l2cap_pi(sk)->link_mode & L2CAP_LM_ENCRYPT ||
- l2cap_pi(sk)->link_mode & L2CAP_LM_SECURE) {
- if (l2cap_pi(sk)->psm == cpu_to_le16(0x0001))
+ if (sk->sk_type == SOCK_RAW) {
+ switch (l2cap_pi(sk)->sec_level) {
+ case BT_SECURITY_HIGH:
+ auth_type = HCI_AT_DEDICATED_BONDING_MITM;
+ break;
+ case BT_SECURITY_MEDIUM:
+ auth_type = HCI_AT_DEDICATED_BONDING;
+ break;
+ default:
+ auth_type = HCI_AT_NO_BONDING;
+ break;
+ }
+ } else if (l2cap_pi(sk)->psm == cpu_to_le16(0x0001)) {
+ if (l2cap_pi(sk)->sec_level == BT_SECURITY_HIGH)
auth_type = HCI_AT_NO_BONDING_MITM;
else
- auth_type = HCI_AT_GENERAL_BONDING_MITM;
- } else {
- if (l2cap_pi(sk)->psm == cpu_to_le16(0x0001))
auth_type = HCI_AT_NO_BONDING;
- else
+
+ if (l2cap_pi(sk)->sec_level == BT_SECURITY_LOW)
+ l2cap_pi(sk)->sec_level = BT_SECURITY_SDP;
+ } else {
+ switch (l2cap_pi(sk)->sec_level) {
+ case BT_SECURITY_HIGH:
+ auth_type = HCI_AT_GENERAL_BONDING_MITM;
+ break;
+ case BT_SECURITY_MEDIUM:
auth_type = HCI_AT_GENERAL_BONDING;
+ break;
+ default:
+ auth_type = HCI_AT_NO_BONDING;
+ break;
+ }
}
- hcon = hci_connect(hdev, ACL_LINK, dst, auth_type);
+ hcon = hci_connect(hdev, ACL_LINK, dst,
+ l2cap_pi(sk)->sec_level, auth_type);
if (!hcon)
goto done;
@@ -835,20 +927,25 @@ done:
static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags)
{
- struct sockaddr_l2 *la = (struct sockaddr_l2 *) addr;
struct sock *sk = sock->sk;
- int err = 0;
-
- lock_sock(sk);
+ struct sockaddr_l2 la;
+ int len, err = 0;
BT_DBG("sk %p", sk);
- if (addr->sa_family != AF_BLUETOOTH || alen < sizeof(struct sockaddr_l2)) {
- err = -EINVAL;
- goto done;
- }
+ if (!addr || addr->sa_family != AF_BLUETOOTH)
+ return -EINVAL;
+
+ memset(&la, 0, sizeof(la));
+ len = min_t(unsigned int, sizeof(la), alen);
+ memcpy(&la, addr, len);
+
+ if (la.l2_cid)
+ return -EINVAL;
+
+ lock_sock(sk);
- if (sk->sk_type == SOCK_SEQPACKET && !la->l2_psm) {
+ if (sk->sk_type == SOCK_SEQPACKET && !la.l2_psm) {
err = -EINVAL;
goto done;
}
@@ -875,8 +972,8 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al
}
/* Set destination address and psm */
- bacpy(&bt_sk(sk)->dst, &la->l2_bdaddr);
- l2cap_pi(sk)->psm = la->l2_psm;
+ bacpy(&bt_sk(sk)->dst, &la.l2_bdaddr);
+ l2cap_pi(sk)->psm = la.l2_psm;
if ((err = l2cap_do_connect(sk)))
goto done;
@@ -1000,12 +1097,16 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *l
addr->sa_family = AF_BLUETOOTH;
*len = sizeof(struct sockaddr_l2);
- if (peer)
+ if (peer) {
+ la->l2_psm = l2cap_pi(sk)->psm;
bacpy(&la->l2_bdaddr, &bt_sk(sk)->dst);
- else
+ la->l2_cid = htobs(l2cap_pi(sk)->dcid);
+ } else {
+ la->l2_psm = l2cap_pi(sk)->sport;
bacpy(&la->l2_bdaddr, &bt_sk(sk)->src);
+ la->l2_cid = htobs(l2cap_pi(sk)->scid);
+ }
- la->l2_psm = l2cap_pi(sk)->psm;
return 0;
}
@@ -1106,11 +1207,38 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms
return err;
}
-static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen)
+static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags)
+{
+ struct sock *sk = sock->sk;
+
+ lock_sock(sk);
+
+ if (sk->sk_state == BT_CONNECT2 && bt_sk(sk)->defer_setup) {
+ struct l2cap_conn_rsp rsp;
+
+ sk->sk_state = BT_CONFIG;
+
+ rsp.scid = cpu_to_le16(l2cap_pi(sk)->dcid);
+ rsp.dcid = cpu_to_le16(l2cap_pi(sk)->scid);
+ rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS);
+ rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
+ l2cap_send_cmd(l2cap_pi(sk)->conn, l2cap_pi(sk)->ident,
+ L2CAP_CONN_RSP, sizeof(rsp), &rsp);
+
+ release_sock(sk);
+ return 0;
+ }
+
+ release_sock(sk);
+
+ return bt_sock_recvmsg(iocb, sock, msg, len, flags);
+}
+
+static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, int optlen)
{
struct sock *sk = sock->sk;
struct l2cap_options opts;
- int err = 0, len;
+ int len, err = 0;
u32 opt;
BT_DBG("sk %p", sk);
@@ -1140,7 +1268,15 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch
break;
}
- l2cap_pi(sk)->link_mode = opt;
+ if (opt & L2CAP_LM_AUTH)
+ l2cap_pi(sk)->sec_level = BT_SECURITY_LOW;
+ if (opt & L2CAP_LM_ENCRYPT)
+ l2cap_pi(sk)->sec_level = BT_SECURITY_MEDIUM;
+ if (opt & L2CAP_LM_SECURE)
+ l2cap_pi(sk)->sec_level = BT_SECURITY_HIGH;
+
+ l2cap_pi(sk)->role_switch = (opt & L2CAP_LM_MASTER);
+ l2cap_pi(sk)->force_reliable = (opt & L2CAP_LM_RELIABLE);
break;
default:
@@ -1152,12 +1288,77 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch
return err;
}
-static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen)
+static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen)
+{
+ struct sock *sk = sock->sk;
+ struct bt_security sec;
+ int len, err = 0;
+ u32 opt;
+
+ BT_DBG("sk %p", sk);
+
+ if (level == SOL_L2CAP)
+ return l2cap_sock_setsockopt_old(sock, optname, optval, optlen);
+
+ if (level != SOL_BLUETOOTH)
+ return -ENOPROTOOPT;
+
+ lock_sock(sk);
+
+ switch (optname) {
+ case BT_SECURITY:
+ if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_RAW) {
+ err = -EINVAL;
+ break;
+ }
+
+ sec.level = BT_SECURITY_LOW;
+
+ len = min_t(unsigned int, sizeof(sec), optlen);
+ if (copy_from_user((char *) &sec, optval, len)) {
+ err = -EFAULT;
+ break;
+ }
+
+ if (sec.level < BT_SECURITY_LOW ||
+ sec.level > BT_SECURITY_HIGH) {
+ err = -EINVAL;
+ break;
+ }
+
+ l2cap_pi(sk)->sec_level = sec.level;
+ break;
+
+ case BT_DEFER_SETUP:
+ if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) {
+ err = -EINVAL;
+ break;
+ }
+
+ if (get_user(opt, (u32 __user *) optval)) {
+ err = -EFAULT;
+ break;
+ }
+
+ bt_sk(sk)->defer_setup = opt;
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ release_sock(sk);
+ return err;
+}
+
+static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
struct l2cap_options opts;
struct l2cap_conninfo cinfo;
int len, err = 0;
+ u32 opt;
BT_DBG("sk %p", sk);
@@ -1180,12 +1381,36 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, ch
break;
case L2CAP_LM:
- if (put_user(l2cap_pi(sk)->link_mode, (u32 __user *) optval))
+ switch (l2cap_pi(sk)->sec_level) {
+ case BT_SECURITY_LOW:
+ opt = L2CAP_LM_AUTH;
+ break;
+ case BT_SECURITY_MEDIUM:
+ opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT;
+ break;
+ case BT_SECURITY_HIGH:
+ opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT |
+ L2CAP_LM_SECURE;
+ break;
+ default:
+ opt = 0;
+ break;
+ }
+
+ if (l2cap_pi(sk)->role_switch)
+ opt |= L2CAP_LM_MASTER;
+
+ if (l2cap_pi(sk)->force_reliable)
+ opt |= L2CAP_LM_RELIABLE;
+
+ if (put_user(opt, (u32 __user *) optval))
err = -EFAULT;
break;
case L2CAP_CONNINFO:
- if (sk->sk_state != BT_CONNECTED) {
+ if (sk->sk_state != BT_CONNECTED &&
+ !(sk->sk_state == BT_CONNECT2 &&
+ bt_sk(sk)->defer_setup)) {
err = -ENOTCONN;
break;
}
@@ -1208,6 +1433,60 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, ch
return err;
}
+static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen)
+{
+ struct sock *sk = sock->sk;
+ struct bt_security sec;
+ int len, err = 0;
+
+ BT_DBG("sk %p", sk);
+
+ if (level == SOL_L2CAP)
+ return l2cap_sock_getsockopt_old(sock, optname, optval, optlen);
+
+ if (level != SOL_BLUETOOTH)
+ return -ENOPROTOOPT;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ lock_sock(sk);
+
+ switch (optname) {
+ case BT_SECURITY:
+ if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_RAW) {
+ err = -EINVAL;
+ break;
+ }
+
+ sec.level = l2cap_pi(sk)->sec_level;
+
+ len = min_t(unsigned int, len, sizeof(sec));
+ if (copy_to_user(optval, (char *) &sec, len))
+ err = -EFAULT;
+
+ break;
+
+ case BT_DEFER_SETUP:
+ if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) {
+ err = -EINVAL;
+ break;
+ }
+
+ if (put_user(bt_sk(sk)->defer_setup, (u32 __user *) optval))
+ err = -EFAULT;
+
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ release_sock(sk);
+ return err;
+}
+
static int l2cap_sock_shutdown(struct socket *sock, int how)
{
struct sock *sk = sock->sk;
@@ -1270,11 +1549,6 @@ static void l2cap_chan_ready(struct sock *sk)
*/
parent->sk_data_ready(parent, 0);
}
-
- if (l2cap_pi(sk)->link_mode & L2CAP_LM_SECURE) {
- struct l2cap_conn *conn = l2cap_pi(sk)->conn;
- hci_conn_change_link_key(conn->hcon);
- }
}
/* Copy frame to all raw sockets on that connection */
@@ -1549,8 +1823,11 @@ static inline int l2cap_command_rej(struct l2cap_conn *conn, struct l2cap_cmd_hd
if ((conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) &&
cmd->ident == conn->info_ident) {
- conn->info_ident = 0;
del_timer(&conn->info_timer);
+
+ conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE;
+ conn->info_ident = 0;
+
l2cap_conn_start(conn);
}
@@ -1580,6 +1857,7 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd
/* Check if the ACL is secure enough (if not SDP) */
if (psm != cpu_to_le16(0x0001) &&
!hci_conn_check_link_mode(conn->hcon)) {
+ conn->disc_reason = 0x05;
result = L2CAP_CR_SEC_BLOCK;
goto response;
}
@@ -1621,11 +1899,18 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd
l2cap_pi(sk)->ident = cmd->ident;
- if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) {
- if (l2cap_check_link_mode(sk)) {
- sk->sk_state = BT_CONFIG;
- result = L2CAP_CR_SUCCESS;
- status = L2CAP_CS_NO_INFO;
+ if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE) {
+ if (l2cap_check_security(sk)) {
+ if (bt_sk(sk)->defer_setup) {
+ sk->sk_state = BT_CONNECT2;
+ result = L2CAP_CR_PEND;
+ status = L2CAP_CS_AUTHOR_PEND;
+ parent->sk_data_ready(parent, 0);
+ } else {
+ sk->sk_state = BT_CONFIG;
+ result = L2CAP_CR_SUCCESS;
+ status = L2CAP_CS_NO_INFO;
+ }
} else {
sk->sk_state = BT_CONNECT2;
result = L2CAP_CR_PEND;
@@ -1695,11 +1980,14 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd
l2cap_pi(sk)->dcid = dcid;
l2cap_pi(sk)->conf_state |= L2CAP_CONF_REQ_SENT;
+ l2cap_pi(sk)->conf_state &= ~L2CAP_CONF_CONNECT_PEND;
+
l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ,
l2cap_build_conf_req(sk, req), req);
break;
case L2CAP_CR_PEND:
+ l2cap_pi(sk)->conf_state |= L2CAP_CONF_CONNECT_PEND;
break;
default:
@@ -1908,6 +2196,14 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, struct l2cap_cm
put_unaligned(cpu_to_le32(l2cap_feat_mask), (__le32 *) rsp->data);
l2cap_send_cmd(conn, cmd->ident,
L2CAP_INFO_RSP, sizeof(buf), buf);
+ } else if (type == L2CAP_IT_FIXED_CHAN) {
+ u8 buf[12];
+ struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) buf;
+ rsp->type = cpu_to_le16(L2CAP_IT_FIXED_CHAN);
+ rsp->result = cpu_to_le16(L2CAP_IR_SUCCESS);
+ memcpy(buf + 4, l2cap_fixed_chan, 8);
+ l2cap_send_cmd(conn, cmd->ident,
+ L2CAP_INFO_RSP, sizeof(buf), buf);
} else {
struct l2cap_info_rsp rsp;
rsp.type = cpu_to_le16(type);
@@ -1929,14 +2225,31 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cm
BT_DBG("type 0x%4.4x result 0x%2.2x", type, result);
- conn->info_ident = 0;
-
del_timer(&conn->info_timer);
- if (type == L2CAP_IT_FEAT_MASK)
+ if (type == L2CAP_IT_FEAT_MASK) {
conn->feat_mask = get_unaligned_le32(rsp->data);
- l2cap_conn_start(conn);
+ if (conn->feat_mask & 0x0080) {
+ struct l2cap_info_req req;
+ req.type = cpu_to_le16(L2CAP_IT_FIXED_CHAN);
+
+ conn->info_ident = l2cap_get_ident(conn);
+
+ l2cap_send_cmd(conn, conn->info_ident,
+ L2CAP_INFO_REQ, sizeof(req), &req);
+ } else {
+ conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE;
+ conn->info_ident = 0;
+
+ l2cap_conn_start(conn);
+ }
+ } else if (type == L2CAP_IT_FIXED_CHAN) {
+ conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE;
+ conn->info_ident = 0;
+
+ l2cap_conn_start(conn);
+ }
return 0;
}
@@ -2143,10 +2456,15 @@ static int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
continue;
if (!bacmp(&bt_sk(sk)->src, &hdev->bdaddr)) {
- lm1 |= (HCI_LM_ACCEPT | l2cap_pi(sk)->link_mode);
+ lm1 |= HCI_LM_ACCEPT;
+ if (l2cap_pi(sk)->role_switch)
+ lm1 |= HCI_LM_MASTER;
exact++;
- } else if (!bacmp(&bt_sk(sk)->src, BDADDR_ANY))
- lm2 |= (HCI_LM_ACCEPT | l2cap_pi(sk)->link_mode);
+ } else if (!bacmp(&bt_sk(sk)->src, BDADDR_ANY)) {
+ lm2 |= HCI_LM_ACCEPT;
+ if (l2cap_pi(sk)->role_switch)
+ lm2 |= HCI_LM_MASTER;
+ }
}
read_unlock(&l2cap_sk_list.lock);
@@ -2172,89 +2490,48 @@ static int l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
return 0;
}
-static int l2cap_disconn_ind(struct hci_conn *hcon, u8 reason)
+static int l2cap_disconn_ind(struct hci_conn *hcon)
{
- BT_DBG("hcon %p reason %d", hcon, reason);
+ struct l2cap_conn *conn = hcon->l2cap_data;
- if (hcon->type != ACL_LINK)
- return 0;
+ BT_DBG("hcon %p", hcon);
- l2cap_conn_del(hcon, bt_err(reason));
+ if (hcon->type != ACL_LINK || !conn)
+ return 0x13;
- return 0;
+ return conn->disc_reason;
}
-static int l2cap_auth_cfm(struct hci_conn *hcon, u8 status)
+static int l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason)
{
- struct l2cap_chan_list *l;
- struct l2cap_conn *conn = hcon->l2cap_data;
- struct sock *sk;
+ BT_DBG("hcon %p reason %d", hcon, reason);
- if (!conn)
+ if (hcon->type != ACL_LINK)
return 0;
- l = &conn->chan_list;
-
- BT_DBG("conn %p", conn);
-
- read_lock(&l->lock);
-
- for (sk = l->head; sk; sk = l2cap_pi(sk)->next_c) {
- struct l2cap_pinfo *pi = l2cap_pi(sk);
-
- bh_lock_sock(sk);
-
- if ((pi->link_mode & (L2CAP_LM_ENCRYPT | L2CAP_LM_SECURE)) &&
- !(hcon->link_mode & HCI_LM_ENCRYPT) &&
- !status) {
- bh_unlock_sock(sk);
- continue;
- }
-
- if (sk->sk_state == BT_CONNECT) {
- if (!status) {
- struct l2cap_conn_req req;
- req.scid = cpu_to_le16(l2cap_pi(sk)->scid);
- req.psm = l2cap_pi(sk)->psm;
-
- l2cap_pi(sk)->ident = l2cap_get_ident(conn);
-
- l2cap_send_cmd(conn, l2cap_pi(sk)->ident,
- L2CAP_CONN_REQ, sizeof(req), &req);
- } else {
- l2cap_sock_clear_timer(sk);
- l2cap_sock_set_timer(sk, HZ / 10);
- }
- } else if (sk->sk_state == BT_CONNECT2) {
- struct l2cap_conn_rsp rsp;
- __u16 result;
+ l2cap_conn_del(hcon, bt_err(reason));
- if (!status) {
- sk->sk_state = BT_CONFIG;
- result = L2CAP_CR_SUCCESS;
- } else {
- sk->sk_state = BT_DISCONN;
- l2cap_sock_set_timer(sk, HZ / 10);
- result = L2CAP_CR_SEC_BLOCK;
- }
+ return 0;
+}
- rsp.scid = cpu_to_le16(l2cap_pi(sk)->dcid);
- rsp.dcid = cpu_to_le16(l2cap_pi(sk)->scid);
- rsp.result = cpu_to_le16(result);
- rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
- l2cap_send_cmd(conn, l2cap_pi(sk)->ident,
- L2CAP_CONN_RSP, sizeof(rsp), &rsp);
- }
+static inline void l2cap_check_encryption(struct sock *sk, u8 encrypt)
+{
+ if (sk->sk_type != SOCK_SEQPACKET)
+ return;
- bh_unlock_sock(sk);
+ if (encrypt == 0x00) {
+ if (l2cap_pi(sk)->sec_level == BT_SECURITY_MEDIUM) {
+ l2cap_sock_clear_timer(sk);
+ l2cap_sock_set_timer(sk, HZ * 5);
+ } else if (l2cap_pi(sk)->sec_level == BT_SECURITY_HIGH)
+ __l2cap_sock_close(sk, ECONNREFUSED);
+ } else {
+ if (l2cap_pi(sk)->sec_level == BT_SECURITY_MEDIUM)
+ l2cap_sock_clear_timer(sk);
}
-
- read_unlock(&l->lock);
-
- return 0;
}
-static int l2cap_encrypt_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
+static int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
{
struct l2cap_chan_list *l;
struct l2cap_conn *conn = hcon->l2cap_data;
@@ -2270,15 +2547,16 @@ static int l2cap_encrypt_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
read_lock(&l->lock);
for (sk = l->head; sk; sk = l2cap_pi(sk)->next_c) {
- struct l2cap_pinfo *pi = l2cap_pi(sk);
-
bh_lock_sock(sk);
- if ((pi->link_mode & (L2CAP_LM_ENCRYPT | L2CAP_LM_SECURE)) &&
- (sk->sk_state == BT_CONNECTED ||
- sk->sk_state == BT_CONFIG) &&
- !status && encrypt == 0x00) {
- __l2cap_sock_close(sk, ECONNREFUSED);
+ if (l2cap_pi(sk)->conf_state & L2CAP_CONF_CONNECT_PEND) {
+ bh_unlock_sock(sk);
+ continue;
+ }
+
+ if (!status && (sk->sk_state == BT_CONNECTED ||
+ sk->sk_state == BT_CONFIG)) {
+ l2cap_check_encryption(sk, encrypt);
bh_unlock_sock(sk);
continue;
}
@@ -2376,7 +2654,7 @@ static int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 fl
goto drop;
skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len),
- skb->len);
+ skb->len);
conn->rx_len = len - skb->len;
} else {
BT_DBG("Cont: frag len %d (expecting %d)", skb->len, conn->rx_len);
@@ -2398,7 +2676,7 @@ static int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 fl
}
skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len),
- skb->len);
+ skb->len);
conn->rx_len -= skb->len;
if (!conn->rx_len) {
@@ -2424,10 +2702,10 @@ static ssize_t l2cap_sysfs_show(struct class *dev, char *buf)
sk_for_each(sk, node, &l2cap_sk_list.head) {
struct l2cap_pinfo *pi = l2cap_pi(sk);
- str += sprintf(str, "%s %s %d %d 0x%4.4x 0x%4.4x %d %d 0x%x\n",
+ str += sprintf(str, "%s %s %d %d 0x%4.4x 0x%4.4x %d %d %d\n",
batostr(&bt_sk(sk)->src), batostr(&bt_sk(sk)->dst),
sk->sk_state, btohs(pi->psm), pi->scid, pi->dcid,
- pi->imtu, pi->omtu, pi->link_mode);
+ pi->imtu, pi->omtu, pi->sec_level);
}
read_unlock_bh(&l2cap_sk_list.lock);
@@ -2447,7 +2725,7 @@ static const struct proto_ops l2cap_sock_ops = {
.accept = l2cap_sock_accept,
.getname = l2cap_sock_getname,
.sendmsg = l2cap_sock_sendmsg,
- .recvmsg = bt_sock_recvmsg,
+ .recvmsg = l2cap_sock_recvmsg,
.poll = bt_sock_poll,
.ioctl = bt_sock_ioctl,
.mmap = sock_no_mmap,
@@ -2469,8 +2747,8 @@ static struct hci_proto l2cap_hci_proto = {
.connect_ind = l2cap_connect_ind,
.connect_cfm = l2cap_connect_cfm,
.disconn_ind = l2cap_disconn_ind,
- .auth_cfm = l2cap_auth_cfm,
- .encrypt_cfm = l2cap_encrypt_cfm,
+ .disconn_cfm = l2cap_disconn_cfm,
+ .security_cfm = l2cap_security_cfm,
.recv_acldata = l2cap_recv_acldata
};
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index acd84fd524b..1d0fb0f23c6 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -46,7 +46,7 @@
#include <net/bluetooth/l2cap.h>
#include <net/bluetooth/rfcomm.h>
-#define VERSION "1.10"
+#define VERSION "1.11"
static int disable_cfc = 0;
static int channel_mtu = -1;
@@ -223,19 +223,25 @@ static int rfcomm_l2sock_create(struct socket **sock)
return err;
}
-static inline int rfcomm_check_link_mode(struct rfcomm_dlc *d)
+static inline int rfcomm_check_security(struct rfcomm_dlc *d)
{
struct sock *sk = d->session->sock->sk;
+ __u8 auth_type;
- if (d->link_mode & (RFCOMM_LM_ENCRYPT | RFCOMM_LM_SECURE)) {
- if (!hci_conn_encrypt(l2cap_pi(sk)->conn->hcon))
- return 1;
- } else if (d->link_mode & RFCOMM_LM_AUTH) {
- if (!hci_conn_auth(l2cap_pi(sk)->conn->hcon))
- return 1;
+ switch (d->sec_level) {
+ case BT_SECURITY_HIGH:
+ auth_type = HCI_AT_GENERAL_BONDING_MITM;
+ break;
+ case BT_SECURITY_MEDIUM:
+ auth_type = HCI_AT_GENERAL_BONDING;
+ break;
+ default:
+ auth_type = HCI_AT_NO_BONDING;
+ break;
}
- return 0;
+ return hci_conn_security(l2cap_pi(sk)->conn->hcon, d->sec_level,
+ auth_type);
}
/* ---- RFCOMM DLCs ---- */
@@ -388,10 +394,10 @@ static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst,
d->cfc = (s->cfc == RFCOMM_CFC_UNKNOWN) ? 0 : s->cfc;
if (s->state == BT_CONNECTED) {
- if (rfcomm_check_link_mode(d))
- set_bit(RFCOMM_AUTH_PENDING, &d->flags);
- else
+ if (rfcomm_check_security(d))
rfcomm_send_pn(s, 1, d);
+ else
+ set_bit(RFCOMM_AUTH_PENDING, &d->flags);
}
rfcomm_dlc_set_timer(d, RFCOMM_CONN_TIMEOUT);
@@ -421,9 +427,16 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err)
d, d->state, d->dlci, err, s);
switch (d->state) {
- case BT_CONNECTED:
- case BT_CONFIG:
case BT_CONNECT:
+ case BT_CONFIG:
+ if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
+ set_bit(RFCOMM_AUTH_REJECT, &d->flags);
+ rfcomm_schedule(RFCOMM_SCHED_AUTH);
+ break;
+ }
+ /* Fall through */
+
+ case BT_CONNECTED:
d->state = BT_DISCONN;
if (skb_queue_empty(&d->tx_queue)) {
rfcomm_send_disc(s, d->dlci);
@@ -434,6 +447,15 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err)
}
break;
+ case BT_OPEN:
+ case BT_CONNECT2:
+ if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
+ set_bit(RFCOMM_AUTH_REJECT, &d->flags);
+ rfcomm_schedule(RFCOMM_SCHED_AUTH);
+ break;
+ }
+ /* Fall through */
+
default:
rfcomm_dlc_clear_timer(d);
@@ -636,6 +658,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst
bacpy(&addr.l2_bdaddr, src);
addr.l2_family = AF_BLUETOOTH;
addr.l2_psm = 0;
+ addr.l2_cid = 0;
*err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr));
if (*err < 0)
goto failed;
@@ -657,6 +680,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst
bacpy(&addr.l2_bdaddr, dst);
addr.l2_family = AF_BLUETOOTH;
addr.l2_psm = htobs(RFCOMM_PSM);
+ addr.l2_cid = 0;
*err = kernel_connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK);
if (*err == 0 || *err == -EINPROGRESS)
return s;
@@ -1162,7 +1186,7 @@ static int rfcomm_recv_disc(struct rfcomm_session *s, u8 dlci)
return 0;
}
-static void rfcomm_dlc_accept(struct rfcomm_dlc *d)
+void rfcomm_dlc_accept(struct rfcomm_dlc *d)
{
struct sock *sk = d->session->sock->sk;
@@ -1175,12 +1199,31 @@ static void rfcomm_dlc_accept(struct rfcomm_dlc *d)
d->state_change(d, 0);
rfcomm_dlc_unlock(d);
- if (d->link_mode & RFCOMM_LM_MASTER)
+ if (d->role_switch)
hci_conn_switch_role(l2cap_pi(sk)->conn->hcon, 0x00);
rfcomm_send_msc(d->session, 1, d->dlci, d->v24_sig);
}
+static void rfcomm_check_accept(struct rfcomm_dlc *d)
+{
+ if (rfcomm_check_security(d)) {
+ if (d->defer_setup) {
+ set_bit(RFCOMM_DEFER_SETUP, &d->flags);
+ rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
+
+ rfcomm_dlc_lock(d);
+ d->state = BT_CONNECT2;
+ d->state_change(d, 0);
+ rfcomm_dlc_unlock(d);
+ } else
+ rfcomm_dlc_accept(d);
+ } else {
+ set_bit(RFCOMM_AUTH_PENDING, &d->flags);
+ rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
+ }
+}
+
static int rfcomm_recv_sabm(struct rfcomm_session *s, u8 dlci)
{
struct rfcomm_dlc *d;
@@ -1203,11 +1246,7 @@ static int rfcomm_recv_sabm(struct rfcomm_session *s, u8 dlci)
if (d) {
if (d->state == BT_OPEN) {
/* DLC was previously opened by PN request */
- if (rfcomm_check_link_mode(d)) {
- set_bit(RFCOMM_AUTH_PENDING, &d->flags);
- rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
- } else
- rfcomm_dlc_accept(d);
+ rfcomm_check_accept(d);
}
return 0;
}
@@ -1219,11 +1258,7 @@ static int rfcomm_recv_sabm(struct rfcomm_session *s, u8 dlci)
d->addr = __addr(s->initiator, dlci);
rfcomm_dlc_link(s, d);
- if (rfcomm_check_link_mode(d)) {
- set_bit(RFCOMM_AUTH_PENDING, &d->flags);
- rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
- } else
- rfcomm_dlc_accept(d);
+ rfcomm_check_accept(d);
} else {
rfcomm_send_dm(s, dlci);
}
@@ -1637,11 +1672,12 @@ static void rfcomm_process_connect(struct rfcomm_session *s)
d = list_entry(p, struct rfcomm_dlc, list);
if (d->state == BT_CONFIG) {
d->mtu = s->mtu;
- if (rfcomm_check_link_mode(d)) {
+ if (rfcomm_check_security(d)) {
+ rfcomm_send_pn(s, 1, d);
+ } else {
set_bit(RFCOMM_AUTH_PENDING, &d->flags);
rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
- } else
- rfcomm_send_pn(s, 1, d);
+ }
}
}
}
@@ -1717,11 +1753,17 @@ static inline void rfcomm_process_dlcs(struct rfcomm_session *s)
if (d->out) {
rfcomm_send_pn(s, 1, d);
rfcomm_dlc_set_timer(d, RFCOMM_CONN_TIMEOUT);
- } else
- rfcomm_dlc_accept(d);
- if (d->link_mode & RFCOMM_LM_SECURE) {
- struct sock *sk = s->sock->sk;
- hci_conn_change_link_key(l2cap_pi(sk)->conn->hcon);
+ } else {
+ if (d->defer_setup) {
+ set_bit(RFCOMM_DEFER_SETUP, &d->flags);
+ rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
+
+ rfcomm_dlc_lock(d);
+ d->state = BT_CONNECT2;
+ d->state_change(d, 0);
+ rfcomm_dlc_unlock(d);
+ } else
+ rfcomm_dlc_accept(d);
}
continue;
} else if (test_and_clear_bit(RFCOMM_AUTH_REJECT, &d->flags)) {
@@ -1734,6 +1776,9 @@ static inline void rfcomm_process_dlcs(struct rfcomm_session *s)
continue;
}
+ if (test_bit(RFCOMM_SEC_PENDING, &d->flags))
+ continue;
+
if (test_bit(RFCOMM_TX_THROTTLED, &s->flags))
continue;
@@ -1876,6 +1921,7 @@ static int rfcomm_add_listener(bdaddr_t *ba)
bacpy(&addr.l2_bdaddr, ba);
addr.l2_family = AF_BLUETOOTH;
addr.l2_psm = htobs(RFCOMM_PSM);
+ addr.l2_cid = 0;
err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr));
if (err < 0) {
BT_ERR("Bind failed %d", err);
@@ -1947,42 +1993,7 @@ static int rfcomm_run(void *unused)
return 0;
}
-static void rfcomm_auth_cfm(struct hci_conn *conn, u8 status)
-{
- struct rfcomm_session *s;
- struct rfcomm_dlc *d;
- struct list_head *p, *n;
-
- BT_DBG("conn %p status 0x%02x", conn, status);
-
- s = rfcomm_session_get(&conn->hdev->bdaddr, &conn->dst);
- if (!s)
- return;
-
- rfcomm_session_hold(s);
-
- list_for_each_safe(p, n, &s->dlcs) {
- d = list_entry(p, struct rfcomm_dlc, list);
-
- if ((d->link_mode & (RFCOMM_LM_ENCRYPT | RFCOMM_LM_SECURE)) &&
- !(conn->link_mode & HCI_LM_ENCRYPT) && !status)
- continue;
-
- if (!test_and_clear_bit(RFCOMM_AUTH_PENDING, &d->flags))
- continue;
-
- if (!status)
- set_bit(RFCOMM_AUTH_ACCEPT, &d->flags);
- else
- set_bit(RFCOMM_AUTH_REJECT, &d->flags);
- }
-
- rfcomm_session_put(s);
-
- rfcomm_schedule(RFCOMM_SCHED_AUTH);
-}
-
-static void rfcomm_encrypt_cfm(struct hci_conn *conn, u8 status, u8 encrypt)
+static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt)
{
struct rfcomm_session *s;
struct rfcomm_dlc *d;
@@ -1999,18 +2010,29 @@ static void rfcomm_encrypt_cfm(struct hci_conn *conn, u8 status, u8 encrypt)
list_for_each_safe(p, n, &s->dlcs) {
d = list_entry(p, struct rfcomm_dlc, list);
- if ((d->link_mode & (RFCOMM_LM_ENCRYPT | RFCOMM_LM_SECURE)) &&
- (d->state == BT_CONNECTED ||
- d->state == BT_CONFIG) &&
- !status && encrypt == 0x00) {
- __rfcomm_dlc_close(d, ECONNREFUSED);
- continue;
+ if (test_and_clear_bit(RFCOMM_SEC_PENDING, &d->flags)) {
+ rfcomm_dlc_clear_timer(d);
+ if (status || encrypt == 0x00) {
+ __rfcomm_dlc_close(d, ECONNREFUSED);
+ continue;
+ }
+ }
+
+ if (d->state == BT_CONNECTED && !status && encrypt == 0x00) {
+ if (d->sec_level == BT_SECURITY_MEDIUM) {
+ set_bit(RFCOMM_SEC_PENDING, &d->flags);
+ rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
+ continue;
+ } else if (d->sec_level == BT_SECURITY_HIGH) {
+ __rfcomm_dlc_close(d, ECONNREFUSED);
+ continue;
+ }
}
if (!test_and_clear_bit(RFCOMM_AUTH_PENDING, &d->flags))
continue;
- if (!status && encrypt)
+ if (!status)
set_bit(RFCOMM_AUTH_ACCEPT, &d->flags);
else
set_bit(RFCOMM_AUTH_REJECT, &d->flags);
@@ -2023,8 +2045,7 @@ static void rfcomm_encrypt_cfm(struct hci_conn *conn, u8 status, u8 encrypt)
static struct hci_cb rfcomm_cb = {
.name = "RFCOMM",
- .auth_cfm = rfcomm_auth_cfm,
- .encrypt_cfm = rfcomm_encrypt_cfm
+ .security_cfm = rfcomm_security_cfm
};
static ssize_t rfcomm_dlc_sysfs_show(struct class *dev, char *buf)
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index d3fc6fca38d..7f482784e9f 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -261,12 +261,19 @@ static void rfcomm_sock_init(struct sock *sk, struct sock *parent)
if (parent) {
sk->sk_type = parent->sk_type;
- pi->link_mode = rfcomm_pi(parent)->link_mode;
+ pi->dlc->defer_setup = bt_sk(parent)->defer_setup;
+
+ pi->sec_level = rfcomm_pi(parent)->sec_level;
+ pi->role_switch = rfcomm_pi(parent)->role_switch;
} else {
- pi->link_mode = 0;
+ pi->dlc->defer_setup = 0;
+
+ pi->sec_level = BT_SECURITY_LOW;
+ pi->role_switch = 0;
}
- pi->dlc->link_mode = pi->link_mode;
+ pi->dlc->sec_level = pi->sec_level;
+ pi->dlc->role_switch = pi->role_switch;
}
static struct proto rfcomm_proto = {
@@ -406,7 +413,8 @@ static int rfcomm_sock_connect(struct socket *sock, struct sockaddr *addr, int a
bacpy(&bt_sk(sk)->dst, &sa->rc_bdaddr);
rfcomm_pi(sk)->channel = sa->rc_channel;
- d->link_mode = rfcomm_pi(sk)->link_mode;
+ d->sec_level = rfcomm_pi(sk)->sec_level;
+ d->role_switch = rfcomm_pi(sk)->role_switch;
err = rfcomm_dlc_open(d, &bt_sk(sk)->src, &sa->rc_bdaddr, sa->rc_channel);
if (!err)
@@ -554,6 +562,9 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
struct sk_buff *skb;
int sent = 0;
+ if (test_bit(RFCOMM_DEFER_SETUP, &d->flags))
+ return -ENOTCONN;
+
if (msg->msg_flags & MSG_OOB)
return -EOPNOTSUPP;
@@ -570,8 +581,11 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
skb = sock_alloc_send_skb(sk, size + RFCOMM_SKB_RESERVE,
msg->msg_flags & MSG_DONTWAIT, &err);
- if (!skb)
+ if (!skb) {
+ if (sent == 0)
+ sent = err;
break;
+ }
skb_reserve(skb, RFCOMM_SKB_HEAD_RESERVE);
err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
@@ -630,10 +644,16 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size, int flags)
{
struct sock *sk = sock->sk;
+ struct rfcomm_dlc *d = rfcomm_pi(sk)->dlc;
int err = 0;
size_t target, copied = 0;
long timeo;
+ if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
+ rfcomm_dlc_accept(d);
+ return 0;
+ }
+
if (flags & MSG_OOB)
return -EOPNOTSUPP;
@@ -710,7 +730,7 @@ out:
return copied ? : err;
}
-static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen)
+static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, int optlen)
{
struct sock *sk = sock->sk;
int err = 0;
@@ -727,7 +747,14 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, c
break;
}
- rfcomm_pi(sk)->link_mode = opt;
+ if (opt & RFCOMM_LM_AUTH)
+ rfcomm_pi(sk)->sec_level = BT_SECURITY_LOW;
+ if (opt & RFCOMM_LM_ENCRYPT)
+ rfcomm_pi(sk)->sec_level = BT_SECURITY_MEDIUM;
+ if (opt & RFCOMM_LM_SECURE)
+ rfcomm_pi(sk)->sec_level = BT_SECURITY_HIGH;
+
+ rfcomm_pi(sk)->role_switch = (opt & RFCOMM_LM_MASTER);
break;
default:
@@ -739,12 +766,76 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, c
return err;
}
-static int rfcomm_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen)
+static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen)
+{
+ struct sock *sk = sock->sk;
+ struct bt_security sec;
+ int len, err = 0;
+ u32 opt;
+
+ BT_DBG("sk %p", sk);
+
+ if (level == SOL_RFCOMM)
+ return rfcomm_sock_setsockopt_old(sock, optname, optval, optlen);
+
+ if (level != SOL_BLUETOOTH)
+ return -ENOPROTOOPT;
+
+ lock_sock(sk);
+
+ switch (optname) {
+ case BT_SECURITY:
+ if (sk->sk_type != SOCK_STREAM) {
+ err = -EINVAL;
+ break;
+ }
+
+ sec.level = BT_SECURITY_LOW;
+
+ len = min_t(unsigned int, sizeof(sec), optlen);
+ if (copy_from_user((char *) &sec, optval, len)) {
+ err = -EFAULT;
+ break;
+ }
+
+ if (sec.level > BT_SECURITY_HIGH) {
+ err = -EINVAL;
+ break;
+ }
+
+ rfcomm_pi(sk)->sec_level = sec.level;
+ break;
+
+ case BT_DEFER_SETUP:
+ if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) {
+ err = -EINVAL;
+ break;
+ }
+
+ if (get_user(opt, (u32 __user *) optval)) {
+ err = -EFAULT;
+ break;
+ }
+
+ bt_sk(sk)->defer_setup = opt;
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ release_sock(sk);
+ return err;
+}
+
+static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
struct sock *l2cap_sk;
struct rfcomm_conninfo cinfo;
int len, err = 0;
+ u32 opt;
BT_DBG("sk %p", sk);
@@ -755,12 +846,32 @@ static int rfcomm_sock_getsockopt(struct socket *sock, int level, int optname, c
switch (optname) {
case RFCOMM_LM:
- if (put_user(rfcomm_pi(sk)->link_mode, (u32 __user *) optval))
+ switch (rfcomm_pi(sk)->sec_level) {
+ case BT_SECURITY_LOW:
+ opt = RFCOMM_LM_AUTH;
+ break;
+ case BT_SECURITY_MEDIUM:
+ opt = RFCOMM_LM_AUTH | RFCOMM_LM_ENCRYPT;
+ break;
+ case BT_SECURITY_HIGH:
+ opt = RFCOMM_LM_AUTH | RFCOMM_LM_ENCRYPT |
+ RFCOMM_LM_SECURE;
+ break;
+ default:
+ opt = 0;
+ break;
+ }
+
+ if (rfcomm_pi(sk)->role_switch)
+ opt |= RFCOMM_LM_MASTER;
+
+ if (put_user(opt, (u32 __user *) optval))
err = -EFAULT;
break;
case RFCOMM_CONNINFO:
- if (sk->sk_state != BT_CONNECTED) {
+ if (sk->sk_state != BT_CONNECTED &&
+ !rfcomm_pi(sk)->dlc->defer_setup) {
err = -ENOTCONN;
break;
}
@@ -785,6 +896,60 @@ static int rfcomm_sock_getsockopt(struct socket *sock, int level, int optname, c
return err;
}
+static int rfcomm_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen)
+{
+ struct sock *sk = sock->sk;
+ struct bt_security sec;
+ int len, err = 0;
+
+ BT_DBG("sk %p", sk);
+
+ if (level == SOL_RFCOMM)
+ return rfcomm_sock_getsockopt_old(sock, optname, optval, optlen);
+
+ if (level != SOL_BLUETOOTH)
+ return -ENOPROTOOPT;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ lock_sock(sk);
+
+ switch (optname) {
+ case BT_SECURITY:
+ if (sk->sk_type != SOCK_STREAM) {
+ err = -EINVAL;
+ break;
+ }
+
+ sec.level = rfcomm_pi(sk)->sec_level;
+
+ len = min_t(unsigned int, len, sizeof(sec));
+ if (copy_to_user(optval, (char *) &sec, len))
+ err = -EFAULT;
+
+ break;
+
+ case BT_DEFER_SETUP:
+ if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) {
+ err = -EINVAL;
+ break;
+ }
+
+ if (put_user(bt_sk(sk)->defer_setup, (u32 __user *) optval))
+ err = -EFAULT;
+
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ release_sock(sk);
+ return err;
+}
+
static int rfcomm_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk __maybe_unused = sock->sk;
@@ -888,6 +1053,10 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc *
done:
bh_unlock_sock(parent);
+
+ if (bt_sk(parent)->defer_setup)
+ parent->sk_state_change(parent);
+
return result;
}
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index d030c69cb5a..abdc703a11d 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -731,7 +731,8 @@ static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp)
remove_wait_queue(&dev->wait, &wait);
if (err == 0)
- device_move(dev->tty_dev, rfcomm_get_device(dev));
+ device_move(dev->tty_dev, rfcomm_get_device(dev),
+ DPM_ORDER_DEV_AFTER_PARENT);
rfcomm_tty_copy_pending(dev);
@@ -751,7 +752,7 @@ static void rfcomm_tty_close(struct tty_struct *tty, struct file *filp)
if (atomic_dec_and_test(&dev->opened)) {
if (dev->tty_dev->parent)
- device_move(dev->tty_dev, NULL);
+ device_move(dev->tty_dev, NULL, DPM_ORDER_DEV_LAST);
/* Close DLC and dettach TTY */
rfcomm_dlc_close(dev->dlc, 0);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 46fd8bf9a69..51ae0c3e470 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -195,7 +195,7 @@ static int sco_connect(struct sock *sk)
else
type = SCO_LINK;
- hcon = hci_connect(hdev, type, dst, HCI_AT_NO_BONDING);
+ hcon = hci_connect(hdev, type, dst, BT_SECURITY_LOW, HCI_AT_NO_BONDING);
if (!hcon)
goto done;
@@ -668,7 +668,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char
return err;
}
-static int sco_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen)
+static int sco_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
struct sco_options opts;
@@ -723,6 +723,31 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, char
return err;
}
+static int sco_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen)
+{
+ struct sock *sk = sock->sk;
+ int len, err = 0;
+
+ BT_DBG("sk %p", sk);
+
+ if (level == SOL_SCO)
+ return sco_sock_getsockopt_old(sock, optname, optval, optlen);
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ lock_sock(sk);
+
+ switch (optname) {
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ release_sock(sk);
+ return err;
+}
+
static int sco_sock_release(struct socket *sock)
{
struct sock *sk = sock->sk;
@@ -832,10 +857,30 @@ done:
/* ----- SCO interface with lower layer (HCI) ----- */
static int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 type)
{
+ register struct sock *sk;
+ struct hlist_node *node;
+ int lm = 0;
+
+ if (type != SCO_LINK && type != ESCO_LINK)
+ return 0;
+
BT_DBG("hdev %s, bdaddr %s", hdev->name, batostr(bdaddr));
- /* Always accept connection */
- return HCI_LM_ACCEPT;
+ /* Find listening sockets */
+ read_lock(&sco_sk_list.lock);
+ sk_for_each(sk, node, &sco_sk_list.head) {
+ if (sk->sk_state != BT_LISTEN)
+ continue;
+
+ if (!bacmp(&bt_sk(sk)->src, &hdev->bdaddr) ||
+ !bacmp(&bt_sk(sk)->src, BDADDR_ANY)) {
+ lm |= HCI_LM_ACCEPT;
+ break;
+ }
+ }
+ read_unlock(&sco_sk_list.lock);
+
+ return lm;
}
static int sco_connect_cfm(struct hci_conn *hcon, __u8 status)
@@ -857,7 +902,7 @@ static int sco_connect_cfm(struct hci_conn *hcon, __u8 status)
return 0;
}
-static int sco_disconn_ind(struct hci_conn *hcon, __u8 reason)
+static int sco_disconn_cfm(struct hci_conn *hcon, __u8 reason)
{
BT_DBG("hcon %p reason %d", hcon, reason);
@@ -940,7 +985,7 @@ static struct hci_proto sco_hci_proto = {
.id = HCI_PROTO_SCO,
.connect_ind = sco_connect_ind,
.connect_cfm = sco_connect_cfm,
- .disconn_ind = sco_disconn_ind,
+ .disconn_cfm = sco_disconn_cfm,
.recv_scodata = sco_recv_scodata
};
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 727c5c510a6..8a96672e2c5 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -426,7 +426,6 @@ err2:
err1:
kobject_del(&p->kobj);
err0:
- kobject_put(&p->kobj);
dev_set_promiscuity(dev, -1);
put_back:
dev_put(dev);
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index cf754ace0b7..3953ac4214c 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -107,7 +107,7 @@ static void fake_update_pmtu(struct dst_entry *dst, u32 mtu)
static struct dst_ops fake_dst_ops = {
.family = AF_INET,
- .protocol = __constant_htons(ETH_P_IP),
+ .protocol = cpu_to_be16(ETH_P_IP),
.update_pmtu = fake_update_pmtu,
.entries = ATOMIC_INIT(0),
};
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index ba7be195803..fcffb3fb117 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -98,7 +98,8 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port)
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
+ rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index d44cbf8c374..a94f3cc377c 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -214,7 +214,7 @@ static struct xt_target ebt_log_tg_reg __read_mostly = {
.me = THIS_MODULE,
};
-static const struct nf_logger ebt_log_logger = {
+static struct nf_logger ebt_log_logger __read_mostly = {
.name = "ebt_log",
.logfn = &ebt_log_packet,
.me = THIS_MODULE,
diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c
index 2c6d6823e70..133eeae45a4 100644
--- a/net/bridge/netfilter/ebt_ulog.c
+++ b/net/bridge/netfilter/ebt_ulog.c
@@ -279,21 +279,21 @@ static struct xt_target ebt_ulog_tg_reg __read_mostly = {
.me = THIS_MODULE,
};
-static const struct nf_logger ebt_ulog_logger = {
- .name = "ulog",
+static struct nf_logger ebt_ulog_logger __read_mostly = {
+ .name = "ebt_ulog",
.logfn = &ebt_log_packet,
.me = THIS_MODULE,
};
static int __init ebt_ulog_init(void)
{
- bool ret = true;
+ int ret;
int i;
if (nlbufsiz >= 128*1024) {
printk(KERN_NOTICE "ebt_ulog: Netlink buffer has to be <= 128kB,"
" please try a smaller nlbufsiz parameter.\n");
- return false;
+ return -EINVAL;
}
/* initialize ulog_buffers */
@@ -308,12 +308,12 @@ static int __init ebt_ulog_init(void)
if (!ebtulognl) {
printk(KERN_WARNING KBUILD_MODNAME ": out of memory trying to "
"call netlink_kernel_create\n");
- ret = false;
- } else if (xt_register_target(&ebt_ulog_tg_reg) != 0) {
+ ret = -ENOMEM;
+ } else if ((ret = xt_register_target(&ebt_ulog_tg_reg)) != 0) {
netlink_kernel_release(ebtulognl);
}
- if (ret)
+ if (ret == 0)
nf_log_register(NFPROTO_BRIDGE, &ebt_ulog_logger);
return ret;
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 8604dfc1fc3..c751111440f 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -46,7 +46,6 @@ static struct ebt_table broute_table =
.name = "broute",
.table = &initial_table,
.valid_hooks = 1 << NF_BR_BROUTING,
- .lock = __RW_LOCK_UNLOCKED(broute_table.lock),
.check = check,
.me = THIS_MODULE,
};
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index 2b2e8040a9c..a5eea72938a 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -55,7 +55,6 @@ static struct ebt_table frame_filter =
.name = "filter",
.table = &initial_table,
.valid_hooks = FILTER_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(frame_filter.lock),
.check = check,
.me = THIS_MODULE,
};
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 3fe1ae87e35..6024c551f9a 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -55,7 +55,6 @@ static struct ebt_table frame_nat =
.name = "nat",
.table = &initial_table,
.valid_hooks = NAT_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(frame_nat.lock),
.check = check,
.me = THIS_MODULE,
};
diff --git a/net/can/af_can.c b/net/can/af_can.c
index fa417ca6cbe..547bafc79e2 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -273,8 +273,7 @@ int can_send(struct sk_buff *skb, int loop)
err = net_xmit_errno(err);
if (err) {
- if (newskb)
- kfree_skb(newskb);
+ kfree_skb(newskb);
return err;
}
@@ -828,7 +827,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
*/
static struct packet_type can_packet __read_mostly = {
- .type = __constant_htons(ETH_P_CAN),
+ .type = cpu_to_be16(ETH_P_CAN),
.dev = NULL,
.func = can_rcv,
};
diff --git a/net/can/raw.c b/net/can/raw.c
index 0703cba4bf9..6aa154e806a 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -648,6 +648,9 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock,
err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
if (err < 0)
goto free_skb;
+ err = sock_tx_timestamp(msg, sk, skb_tx(skb));
+ if (err < 0)
+ goto free_skb;
skb->dev = dev;
skb->sk = sk;
diff --git a/net/compat.c b/net/compat.c
index a3a2ba0fac0..8d739053afe 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -216,7 +216,7 @@ Efault:
int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *data)
{
struct compat_timeval ctv;
- struct compat_timespec cts;
+ struct compat_timespec cts[3];
struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control;
struct compat_cmsghdr cmhdr;
int cmlen;
@@ -233,12 +233,17 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat
data = &ctv;
len = sizeof(ctv);
}
- if (level == SOL_SOCKET && type == SCM_TIMESTAMPNS) {
+ if (level == SOL_SOCKET &&
+ (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) {
+ int count = type == SCM_TIMESTAMPNS ? 1 : 3;
+ int i;
struct timespec *ts = (struct timespec *)data;
- cts.tv_sec = ts->tv_sec;
- cts.tv_nsec = ts->tv_nsec;
+ for (i = 0; i < count; i++) {
+ cts[i].tv_sec = ts[i].tv_sec;
+ cts[i].tv_nsec = ts[i].tv_nsec;
+ }
data = &cts;
- len = sizeof(cts);
+ len = sizeof(cts[0]) * count;
}
cmlen = CMSG_COMPAT_LEN(len);
@@ -455,7 +460,7 @@ int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
struct timeval tv;
if (!sock_flag(sk, SOCK_TIMESTAMP))
- sock_enable_timestamp(sk);
+ sock_enable_timestamp(sk, SOCK_TIMESTAMP);
tv = ktime_to_timeval(sk->sk_stamp);
if (tv.tv_sec == -1)
return err;
@@ -479,7 +484,7 @@ int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *usersta
struct timespec ts;
if (!sock_flag(sk, SOCK_TIMESTAMP))
- sock_enable_timestamp(sk);
+ sock_enable_timestamp(sk, SOCK_TIMESTAMP);
ts = ktime_to_timespec(sk->sk_stamp);
if (ts.tv_sec == -1)
return err;
diff --git a/net/core/Makefile b/net/core/Makefile
index 26a37cb3192..796f46eece5 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -17,3 +17,6 @@ obj-$(CONFIG_NET_PKTGEN) += pktgen.o
obj-$(CONFIG_NETPOLL) += netpoll.o
obj-$(CONFIG_NET_DMA) += user_dma.o
obj-$(CONFIG_FIB_RULES) += fib_rules.o
+obj-$(CONFIG_TRACEPOINTS) += net-traces.o
+obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o
+
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 5e2ac0c4b07..d0de644b378 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -208,7 +208,7 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
{
- kfree_skb(skb);
+ consume_skb(skb);
sk_mem_reclaim_partial(sk);
}
diff --git a/net/core/dev.c b/net/core/dev.c
index f1129706ce7..52fea5b28ca 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1457,7 +1457,9 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol)
((features & NETIF_F_IP_CSUM) &&
protocol == htons(ETH_P_IP)) ||
((features & NETIF_F_IPV6_CSUM) &&
- protocol == htons(ETH_P_IPV6)));
+ protocol == htons(ETH_P_IPV6)) ||
+ ((features & NETIF_F_FCOE_CRC) &&
+ protocol == htons(ETH_P_FCOE)));
}
static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb)
@@ -1668,8 +1670,8 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
{
const struct net_device_ops *ops = dev->netdev_ops;
+ int rc;
- prefetch(&dev->netdev_ops->ndo_start_xmit);
if (likely(!skb->next)) {
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
@@ -1681,13 +1683,27 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
goto gso;
}
- return ops->ndo_start_xmit(skb, dev);
+ rc = ops->ndo_start_xmit(skb, dev);
+ /*
+ * TODO: if skb_orphan() was called by
+ * dev->hard_start_xmit() (for example, the unmodified
+ * igb driver does that; bnx2 doesn't), then
+ * skb_tx_software_timestamp() will be unable to send
+ * back the time stamp.
+ *
+ * How can this be prevented? Always create another
+ * reference to the socket before calling
+ * dev->hard_start_xmit()? Prevent that skb_orphan()
+ * does anything in dev->hard_start_xmit() by clearing
+ * the skb destructor before the call and restoring it
+ * afterwards, then doing the skb_orphan() ourselves?
+ */
+ return rc;
}
gso:
do {
struct sk_buff *nskb = skb->next;
- int rc;
skb->next = nskb->next;
nskb->next = NULL;
@@ -1708,59 +1724,24 @@ out_kfree_skb:
return 0;
}
-static u32 simple_tx_hashrnd;
-static int simple_tx_hashrnd_initialized = 0;
+static u32 skb_tx_hashrnd;
-static u16 simple_tx_hash(struct net_device *dev, struct sk_buff *skb)
+u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
{
- u32 addr1, addr2, ports;
- u32 hash, ihl;
- u8 ip_proto = 0;
-
- if (unlikely(!simple_tx_hashrnd_initialized)) {
- get_random_bytes(&simple_tx_hashrnd, 4);
- simple_tx_hashrnd_initialized = 1;
- }
-
- switch (skb->protocol) {
- case htons(ETH_P_IP):
- if (!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)))
- ip_proto = ip_hdr(skb)->protocol;
- addr1 = ip_hdr(skb)->saddr;
- addr2 = ip_hdr(skb)->daddr;
- ihl = ip_hdr(skb)->ihl;
- break;
- case htons(ETH_P_IPV6):
- ip_proto = ipv6_hdr(skb)->nexthdr;
- addr1 = ipv6_hdr(skb)->saddr.s6_addr32[3];
- addr2 = ipv6_hdr(skb)->daddr.s6_addr32[3];
- ihl = (40 >> 2);
- break;
- default:
- return 0;
- }
-
+ u32 hash;
- switch (ip_proto) {
- case IPPROTO_TCP:
- case IPPROTO_UDP:
- case IPPROTO_DCCP:
- case IPPROTO_ESP:
- case IPPROTO_AH:
- case IPPROTO_SCTP:
- case IPPROTO_UDPLITE:
- ports = *((u32 *) (skb_network_header(skb) + (ihl * 4)));
- break;
-
- default:
- ports = 0;
- break;
- }
+ if (skb_rx_queue_recorded(skb)) {
+ hash = skb_get_rx_queue(skb);
+ } else if (skb->sk && skb->sk->sk_hash) {
+ hash = skb->sk->sk_hash;
+ } else
+ hash = skb->protocol;
- hash = jhash_3words(addr1, addr2, ports, simple_tx_hashrnd);
+ hash = jhash_1word(hash, skb_tx_hashrnd);
return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
}
+EXPORT_SYMBOL(skb_tx_hash);
static struct netdev_queue *dev_pick_tx(struct net_device *dev,
struct sk_buff *skb)
@@ -1771,7 +1752,7 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev,
if (ops->ndo_select_queue)
queue_index = ops->ndo_select_queue(dev, skb);
else if (dev->real_num_tx_queues > 1)
- queue_index = simple_tx_hash(dev, skb);
+ queue_index = skb_tx_hash(dev, skb);
skb_set_queue_mapping(skb, queue_index);
return netdev_get_tx_queue(dev, queue_index);
@@ -2297,6 +2278,8 @@ ncls:
if (!skb)
goto out;
+ skb_orphan(skb);
+
type = skb->protocol;
list_for_each_entry_rcu(ptype,
&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
@@ -2366,7 +2349,6 @@ static int napi_gro_complete(struct sk_buff *skb)
out:
skb_shinfo(skb)->gso_size = 0;
- __skb_push(skb, -skb_network_offset(skb));
return netif_receive_skb(skb);
}
@@ -2380,20 +2362,40 @@ void napi_gro_flush(struct napi_struct *napi)
napi_gro_complete(skb);
}
+ napi->gro_count = 0;
napi->gro_list = NULL;
}
EXPORT_SYMBOL(napi_gro_flush);
+void *skb_gro_header(struct sk_buff *skb, unsigned int hlen)
+{
+ unsigned int offset = skb_gro_offset(skb);
+
+ hlen += offset;
+ if (hlen <= skb_headlen(skb))
+ return skb->data + offset;
+
+ if (unlikely(!skb_shinfo(skb)->nr_frags ||
+ skb_shinfo(skb)->frags[0].size <=
+ hlen - skb_headlen(skb) ||
+ PageHighMem(skb_shinfo(skb)->frags[0].page)))
+ return pskb_may_pull(skb, hlen) ? skb->data + offset : NULL;
+
+ return page_address(skb_shinfo(skb)->frags[0].page) +
+ skb_shinfo(skb)->frags[0].page_offset +
+ offset - skb_headlen(skb);
+}
+EXPORT_SYMBOL(skb_gro_header);
+
int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff **pp = NULL;
struct packet_type *ptype;
__be16 type = skb->protocol;
struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
- int count = 0;
int same_flow;
int mac_len;
- int free;
+ int ret;
if (!(skb->dev->features & NETIF_F_GRO))
goto normal;
@@ -2403,30 +2405,16 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
rcu_read_lock();
list_for_each_entry_rcu(ptype, head, list) {
- struct sk_buff *p;
-
if (ptype->type != type || ptype->dev || !ptype->gro_receive)
continue;
- skb_reset_network_header(skb);
+ skb_set_network_header(skb, skb_gro_offset(skb));
mac_len = skb->network_header - skb->mac_header;
skb->mac_len = mac_len;
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 0;
NAPI_GRO_CB(skb)->free = 0;
- for (p = napi->gro_list; p; p = p->next) {
- count++;
-
- if (!NAPI_GRO_CB(p)->same_flow)
- continue;
-
- if (p->mac_len != mac_len ||
- memcmp(skb_mac_header(p), skb_mac_header(skb),
- mac_len))
- NAPI_GRO_CB(p)->same_flow = 0;
- }
-
pp = ptype->gro_receive(&napi->gro_list, skb);
break;
}
@@ -2436,7 +2424,7 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
goto normal;
same_flow = NAPI_GRO_CB(skb)->same_flow;
- free = NAPI_GRO_CB(skb)->free;
+ ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
if (pp) {
struct sk_buff *nskb = *pp;
@@ -2444,27 +2432,35 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
*pp = nskb->next;
nskb->next = NULL;
napi_gro_complete(nskb);
- count--;
+ napi->gro_count--;
}
if (same_flow)
goto ok;
- if (NAPI_GRO_CB(skb)->flush || count >= MAX_GRO_SKBS) {
- __skb_push(skb, -skb_network_offset(skb));
+ if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS)
goto normal;
- }
+ napi->gro_count++;
NAPI_GRO_CB(skb)->count = 1;
- skb_shinfo(skb)->gso_size = skb->len;
+ skb_shinfo(skb)->gso_size = skb_gro_len(skb);
skb->next = napi->gro_list;
napi->gro_list = skb;
+ ret = GRO_HELD;
+
+pull:
+ if (unlikely(!pskb_may_pull(skb, skb_gro_offset(skb)))) {
+ if (napi->gro_list == skb)
+ napi->gro_list = skb->next;
+ ret = GRO_DROP;
+ }
ok:
- return free;
+ return ret;
normal:
- return -1;
+ ret = GRO_NORMAL;
+ goto pull;
}
EXPORT_SYMBOL(dev_gro_receive);
@@ -2472,29 +2468,44 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff *p;
+ if (netpoll_rx_on(skb))
+ return GRO_NORMAL;
+
for (p = napi->gro_list; p; p = p->next) {
- NAPI_GRO_CB(p)->same_flow = 1;
+ NAPI_GRO_CB(p)->same_flow = !compare_ether_header(
+ skb_mac_header(p), skb_gro_mac_header(skb));
NAPI_GRO_CB(p)->flush = 0;
}
return dev_gro_receive(napi, skb);
}
-int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+int napi_skb_finish(int ret, struct sk_buff *skb)
{
- if (netpoll_receive_skb(skb))
- return NET_RX_DROP;
+ int err = NET_RX_SUCCESS;
- switch (__napi_gro_receive(napi, skb)) {
- case -1:
+ switch (ret) {
+ case GRO_NORMAL:
return netif_receive_skb(skb);
- case 1:
+ case GRO_DROP:
+ err = NET_RX_DROP;
+ /* fall through */
+
+ case GRO_MERGED_FREE:
kfree_skb(skb);
break;
}
- return NET_RX_SUCCESS;
+ return err;
+}
+EXPORT_SYMBOL(napi_skb_finish);
+
+int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+{
+ skb_gro_reset_offset(skb);
+
+ return napi_skb_finish(__napi_gro_receive(napi, skb), skb);
}
EXPORT_SYMBOL(napi_gro_receive);
@@ -2512,6 +2523,9 @@ struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi,
{
struct net_device *dev = napi->dev;
struct sk_buff *skb = napi->skb;
+ struct ethhdr *eth;
+ skb_frag_t *frag;
+ int i;
napi->skb = NULL;
@@ -2524,20 +2538,36 @@ struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi,
}
BUG_ON(info->nr_frags > MAX_SKB_FRAGS);
+ frag = &info->frags[info->nr_frags - 1];
+
+ for (i = skb_shinfo(skb)->nr_frags; i < info->nr_frags; i++) {
+ skb_fill_page_desc(skb, i, frag->page, frag->page_offset,
+ frag->size);
+ frag++;
+ }
skb_shinfo(skb)->nr_frags = info->nr_frags;
- memcpy(skb_shinfo(skb)->frags, info->frags, sizeof(info->frags));
skb->data_len = info->len;
skb->len += info->len;
skb->truesize += info->len;
- if (!pskb_may_pull(skb, ETH_HLEN)) {
+ skb_reset_mac_header(skb);
+ skb_gro_reset_offset(skb);
+
+ eth = skb_gro_header(skb, sizeof(*eth));
+ if (!eth) {
napi_reuse_skb(napi, skb);
skb = NULL;
goto out;
}
- skb->protocol = eth_type_trans(skb, dev);
+ skb_gro_pull(skb, sizeof(*eth));
+
+ /*
+ * This works because the only protocols we care about don't require
+ * special handling. We'll fix it up properly at the end.
+ */
+ skb->protocol = eth->h_proto;
skb->ip_summed = info->ip_summed;
skb->csum = info->csum;
@@ -2547,32 +2577,43 @@ out:
}
EXPORT_SYMBOL(napi_fraginfo_skb);
-int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info)
+int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret)
{
- struct sk_buff *skb = napi_fraginfo_skb(napi, info);
- int err = NET_RX_DROP;
+ int err = NET_RX_SUCCESS;
- if (!skb)
- goto out;
+ switch (ret) {
+ case GRO_NORMAL:
+ case GRO_HELD:
+ skb->protocol = eth_type_trans(skb, napi->dev);
- if (netpoll_receive_skb(skb))
- goto out;
+ if (ret == GRO_NORMAL)
+ return netif_receive_skb(skb);
- err = NET_RX_SUCCESS;
+ skb_gro_pull(skb, -ETH_HLEN);
+ break;
- switch (__napi_gro_receive(napi, skb)) {
- case -1:
- return netif_receive_skb(skb);
+ case GRO_DROP:
+ err = NET_RX_DROP;
+ /* fall through */
- case 0:
- goto out;
+ case GRO_MERGED_FREE:
+ napi_reuse_skb(napi, skb);
+ break;
}
- napi_reuse_skb(napi, skb);
-
-out:
return err;
}
+EXPORT_SYMBOL(napi_frags_finish);
+
+int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info)
+{
+ struct sk_buff *skb = napi_fraginfo_skb(napi, info);
+
+ if (!skb)
+ return NET_RX_DROP;
+
+ return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb));
+}
EXPORT_SYMBOL(napi_gro_frags);
static int process_backlog(struct napi_struct *napi, int quota)
@@ -2594,11 +2635,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
}
local_irq_enable();
- napi_gro_receive(napi, skb);
+ netif_receive_skb(skb);
} while (++work < quota && jiffies == start_time);
- napi_gro_flush(napi);
-
return work;
}
@@ -2652,6 +2691,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight)
{
INIT_LIST_HEAD(&napi->poll_list);
+ napi->gro_count = 0;
napi->gro_list = NULL;
napi->skb = NULL;
napi->poll = poll;
@@ -2671,7 +2711,7 @@ void netif_napi_del(struct napi_struct *napi)
struct sk_buff *skb, *next;
list_del_init(&napi->dev_list);
- kfree(napi->skb);
+ kfree_skb(napi->skb);
for (skb = napi->gro_list; skb; skb = next) {
next = skb->next;
@@ -2680,6 +2720,7 @@ void netif_napi_del(struct napi_struct *napi)
}
napi->gro_list = NULL;
+ napi->gro_count = 0;
}
EXPORT_SYMBOL(netif_napi_del);
@@ -3948,6 +3989,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
cmd == SIOCSMIIREG ||
cmd == SIOCBRADDIF ||
cmd == SIOCBRDELIF ||
+ cmd == SIOCSHWTSTAMP ||
cmd == SIOCWANDEV) {
err = -EOPNOTSUPP;
if (ops->ndo_do_ioctl) {
@@ -4102,6 +4144,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
case SIOCBONDCHANGEACTIVE:
case SIOCBRADDIF:
case SIOCBRDELIF:
+ case SIOCSHWTSTAMP:
if (!capable(CAP_NET_ADMIN))
return -EPERM;
/* fall through */
@@ -5198,6 +5241,7 @@ static int __init net_dev_init(void)
queue->backlog.poll = process_backlog;
queue->backlog.weight = weight_p;
queue->backlog.gro_list = NULL;
+ queue->backlog.gro_count = 0;
}
dev_boot_phase = 0;
@@ -5230,6 +5274,14 @@ out:
subsys_initcall(net_dev_init);
+static int __init initialize_hashrnd(void)
+{
+ get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd));
+ return 0;
+}
+
+late_initcall_sync(initialize_hashrnd);
+
EXPORT_SYMBOL(__dev_get_by_index);
EXPORT_SYMBOL(__dev_get_by_name);
EXPORT_SYMBOL(__dev_remove_pack);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
new file mode 100644
index 00000000000..9fd0dc3cca9
--- /dev/null
+++ b/net/core/drop_monitor.c
@@ -0,0 +1,263 @@
+/*
+ * Monitoring code for network dropped packet alerts
+ *
+ * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/string.h>
+#include <linux/if_arp.h>
+#include <linux/inetdevice.h>
+#include <linux/inet.h>
+#include <linux/interrupt.h>
+#include <linux/netpoll.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/netlink.h>
+#include <linux/net_dropmon.h>
+#include <linux/percpu.h>
+#include <linux/timer.h>
+#include <linux/bitops.h>
+#include <net/genetlink.h>
+
+#include <trace/skb.h>
+
+#include <asm/unaligned.h>
+
+#define TRACE_ON 1
+#define TRACE_OFF 0
+
+static void send_dm_alert(struct work_struct *unused);
+
+
+/*
+ * Globals, our netlink socket pointer
+ * and the work handle that will send up
+ * netlink alerts
+ */
+struct sock *dm_sock;
+
+struct per_cpu_dm_data {
+ struct work_struct dm_alert_work;
+ struct sk_buff *skb;
+ atomic_t dm_hit_count;
+ struct timer_list send_timer;
+};
+
+static struct genl_family net_drop_monitor_family = {
+ .id = GENL_ID_GENERATE,
+ .hdrsize = 0,
+ .name = "NET_DM",
+ .version = 1,
+ .maxattr = NET_DM_CMD_MAX,
+};
+
+static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
+
+static int dm_hit_limit = 64;
+static int dm_delay = 1;
+
+
+static void reset_per_cpu_data(struct per_cpu_dm_data *data)
+{
+ size_t al;
+ struct net_dm_alert_msg *msg;
+
+ al = sizeof(struct net_dm_alert_msg);
+ al += dm_hit_limit * sizeof(struct net_dm_drop_point);
+ data->skb = genlmsg_new(al, GFP_KERNEL);
+ genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family,
+ 0, NET_DM_CMD_ALERT);
+ msg = __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_alert_msg));
+ memset(msg, 0, al);
+ atomic_set(&data->dm_hit_count, dm_hit_limit);
+}
+
+static void send_dm_alert(struct work_struct *unused)
+{
+ struct sk_buff *skb;
+ struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+
+ /*
+ * Grab the skb we're about to send
+ */
+ skb = data->skb;
+
+ /*
+ * Replace it with a new one
+ */
+ reset_per_cpu_data(data);
+
+ /*
+ * Ship it!
+ */
+ genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
+
+}
+
+/*
+ * This is the timer function to delay the sending of an alert
+ * in the event that more drops will arrive during the
+ * hysteresis period. Note that it operates under the timer interrupt
+ * so we don't need to disable preemption here
+ */
+static void sched_send_work(unsigned long unused)
+{
+ struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+
+ schedule_work(&data->dm_alert_work);
+}
+
+static void trace_kfree_skb_hit(struct sk_buff *skb, void *location)
+{
+ struct net_dm_alert_msg *msg;
+ struct nlmsghdr *nlh;
+ int i;
+ struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+
+
+ if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) {
+ /*
+ * we're already at zero, discard this hit
+ */
+ goto out;
+ }
+
+ nlh = (struct nlmsghdr *)data->skb->data;
+ msg = genlmsg_data(nlmsg_data(nlh));
+ for (i = 0; i < msg->entries; i++) {
+ if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) {
+ msg->points[i].count++;
+ goto out;
+ }
+ }
+
+ /*
+ * We need to create a new entry
+ */
+ __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point));
+ memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
+ msg->points[msg->entries].count = 1;
+ msg->entries++;
+
+ if (!timer_pending(&data->send_timer)) {
+ data->send_timer.expires = jiffies + dm_delay * HZ;
+ add_timer_on(&data->send_timer, smp_processor_id());
+ }
+
+out:
+ return;
+}
+
+static int set_all_monitor_traces(int state)
+{
+ int rc = 0;
+
+ switch (state) {
+ case TRACE_ON:
+ rc |= register_trace_kfree_skb(trace_kfree_skb_hit);
+ break;
+ case TRACE_OFF:
+ rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit);
+
+ tracepoint_synchronize_unregister();
+ break;
+ default:
+ rc = 1;
+ break;
+ }
+
+ if (rc)
+ return -EINPROGRESS;
+ return rc;
+}
+
+
+static int net_dm_cmd_config(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ return -ENOTSUPP;
+}
+
+static int net_dm_cmd_trace(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ switch (info->genlhdr->cmd) {
+ case NET_DM_CMD_START:
+ return set_all_monitor_traces(TRACE_ON);
+ break;
+ case NET_DM_CMD_STOP:
+ return set_all_monitor_traces(TRACE_OFF);
+ break;
+ }
+
+ return -ENOTSUPP;
+}
+
+
+static struct genl_ops dropmon_ops[] = {
+ {
+ .cmd = NET_DM_CMD_CONFIG,
+ .doit = net_dm_cmd_config,
+ },
+ {
+ .cmd = NET_DM_CMD_START,
+ .doit = net_dm_cmd_trace,
+ },
+ {
+ .cmd = NET_DM_CMD_STOP,
+ .doit = net_dm_cmd_trace,
+ },
+};
+
+static int __init init_net_drop_monitor(void)
+{
+ int cpu;
+ int rc, i, ret;
+ struct per_cpu_dm_data *data;
+ printk(KERN_INFO "Initalizing network drop monitor service\n");
+
+ if (sizeof(void *) > 8) {
+ printk(KERN_ERR "Unable to store program counters on this arch, Drop monitor failed\n");
+ return -ENOSPC;
+ }
+
+ if (genl_register_family(&net_drop_monitor_family) < 0) {
+ printk(KERN_ERR "Could not create drop monitor netlink family\n");
+ return -EFAULT;
+ }
+
+ rc = -EFAULT;
+
+ for (i = 0; i < ARRAY_SIZE(dropmon_ops); i++) {
+ ret = genl_register_ops(&net_drop_monitor_family,
+ &dropmon_ops[i]);
+ if (ret) {
+ printk(KERN_CRIT "failed to register operation %d\n",
+ dropmon_ops[i].cmd);
+ goto out_unreg;
+ }
+ }
+
+ rc = 0;
+
+ for_each_present_cpu(cpu) {
+ data = &per_cpu(dm_cpu_data, cpu);
+ reset_per_cpu_data(data);
+ INIT_WORK(&data->dm_alert_work, send_dm_alert);
+ init_timer(&data->send_timer);
+ data->send_timer.data = cpu;
+ data->send_timer.function = sched_send_work;
+ }
+ goto out;
+
+out_unreg:
+ genl_unregister_family(&net_drop_monitor_family);
+out:
+ return rc;
+}
+
+late_initcall(init_net_drop_monitor);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 947710a36ce..244ca56dffa 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -209,34 +209,62 @@ static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr)
return 0;
}
-static int ethtool_set_rxhash(struct net_device *dev, void __user *useraddr)
+static int ethtool_set_rxnfc(struct net_device *dev, void __user *useraddr)
{
struct ethtool_rxnfc cmd;
- if (!dev->ethtool_ops->set_rxhash)
+ if (!dev->ethtool_ops->set_rxnfc)
return -EOPNOTSUPP;
if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
return -EFAULT;
- return dev->ethtool_ops->set_rxhash(dev, &cmd);
+ return dev->ethtool_ops->set_rxnfc(dev, &cmd);
}
-static int ethtool_get_rxhash(struct net_device *dev, void __user *useraddr)
+static int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr)
{
struct ethtool_rxnfc info;
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+ int ret;
+ void *rule_buf = NULL;
- if (!dev->ethtool_ops->get_rxhash)
+ if (!ops->get_rxnfc)
return -EOPNOTSUPP;
if (copy_from_user(&info, useraddr, sizeof(info)))
return -EFAULT;
- dev->ethtool_ops->get_rxhash(dev, &info);
+ if (info.cmd == ETHTOOL_GRXCLSRLALL) {
+ if (info.rule_cnt > 0) {
+ rule_buf = kmalloc(info.rule_cnt * sizeof(u32),
+ GFP_USER);
+ if (!rule_buf)
+ return -ENOMEM;
+ }
+ }
+ ret = ops->get_rxnfc(dev, &info, rule_buf);
+ if (ret < 0)
+ goto err_out;
+
+ ret = -EFAULT;
if (copy_to_user(useraddr, &info, sizeof(info)))
- return -EFAULT;
- return 0;
+ goto err_out;
+
+ if (rule_buf) {
+ useraddr += offsetof(struct ethtool_rxnfc, rule_locs);
+ if (copy_to_user(useraddr, rule_buf,
+ info.rule_cnt * sizeof(u32)))
+ goto err_out;
+ }
+ ret = 0;
+
+err_out:
+ if (rule_buf)
+ kfree(rule_buf);
+
+ return ret;
}
static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
@@ -901,6 +929,10 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GFLAGS:
case ETHTOOL_GPFLAGS:
case ETHTOOL_GRXFH:
+ case ETHTOOL_GRXRINGS:
+ case ETHTOOL_GRXCLSRLCNT:
+ case ETHTOOL_GRXCLSRULE:
+ case ETHTOOL_GRXCLSRLALL:
break;
default:
if (!capable(CAP_NET_ADMIN))
@@ -1052,10 +1084,16 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
dev->ethtool_ops->set_priv_flags);
break;
case ETHTOOL_GRXFH:
- rc = ethtool_get_rxhash(dev, useraddr);
+ case ETHTOOL_GRXRINGS:
+ case ETHTOOL_GRXCLSRLCNT:
+ case ETHTOOL_GRXCLSRULE:
+ case ETHTOOL_GRXCLSRLALL:
+ rc = ethtool_get_rxnfc(dev, useraddr);
break;
case ETHTOOL_SRXFH:
- rc = ethtool_set_rxhash(dev, useraddr);
+ case ETHTOOL_SRXCLSRLDEL:
+ case ETHTOOL_SRXCLSRLINS:
+ rc = ethtool_set_rxnfc(dev, useraddr);
break;
case ETHTOOL_GGRO:
rc = ethtool_get_gro(dev, useraddr);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 32b3a0152d7..98691e1466b 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -588,7 +588,8 @@ static void notify_rule_change(int event, struct fib_rule *rule,
goto errout;
}
- err = rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL);
+ rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(net, ops->nlgroup, err);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 278a142d104..a1cbce7fdae 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -871,8 +871,7 @@ static void neigh_timer_handler(unsigned long arg)
write_unlock(&neigh->lock);
neigh->ops->solicit(neigh, skb);
atomic_inc(&neigh->probes);
- if (skb)
- kfree_skb(skb);
+ kfree_skb(skb);
} else {
out:
write_unlock(&neigh->lock);
@@ -908,8 +907,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
neigh->updated = jiffies;
write_unlock_bh(&neigh->lock);
- if (skb)
- kfree_skb(skb);
+ kfree_skb(skb);
return 1;
}
} else if (neigh->nud_state & NUD_STALE) {
@@ -1656,7 +1654,11 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
flags &= ~NEIGH_UPDATE_F_OVERRIDE;
}
- err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
+ if (ndm->ndm_flags & NTF_USE) {
+ neigh_event_send(neigh, NULL);
+ err = 0;
+ } else
+ err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
neigh_release(neigh);
goto out_dev_put;
}
@@ -2534,7 +2536,8 @@ static void __neigh_notify(struct neighbour *n, int type, int flags)
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
+ rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 484f58750eb..2da59a0ac4a 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -498,7 +498,7 @@ int netdev_register_kobject(struct net_device *net)
dev->groups = groups;
BUILD_BUG_ON(BUS_ID_SIZE < IFNAMSIZ);
- dev_set_name(dev, net->name);
+ dev_set_name(dev, "%s", net->name);
#ifdef CONFIG_SYSFS
*groups++ = &netstat_group;
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
new file mode 100644
index 00000000000..c8fb45665e4
--- /dev/null
+++ b/net/core/net-traces.c
@@ -0,0 +1,29 @@
+/*
+ * consolidates trace point definitions
+ *
+ * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/string.h>
+#include <linux/if_arp.h>
+#include <linux/inetdevice.h>
+#include <linux/inet.h>
+#include <linux/interrupt.h>
+#include <linux/netpoll.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/rcupdate.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/netlink.h>
+#include <linux/net_dropmon.h>
+#include <trace/skb.h>
+
+#include <asm/unaligned.h>
+#include <asm/bitops.h>
+
+
+DEFINE_TRACE(kfree_skb);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 65498483325..32d419f5ac9 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3275,8 +3275,7 @@ static void pktgen_stop(struct pktgen_thread *t)
list_for_each_entry(pkt_dev, &t->if_list, list) {
pktgen_stop_device(pkt_dev);
- if (pkt_dev->skb)
- kfree_skb(pkt_dev->skb);
+ kfree_skb(pkt_dev->skb);
pkt_dev->skb = NULL;
}
@@ -3303,8 +3302,7 @@ static void pktgen_rem_one_if(struct pktgen_thread *t)
if (!cur->removal_mark)
continue;
- if (cur->skb)
- kfree_skb(cur->skb);
+ kfree_skb(cur->skb);
cur->skb = NULL;
pktgen_remove_device(t, cur);
@@ -3328,8 +3326,7 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t)
list_for_each_safe(q, n, &t->if_list) {
cur = list_entry(q, struct pktgen_dev, list);
- if (cur->skb)
- kfree_skb(cur->skb);
+ kfree_skb(cur->skb);
cur->skb = NULL;
pktgen_remove_device(t, cur);
@@ -3393,8 +3390,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
if (!netif_running(odev)) {
pktgen_stop_device(pkt_dev);
- if (pkt_dev->skb)
- kfree_skb(pkt_dev->skb);
+ kfree_skb(pkt_dev->skb);
pkt_dev->skb = NULL;
goto out;
}
@@ -3415,8 +3411,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
if ((++pkt_dev->clone_count >= pkt_dev->clone_skb)
|| (!pkt_dev->skb)) {
/* build a new pkt */
- if (pkt_dev->skb)
- kfree_skb(pkt_dev->skb);
+ kfree_skb(pkt_dev->skb);
pkt_dev->skb = fill_packet(odev, pkt_dev);
if (pkt_dev->skb == NULL) {
@@ -3498,8 +3493,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
/* Done with this */
pktgen_stop_device(pkt_dev);
- if (pkt_dev->skb)
- kfree_skb(pkt_dev->skb);
+ kfree_skb(pkt_dev->skb);
pkt_dev->skb = NULL;
}
out:;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 790dd205bb5..d78030f88bd 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -455,8 +455,8 @@ int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid)
return nlmsg_unicast(rtnl, skb, pid);
}
-int rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
- struct nlmsghdr *nlh, gfp_t flags)
+void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
+ struct nlmsghdr *nlh, gfp_t flags)
{
struct sock *rtnl = net->rtnl;
int report = 0;
@@ -464,7 +464,7 @@ int rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
if (nlh)
report = nlmsg_report(nlh);
- return nlmsg_notify(rtnl, skb, pid, group, report, flags);
+ nlmsg_notify(rtnl, skb, pid, group, report, flags);
}
void rtnl_set_sk_err(struct net *net, u32 group, int error)
@@ -1246,7 +1246,8 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL);
+ rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c6a6b166f8d..6acbf9e79eb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -55,6 +55,7 @@
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/scatterlist.h>
+#include <linux/errqueue.h>
#include <net/protocol.h>
#include <net/dst.h>
@@ -64,6 +65,7 @@
#include <asm/uaccess.h>
#include <asm/system.h>
+#include <trace/skb.h>
#include "kmap_skb.h"
@@ -123,6 +125,7 @@ void skb_over_panic(struct sk_buff *skb, int sz, void *here)
skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
+EXPORT_SYMBOL(skb_over_panic);
/**
* skb_under_panic - private function
@@ -142,6 +145,7 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here)
skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
+EXPORT_SYMBOL(skb_under_panic);
/* Allocate a new skbuff. We do this ourselves so we can fill in a few
* 'private' fields and also do memory statistics to find all the
@@ -205,7 +209,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
shinfo->gso_segs = 0;
shinfo->gso_type = 0;
shinfo->ip6_frag_id = 0;
+ shinfo->tx_flags.flags = 0;
shinfo->frag_list = NULL;
+ memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps));
if (fclone) {
struct sk_buff *child = skb + 1;
@@ -223,6 +229,7 @@ nodata:
skb = NULL;
goto out;
}
+EXPORT_SYMBOL(__alloc_skb);
/**
* __netdev_alloc_skb - allocate an skbuff for rx on a specific device
@@ -250,6 +257,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
}
return skb;
}
+EXPORT_SYMBOL(__netdev_alloc_skb);
struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
{
@@ -418,6 +426,7 @@ void __kfree_skb(struct sk_buff *skb)
skb_release_all(skb);
kfree_skbmem(skb);
}
+EXPORT_SYMBOL(__kfree_skb);
/**
* kfree_skb - free an sk_buff
@@ -434,8 +443,30 @@ void kfree_skb(struct sk_buff *skb)
smp_rmb();
else if (likely(!atomic_dec_and_test(&skb->users)))
return;
+ trace_kfree_skb(skb, __builtin_return_address(0));
+ __kfree_skb(skb);
+}
+EXPORT_SYMBOL(kfree_skb);
+
+/**
+ * consume_skb - free an skbuff
+ * @skb: buffer to free
+ *
+ * Drop a ref to the buffer and free it if the usage count has hit zero
+ * Functions identically to kfree_skb, but kfree_skb assumes that the frame
+ * is being dropped after a failure and notes that
+ */
+void consume_skb(struct sk_buff *skb)
+{
+ if (unlikely(!skb))
+ return;
+ if (likely(atomic_read(&skb->users) == 1))
+ smp_rmb();
+ else if (likely(!atomic_dec_and_test(&skb->users)))
+ return;
__kfree_skb(skb);
}
+EXPORT_SYMBOL(consume_skb);
/**
* skb_recycle_check - check if skb can be reused for receive
@@ -605,6 +636,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
return __skb_clone(n, skb);
}
+EXPORT_SYMBOL(skb_clone);
static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
@@ -671,7 +703,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
copy_skb_header(n, skb);
return n;
}
-
+EXPORT_SYMBOL(skb_copy);
/**
* pskb_copy - create copy of an sk_buff with private head.
@@ -730,6 +762,7 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
out:
return n;
}
+EXPORT_SYMBOL(pskb_copy);
/**
* pskb_expand_head - reallocate header of &sk_buff
@@ -813,6 +846,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
nodata:
return -ENOMEM;
}
+EXPORT_SYMBOL(pskb_expand_head);
/* Make private copy of skb with writable head and some headroom */
@@ -833,7 +867,7 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom)
}
return skb2;
}
-
+EXPORT_SYMBOL(skb_realloc_headroom);
/**
* skb_copy_expand - copy and expand sk_buff
@@ -898,6 +932,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
return n;
}
+EXPORT_SYMBOL(skb_copy_expand);
/**
* skb_pad - zero pad the tail of an skb
@@ -943,6 +978,7 @@ free_skb:
kfree_skb(skb);
return err;
}
+EXPORT_SYMBOL(skb_pad);
/**
* skb_put - add data to a buffer
@@ -1100,6 +1136,7 @@ done:
return 0;
}
+EXPORT_SYMBOL(___pskb_trim);
/**
* __pskb_pull_tail - advance tail of skb header
@@ -1193,8 +1230,7 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta)
insp = list;
}
if (!pskb_pull(list, eat)) {
- if (clone)
- kfree_skb(clone);
+ kfree_skb(clone);
return NULL;
}
break;
@@ -1238,6 +1274,7 @@ pull_pages:
return skb_tail_pointer(skb);
}
+EXPORT_SYMBOL(__pskb_pull_tail);
/* Copy some data bits from skb to kernel buffer. */
@@ -1315,6 +1352,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
fault:
return -EFAULT;
}
+EXPORT_SYMBOL(skb_copy_bits);
/*
* Callback from splice_to_pipe(), if we need to release some pages
@@ -1325,14 +1363,39 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
put_page(spd->pages[i]);
}
-static inline struct page *linear_to_page(struct page *page, unsigned int len,
- unsigned int offset)
+static inline struct page *linear_to_page(struct page *page, unsigned int *len,
+ unsigned int *offset,
+ struct sk_buff *skb)
{
- struct page *p = alloc_pages(GFP_KERNEL, 0);
+ struct sock *sk = skb->sk;
+ struct page *p = sk->sk_sndmsg_page;
+ unsigned int off;
- if (!p)
- return NULL;
- memcpy(page_address(p) + offset, page_address(page) + offset, len);
+ if (!p) {
+new_page:
+ p = sk->sk_sndmsg_page = alloc_pages(sk->sk_allocation, 0);
+ if (!p)
+ return NULL;
+
+ off = sk->sk_sndmsg_off = 0;
+ /* hold one ref to this page until it's full */
+ } else {
+ unsigned int mlen;
+
+ off = sk->sk_sndmsg_off;
+ mlen = PAGE_SIZE - off;
+ if (mlen < 64 && mlen < *len) {
+ put_page(p);
+ goto new_page;
+ }
+
+ *len = min_t(unsigned int, *len, mlen);
+ }
+
+ memcpy(page_address(p) + off, page_address(page) + *offset, *len);
+ sk->sk_sndmsg_off += *len;
+ *offset = off;
+ get_page(p);
return p;
}
@@ -1341,21 +1404,21 @@ static inline struct page *linear_to_page(struct page *page, unsigned int len,
* Fill page/offset/length into spd, if it can hold more pages.
*/
static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page,
- unsigned int len, unsigned int offset,
+ unsigned int *len, unsigned int offset,
struct sk_buff *skb, int linear)
{
if (unlikely(spd->nr_pages == PIPE_BUFFERS))
return 1;
if (linear) {
- page = linear_to_page(page, len, offset);
+ page = linear_to_page(page, len, &offset, skb);
if (!page)
return 1;
} else
get_page(page);
spd->pages[spd->nr_pages] = page;
- spd->partial[spd->nr_pages].len = len;
+ spd->partial[spd->nr_pages].len = *len;
spd->partial[spd->nr_pages].offset = offset;
spd->nr_pages++;
@@ -1365,8 +1428,13 @@ static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page,
static inline void __segment_seek(struct page **page, unsigned int *poff,
unsigned int *plen, unsigned int off)
{
+ unsigned long n;
+
*poff += off;
- *page += *poff / PAGE_SIZE;
+ n = *poff / PAGE_SIZE;
+ if (n)
+ *page = nth_page(*page, n);
+
*poff = *poff % PAGE_SIZE;
*plen -= off;
}
@@ -1397,7 +1465,7 @@ static inline int __splice_segment(struct page *page, unsigned int poff,
/* the linear region may spread across several pages */
flen = min_t(unsigned int, flen, PAGE_SIZE - poff);
- if (spd_fill_page(spd, page, flen, poff, skb, linear))
+ if (spd_fill_page(spd, page, &flen, poff, skb, linear))
return 1;
__segment_seek(&page, &poff, &plen, flen);
@@ -1590,7 +1658,6 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len)
fault:
return -EFAULT;
}
-
EXPORT_SYMBOL(skb_store_bits);
/* Checksum skb data. */
@@ -1667,6 +1734,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
return csum;
}
+EXPORT_SYMBOL(skb_checksum);
/* Both of above in one bottle. */
@@ -1748,6 +1816,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
BUG_ON(len);
return csum;
}
+EXPORT_SYMBOL(skb_copy_and_csum_bits);
void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
{
@@ -1774,6 +1843,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
*((__sum16 *)(to + csstuff)) = csum_fold(csum);
}
}
+EXPORT_SYMBOL(skb_copy_and_csum_dev);
/**
* skb_dequeue - remove from the head of the queue
@@ -1794,6 +1864,7 @@ struct sk_buff *skb_dequeue(struct sk_buff_head *list)
spin_unlock_irqrestore(&list->lock, flags);
return result;
}
+EXPORT_SYMBOL(skb_dequeue);
/**
* skb_dequeue_tail - remove from the tail of the queue
@@ -1813,6 +1884,7 @@ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list)
spin_unlock_irqrestore(&list->lock, flags);
return result;
}
+EXPORT_SYMBOL(skb_dequeue_tail);
/**
* skb_queue_purge - empty a list
@@ -1828,6 +1900,7 @@ void skb_queue_purge(struct sk_buff_head *list)
while ((skb = skb_dequeue(list)) != NULL)
kfree_skb(skb);
}
+EXPORT_SYMBOL(skb_queue_purge);
/**
* skb_queue_head - queue a buffer at the list head
@@ -1848,6 +1921,7 @@ void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk)
__skb_queue_head(list, newsk);
spin_unlock_irqrestore(&list->lock, flags);
}
+EXPORT_SYMBOL(skb_queue_head);
/**
* skb_queue_tail - queue a buffer at the list tail
@@ -1868,6 +1942,7 @@ void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk)
__skb_queue_tail(list, newsk);
spin_unlock_irqrestore(&list->lock, flags);
}
+EXPORT_SYMBOL(skb_queue_tail);
/**
* skb_unlink - remove a buffer from a list
@@ -1887,6 +1962,7 @@ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
__skb_unlink(skb, list);
spin_unlock_irqrestore(&list->lock, flags);
}
+EXPORT_SYMBOL(skb_unlink);
/**
* skb_append - append a buffer
@@ -1906,7 +1982,7 @@ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head
__skb_queue_after(list, old, newsk);
spin_unlock_irqrestore(&list->lock, flags);
}
-
+EXPORT_SYMBOL(skb_append);
/**
* skb_insert - insert a buffer
@@ -1928,6 +2004,7 @@ void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head
__skb_insert(newsk, old->prev, old, list);
spin_unlock_irqrestore(&list->lock, flags);
}
+EXPORT_SYMBOL(skb_insert);
static inline void skb_split_inside_header(struct sk_buff *skb,
struct sk_buff* skb1,
@@ -2006,6 +2083,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)
else /* Second chunk has no header, nothing to copy. */
skb_split_no_header(skb, skb1, len, pos);
}
+EXPORT_SYMBOL(skb_split);
/* Shifting from/to a cloned skb is a no-go.
*
@@ -2168,6 +2246,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
st->frag_idx = st->stepped_offset = 0;
st->frag_data = NULL;
}
+EXPORT_SYMBOL(skb_prepare_seq_read);
/**
* skb_seq_read - Sequentially read skb data
@@ -2255,6 +2334,7 @@ next_skb:
return 0;
}
+EXPORT_SYMBOL(skb_seq_read);
/**
* skb_abort_seq_read - Abort a sequential read of skb data
@@ -2268,6 +2348,7 @@ void skb_abort_seq_read(struct skb_seq_state *st)
if (st->frag_data)
kunmap_skb_frag(st->frag_data);
}
+EXPORT_SYMBOL(skb_abort_seq_read);
#define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb))
@@ -2310,6 +2391,7 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
ret = textsearch_find(config, state);
return (ret <= to - from ? ret : UINT_MAX);
}
+EXPORT_SYMBOL(skb_find_text);
/**
* skb_append_datato_frags: - append the user data to a skb
@@ -2382,6 +2464,7 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
return 0;
}
+EXPORT_SYMBOL(skb_append_datato_frags);
/**
* skb_pull_rcsum - pull skb and update receive checksum
@@ -2569,7 +2652,6 @@ err:
}
return ERR_PTR(err);
}
-
EXPORT_SYMBOL_GPL(skb_segment);
int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
@@ -2577,17 +2659,23 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
struct sk_buff *p = *head;
struct sk_buff *nskb;
unsigned int headroom;
- unsigned int hlen = p->data - skb_mac_header(p);
- unsigned int len = skb->len;
+ unsigned int len = skb_gro_len(skb);
- if (hlen + p->len + len >= 65536)
+ if (p->len + len >= 65536)
return -E2BIG;
if (skb_shinfo(p)->frag_list)
goto merge;
- else if (!skb_headlen(p) && !skb_headlen(skb) &&
- skb_shinfo(p)->nr_frags + skb_shinfo(skb)->nr_frags <
- MAX_SKB_FRAGS) {
+ else if (skb_headlen(skb) <= skb_gro_offset(skb)) {
+ if (skb_shinfo(p)->nr_frags + skb_shinfo(skb)->nr_frags >
+ MAX_SKB_FRAGS)
+ return -E2BIG;
+
+ skb_shinfo(skb)->frags[0].page_offset +=
+ skb_gro_offset(skb) - skb_headlen(skb);
+ skb_shinfo(skb)->frags[0].size -=
+ skb_gro_offset(skb) - skb_headlen(skb);
+
memcpy(skb_shinfo(p)->frags + skb_shinfo(p)->nr_frags,
skb_shinfo(skb)->frags,
skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
@@ -2604,7 +2692,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
}
headroom = skb_headroom(p);
- nskb = netdev_alloc_skb(p->dev, headroom);
+ nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p));
if (unlikely(!nskb))
return -ENOMEM;
@@ -2612,12 +2700,15 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
nskb->mac_len = p->mac_len;
skb_reserve(nskb, headroom);
+ __skb_put(nskb, skb_gro_offset(p));
- skb_set_mac_header(nskb, -hlen);
+ skb_set_mac_header(nskb, skb_mac_header(p) - p->data);
skb_set_network_header(nskb, skb_network_offset(p));
skb_set_transport_header(nskb, skb_transport_offset(p));
- memcpy(skb_mac_header(nskb), skb_mac_header(p), hlen);
+ __skb_pull(p, skb_gro_offset(p));
+ memcpy(skb_mac_header(nskb), skb_mac_header(p),
+ p->data - skb_mac_header(p));
*NAPI_GRO_CB(nskb) = *NAPI_GRO_CB(p);
skb_shinfo(nskb)->frag_list = p;
@@ -2636,6 +2727,17 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
p = nskb;
merge:
+ if (skb_gro_offset(skb) > skb_headlen(skb)) {
+ skb_shinfo(skb)->frags[0].page_offset +=
+ skb_gro_offset(skb) - skb_headlen(skb);
+ skb_shinfo(skb)->frags[0].size -=
+ skb_gro_offset(skb) - skb_headlen(skb);
+ skb_gro_reset_offset(skb);
+ skb_gro_pull(skb, skb_headlen(skb));
+ }
+
+ __skb_pull(skb, skb_gro_offset(skb));
+
p->prev->next = skb;
p->prev = skb;
skb_header_release(skb);
@@ -2747,6 +2849,7 @@ int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int le
return nsg;
}
+EXPORT_SYMBOL_GPL(skb_to_sgvec);
/**
* skb_cow_data - Check that a socket buffer's data buffers are writable
@@ -2856,6 +2959,45 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
return elt;
}
+EXPORT_SYMBOL_GPL(skb_cow_data);
+
+void skb_tstamp_tx(struct sk_buff *orig_skb,
+ struct skb_shared_hwtstamps *hwtstamps)
+{
+ struct sock *sk = orig_skb->sk;
+ struct sock_exterr_skb *serr;
+ struct sk_buff *skb;
+ int err;
+
+ if (!sk)
+ return;
+
+ skb = skb_clone(orig_skb, GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ if (hwtstamps) {
+ *skb_hwtstamps(skb) =
+ *hwtstamps;
+ } else {
+ /*
+ * no hardware time stamps available,
+ * so keep the skb_shared_tx and only
+ * store software time stamp
+ */
+ skb->tstamp = ktime_get_real();
+ }
+
+ serr = SKB_EXT_ERR(skb);
+ memset(serr, 0, sizeof(*serr));
+ serr->ee.ee_errno = ENOMSG;
+ serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
+ err = sock_queue_err_skb(sk, skb);
+ if (err)
+ kfree_skb(skb);
+}
+EXPORT_SYMBOL_GPL(skb_tstamp_tx);
+
/**
* skb_partial_csum_set - set up and verify partial csum values for packet
@@ -2884,6 +3026,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
skb->csum_offset = off;
return true;
}
+EXPORT_SYMBOL_GPL(skb_partial_csum_set);
void __skb_warn_lro_forwarding(const struct sk_buff *skb)
{
@@ -2891,42 +3034,4 @@ void __skb_warn_lro_forwarding(const struct sk_buff *skb)
pr_warning("%s: received packets cannot be forwarded"
" while LRO is enabled\n", skb->dev->name);
}
-
-EXPORT_SYMBOL(___pskb_trim);
-EXPORT_SYMBOL(__kfree_skb);
-EXPORT_SYMBOL(kfree_skb);
-EXPORT_SYMBOL(__pskb_pull_tail);
-EXPORT_SYMBOL(__alloc_skb);
-EXPORT_SYMBOL(__netdev_alloc_skb);
-EXPORT_SYMBOL(pskb_copy);
-EXPORT_SYMBOL(pskb_expand_head);
-EXPORT_SYMBOL(skb_checksum);
-EXPORT_SYMBOL(skb_clone);
-EXPORT_SYMBOL(skb_copy);
-EXPORT_SYMBOL(skb_copy_and_csum_bits);
-EXPORT_SYMBOL(skb_copy_and_csum_dev);
-EXPORT_SYMBOL(skb_copy_bits);
-EXPORT_SYMBOL(skb_copy_expand);
-EXPORT_SYMBOL(skb_over_panic);
-EXPORT_SYMBOL(skb_pad);
-EXPORT_SYMBOL(skb_realloc_headroom);
-EXPORT_SYMBOL(skb_under_panic);
-EXPORT_SYMBOL(skb_dequeue);
-EXPORT_SYMBOL(skb_dequeue_tail);
-EXPORT_SYMBOL(skb_insert);
-EXPORT_SYMBOL(skb_queue_purge);
-EXPORT_SYMBOL(skb_queue_head);
-EXPORT_SYMBOL(skb_queue_tail);
-EXPORT_SYMBOL(skb_unlink);
-EXPORT_SYMBOL(skb_append);
-EXPORT_SYMBOL(skb_split);
-EXPORT_SYMBOL(skb_prepare_seq_read);
-EXPORT_SYMBOL(skb_seq_read);
-EXPORT_SYMBOL(skb_abort_seq_read);
-EXPORT_SYMBOL(skb_find_text);
-EXPORT_SYMBOL(skb_append_datato_frags);
EXPORT_SYMBOL(__skb_warn_lro_forwarding);
-
-EXPORT_SYMBOL_GPL(skb_to_sgvec);
-EXPORT_SYMBOL_GPL(skb_cow_data);
-EXPORT_SYMBOL_GPL(skb_partial_csum_set);
diff --git a/net/core/sock.c b/net/core/sock.c
index 5f97caa158e..0620046e4eb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -120,6 +120,7 @@
#include <net/net_namespace.h>
#include <net/request_sock.h>
#include <net/sock.h>
+#include <linux/net_tstamp.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>
@@ -149,7 +150,7 @@ static const char *af_family_key_strings[AF_MAX+1] = {
"sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" ,
"sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" ,
"sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" ,
- "sk_lock-21" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" ,
+ "sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" ,
"sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" ,
"sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" ,
"sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" ,
@@ -164,7 +165,7 @@ static const char *af_family_slock_key_strings[AF_MAX+1] = {
"slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" ,
"slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" ,
"slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" ,
- "slock-21" , "slock-AF_SNA" , "slock-AF_IRDA" ,
+ "slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" ,
"slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" ,
"slock-27" , "slock-28" , "slock-AF_CAN" ,
"slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" ,
@@ -179,7 +180,7 @@ static const char *af_family_clock_key_strings[AF_MAX+1] = {
"clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" ,
"clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" ,
"clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" ,
- "clock-21" , "clock-AF_SNA" , "clock-AF_IRDA" ,
+ "clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" ,
"clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" ,
"clock-27" , "clock-28" , "clock-AF_CAN" ,
"clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" ,
@@ -255,11 +256,14 @@ static void sock_warn_obsolete_bsdism(const char *name)
}
}
-static void sock_disable_timestamp(struct sock *sk)
+static void sock_disable_timestamp(struct sock *sk, int flag)
{
- if (sock_flag(sk, SOCK_TIMESTAMP)) {
- sock_reset_flag(sk, SOCK_TIMESTAMP);
- net_disable_timestamp();
+ if (sock_flag(sk, flag)) {
+ sock_reset_flag(sk, flag);
+ if (!sock_flag(sk, SOCK_TIMESTAMP) &&
+ !sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) {
+ net_disable_timestamp();
+ }
}
}
@@ -614,13 +618,38 @@ set_rcvbuf:
else
sock_set_flag(sk, SOCK_RCVTSTAMPNS);
sock_set_flag(sk, SOCK_RCVTSTAMP);
- sock_enable_timestamp(sk);
+ sock_enable_timestamp(sk, SOCK_TIMESTAMP);
} else {
sock_reset_flag(sk, SOCK_RCVTSTAMP);
sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
}
break;
+ case SO_TIMESTAMPING:
+ if (val & ~SOF_TIMESTAMPING_MASK) {
+ ret = EINVAL;
+ break;
+ }
+ sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE,
+ val & SOF_TIMESTAMPING_TX_HARDWARE);
+ sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE,
+ val & SOF_TIMESTAMPING_TX_SOFTWARE);
+ sock_valbool_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE,
+ val & SOF_TIMESTAMPING_RX_HARDWARE);
+ if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
+ sock_enable_timestamp(sk,
+ SOCK_TIMESTAMPING_RX_SOFTWARE);
+ else
+ sock_disable_timestamp(sk,
+ SOCK_TIMESTAMPING_RX_SOFTWARE);
+ sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE,
+ val & SOF_TIMESTAMPING_SOFTWARE);
+ sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE,
+ val & SOF_TIMESTAMPING_SYS_HARDWARE);
+ sock_valbool_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE,
+ val & SOF_TIMESTAMPING_RAW_HARDWARE);
+ break;
+
case SO_RCVLOWAT:
if (val < 0)
val = INT_MAX;
@@ -768,6 +797,24 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sock_flag(sk, SOCK_RCVTSTAMPNS);
break;
+ case SO_TIMESTAMPING:
+ v.val = 0;
+ if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE))
+ v.val |= SOF_TIMESTAMPING_TX_HARDWARE;
+ if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE))
+ v.val |= SOF_TIMESTAMPING_TX_SOFTWARE;
+ if (sock_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE))
+ v.val |= SOF_TIMESTAMPING_RX_HARDWARE;
+ if (sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE))
+ v.val |= SOF_TIMESTAMPING_RX_SOFTWARE;
+ if (sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE))
+ v.val |= SOF_TIMESTAMPING_SOFTWARE;
+ if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE))
+ v.val |= SOF_TIMESTAMPING_SYS_HARDWARE;
+ if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE))
+ v.val |= SOF_TIMESTAMPING_RAW_HARDWARE;
+ break;
+
case SO_RCVTIMEO:
lv=sizeof(struct timeval);
if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) {
@@ -969,7 +1016,8 @@ void sk_free(struct sock *sk)
rcu_assign_pointer(sk->sk_filter, NULL);
}
- sock_disable_timestamp(sk);
+ sock_disable_timestamp(sk, SOCK_TIMESTAMP);
+ sock_disable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE);
if (atomic_read(&sk->sk_omem_alloc))
printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
@@ -1255,10 +1303,9 @@ static long sock_wait_for_wmem(struct sock * sk, long timeo)
* Generic send/receive buffer handlers
*/
-static struct sk_buff *sock_alloc_send_pskb(struct sock *sk,
- unsigned long header_len,
- unsigned long data_len,
- int noblock, int *errcode)
+struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
+ unsigned long data_len, int noblock,
+ int *errcode)
{
struct sk_buff *skb;
gfp_t gfp_mask;
@@ -1338,6 +1385,7 @@ failure:
*errcode = err;
return NULL;
}
+EXPORT_SYMBOL(sock_alloc_send_pskb);
struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
int noblock, int *errcode)
@@ -1786,7 +1834,7 @@ int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
{
struct timeval tv;
if (!sock_flag(sk, SOCK_TIMESTAMP))
- sock_enable_timestamp(sk);
+ sock_enable_timestamp(sk, SOCK_TIMESTAMP);
tv = ktime_to_timeval(sk->sk_stamp);
if (tv.tv_sec == -1)
return -ENOENT;
@@ -1802,7 +1850,7 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
{
struct timespec ts;
if (!sock_flag(sk, SOCK_TIMESTAMP))
- sock_enable_timestamp(sk);
+ sock_enable_timestamp(sk, SOCK_TIMESTAMP);
ts = ktime_to_timespec(sk->sk_stamp);
if (ts.tv_sec == -1)
return -ENOENT;
@@ -1814,11 +1862,20 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
}
EXPORT_SYMBOL(sock_get_timestampns);
-void sock_enable_timestamp(struct sock *sk)
+void sock_enable_timestamp(struct sock *sk, int flag)
{
- if (!sock_flag(sk, SOCK_TIMESTAMP)) {
- sock_set_flag(sk, SOCK_TIMESTAMP);
- net_enable_timestamp();
+ if (!sock_flag(sk, flag)) {
+ sock_set_flag(sk, flag);
+ /*
+ * we just set one of the two flags which require net
+ * time stamping, but time stamping might have been on
+ * already because of the other one
+ */
+ if (!sock_flag(sk,
+ flag == SOCK_TIMESTAMP ?
+ SOCK_TIMESTAMPING_RX_SOFTWARE :
+ SOCK_TIMESTAMP))
+ net_enable_timestamp();
}
}
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 83d3398559e..7db1de0497c 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -11,6 +11,7 @@
#include <linux/socket.h>
#include <linux/netdevice.h>
#include <linux/init.h>
+#include <net/ip.h>
#include <net/sock.h>
static struct ctl_table net_core_table[] = {
diff --git a/net/core/utils.c b/net/core/utils.c
index 72e0ebe964a..83221aee708 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -22,7 +22,6 @@
#include <linux/net.h>
#include <linux/string.h>
#include <linux/types.h>
-#include <linux/random.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <net/sock.h>
diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h
index 45f95e55f87..7ea557b7c6b 100644
--- a/net/dccp/ackvec.h
+++ b/net/dccp/ackvec.h
@@ -20,6 +20,9 @@
/* We can spread an ack vector across multiple options */
#define DCCP_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * 2)
+/* Estimated minimum average Ack Vector length - used for updating MPS */
+#define DCCPAV_MIN_OPTLEN 16
+
#define DCCP_ACKVEC_STATE_RECEIVED 0
#define DCCP_ACKVEC_STATE_ECN_MARKED (1 << 6)
#define DCCP_ACKVEC_STATE_NOT_RECEIVED (3 << 6)
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index f2230fc168e..d6bc47363b1 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -42,9 +42,11 @@
extern int dccp_debug;
#define dccp_pr_debug(format, a...) DCCP_PR_DEBUG(dccp_debug, format, ##a)
#define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a)
+#define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a)
#else
#define dccp_pr_debug(format, a...)
#define dccp_pr_debug_cat(format, a...)
+#define dccp_debug(format, a...)
#endif
extern struct inet_hashinfo dccp_hashinfo;
@@ -61,11 +63,14 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo);
* - DCCP-Reset with ACK Subheader and 4 bytes of Reset Code fields
* Hence a safe upper bound for the maximum option length is 1020-28 = 992
*/
-#define MAX_DCCP_SPECIFIC_HEADER (255 * sizeof(int))
+#define MAX_DCCP_SPECIFIC_HEADER (255 * sizeof(uint32_t))
#define DCCP_MAX_PACKET_HDR 28
#define DCCP_MAX_OPT_LEN (MAX_DCCP_SPECIFIC_HEADER - DCCP_MAX_PACKET_HDR)
#define MAX_DCCP_HEADER (MAX_DCCP_SPECIFIC_HEADER + MAX_HEADER)
+/* Upper bound for initial feature-negotiation overhead (padded to 32 bits) */
+#define DCCP_FEATNEG_OVERHEAD (32 * sizeof(uint32_t))
+
#define DCCP_TIMEWAIT_LEN (60 * HZ) /* how long to wait to destroy TIME-WAIT
* state, about 60 seconds */
@@ -95,9 +100,6 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo);
extern int sysctl_dccp_request_retries;
extern int sysctl_dccp_retries1;
extern int sysctl_dccp_retries2;
-extern int sysctl_dccp_feat_sequence_window;
-extern int sysctl_dccp_feat_rx_ccid;
-extern int sysctl_dccp_feat_tx_ccid;
extern int sysctl_dccp_tx_qlen;
extern int sysctl_dccp_sync_ratelimit;
@@ -409,23 +411,21 @@ static inline void dccp_hdr_set_ack(struct dccp_hdr_ack_bits *dhack,
static inline void dccp_update_gsr(struct sock *sk, u64 seq)
{
struct dccp_sock *dp = dccp_sk(sk);
- const struct dccp_minisock *dmsk = dccp_msk(sk);
dp->dccps_gsr = seq;
- dccp_set_seqno(&dp->dccps_swl,
- dp->dccps_gsr + 1 - (dmsk->dccpms_sequence_window / 4));
- dccp_set_seqno(&dp->dccps_swh,
- dp->dccps_gsr + (3 * dmsk->dccpms_sequence_window) / 4);
+ /* Sequence validity window depends on remote Sequence Window (7.5.1) */
+ dp->dccps_swl = SUB48(ADD48(dp->dccps_gsr, 1), dp->dccps_r_seq_win / 4);
+ dp->dccps_swh = ADD48(dp->dccps_gsr, (3 * dp->dccps_r_seq_win) / 4);
}
static inline void dccp_update_gss(struct sock *sk, u64 seq)
{
struct dccp_sock *dp = dccp_sk(sk);
- dp->dccps_awh = dp->dccps_gss = seq;
- dccp_set_seqno(&dp->dccps_awl,
- (dp->dccps_gss -
- dccp_msk(sk)->dccpms_sequence_window + 1));
+ dp->dccps_gss = seq;
+ /* Ack validity window depends on local Sequence Window value (7.5.1) */
+ dp->dccps_awl = SUB48(ADD48(dp->dccps_gss, 1), dp->dccps_l_seq_win);
+ dp->dccps_awh = dp->dccps_gss;
}
static inline int dccp_ack_pending(const struct sock *sk)
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 4152308958a..b04160a2eea 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -25,6 +25,11 @@
#include "ccid.h"
#include "feat.h"
+/* feature-specific sysctls - initialised to the defaults from RFC 4340, 6.4 */
+unsigned long sysctl_dccp_sequence_window __read_mostly = 100;
+int sysctl_dccp_rx_ccid __read_mostly = 2,
+ sysctl_dccp_tx_ccid __read_mostly = 2;
+
/*
* Feature activation handlers.
*
@@ -51,8 +56,17 @@ static int dccp_hdlr_ccid(struct sock *sk, u64 ccid, bool rx)
static int dccp_hdlr_seq_win(struct sock *sk, u64 seq_win, bool rx)
{
- if (!rx)
- dccp_msk(sk)->dccpms_sequence_window = seq_win;
+ struct dccp_sock *dp = dccp_sk(sk);
+
+ if (rx) {
+ dp->dccps_r_seq_win = seq_win;
+ /* propagate changes to update SWL/SWH */
+ dccp_update_gsr(sk, dp->dccps_gsr);
+ } else {
+ dp->dccps_l_seq_win = seq_win;
+ /* propagate changes to update AWL */
+ dccp_update_gss(sk, dp->dccps_gss);
+ }
return 0;
}
@@ -194,6 +208,100 @@ static int dccp_feat_default_value(u8 feat_num)
return idx < 0 ? 0 : dccp_feat_table[idx].default_value;
}
+/*
+ * Debugging and verbose-printing section
+ */
+static const char *dccp_feat_fname(const u8 feat)
+{
+ static const char *feature_names[] = {
+ [DCCPF_RESERVED] = "Reserved",
+ [DCCPF_CCID] = "CCID",
+ [DCCPF_SHORT_SEQNOS] = "Allow Short Seqnos",
+ [DCCPF_SEQUENCE_WINDOW] = "Sequence Window",
+ [DCCPF_ECN_INCAPABLE] = "ECN Incapable",
+ [DCCPF_ACK_RATIO] = "Ack Ratio",
+ [DCCPF_SEND_ACK_VECTOR] = "Send ACK Vector",
+ [DCCPF_SEND_NDP_COUNT] = "Send NDP Count",
+ [DCCPF_MIN_CSUM_COVER] = "Min. Csum Coverage",
+ [DCCPF_DATA_CHECKSUM] = "Send Data Checksum",
+ };
+ if (feat > DCCPF_DATA_CHECKSUM && feat < DCCPF_MIN_CCID_SPECIFIC)
+ return feature_names[DCCPF_RESERVED];
+
+ if (feat == DCCPF_SEND_LEV_RATE)
+ return "Send Loss Event Rate";
+ if (feat >= DCCPF_MIN_CCID_SPECIFIC)
+ return "CCID-specific";
+
+ return feature_names[feat];
+}
+
+static const char *dccp_feat_sname[] = { "DEFAULT", "INITIALISING", "CHANGING",
+ "UNSTABLE", "STABLE" };
+
+#ifdef CONFIG_IP_DCCP_DEBUG
+static const char *dccp_feat_oname(const u8 opt)
+{
+ switch (opt) {
+ case DCCPO_CHANGE_L: return "Change_L";
+ case DCCPO_CONFIRM_L: return "Confirm_L";
+ case DCCPO_CHANGE_R: return "Change_R";
+ case DCCPO_CONFIRM_R: return "Confirm_R";
+ }
+ return NULL;
+}
+
+static void dccp_feat_printval(u8 feat_num, dccp_feat_val const *val)
+{
+ u8 i, type = dccp_feat_type(feat_num);
+
+ if (val == NULL || (type == FEAT_SP && val->sp.vec == NULL))
+ dccp_pr_debug_cat("(NULL)");
+ else if (type == FEAT_SP)
+ for (i = 0; i < val->sp.len; i++)
+ dccp_pr_debug_cat("%s%u", i ? " " : "", val->sp.vec[i]);
+ else if (type == FEAT_NN)
+ dccp_pr_debug_cat("%llu", (unsigned long long)val->nn);
+ else
+ dccp_pr_debug_cat("unknown type %u", type);
+}
+
+static void dccp_feat_printvals(u8 feat_num, u8 *list, u8 len)
+{
+ u8 type = dccp_feat_type(feat_num);
+ dccp_feat_val fval = { .sp.vec = list, .sp.len = len };
+
+ if (type == FEAT_NN)
+ fval.nn = dccp_decode_value_var(list, len);
+ dccp_feat_printval(feat_num, &fval);
+}
+
+static void dccp_feat_print_entry(struct dccp_feat_entry const *entry)
+{
+ dccp_debug(" * %s %s = ", entry->is_local ? "local" : "remote",
+ dccp_feat_fname(entry->feat_num));
+ dccp_feat_printval(entry->feat_num, &entry->val);
+ dccp_pr_debug_cat(", state=%s %s\n", dccp_feat_sname[entry->state],
+ entry->needs_confirm ? "(Confirm pending)" : "");
+}
+
+#define dccp_feat_print_opt(opt, feat, val, len, mandatory) do { \
+ dccp_pr_debug("%s(%s, ", dccp_feat_oname(opt), dccp_feat_fname(feat));\
+ dccp_feat_printvals(feat, val, len); \
+ dccp_pr_debug_cat(") %s\n", mandatory ? "!" : ""); } while (0)
+
+#define dccp_feat_print_fnlist(fn_list) { \
+ const struct dccp_feat_entry *___entry; \
+ \
+ dccp_pr_debug("List Dump:\n"); \
+ list_for_each_entry(___entry, fn_list, node) \
+ dccp_feat_print_entry(___entry); \
+}
+#else /* ! CONFIG_IP_DCCP_DEBUG */
+#define dccp_feat_print_opt(opt, feat, val, len, mandatory)
+#define dccp_feat_print_fnlist(fn_list)
+#endif
+
static int __dccp_feat_activate(struct sock *sk, const int idx,
const bool is_local, dccp_feat_val const *fval)
{
@@ -226,6 +334,10 @@ static int __dccp_feat_activate(struct sock *sk, const int idx,
/* Location is RX if this is a local-RX or remote-TX feature */
rx = (is_local == (dccp_feat_table[idx].rxtx == FEAT_AT_RX));
+ dccp_debug(" -> activating %s %s, %sval=%llu\n", rx ? "RX" : "TX",
+ dccp_feat_fname(dccp_feat_table[idx].feat_num),
+ fval ? "" : "default ", (unsigned long long)val);
+
return dccp_feat_table[idx].activation_hdlr(sk, val, rx);
}
@@ -530,6 +642,7 @@ int dccp_feat_insert_opts(struct dccp_sock *dp, struct dccp_request_sock *dreq,
return -1;
}
}
+ dccp_feat_print_opt(opt, pos->feat_num, ptr, len, 0);
if (dccp_insert_fn_opt(skb, opt, pos->feat_num, ptr, len, rpt))
return -1;
@@ -783,6 +896,7 @@ int dccp_feat_finalise_settings(struct dccp_sock *dp)
while (i--)
if (ccids[i] > 0 && dccp_feat_propagate_ccid(fn, ccids[i], i))
return -1;
+ dccp_feat_print_fnlist(fn);
return 0;
}
@@ -901,6 +1015,8 @@ static u8 dccp_feat_change_recv(struct list_head *fn, u8 is_mandatory, u8 opt,
if (len == 0 || type == FEAT_UNKNOWN) /* 6.1 and 6.6.8 */
goto unknown_feature_or_value;
+ dccp_feat_print_opt(opt, feat, val, len, is_mandatory);
+
/*
* Negotiation of NN features: Change R is invalid, so there is no
* simultaneous negotiation; hence we do not look up in the list.
@@ -1006,6 +1122,8 @@ static u8 dccp_feat_confirm_recv(struct list_head *fn, u8 is_mandatory, u8 opt,
const bool local = (opt == DCCPO_CONFIRM_R);
struct dccp_feat_entry *entry = dccp_feat_list_lookup(fn, feat, local);
+ dccp_feat_print_opt(opt, feat, val, len, is_mandatory);
+
if (entry == NULL) { /* nothing queued: ignore or handle error */
if (is_mandatory && type == FEAT_UNKNOWN)
return DCCP_RESET_CODE_MANDATORY_ERROR;
@@ -1115,23 +1233,70 @@ int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
return 0; /* ignore FN options in all other states */
}
+/**
+ * dccp_feat_init - Seed feature negotiation with host-specific defaults
+ * This initialises global defaults, depending on the value of the sysctls.
+ * These can later be overridden by registering changes via setsockopt calls.
+ * The last link in the chain is finalise_settings, to make sure that between
+ * here and the start of actual feature negotiation no inconsistencies enter.
+ *
+ * All features not appearing below use either defaults or are otherwise
+ * later adjusted through dccp_feat_finalise_settings().
+ */
int dccp_feat_init(struct sock *sk)
{
- struct dccp_sock *dp = dccp_sk(sk);
- struct dccp_minisock *dmsk = dccp_msk(sk);
+ struct list_head *fn = &dccp_sk(sk)->dccps_featneg;
+ u8 on = 1, off = 0;
int rc;
+ struct {
+ u8 *val;
+ u8 len;
+ } tx, rx;
+
+ /* Non-negotiable (NN) features */
+ rc = __feat_register_nn(fn, DCCPF_SEQUENCE_WINDOW, 0,
+ sysctl_dccp_sequence_window);
+ if (rc)
+ return rc;
+
+ /* Server-priority (SP) features */
+
+ /* Advertise that short seqnos are not supported (7.6.1) */
+ rc = __feat_register_sp(fn, DCCPF_SHORT_SEQNOS, true, true, &off, 1);
+ if (rc)
+ return rc;
- INIT_LIST_HEAD(&dmsk->dccpms_pending); /* XXX no longer used */
- INIT_LIST_HEAD(&dmsk->dccpms_conf); /* XXX no longer used */
+ /* RFC 4340 12.1: "If a DCCP is not ECN capable, ..." */
+ rc = __feat_register_sp(fn, DCCPF_ECN_INCAPABLE, true, true, &on, 1);
+ if (rc)
+ return rc;
+
+ /*
+ * We advertise the available list of CCIDs and reorder according to
+ * preferences, to avoid failure resulting from negotiating different
+ * singleton values (which always leads to failure).
+ * These settings can still (later) be overridden via sockopts.
+ */
+ if (ccid_get_builtin_ccids(&tx.val, &tx.len) ||
+ ccid_get_builtin_ccids(&rx.val, &rx.len))
+ return -ENOBUFS;
+
+ if (!dccp_feat_prefer(sysctl_dccp_tx_ccid, tx.val, tx.len) ||
+ !dccp_feat_prefer(sysctl_dccp_rx_ccid, rx.val, rx.len))
+ goto free_ccid_lists;
+
+ rc = __feat_register_sp(fn, DCCPF_CCID, true, false, tx.val, tx.len);
+ if (rc)
+ goto free_ccid_lists;
+
+ rc = __feat_register_sp(fn, DCCPF_CCID, false, false, rx.val, rx.len);
- /* Ack ratio */
- rc = __feat_register_nn(&dp->dccps_featneg, DCCPF_ACK_RATIO, 0,
- dp->dccps_l_ack_ratio);
+free_ccid_lists:
+ kfree(tx.val);
+ kfree(rx.val);
return rc;
}
-EXPORT_SYMBOL_GPL(dccp_feat_init);
-
int dccp_feat_activate_values(struct sock *sk, struct list_head *fn_list)
{
struct dccp_sock *dp = dccp_sk(sk);
@@ -1156,9 +1321,10 @@ int dccp_feat_activate_values(struct sock *sk, struct list_head *fn_list)
goto activation_failed;
}
if (cur->state != FEAT_STABLE) {
- DCCP_CRIT("Negotiation of %s %u failed in state %u",
+ DCCP_CRIT("Negotiation of %s %s failed in state %s",
cur->is_local ? "local" : "remote",
- cur->feat_num, cur->state);
+ dccp_feat_fname(cur->feat_num),
+ dccp_feat_sname[cur->state]);
goto activation_failed;
}
fvals[idx][cur->is_local] = &cur->val;
@@ -1199,43 +1365,3 @@ activation_failed:
dp->dccps_hc_rx_ackvec = NULL;
return -1;
}
-
-#ifdef CONFIG_IP_DCCP_DEBUG
-const char *dccp_feat_typename(const u8 type)
-{
- switch(type) {
- case DCCPO_CHANGE_L: return("ChangeL");
- case DCCPO_CONFIRM_L: return("ConfirmL");
- case DCCPO_CHANGE_R: return("ChangeR");
- case DCCPO_CONFIRM_R: return("ConfirmR");
- /* the following case must not appear in feature negotation */
- default: dccp_pr_debug("unknown type %d [BUG!]\n", type);
- }
- return NULL;
-}
-
-const char *dccp_feat_name(const u8 feat)
-{
- static const char *feature_names[] = {
- [DCCPF_RESERVED] = "Reserved",
- [DCCPF_CCID] = "CCID",
- [DCCPF_SHORT_SEQNOS] = "Allow Short Seqnos",
- [DCCPF_SEQUENCE_WINDOW] = "Sequence Window",
- [DCCPF_ECN_INCAPABLE] = "ECN Incapable",
- [DCCPF_ACK_RATIO] = "Ack Ratio",
- [DCCPF_SEND_ACK_VECTOR] = "Send ACK Vector",
- [DCCPF_SEND_NDP_COUNT] = "Send NDP Count",
- [DCCPF_MIN_CSUM_COVER] = "Min. Csum Coverage",
- [DCCPF_DATA_CHECKSUM] = "Send Data Checksum",
- };
- if (feat > DCCPF_DATA_CHECKSUM && feat < DCCPF_MIN_CCID_SPECIFIC)
- return feature_names[DCCPF_RESERVED];
-
- if (feat == DCCPF_SEND_LEV_RATE)
- return "Send Loss Event Rate";
- if (feat >= DCCPF_MIN_CCID_SPECIFIC)
- return "CCID-specific";
-
- return feature_names[feat];
-}
-#endif /* CONFIG_IP_DCCP_DEBUG */
diff --git a/net/dccp/feat.h b/net/dccp/feat.h
index 9b46e2a7866..f96721619de 100644
--- a/net/dccp/feat.h
+++ b/net/dccp/feat.h
@@ -100,26 +100,21 @@ struct ccid_dependency {
u8 val;
};
-#ifdef CONFIG_IP_DCCP_DEBUG
-extern const char *dccp_feat_typename(const u8 type);
-extern const char *dccp_feat_name(const u8 feat);
-
-static inline void dccp_feat_debug(const u8 type, const u8 feat, const u8 val)
-{
- dccp_pr_debug("%s(%s (%d), %d)\n", dccp_feat_typename(type),
- dccp_feat_name(feat), feat, val);
-}
-#else
-#define dccp_feat_debug(type, feat, val)
-#endif /* CONFIG_IP_DCCP_DEBUG */
+/*
+ * Sysctls to seed defaults for feature negotiation
+ */
+extern unsigned long sysctl_dccp_sequence_window;
+extern int sysctl_dccp_rx_ccid;
+extern int sysctl_dccp_tx_ccid;
+extern int dccp_feat_init(struct sock *sk);
+extern void dccp_feat_initialise_sysctls(void);
extern int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local,
u8 const *list, u8 len);
extern int dccp_feat_register_nn(struct sock *sk, u8 feat, u64 val);
extern int dccp_feat_parse_options(struct sock *, struct dccp_request_sock *,
u8 mand, u8 opt, u8 feat, u8 *val, u8 len);
extern int dccp_feat_clone_list(struct list_head const *, struct list_head *);
-extern int dccp_feat_init(struct sock *sk);
/*
* Encoding variable-length options and their maximum length.
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 6821ae33dd3..5ca49cec95f 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -42,11 +42,6 @@ struct inet_timewait_death_row dccp_death_row = {
EXPORT_SYMBOL_GPL(dccp_death_row);
-void dccp_minisock_init(struct dccp_minisock *dmsk)
-{
- dmsk->dccpms_sequence_window = sysctl_dccp_feat_sequence_window;
-}
-
void dccp_time_wait(struct sock *sk, int state, int timeo)
{
struct inet_timewait_sock *tw = NULL;
@@ -110,7 +105,6 @@ struct sock *dccp_create_openreq_child(struct sock *sk,
struct dccp_request_sock *dreq = dccp_rsk(req);
struct inet_connection_sock *newicsk = inet_csk(newsk);
struct dccp_sock *newdp = dccp_sk(newsk);
- struct dccp_minisock *newdmsk = dccp_msk(newsk);
newdp->dccps_role = DCCP_ROLE_SERVER;
newdp->dccps_hc_rx_ackvec = NULL;
@@ -128,10 +122,6 @@ struct sock *dccp_create_openreq_child(struct sock *sk,
* Initialize S.GAR := S.ISS
* Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies
*/
-
- /* See dccp_v4_conn_request */
- newdmsk->dccpms_sequence_window = req->rcv_wnd;
-
newdp->dccps_gar = newdp->dccps_iss = dreq->dreq_iss;
dccp_update_gss(newsk, dreq->dreq_iss);
@@ -290,7 +280,6 @@ int dccp_reqsk_init(struct request_sock *req,
inet_rsk(req)->rmt_port = dccp_hdr(skb)->dccph_sport;
inet_rsk(req)->loc_port = dccp_hdr(skb)->dccph_dport;
inet_rsk(req)->acked = 0;
- req->rcv_wnd = sysctl_dccp_feat_sequence_window;
dreq->dreq_timestamp_echo = 0;
/* inherit feature negotiation options from listening socket */
diff --git a/net/dccp/options.c b/net/dccp/options.c
index 7b1165c21f5..1b08cae9c65 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -23,10 +23,6 @@
#include "dccp.h"
#include "feat.h"
-int sysctl_dccp_feat_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW;
-int sysctl_dccp_feat_rx_ccid = DCCPF_INITIAL_CCID;
-int sysctl_dccp_feat_tx_ccid = DCCPF_INITIAL_CCID;
-
u64 dccp_decode_value_var(const u8 *bf, const u8 len)
{
u64 value = 0;
@@ -502,10 +498,6 @@ int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat,
*to++ = *val;
if (len)
memcpy(to, val, len);
-
- dccp_pr_debug("%s(%s (%d), ...), length %d\n",
- dccp_feat_typename(type),
- dccp_feat_name(feat), feat, len);
return 0;
}
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 22a618af489..36bcc00654d 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -161,21 +161,27 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu)
struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
u32 ccmps = dccp_determine_ccmps(dp);
- int cur_mps = ccmps ? min(pmtu, ccmps) : pmtu;
+ u32 cur_mps = ccmps ? min(pmtu, ccmps) : pmtu;
/* Account for header lengths and IPv4/v6 option overhead */
cur_mps -= (icsk->icsk_af_ops->net_header_len + icsk->icsk_ext_hdr_len +
sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext));
/*
- * FIXME: this should come from the CCID infrastructure, where, say,
- * TFRC will say it wants TIMESTAMPS, ELAPSED time, etc, for now lets
- * put a rough estimate for NDP + TIMESTAMP + TIMESTAMP_ECHO + ELAPSED
- * TIME + TFRC_OPT_LOSS_EVENT_RATE + TFRC_OPT_RECEIVE_RATE + padding to
- * make it a multiple of 4
+ * Leave enough headroom for common DCCP header options.
+ * This only considers options which may appear on DCCP-Data packets, as
+ * per table 3 in RFC 4340, 5.8. When running out of space for other
+ * options (eg. Ack Vector which can take up to 255 bytes), it is better
+ * to schedule a separate Ack. Thus we leave headroom for the following:
+ * - 1 byte for Slow Receiver (11.6)
+ * - 6 bytes for Timestamp (13.1)
+ * - 10 bytes for Timestamp Echo (13.3)
+ * - 8 bytes for NDP count (7.7, when activated)
+ * - 6 bytes for Data Checksum (9.3)
+ * - %DCCPAV_MIN_OPTLEN bytes for Ack Vector size (11.4, when enabled)
*/
-
- cur_mps -= roundup(5 + 6 + 10 + 6 + 6 + 6, 4);
+ cur_mps -= roundup(1 + 6 + 10 + dp->dccps_send_ndp_count * 8 + 6 +
+ (dp->dccps_hc_rx_ackvec ? DCCPAV_MIN_OPTLEN : 0), 4);
/* And store cached results */
icsk->icsk_pmtu_cookie = pmtu;
@@ -270,7 +276,20 @@ void dccp_write_xmit(struct sock *sk, int block)
const int len = skb->len;
if (sk->sk_state == DCCP_PARTOPEN) {
- /* See 8.1.5. Handshake Completion */
+ const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD;
+ /*
+ * See 8.1.5 - Handshake Completion.
+ *
+ * For robustness we resend Confirm options until the client has
+ * entered OPEN. During the initial feature negotiation, the MPS
+ * is smaller than usual, reduced by the Change/Confirm options.
+ */
+ if (!list_empty(&dp->dccps_featneg) && len > cur_mps) {
+ DCCP_WARN("Payload too large (%d) for featneg.\n", len);
+ dccp_send_ack(sk);
+ dccp_feat_list_purge(&dp->dccps_featneg);
+ }
+
inet_csk_schedule_ack(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
inet_csk(sk)->icsk_rto,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 945b4d5d23b..314a1b5c033 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -174,8 +174,6 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
struct dccp_sock *dp = dccp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
- dccp_minisock_init(&dp->dccps_minisock);
-
icsk->icsk_rto = DCCP_TIMEOUT_INIT;
icsk->icsk_syn_retries = sysctl_dccp_request_retries;
sk->sk_state = DCCP_CLOSED;
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
index 018e210875e..a5a1856234e 100644
--- a/net/dccp/sysctl.c
+++ b/net/dccp/sysctl.c
@@ -18,55 +18,72 @@
#error This file should not be compiled without CONFIG_SYSCTL defined
#endif
+/* Boundary values */
+static int zero = 0,
+ u8_max = 0xFF;
+static unsigned long seqw_min = 32;
+
static struct ctl_table dccp_default_table[] = {
{
.procname = "seq_window",
- .data = &sysctl_dccp_feat_sequence_window,
- .maxlen = sizeof(sysctl_dccp_feat_sequence_window),
+ .data = &sysctl_dccp_sequence_window,
+ .maxlen = sizeof(sysctl_dccp_sequence_window),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_doulongvec_minmax,
+ .extra1 = &seqw_min, /* RFC 4340, 7.5.2 */
},
{
.procname = "rx_ccid",
- .data = &sysctl_dccp_feat_rx_ccid,
- .maxlen = sizeof(sysctl_dccp_feat_rx_ccid),
+ .data = &sysctl_dccp_rx_ccid,
+ .maxlen = sizeof(sysctl_dccp_rx_ccid),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &u8_max, /* RFC 4340, 10. */
},
{
.procname = "tx_ccid",
- .data = &sysctl_dccp_feat_tx_ccid,
- .maxlen = sizeof(sysctl_dccp_feat_tx_ccid),
+ .data = &sysctl_dccp_tx_ccid,
+ .maxlen = sizeof(sysctl_dccp_tx_ccid),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &u8_max, /* RFC 4340, 10. */
},
{
.procname = "request_retries",
.data = &sysctl_dccp_request_retries,
.maxlen = sizeof(sysctl_dccp_request_retries),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &u8_max,
},
{
.procname = "retries1",
.data = &sysctl_dccp_retries1,
.maxlen = sizeof(sysctl_dccp_retries1),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &u8_max,
},
{
.procname = "retries2",
.data = &sysctl_dccp_retries2,
.maxlen = sizeof(sysctl_dccp_retries2),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &u8_max,
},
{
.procname = "tx_qlen",
.data = &sysctl_dccp_tx_qlen,
.maxlen = sizeof(sysctl_dccp_tx_qlen),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
.procname = "sync_ratelimit",
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index cf0e1849929..9647d911f91 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1246,11 +1246,12 @@ static int dn_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
case TIOCINQ:
lock_sock(sk);
- if ((skb = skb_peek(&scp->other_receive_queue)) != NULL) {
+ skb = skb_peek(&scp->other_receive_queue);
+ if (skb) {
amount = skb->len;
} else {
- struct sk_buff *skb = sk->sk_receive_queue.next;
- for(;;) {
+ skb = sk->sk_receive_queue.next;
+ for (;;) {
if (skb ==
(struct sk_buff *)&sk->sk_receive_queue)
break;
@@ -1579,16 +1580,16 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us
default:
#ifdef CONFIG_NETFILTER
{
- int val, len;
+ int ret, len;
if(get_user(len, optlen))
return -EFAULT;
- val = nf_getsockopt(sk, PF_DECnet, optname,
+ ret = nf_getsockopt(sk, PF_DECnet, optname,
optval, &len);
- if (val >= 0)
- val = put_user(len, optlen);
- return val;
+ if (ret >= 0)
+ ret = put_user(len, optlen);
+ return ret;
}
#endif
case DSO_STREAM:
@@ -2071,8 +2072,7 @@ static int dn_sendmsg(struct kiocb *iocb, struct socket *sock,
}
out:
- if (skb)
- kfree_skb(skb);
+ kfree_skb(skb);
release_sock(sk);
@@ -2112,9 +2112,8 @@ static struct notifier_block dn_dev_notifier = {
extern int dn_route_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *);
-static struct packet_type dn_dix_packet_type = {
- .type = __constant_htons(ETH_P_DNA_RT),
- .dev = NULL, /* All devices */
+static struct packet_type dn_dix_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_DNA_RT),
.func = dn_route_rcv,
};
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index daf2b98b15f..1c6a5bb6f0c 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -684,7 +684,6 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
return -ENODEV;
if ((dn_db = dev->dn_ptr) == NULL) {
- int err;
dn_db = dn_dev_create(dev, &err);
if (!dn_db)
return err;
@@ -769,7 +768,8 @@ static void dn_ifaddr_notify(int event, struct dn_ifaddr *ifa)
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, &init_net, 0, RTNLGRP_DECnet_IFADDR, NULL, GFP_KERNEL);
+ rtnl_notify(skb, &init_net, 0, RTNLGRP_DECnet_IFADDR, NULL, GFP_KERNEL);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(&init_net, RTNLGRP_DECnet_IFADDR, err);
@@ -1322,6 +1322,7 @@ static inline int is_dn_dev(struct net_device *dev)
}
static void *dn_dev_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(&dev_base_lock)
{
int i;
struct net_device *dev;
@@ -1364,6 +1365,7 @@ static void *dn_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
}
static void dn_dev_seq_stop(struct seq_file *seq, void *v)
+ __releases(&dev_base_lock)
{
read_unlock(&dev_base_lock);
}
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index c754670b7fc..0cc4394117d 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -124,7 +124,7 @@ int decnet_dst_gc_interval = 2;
static struct dst_ops dn_dst_ops = {
.family = PF_DECnet,
- .protocol = __constant_htons(ETH_P_DNA_RT),
+ .protocol = cpu_to_be16(ETH_P_DNA_RT),
.gc_thresh = 128,
.gc = dn_dst_gc,
.check = dn_dst_check,
@@ -380,7 +380,6 @@ static int dn_return_short(struct sk_buff *skb)
unsigned char *ptr;
__le16 *src;
__le16 *dst;
- __le16 tmp;
/* Add back headers */
skb_push(skb, skb->data - skb_network_header(skb));
@@ -399,10 +398,7 @@ static int dn_return_short(struct sk_buff *skb)
ptr += 2;
*ptr = 0; /* Zero hop count */
- /* Swap source and destination */
- tmp = *src;
- *src = *dst;
- *dst = tmp;
+ swap(*src, *dst);
skb->pkt_type = PACKET_OUTGOING;
dn_rt_finish_output(skb, NULL, NULL);
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index 69ad9280c69..67054b0d550 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -375,7 +375,8 @@ static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, u32 tb_id,
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, &init_net, pid, RTNLGRP_DECnet_ROUTE, nlh, GFP_KERNEL);
+ rtnl_notify(skb, &init_net, pid, RTNLGRP_DECnet_ROUTE, nlh, GFP_KERNEL);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(&init_net, RTNLGRP_DECnet_ROUTE, err);
diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c
index 965397af9a8..5bcd592ae6d 100644
--- a/net/decnet/sysctl_net_decnet.c
+++ b/net/decnet/sysctl_net_decnet.c
@@ -179,7 +179,7 @@ static int dn_node_address_handler(ctl_table *table, int write,
}
if (write) {
- int len = (*lenp < DN_ASCBUF_LEN) ? *lenp : (DN_ASCBUF_LEN-1);
+ len = (*lenp < DN_ASCBUF_LEN) ? *lenp : (DN_ASCBUF_LEN-1);
if (copy_from_user(addr, buffer, len))
return -EFAULT;
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 49211b35725..c51b55400dc 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -41,13 +41,13 @@ config NET_DSA_MV88E6XXX_NEED_PPU
default n
config NET_DSA_MV88E6131
- bool "Marvell 88E6131 ethernet switch chip support"
+ bool "Marvell 88E6095/6095F/6131 ethernet switch chip support"
select NET_DSA_MV88E6XXX
select NET_DSA_MV88E6XXX_NEED_PPU
select NET_DSA_TAG_DSA
---help---
- This enables support for the Marvell 88E6131 ethernet switch
- chip.
+ This enables support for the Marvell 88E6095/6095F/6131
+ ethernet switch chips.
config NET_DSA_MV88E6123_61_65
bool "Marvell 88E6123/6161/6165 ethernet switch chip support"
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 33e99462023..71489f69a42 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -1,6 +1,6 @@
/*
* net/dsa/dsa.c - Hardware switch handling
- * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2008-2009 Marvell Semiconductor
*
* 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
@@ -67,12 +67,13 @@ dsa_switch_probe(struct mii_bus *bus, int sw_addr, char **_name)
/* basic switch operations **************************************************/
static struct dsa_switch *
-dsa_switch_setup(struct device *parent, struct dsa_platform_data *pd,
- struct mii_bus *bus, struct net_device *dev)
+dsa_switch_setup(struct dsa_switch_tree *dst, int index,
+ struct device *parent, struct mii_bus *bus)
{
+ struct dsa_chip_data *pd = dst->pd->chip + index;
+ struct dsa_switch_driver *drv;
struct dsa_switch *ds;
int ret;
- struct dsa_switch_driver *drv;
char *name;
int i;
@@ -81,11 +82,12 @@ dsa_switch_setup(struct device *parent, struct dsa_platform_data *pd,
*/
drv = dsa_switch_probe(bus, pd->sw_addr, &name);
if (drv == NULL) {
- printk(KERN_ERR "%s: could not detect attached switch\n",
- dev->name);
+ printk(KERN_ERR "%s[%d]: could not detect attached switch\n",
+ dst->master_netdev->name, index);
return ERR_PTR(-EINVAL);
}
- printk(KERN_INFO "%s: detected a %s switch\n", dev->name, name);
+ printk(KERN_INFO "%s[%d]: detected a %s switch\n",
+ dst->master_netdev->name, index, name);
/*
@@ -95,18 +97,16 @@ dsa_switch_setup(struct device *parent, struct dsa_platform_data *pd,
if (ds == NULL)
return ERR_PTR(-ENOMEM);
- ds->pd = pd;
- ds->master_netdev = dev;
- ds->master_mii_bus = bus;
-
+ ds->dst = dst;
+ ds->index = index;
+ ds->pd = dst->pd->chip + index;
ds->drv = drv;
- ds->tag_protocol = drv->tag_protocol;
+ ds->master_mii_bus = bus;
/*
* Validate supplied switch configuration.
*/
- ds->cpu_port = -1;
for (i = 0; i < DSA_MAX_PORTS; i++) {
char *name;
@@ -115,32 +115,28 @@ dsa_switch_setup(struct device *parent, struct dsa_platform_data *pd,
continue;
if (!strcmp(name, "cpu")) {
- if (ds->cpu_port != -1) {
+ if (dst->cpu_switch != -1) {
printk(KERN_ERR "multiple cpu ports?!\n");
ret = -EINVAL;
goto out;
}
- ds->cpu_port = i;
+ dst->cpu_switch = index;
+ dst->cpu_port = i;
+ } else if (!strcmp(name, "dsa")) {
+ ds->dsa_port_mask |= 1 << i;
} else {
- ds->valid_port_mask |= 1 << i;
+ ds->phys_port_mask |= 1 << i;
}
}
- if (ds->cpu_port == -1) {
- printk(KERN_ERR "no cpu port?!\n");
- ret = -EINVAL;
- goto out;
- }
-
/*
- * If we use a tagging format that doesn't have an ethertype
- * field, make sure that all packets from this point on get
- * sent to the tag format's receive function. (Which will
- * discard received packets until we set ds->ports[] below.)
+ * If the CPU connects to this switch, set the switch tree
+ * tagging protocol to the preferred tagging format of this
+ * switch.
*/
- wmb();
- dev->dsa_ptr = (void *)ds;
+ if (ds->dst->cpu_switch == index)
+ ds->dst->tag_protocol = drv->tag_protocol;
/*
@@ -150,7 +146,7 @@ dsa_switch_setup(struct device *parent, struct dsa_platform_data *pd,
if (ret < 0)
goto out;
- ret = drv->set_addr(ds, dev->dev_addr);
+ ret = drv->set_addr(ds, dst->master_netdev->dev_addr);
if (ret < 0)
goto out;
@@ -169,18 +165,18 @@ dsa_switch_setup(struct device *parent, struct dsa_platform_data *pd,
/*
* Create network devices for physical switch ports.
*/
- wmb();
for (i = 0; i < DSA_MAX_PORTS; i++) {
struct net_device *slave_dev;
- if (!(ds->valid_port_mask & (1 << i)))
+ if (!(ds->phys_port_mask & (1 << i)))
continue;
slave_dev = dsa_slave_create(ds, parent, i, pd->port_names[i]);
if (slave_dev == NULL) {
- printk(KERN_ERR "%s: can't create dsa slave "
- "device for port %d(%s)\n",
- dev->name, i, pd->port_names[i]);
+ printk(KERN_ERR "%s[%d]: can't create dsa "
+ "slave device for port %d(%s)\n",
+ dst->master_netdev->name,
+ index, i, pd->port_names[i]);
continue;
}
@@ -192,7 +188,6 @@ dsa_switch_setup(struct device *parent, struct dsa_platform_data *pd,
out_free:
mdiobus_free(ds->slave_mii_bus);
out:
- dev->dsa_ptr = NULL;
kfree(ds);
return ERR_PTR(ret);
}
@@ -212,35 +207,42 @@ static void dsa_switch_destroy(struct dsa_switch *ds)
*/
bool dsa_uses_dsa_tags(void *dsa_ptr)
{
- struct dsa_switch *ds = dsa_ptr;
+ struct dsa_switch_tree *dst = dsa_ptr;
- return !!(ds->tag_protocol == htons(ETH_P_DSA));
+ return !!(dst->tag_protocol == htons(ETH_P_DSA));
}
bool dsa_uses_trailer_tags(void *dsa_ptr)
{
- struct dsa_switch *ds = dsa_ptr;
+ struct dsa_switch_tree *dst = dsa_ptr;
- return !!(ds->tag_protocol == htons(ETH_P_TRAILER));
+ return !!(dst->tag_protocol == htons(ETH_P_TRAILER));
}
/* link polling *************************************************************/
static void dsa_link_poll_work(struct work_struct *ugly)
{
- struct dsa_switch *ds;
+ struct dsa_switch_tree *dst;
+ int i;
+
+ dst = container_of(ugly, struct dsa_switch_tree, link_poll_work);
- ds = container_of(ugly, struct dsa_switch, link_poll_work);
+ for (i = 0; i < dst->pd->nr_chips; i++) {
+ struct dsa_switch *ds = dst->ds[i];
- ds->drv->poll_link(ds);
- mod_timer(&ds->link_poll_timer, round_jiffies(jiffies + HZ));
+ if (ds != NULL && ds->drv->poll_link != NULL)
+ ds->drv->poll_link(ds);
+ }
+
+ mod_timer(&dst->link_poll_timer, round_jiffies(jiffies + HZ));
}
-static void dsa_link_poll_timer(unsigned long _ds)
+static void dsa_link_poll_timer(unsigned long _dst)
{
- struct dsa_switch *ds = (void *)_ds;
+ struct dsa_switch_tree *dst = (void *)_dst;
- schedule_work(&ds->link_poll_work);
+ schedule_work(&dst->link_poll_work);
}
@@ -303,18 +305,14 @@ static int dsa_probe(struct platform_device *pdev)
static int dsa_version_printed;
struct dsa_platform_data *pd = pdev->dev.platform_data;
struct net_device *dev;
- struct mii_bus *bus;
- struct dsa_switch *ds;
+ struct dsa_switch_tree *dst;
+ int i;
if (!dsa_version_printed++)
printk(KERN_NOTICE "Distributed Switch Architecture "
"driver version %s\n", dsa_driver_version);
- if (pd == NULL || pd->mii_bus == NULL || pd->netdev == NULL)
- return -EINVAL;
-
- bus = dev_to_mii_bus(pd->mii_bus);
- if (bus == NULL)
+ if (pd == NULL || pd->netdev == NULL)
return -EINVAL;
dev = dev_to_net_device(pd->netdev);
@@ -326,36 +324,79 @@ static int dsa_probe(struct platform_device *pdev)
return -EEXIST;
}
- ds = dsa_switch_setup(&pdev->dev, pd, bus, dev);
- if (IS_ERR(ds)) {
+ dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ if (dst == NULL) {
dev_put(dev);
- return PTR_ERR(ds);
+ return -ENOMEM;
}
- if (ds->drv->poll_link != NULL) {
- INIT_WORK(&ds->link_poll_work, dsa_link_poll_work);
- init_timer(&ds->link_poll_timer);
- ds->link_poll_timer.data = (unsigned long)ds;
- ds->link_poll_timer.function = dsa_link_poll_timer;
- ds->link_poll_timer.expires = round_jiffies(jiffies + HZ);
- add_timer(&ds->link_poll_timer);
+ platform_set_drvdata(pdev, dst);
+
+ dst->pd = pd;
+ dst->master_netdev = dev;
+ dst->cpu_switch = -1;
+ dst->cpu_port = -1;
+
+ for (i = 0; i < pd->nr_chips; i++) {
+ struct mii_bus *bus;
+ struct dsa_switch *ds;
+
+ bus = dev_to_mii_bus(pd->chip[i].mii_bus);
+ if (bus == NULL) {
+ printk(KERN_ERR "%s[%d]: no mii bus found for "
+ "dsa switch\n", dev->name, i);
+ continue;
+ }
+
+ ds = dsa_switch_setup(dst, i, &pdev->dev, bus);
+ if (IS_ERR(ds)) {
+ printk(KERN_ERR "%s[%d]: couldn't create dsa switch "
+ "instance (error %ld)\n", dev->name, i,
+ PTR_ERR(ds));
+ continue;
+ }
+
+ dst->ds[i] = ds;
+ if (ds->drv->poll_link != NULL)
+ dst->link_poll_needed = 1;
}
- platform_set_drvdata(pdev, ds);
+ /*
+ * If we use a tagging format that doesn't have an ethertype
+ * field, make sure that all packets from this point on get
+ * sent to the tag format's receive function.
+ */
+ wmb();
+ dev->dsa_ptr = (void *)dst;
+
+ if (dst->link_poll_needed) {
+ INIT_WORK(&dst->link_poll_work, dsa_link_poll_work);
+ init_timer(&dst->link_poll_timer);
+ dst->link_poll_timer.data = (unsigned long)dst;
+ dst->link_poll_timer.function = dsa_link_poll_timer;
+ dst->link_poll_timer.expires = round_jiffies(jiffies + HZ);
+ add_timer(&dst->link_poll_timer);
+ }
return 0;
}
static int dsa_remove(struct platform_device *pdev)
{
- struct dsa_switch *ds = platform_get_drvdata(pdev);
+ struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
+ int i;
- if (ds->drv->poll_link != NULL)
- del_timer_sync(&ds->link_poll_timer);
+ if (dst->link_poll_needed)
+ del_timer_sync(&dst->link_poll_timer);
flush_scheduled_work();
- dsa_switch_destroy(ds);
+ for (i = 0; i < dst->pd->nr_chips; i++) {
+ struct dsa_switch *ds = dst->ds[i];
+
+ if (ds != NULL)
+ dsa_switch_destroy(ds);
+ }
return 0;
}
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 7063378a1eb..41055f33d28 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -1,6 +1,6 @@
/*
* net/dsa/dsa_priv.h - Hardware switch handling
- * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2008-2009 Marvell Semiconductor
*
* 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
@@ -19,42 +19,107 @@
struct dsa_switch {
/*
- * Configuration data for the platform device that owns
- * this dsa switch instance.
+ * Parent switch tree, and switch index.
*/
- struct dsa_platform_data *pd;
+ struct dsa_switch_tree *dst;
+ int index;
/*
- * References to network device and mii bus to use.
+ * Configuration data for this switch.
*/
- struct net_device *master_netdev;
- struct mii_bus *master_mii_bus;
+ struct dsa_chip_data *pd;
/*
- * The used switch driver and frame tagging type.
+ * The used switch driver.
*/
struct dsa_switch_driver *drv;
- __be16 tag_protocol;
+
+ /*
+ * Reference to mii bus to use.
+ */
+ struct mii_bus *master_mii_bus;
/*
* Slave mii_bus and devices for the individual ports.
*/
- int cpu_port;
- u32 valid_port_mask;
- struct mii_bus *slave_mii_bus;
- struct net_device *ports[DSA_MAX_PORTS];
+ u32 dsa_port_mask;
+ u32 phys_port_mask;
+ struct mii_bus *slave_mii_bus;
+ struct net_device *ports[DSA_MAX_PORTS];
+};
+
+struct dsa_switch_tree {
+ /*
+ * Configuration data for the platform device that owns
+ * this dsa switch tree instance.
+ */
+ struct dsa_platform_data *pd;
+
+ /*
+ * Reference to network device to use, and which tagging
+ * protocol to use.
+ */
+ struct net_device *master_netdev;
+ __be16 tag_protocol;
+
+ /*
+ * The switch and port to which the CPU is attached.
+ */
+ s8 cpu_switch;
+ s8 cpu_port;
/*
* Link state polling.
*/
- struct work_struct link_poll_work;
- struct timer_list link_poll_timer;
+ int link_poll_needed;
+ struct work_struct link_poll_work;
+ struct timer_list link_poll_timer;
+
+ /*
+ * Data for the individual switch chips.
+ */
+ struct dsa_switch *ds[DSA_MAX_SWITCHES];
};
+static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p)
+{
+ return !!(ds->index == ds->dst->cpu_switch && p == ds->dst->cpu_port);
+}
+
+static inline u8 dsa_upstream_port(struct dsa_switch *ds)
+{
+ struct dsa_switch_tree *dst = ds->dst;
+
+ /*
+ * If this is the root switch (i.e. the switch that connects
+ * to the CPU), return the cpu port number on this switch.
+ * Else return the (DSA) port number that connects to the
+ * switch that is one hop closer to the cpu.
+ */
+ if (dst->cpu_switch == ds->index)
+ return dst->cpu_port;
+ else
+ return ds->pd->rtable[dst->cpu_switch];
+}
+
struct dsa_slave_priv {
+ /*
+ * The linux network interface corresponding to this
+ * switch port.
+ */
struct net_device *dev;
+
+ /*
+ * Which switch this port is a part of, and the port index
+ * for this port.
+ */
struct dsa_switch *parent;
- int port;
+ u8 port;
+
+ /*
+ * The phylib phy_device pointer for the PHY connected
+ * to this port.
+ */
struct phy_device *phy;
};
diff --git a/net/dsa/mv88e6060.c b/net/dsa/mv88e6060.c
index 85081ae9fe8..83277f463af 100644
--- a/net/dsa/mv88e6060.c
+++ b/net/dsa/mv88e6060.c
@@ -1,6 +1,6 @@
/*
* net/dsa/mv88e6060.c - Driver for Marvell 88e6060 switch chips
- * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2008-2009 Marvell Semiconductor
*
* 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
@@ -81,7 +81,7 @@ static int mv88e6060_switch_reset(struct dsa_switch *ds)
/*
* Reset the switch.
*/
- REG_WRITE(REG_GLOBAL, 0x0A, 0xa130);
+ REG_WRITE(REG_GLOBAL, 0x0a, 0xa130);
/*
* Wait up to one second for reset to complete.
@@ -128,7 +128,7 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p)
* state to Forwarding. Additionally, if this is the CPU
* port, enable Ingress and Egress Trailer tagging mode.
*/
- REG_WRITE(addr, 0x04, (p == ds->cpu_port) ? 0x4103 : 0x0003);
+ REG_WRITE(addr, 0x04, dsa_is_cpu_port(ds, p) ? 0x4103 : 0x0003);
/*
* Port based VLAN map: give each port its own address
@@ -138,9 +138,9 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p)
*/
REG_WRITE(addr, 0x06,
((p & 0xf) << 12) |
- ((p == ds->cpu_port) ?
- ds->valid_port_mask :
- (1 << ds->cpu_port)));
+ (dsa_is_cpu_port(ds, p) ?
+ ds->phys_port_mask :
+ (1 << ds->dst->cpu_port)));
/*
* Port Association Vector: when learning source addresses
diff --git a/net/dsa/mv88e6123_61_65.c b/net/dsa/mv88e6123_61_65.c
index ec8c6a0482d..52faaa21a4d 100644
--- a/net/dsa/mv88e6123_61_65.c
+++ b/net/dsa/mv88e6123_61_65.c
@@ -1,6 +1,6 @@
/*
* net/dsa/mv88e6123_61_65.c - Marvell 88e6123/6161/6165 switch chip support
- * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2008-2009 Marvell Semiconductor
*
* 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
@@ -98,17 +98,17 @@ static int mv88e6123_61_65_setup_global(struct dsa_switch *ds)
return ret;
/*
- * Configure the cpu port, and configure the cpu port as the
- * port to which ingress and egress monitor frames are to be
- * sent.
+ * Configure the upstream port, and configure the upstream
+ * port as the port to which ingress and egress monitor frames
+ * are to be sent.
*/
- REG_WRITE(REG_GLOBAL, 0x1a, (ds->cpu_port * 0x1110));
+ REG_WRITE(REG_GLOBAL, 0x1a, (dsa_upstream_port(ds) * 0x1110));
/*
* Disable remote management for now, and set the switch's
- * DSA device number to zero.
+ * DSA device number.
*/
- REG_WRITE(REG_GLOBAL, 0x1c, 0x0000);
+ REG_WRITE(REG_GLOBAL, 0x1c, ds->index & 0x1f);
/*
* Send all frames with destination addresses matching
@@ -133,10 +133,17 @@ static int mv88e6123_61_65_setup_global(struct dsa_switch *ds)
REG_WRITE(REG_GLOBAL2, 0x05, 0x00ff);
/*
- * Map all DSA device IDs to the CPU port.
+ * Program the DSA routing table.
*/
- for (i = 0; i < 32; i++)
- REG_WRITE(REG_GLOBAL2, 0x06, 0x8000 | (i << 8) | ds->cpu_port);
+ for (i = 0; i < 32; i++) {
+ int nexthop;
+
+ nexthop = 0x1f;
+ if (i != ds->index && i < ds->dst->pd->nr_chips)
+ nexthop = ds->pd->rtable[i] & 0x1f;
+
+ REG_WRITE(REG_GLOBAL2, 0x06, 0x8000 | (i << 8) | nexthop);
+ }
/*
* Clear all trunk masks.
@@ -176,12 +183,18 @@ static int mv88e6123_61_65_setup_global(struct dsa_switch *ds)
static int mv88e6123_61_65_setup_port(struct dsa_switch *ds, int p)
{
int addr = REG_PORT(p);
+ u16 val;
/*
* MAC Forcing register: don't force link, speed, duplex
- * or flow control state to any particular values.
+ * or flow control state to any particular values on physical
+ * ports, but force the CPU port and all DSA ports to 1000 Mb/s
+ * full duplex.
*/
- REG_WRITE(addr, 0x01, 0x0003);
+ if (dsa_is_cpu_port(ds, p) || ds->dsa_port_mask & (1 << p))
+ REG_WRITE(addr, 0x01, 0x003e);
+ else
+ REG_WRITE(addr, 0x01, 0x0003);
/*
* Do not limit the period of time that this port can be
@@ -192,37 +205,50 @@ static int mv88e6123_61_65_setup_port(struct dsa_switch *ds, int p)
/*
* Port Control: disable Drop-on-Unlock, disable Drop-on-Lock,
- * configure the requested (DSA/EDSA) tagging mode if this is
- * the CPU port, disable Header mode, enable IGMP/MLD snooping,
- * disable VLAN tunneling, determine priority by looking at
- * 802.1p and IP priority fields (IP prio has precedence), and
- * set STP state to Forwarding. Finally, if this is the CPU
- * port, additionally enable forwarding of unknown unicast and
- * multicast addresses.
- */
- REG_WRITE(addr, 0x04,
- (p == ds->cpu_port) ?
- (ds->tag_protocol == htons(ETH_P_DSA)) ?
- 0x053f : 0x373f :
- 0x0433);
+ * disable Header mode, enable IGMP/MLD snooping, disable VLAN
+ * tunneling, determine priority by looking at 802.1p and IP
+ * priority fields (IP prio has precedence), and set STP state
+ * to Forwarding.
+ *
+ * If this is the CPU link, use DSA or EDSA tagging depending
+ * on which tagging mode was configured.
+ *
+ * If this is a link to another switch, use DSA tagging mode.
+ *
+ * If this is the upstream port for this switch, enable
+ * forwarding of unknown unicasts and multicasts.
+ */
+ val = 0x0433;
+ if (dsa_is_cpu_port(ds, p)) {
+ if (ds->dst->tag_protocol == htons(ETH_P_EDSA))
+ val |= 0x3300;
+ else
+ val |= 0x0100;
+ }
+ if (ds->dsa_port_mask & (1 << p))
+ val |= 0x0100;
+ if (p == dsa_upstream_port(ds))
+ val |= 0x000c;
+ REG_WRITE(addr, 0x04, val);
/*
* Port Control 1: disable trunking. Also, if this is the
* CPU port, enable learn messages to be sent to this port.
*/
- REG_WRITE(addr, 0x05, (p == ds->cpu_port) ? 0x8000 : 0x0000);
+ REG_WRITE(addr, 0x05, dsa_is_cpu_port(ds, p) ? 0x8000 : 0x0000);
/*
* Port based VLAN map: give each port its own address
* database, allow the CPU port to talk to each of the 'real'
* ports, and allow each of the 'real' ports to only talk to
- * the CPU port.
+ * the upstream port.
*/
- REG_WRITE(addr, 0x06,
- ((p & 0xf) << 12) |
- ((p == ds->cpu_port) ?
- ds->valid_port_mask :
- (1 << ds->cpu_port)));
+ val = (p & 0xf) << 12;
+ if (dsa_is_cpu_port(ds, p))
+ val |= ds->phys_port_mask;
+ else
+ val |= 1 << dsa_upstream_port(ds);
+ REG_WRITE(addr, 0x06, val);
/*
* Default VLAN ID and priority: don't set a default VLAN
@@ -394,7 +420,7 @@ static int mv88e6123_61_65_get_sset_count(struct dsa_switch *ds)
}
static struct dsa_switch_driver mv88e6123_61_65_switch_driver = {
- .tag_protocol = __constant_htons(ETH_P_EDSA),
+ .tag_protocol = cpu_to_be16(ETH_P_EDSA),
.priv_size = sizeof(struct mv88e6xxx_priv_state),
.probe = mv88e6123_61_65_probe,
.setup = mv88e6123_61_65_setup,
diff --git a/net/dsa/mv88e6131.c b/net/dsa/mv88e6131.c
index 374d46a0126..bb2b41bc854 100644
--- a/net/dsa/mv88e6131.c
+++ b/net/dsa/mv88e6131.c
@@ -1,6 +1,6 @@
/*
- * net/dsa/mv88e6131.c - Marvell 88e6131 switch chip support
- * Copyright (c) 2008 Marvell Semiconductor
+ * net/dsa/mv88e6131.c - Marvell 88e6095/6095f/6131 switch chip support
+ * Copyright (c) 2008-2009 Marvell Semiconductor
*
* 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
@@ -21,6 +21,8 @@ static char *mv88e6131_probe(struct mii_bus *bus, int sw_addr)
ret = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), 0x03);
if (ret >= 0) {
ret &= 0xfff0;
+ if (ret == 0x0950)
+ return "Marvell 88E6095/88E6095F";
if (ret == 0x1060)
return "Marvell 88E6131";
}
@@ -36,7 +38,7 @@ static int mv88e6131_switch_reset(struct dsa_switch *ds)
/*
* Set all ports to the disabled state.
*/
- for (i = 0; i < 8; i++) {
+ for (i = 0; i < 11; i++) {
ret = REG_READ(REG_PORT(i), 0x04);
REG_WRITE(REG_PORT(i), 0x04, ret & 0xfffc);
}
@@ -100,17 +102,17 @@ static int mv88e6131_setup_global(struct dsa_switch *ds)
REG_WRITE(REG_GLOBAL, 0x19, 0x8100);
/*
- * Disable ARP mirroring, and configure the cpu port as the
- * port to which ingress and egress monitor frames are to be
- * sent.
+ * Disable ARP mirroring, and configure the upstream port as
+ * the port to which ingress and egress monitor frames are to
+ * be sent.
*/
- REG_WRITE(REG_GLOBAL, 0x1a, (ds->cpu_port * 0x1100) | 0x00f0);
+ REG_WRITE(REG_GLOBAL, 0x1a, (dsa_upstream_port(ds) * 0x1100) | 0x00f0);
/*
* Disable cascade port functionality, and set the switch's
- * DSA device number to zero.
+ * DSA device number.
*/
- REG_WRITE(REG_GLOBAL, 0x1c, 0xe000);
+ REG_WRITE(REG_GLOBAL, 0x1c, 0xe000 | (ds->index & 0x1f));
/*
* Send all frames with destination addresses matching
@@ -127,16 +129,23 @@ static int mv88e6131_setup_global(struct dsa_switch *ds)
REG_WRITE(REG_GLOBAL2, 0x05, 0x00ff);
/*
- * Map all DSA device IDs to the CPU port.
+ * Program the DSA routing table.
*/
- for (i = 0; i < 32; i++)
- REG_WRITE(REG_GLOBAL2, 0x06, 0x8000 | (i << 8) | ds->cpu_port);
+ for (i = 0; i < 32; i++) {
+ int nexthop;
+
+ nexthop = 0x1f;
+ if (i != ds->index && i < ds->dst->pd->nr_chips)
+ nexthop = ds->pd->rtable[i] & 0x1f;
+
+ REG_WRITE(REG_GLOBAL2, 0x06, 0x8000 | (i << 8) | nexthop);
+ }
/*
* Clear all trunk masks.
*/
for (i = 0; i < 8; i++)
- REG_WRITE(REG_GLOBAL2, 0x07, 0x8000 | (i << 12) | 0xff);
+ REG_WRITE(REG_GLOBAL2, 0x07, 0x8000 | (i << 12) | 0x7ff);
/*
* Clear all trunk mappings.
@@ -156,12 +165,18 @@ static int mv88e6131_setup_global(struct dsa_switch *ds)
static int mv88e6131_setup_port(struct dsa_switch *ds, int p)
{
int addr = REG_PORT(p);
+ u16 val;
/*
* MAC Forcing register: don't force link, speed, duplex
- * or flow control state to any particular values.
+ * or flow control state to any particular values on physical
+ * ports, but force the CPU port and all DSA ports to 1000 Mb/s
+ * full duplex.
*/
- REG_WRITE(addr, 0x01, 0x0003);
+ if (dsa_is_cpu_port(ds, p) || ds->dsa_port_mask & (1 << p))
+ REG_WRITE(addr, 0x01, 0x003e);
+ else
+ REG_WRITE(addr, 0x01, 0x0003);
/*
* Port Control: disable Core Tag, disable Drop-on-Lock,
@@ -169,29 +184,40 @@ static int mv88e6131_setup_port(struct dsa_switch *ds, int p)
* enable IGMP/MLD snoop, disable DoubleTag, disable VLAN
* tunneling, determine priority by looking at 802.1p and
* IP priority fields (IP prio has precedence), and set STP
- * state to Forwarding. Finally, if this is the CPU port,
- * additionally enable DSA tagging and forwarding of unknown
- * unicast addresses.
+ * state to Forwarding.
+ *
+ * If this is the upstream port for this switch, enable
+ * forwarding of unknown unicasts, and enable DSA tagging
+ * mode.
+ *
+ * If this is the link to another switch, use DSA tagging
+ * mode, but do not enable forwarding of unknown unicasts.
*/
- REG_WRITE(addr, 0x04, (p == ds->cpu_port) ? 0x0537 : 0x0433);
+ val = 0x0433;
+ if (p == dsa_upstream_port(ds))
+ val |= 0x0104;
+ if (ds->dsa_port_mask & (1 << p))
+ val |= 0x0100;
+ REG_WRITE(addr, 0x04, val);
/*
* Port Control 1: disable trunking. Also, if this is the
* CPU port, enable learn messages to be sent to this port.
*/
- REG_WRITE(addr, 0x05, (p == ds->cpu_port) ? 0x8000 : 0x0000);
+ REG_WRITE(addr, 0x05, dsa_is_cpu_port(ds, p) ? 0x8000 : 0x0000);
/*
* Port based VLAN map: give each port its own address
* database, allow the CPU port to talk to each of the 'real'
* ports, and allow each of the 'real' ports to only talk to
- * the CPU port.
+ * the upstream port.
*/
- REG_WRITE(addr, 0x06,
- ((p & 0xf) << 12) |
- ((p == ds->cpu_port) ?
- ds->valid_port_mask :
- (1 << ds->cpu_port)));
+ val = (p & 0xf) << 12;
+ if (dsa_is_cpu_port(ds, p))
+ val |= ds->phys_port_mask;
+ else
+ val |= 1 << dsa_upstream_port(ds);
+ REG_WRITE(addr, 0x06, val);
/*
* Default VLAN ID and priority: don't set a default VLAN
@@ -207,13 +233,15 @@ static int mv88e6131_setup_port(struct dsa_switch *ds, int p)
* untagged frames on this port, do a destination address
* lookup on received packets as usual, don't send a copy
* of all transmitted/received frames on this port to the
- * CPU, and configure the CPU port number. Also, if this
- * is the CPU port, enable forwarding of unknown multicast
- * addresses.
+ * CPU, and configure the upstream port number.
+ *
+ * If this is the upstream port for this switch, enable
+ * forwarding of unknown multicast addresses.
*/
- REG_WRITE(addr, 0x08,
- ((p == ds->cpu_port) ? 0x00c0 : 0x0080) |
- ds->cpu_port);
+ val = 0x0080 | dsa_upstream_port(ds);
+ if (p == dsa_upstream_port(ds))
+ val |= 0x0040;
+ REG_WRITE(addr, 0x08, val);
/*
* Rate Control: disable ingress rate limiting.
@@ -268,7 +296,7 @@ static int mv88e6131_setup(struct dsa_switch *ds)
if (ret < 0)
return ret;
- for (i = 0; i < 6; i++) {
+ for (i = 0; i < 11; i++) {
ret = mv88e6131_setup_port(ds, i);
if (ret < 0)
return ret;
@@ -279,7 +307,7 @@ static int mv88e6131_setup(struct dsa_switch *ds)
static int mv88e6131_port_to_phy_addr(int port)
{
- if (port >= 0 && port != 3 && port <= 7)
+ if (port >= 0 && port <= 11)
return port;
return -1;
}
@@ -353,7 +381,7 @@ static int mv88e6131_get_sset_count(struct dsa_switch *ds)
}
static struct dsa_switch_driver mv88e6131_switch_driver = {
- .tag_protocol = __constant_htons(ETH_P_DSA),
+ .tag_protocol = cpu_to_be16(ETH_P_DSA),
.priv_size = sizeof(struct mv88e6xxx_priv_state),
.probe = mv88e6131_probe,
.setup = mv88e6131_setup,
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index a68fd79e9ec..ed131181215 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1,6 +1,6 @@
/*
* net/dsa/slave.c - Slave device handling
- * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2008-2009 Marvell Semiconductor
*
* 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
@@ -19,7 +19,7 @@ static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg)
{
struct dsa_switch *ds = bus->priv;
- if (ds->valid_port_mask & (1 << addr))
+ if (ds->phys_port_mask & (1 << addr))
return ds->drv->phy_read(ds, addr, reg);
return 0xffff;
@@ -29,7 +29,7 @@ static int dsa_slave_phy_write(struct mii_bus *bus, int addr, int reg, u16 val)
{
struct dsa_switch *ds = bus->priv;
- if (ds->valid_port_mask & (1 << addr))
+ if (ds->phys_port_mask & (1 << addr))
return ds->drv->phy_write(ds, addr, reg, val);
return 0;
@@ -43,15 +43,24 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds)
ds->slave_mii_bus->write = dsa_slave_phy_write;
snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "%s:%.2x",
ds->master_mii_bus->id, ds->pd->sw_addr);
- ds->slave_mii_bus->parent = &(ds->master_mii_bus->dev);
+ ds->slave_mii_bus->parent = &ds->master_mii_bus->dev;
}
/* slave device handling ****************************************************/
+static int dsa_slave_init(struct net_device *dev)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+
+ dev->iflink = p->parent->dst->master_netdev->ifindex;
+
+ return 0;
+}
+
static int dsa_slave_open(struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
- struct net_device *master = p->parent->master_netdev;
+ struct net_device *master = p->parent->dst->master_netdev;
int err;
if (!(master->flags & IFF_UP))
@@ -89,7 +98,7 @@ out:
static int dsa_slave_close(struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
- struct net_device *master = p->parent->master_netdev;
+ struct net_device *master = p->parent->dst->master_netdev;
dev_mc_unsync(master, dev);
dev_unicast_unsync(master, dev);
@@ -107,7 +116,7 @@ static int dsa_slave_close(struct net_device *dev)
static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
{
struct dsa_slave_priv *p = netdev_priv(dev);
- struct net_device *master = p->parent->master_netdev;
+ struct net_device *master = p->parent->dst->master_netdev;
if (change & IFF_ALLMULTI)
dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1);
@@ -118,7 +127,7 @@ static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
static void dsa_slave_set_rx_mode(struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
- struct net_device *master = p->parent->master_netdev;
+ struct net_device *master = p->parent->dst->master_netdev;
dev_mc_sync(master, dev);
dev_unicast_sync(master, dev);
@@ -127,7 +136,7 @@ static void dsa_slave_set_rx_mode(struct net_device *dev)
static int dsa_slave_set_mac_address(struct net_device *dev, void *a)
{
struct dsa_slave_priv *p = netdev_priv(dev);
- struct net_device *master = p->parent->master_netdev;
+ struct net_device *master = p->parent->dst->master_netdev;
struct sockaddr *addr = a;
int err;
@@ -288,6 +297,7 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
#ifdef CONFIG_NET_DSA_TAG_DSA
static const struct net_device_ops dsa_netdev_ops = {
+ .ndo_init = dsa_slave_init,
.ndo_open = dsa_slave_open,
.ndo_stop = dsa_slave_close,
.ndo_start_xmit = dsa_xmit,
@@ -300,6 +310,7 @@ static const struct net_device_ops dsa_netdev_ops = {
#endif
#ifdef CONFIG_NET_DSA_TAG_EDSA
static const struct net_device_ops edsa_netdev_ops = {
+ .ndo_init = dsa_slave_init,
.ndo_open = dsa_slave_open,
.ndo_stop = dsa_slave_close,
.ndo_start_xmit = edsa_xmit,
@@ -312,6 +323,7 @@ static const struct net_device_ops edsa_netdev_ops = {
#endif
#ifdef CONFIG_NET_DSA_TAG_TRAILER
static const struct net_device_ops trailer_netdev_ops = {
+ .ndo_init = dsa_slave_init,
.ndo_open = dsa_slave_open,
.ndo_stop = dsa_slave_close,
.ndo_start_xmit = trailer_xmit,
@@ -328,7 +340,7 @@ struct net_device *
dsa_slave_create(struct dsa_switch *ds, struct device *parent,
int port, char *name)
{
- struct net_device *master = ds->master_netdev;
+ struct net_device *master = ds->dst->master_netdev;
struct net_device *slave_dev;
struct dsa_slave_priv *p;
int ret;
@@ -343,7 +355,7 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
memcpy(slave_dev->dev_addr, master->dev_addr, ETH_ALEN);
slave_dev->tx_queue_len = 0;
- switch (ds->tag_protocol) {
+ switch (ds->dst->tag_protocol) {
#ifdef CONFIG_NET_DSA_TAG_DSA
case htons(ETH_P_DSA):
slave_dev->netdev_ops = &dsa_netdev_ops;
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index f99a019b939..8fa25bafe6c 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -1,6 +1,6 @@
/*
* net/dsa/tag_dsa.c - (Non-ethertype) DSA tagging
- * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2008-2009 Marvell Semiconductor
*
* 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
@@ -36,7 +36,7 @@ int dsa_xmit(struct sk_buff *skb, struct net_device *dev)
* Construct tagged FROM_CPU DSA tag from 802.1q tag.
*/
dsa_header = skb->data + 2 * ETH_ALEN;
- dsa_header[0] = 0x60;
+ dsa_header[0] = 0x60 | p->parent->index;
dsa_header[1] = p->port << 3;
/*
@@ -57,7 +57,7 @@ int dsa_xmit(struct sk_buff *skb, struct net_device *dev)
* Construct untagged FROM_CPU DSA tag.
*/
dsa_header = skb->data + 2 * ETH_ALEN;
- dsa_header[0] = 0x40;
+ dsa_header[0] = 0x40 | p->parent->index;
dsa_header[1] = p->port << 3;
dsa_header[2] = 0x00;
dsa_header[3] = 0x00;
@@ -65,7 +65,7 @@ int dsa_xmit(struct sk_buff *skb, struct net_device *dev)
skb->protocol = htons(ETH_P_DSA);
- skb->dev = p->parent->master_netdev;
+ skb->dev = p->parent->dst->master_netdev;
dev_queue_xmit(skb);
return NETDEV_TX_OK;
@@ -78,11 +78,13 @@ out_free:
static int dsa_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
- struct dsa_switch *ds = dev->dsa_ptr;
+ struct dsa_switch_tree *dst = dev->dsa_ptr;
+ struct dsa_switch *ds;
u8 *dsa_header;
+ int source_device;
int source_port;
- if (unlikely(ds == NULL))
+ if (unlikely(dst == NULL))
goto out_drop;
skb = skb_unshare(skb, GFP_ATOMIC);
@@ -98,16 +100,24 @@ static int dsa_rcv(struct sk_buff *skb, struct net_device *dev,
dsa_header = skb->data - 2;
/*
- * Check that frame type is either TO_CPU or FORWARD, and
- * that the source device is zero.
+ * Check that frame type is either TO_CPU or FORWARD.
*/
- if ((dsa_header[0] & 0xdf) != 0x00 && (dsa_header[0] & 0xdf) != 0xc0)
+ if ((dsa_header[0] & 0xc0) != 0x00 && (dsa_header[0] & 0xc0) != 0xc0)
goto out_drop;
/*
- * Check that the source port is a registered DSA port.
+ * Determine source device and port.
*/
+ source_device = dsa_header[0] & 0x1f;
source_port = (dsa_header[1] >> 3) & 0x1f;
+
+ /*
+ * Check that the source device exists and that the source
+ * port is a registered DSA port.
+ */
+ if (source_device >= dst->pd->nr_chips)
+ goto out_drop;
+ ds = dst->ds[source_device];
if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL)
goto out_drop;
@@ -175,8 +185,8 @@ out:
return 0;
}
-static struct packet_type dsa_packet_type = {
- .type = __constant_htons(ETH_P_DSA),
+static struct packet_type dsa_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_DSA),
.func = dsa_rcv,
};
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 328ec957f78..815607bd286 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -1,6 +1,6 @@
/*
* net/dsa/tag_edsa.c - Ethertype DSA tagging
- * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2008-2009 Marvell Semiconductor
*
* 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
@@ -45,7 +45,7 @@ int edsa_xmit(struct sk_buff *skb, struct net_device *dev)
edsa_header[1] = ETH_P_EDSA & 0xff;
edsa_header[2] = 0x00;
edsa_header[3] = 0x00;
- edsa_header[4] = 0x60;
+ edsa_header[4] = 0x60 | p->parent->index;
edsa_header[5] = p->port << 3;
/*
@@ -70,7 +70,7 @@ int edsa_xmit(struct sk_buff *skb, struct net_device *dev)
edsa_header[1] = ETH_P_EDSA & 0xff;
edsa_header[2] = 0x00;
edsa_header[3] = 0x00;
- edsa_header[4] = 0x40;
+ edsa_header[4] = 0x40 | p->parent->index;
edsa_header[5] = p->port << 3;
edsa_header[6] = 0x00;
edsa_header[7] = 0x00;
@@ -78,7 +78,7 @@ int edsa_xmit(struct sk_buff *skb, struct net_device *dev)
skb->protocol = htons(ETH_P_EDSA);
- skb->dev = p->parent->master_netdev;
+ skb->dev = p->parent->dst->master_netdev;
dev_queue_xmit(skb);
return NETDEV_TX_OK;
@@ -91,11 +91,13 @@ out_free:
static int edsa_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
- struct dsa_switch *ds = dev->dsa_ptr;
+ struct dsa_switch_tree *dst = dev->dsa_ptr;
+ struct dsa_switch *ds;
u8 *edsa_header;
+ int source_device;
int source_port;
- if (unlikely(ds == NULL))
+ if (unlikely(dst == NULL))
goto out_drop;
skb = skb_unshare(skb, GFP_ATOMIC);
@@ -111,16 +113,24 @@ static int edsa_rcv(struct sk_buff *skb, struct net_device *dev,
edsa_header = skb->data + 2;
/*
- * Check that frame type is either TO_CPU or FORWARD, and
- * that the source device is zero.
+ * Check that frame type is either TO_CPU or FORWARD.
*/
- if ((edsa_header[0] & 0xdf) != 0x00 && (edsa_header[0] & 0xdf) != 0xc0)
+ if ((edsa_header[0] & 0xc0) != 0x00 && (edsa_header[0] & 0xc0) != 0xc0)
goto out_drop;
/*
- * Check that the source port is a registered DSA port.
+ * Determine source device and port.
*/
+ source_device = edsa_header[0] & 0x1f;
source_port = (edsa_header[1] >> 3) & 0x1f;
+
+ /*
+ * Check that the source device exists and that the source
+ * port is a registered DSA port.
+ */
+ if (source_device >= dst->pd->nr_chips)
+ goto out_drop;
+ ds = dst->ds[source_device];
if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL)
goto out_drop;
@@ -194,8 +204,8 @@ out:
return 0;
}
-static struct packet_type edsa_packet_type = {
- .type = __constant_htons(ETH_P_EDSA),
+static struct packet_type edsa_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_EDSA),
.func = edsa_rcv,
};
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index b59132878ad..1c3e30c38b8 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -1,6 +1,6 @@
/*
* net/dsa/tag_trailer.c - Trailer tag format handling
- * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2008-2009 Marvell Semiconductor
*
* 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
@@ -59,7 +59,7 @@ int trailer_xmit(struct sk_buff *skb, struct net_device *dev)
nskb->protocol = htons(ETH_P_TRAILER);
- nskb->dev = p->parent->master_netdev;
+ nskb->dev = p->parent->dst->master_netdev;
dev_queue_xmit(nskb);
return NETDEV_TX_OK;
@@ -68,12 +68,14 @@ int trailer_xmit(struct sk_buff *skb, struct net_device *dev)
static int trailer_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
- struct dsa_switch *ds = dev->dsa_ptr;
+ struct dsa_switch_tree *dst = dev->dsa_ptr;
+ struct dsa_switch *ds;
u8 *trailer;
int source_port;
- if (unlikely(ds == NULL))
+ if (unlikely(dst == NULL))
goto out_drop;
+ ds = dst->ds[0];
skb = skb_unshare(skb, GFP_ATOMIC);
if (skb == NULL)
@@ -111,8 +113,8 @@ out:
return 0;
}
-static struct packet_type trailer_packet_type = {
- .type = __constant_htons(ETH_P_TRAILER),
+static struct packet_type trailer_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_TRAILER),
.func = trailer_rcv,
};
diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c
index 8789d2bb1b0..6f479fa522c 100644
--- a/net/econet/af_econet.c
+++ b/net/econet/af_econet.c
@@ -1102,8 +1102,8 @@ drop:
return NET_RX_DROP;
}
-static struct packet_type econet_packet_type = {
- .type = __constant_htons(ETH_P_ECONET),
+static struct packet_type econet_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_ECONET),
.func = econet_rcv,
};
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 691268f3a35..b2cf91e4cca 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -35,7 +35,7 @@ config IP_ADVANCED_ROUTER
at boot time after the /proc file system has been mounted.
- If you turn on IP forwarding, you will also get the rp_filter, which
+ If you turn on IP forwarding, you should consider the rp_filter, which
automatically rejects incoming packets if the routing table entry
for their source address doesn't match the network interface they're
arriving on. This has security advantages because it prevents the
@@ -46,12 +46,16 @@ config IP_ADVANCED_ROUTER
rp_filter on use:
echo 1 > /proc/sys/net/ipv4/conf/<device>/rp_filter
- or
+ and
echo 1 > /proc/sys/net/ipv4/conf/all/rp_filter
+ Note that some distributions enable it in startup scripts.
+ For details about rp_filter strict and loose mode read
+ <file:Documentation/networking/ip-sysctl.txt>.
+
If unsure, say N here.
-choice
+choice
prompt "Choose IP: FIB lookup algorithm (choose FIB_HASH if unsure)"
depends on IP_ADVANCED_ROUTER
default ASK_IP_FIB_HASH
@@ -59,27 +63,29 @@ choice
config ASK_IP_FIB_HASH
bool "FIB_HASH"
---help---
- Current FIB is very proven and good enough for most users.
+ Current FIB is very proven and good enough for most users.
config IP_FIB_TRIE
bool "FIB_TRIE"
---help---
- Use new experimental LC-trie as FIB lookup algorithm.
- This improves lookup performance if you have a large
- number of routes.
-
- LC-trie is a longest matching prefix lookup algorithm which
- performs better than FIB_HASH for large routing tables.
- But, it consumes more memory and is more complex.
-
- LC-trie is described in:
-
- IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson
- IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999
- An experimental study of compression methods for dynamic tries
- Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002.
- http://www.nada.kth.se/~snilsson/public/papers/dyntrie2/
-
+ Use new experimental LC-trie as FIB lookup algorithm.
+ This improves lookup performance if you have a large
+ number of routes.
+
+ LC-trie is a longest matching prefix lookup algorithm which
+ performs better than FIB_HASH for large routing tables.
+ But, it consumes more memory and is more complex.
+
+ LC-trie is described in:
+
+ IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson
+ IEEE Journal on Selected Areas in Communications, 17(6):1083-1092,
+ June 1999
+
+ An experimental study of compression methods for dynamic tries
+ Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002.
+ http://www.nada.kth.se/~snilsson/public/papers/dyntrie2/
+
endchoice
config IP_FIB_HASH
@@ -191,7 +197,7 @@ config IP_PNP_RARP
<file:Documentation/filesystems/nfsroot.txt> for details.
# not yet ready..
-# bool ' IP: ARP support' CONFIG_IP_PNP_ARP
+# bool ' IP: ARP support' CONFIG_IP_PNP_ARP
config NET_IPIP
tristate "IP: tunneling"
select INET_TUNNEL
@@ -361,7 +367,7 @@ config INET_IPCOMP
---help---
Support for IP Payload Compression Protocol (IPComp) (RFC3173),
typically needed for IPsec.
-
+
If unsure, say Y.
config INET_XFRM_TUNNEL
@@ -415,7 +421,7 @@ config INET_DIAG
Support for INET (TCP, DCCP, etc) socket monitoring interface used by
native Linux tools such as ss. ss is included in iproute2, currently
downloadable at <http://linux-net.osdl.org/index.php/Iproute2>.
-
+
If unsure, say Y.
config INET_TCP_DIAG
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 3a3dad80135..7f03373b8c0 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -369,7 +369,6 @@ lookup_protocol:
sock_init_data(sock, sk);
sk->sk_destruct = inet_sock_destruct;
- sk->sk_family = PF_INET;
sk->sk_protocol = protocol;
sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
@@ -1253,10 +1252,10 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
int proto;
int id;
- if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
+ iph = skb_gro_header(skb, sizeof(*iph));
+ if (unlikely(!iph))
goto out;
- iph = ip_hdr(skb);
proto = iph->protocol & (MAX_INET_PROTOS - 1);
rcu_read_lock();
@@ -1264,13 +1263,13 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
if (!ops || !ops->gro_receive)
goto out_unlock;
- if (iph->version != 4 || iph->ihl != 5)
+ if (*(u8 *)iph != 0x45)
goto out_unlock;
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto out_unlock;
- flush = ntohs(iph->tot_len) != skb->len ||
+ flush = ntohs(iph->tot_len) != skb_gro_len(skb) ||
iph->frag_off != htons(IP_DF);
id = ntohs(iph->id);
@@ -1282,24 +1281,25 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
iph2 = ip_hdr(p);
- if (iph->protocol != iph2->protocol ||
- iph->tos != iph2->tos ||
- memcmp(&iph->saddr, &iph2->saddr, 8)) {
+ if ((iph->protocol ^ iph2->protocol) |
+ (iph->tos ^ iph2->tos) |
+ (iph->saddr ^ iph2->saddr) |
+ (iph->daddr ^ iph2->daddr)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
/* All fields must match except length and checksum. */
NAPI_GRO_CB(p)->flush |=
- memcmp(&iph->frag_off, &iph2->frag_off, 4) ||
- (u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) != id;
+ (iph->ttl ^ iph2->ttl) |
+ ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
NAPI_GRO_CB(p)->flush |= flush;
}
NAPI_GRO_CB(skb)->flush |= flush;
- __skb_pull(skb, sizeof(*iph));
- skb_reset_transport_header(skb);
+ skb_gro_pull(skb, sizeof(*iph));
+ skb_set_transport_header(skb, skb_gro_offset(skb));
pp = ops->gro_receive(head, skb);
@@ -1500,8 +1500,8 @@ static int ipv4_proc_init(void);
* IP protocol layer initialiser
*/
-static struct packet_type ip_packet_type = {
- .type = __constant_htons(ETH_P_IP),
+static struct packet_type ip_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_IP),
.func = ip_rcv,
.gso_send_check = inet_gso_send_check,
.gso_segment = inet_gso_segment,
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 29a74c01d8d..f11931c1838 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -801,8 +801,11 @@ static int arp_process(struct sk_buff *skb)
* cache.
*/
- /* Special case: IPv4 duplicate address detection packet (RFC2131) */
- if (sip == 0) {
+ /*
+ * Special case: IPv4 duplicate address detection packet (RFC2131)
+ * and Gratuitous ARP/ARP Announce. (RFC3927, Section 2.4)
+ */
+ if (sip == 0 || tip == sip) {
if (arp->ar_op == htons(ARPOP_REQUEST) &&
inet_addr_type(net, tip) == RTN_LOCAL &&
!arp_ignore(in_dev, sip, tip))
@@ -892,7 +895,7 @@ static int arp_process(struct sk_buff *skb)
out:
if (in_dev)
in_dev_put(in_dev);
- kfree_skb(skb);
+ consume_skb(skb);
return 0;
}
@@ -1225,8 +1228,8 @@ void arp_ifdown(struct net_device *dev)
* Called once on startup.
*/
-static struct packet_type arp_packet_type = {
- .type = __constant_htons(ETH_P_ARP),
+static struct packet_type arp_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_ARP),
.func = arp_rcv,
};
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 7bc992976d2..039cc1ffe97 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1942,23 +1942,85 @@ socket_setattr_failure:
}
/**
- * cipso_v4_sock_delattr - Delete the CIPSO option from a socket
- * @sk: the socket
+ * cipso_v4_req_setattr - Add a CIPSO option to a connection request socket
+ * @req: the connection request socket
+ * @doi_def: the CIPSO DOI to use
+ * @secattr: the specific security attributes of the socket
*
* Description:
- * Removes the CIPSO option from a socket, if present.
+ * Set the CIPSO option on the given socket using the DOI definition and
+ * security attributes passed to the function. Returns zero on success and
+ * negative values on failure.
*
*/
-void cipso_v4_sock_delattr(struct sock *sk)
+int cipso_v4_req_setattr(struct request_sock *req,
+ const struct cipso_v4_doi *doi_def,
+ const struct netlbl_lsm_secattr *secattr)
{
- u8 hdr_delta;
- struct ip_options *opt;
- struct inet_sock *sk_inet;
+ int ret_val = -EPERM;
+ unsigned char *buf = NULL;
+ u32 buf_len;
+ u32 opt_len;
+ struct ip_options *opt = NULL;
+ struct inet_request_sock *req_inet;
- sk_inet = inet_sk(sk);
- opt = sk_inet->opt;
- if (opt == NULL || opt->cipso == 0)
- return;
+ /* We allocate the maximum CIPSO option size here so we are probably
+ * being a little wasteful, but it makes our life _much_ easier later
+ * on and after all we are only talking about 40 bytes. */
+ buf_len = CIPSO_V4_OPT_LEN_MAX;
+ buf = kmalloc(buf_len, GFP_ATOMIC);
+ if (buf == NULL) {
+ ret_val = -ENOMEM;
+ goto req_setattr_failure;
+ }
+
+ ret_val = cipso_v4_genopt(buf, buf_len, doi_def, secattr);
+ if (ret_val < 0)
+ goto req_setattr_failure;
+ buf_len = ret_val;
+
+ /* We can't use ip_options_get() directly because it makes a call to
+ * ip_options_get_alloc() which allocates memory with GFP_KERNEL and
+ * we won't always have CAP_NET_RAW even though we _always_ want to
+ * set the IPOPT_CIPSO option. */
+ opt_len = (buf_len + 3) & ~3;
+ opt = kzalloc(sizeof(*opt) + opt_len, GFP_ATOMIC);
+ if (opt == NULL) {
+ ret_val = -ENOMEM;
+ goto req_setattr_failure;
+ }
+ memcpy(opt->__data, buf, buf_len);
+ opt->optlen = opt_len;
+ opt->cipso = sizeof(struct iphdr);
+ kfree(buf);
+ buf = NULL;
+
+ req_inet = inet_rsk(req);
+ opt = xchg(&req_inet->opt, opt);
+ kfree(opt);
+
+ return 0;
+
+req_setattr_failure:
+ kfree(buf);
+ kfree(opt);
+ return ret_val;
+}
+
+/**
+ * cipso_v4_delopt - Delete the CIPSO option from a set of IP options
+ * @opt_ptr: IP option pointer
+ *
+ * Description:
+ * Deletes the CIPSO IP option from a set of IP options and makes the necessary
+ * adjustments to the IP option structure. Returns zero on success, negative
+ * values on failure.
+ *
+ */
+int cipso_v4_delopt(struct ip_options **opt_ptr)
+{
+ int hdr_delta = 0;
+ struct ip_options *opt = *opt_ptr;
if (opt->srr || opt->rr || opt->ts || opt->router_alert) {
u8 cipso_len;
@@ -2003,11 +2065,34 @@ void cipso_v4_sock_delattr(struct sock *sk)
} else {
/* only the cipso option was present on the socket so we can
* remove the entire option struct */
- sk_inet->opt = NULL;
+ *opt_ptr = NULL;
hdr_delta = opt->optlen;
kfree(opt);
}
+ return hdr_delta;
+}
+
+/**
+ * cipso_v4_sock_delattr - Delete the CIPSO option from a socket
+ * @sk: the socket
+ *
+ * Description:
+ * Removes the CIPSO option from a socket, if present.
+ *
+ */
+void cipso_v4_sock_delattr(struct sock *sk)
+{
+ int hdr_delta;
+ struct ip_options *opt;
+ struct inet_sock *sk_inet;
+
+ sk_inet = inet_sk(sk);
+ opt = sk_inet->opt;
+ if (opt == NULL || opt->cipso == 0)
+ return;
+
+ hdr_delta = cipso_v4_delopt(&sk_inet->opt);
if (sk_inet->is_icsk && hdr_delta > 0) {
struct inet_connection_sock *sk_conn = inet_csk(sk);
sk_conn->icsk_ext_hdr_len -= hdr_delta;
@@ -2016,6 +2101,27 @@ void cipso_v4_sock_delattr(struct sock *sk)
}
/**
+ * cipso_v4_req_delattr - Delete the CIPSO option from a request socket
+ * @reg: the request socket
+ *
+ * Description:
+ * Removes the CIPSO option from a request socket, if present.
+ *
+ */
+void cipso_v4_req_delattr(struct request_sock *req)
+{
+ struct ip_options *opt;
+ struct inet_request_sock *req_inet;
+
+ req_inet = inet_rsk(req);
+ opt = req_inet->opt;
+ if (opt == NULL || opt->cipso == 0)
+ return;
+
+ cipso_v4_delopt(&req_inet->opt);
+}
+
+/**
* cipso_v4_getattr - Helper function for the cipso_v4_*_getattr functions
* @cipso: the CIPSO v4 option
* @secattr: the security attributes
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 309997edc8a..126bb911880 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1075,6 +1075,14 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
}
}
ip_mc_up(in_dev);
+ /* fall through */
+ case NETDEV_CHANGEADDR:
+ if (IN_DEV_ARP_NOTIFY(in_dev))
+ arp_send(ARPOP_REQUEST, ETH_P_ARP,
+ in_dev->ifa_list->ifa_address,
+ dev,
+ in_dev->ifa_list->ifa_address,
+ NULL, dev->dev_addr, NULL);
break;
case NETDEV_DOWN:
ip_mc_down(in_dev);
@@ -1208,7 +1216,8 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, net, pid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL);
+ rtnl_notify(skb, net, pid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err);
@@ -1439,6 +1448,7 @@ static struct devinet_sysctl_table {
DEVINET_SYSCTL_RW_ENTRY(ARP_ANNOUNCE, "arp_announce"),
DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"),
DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"),
+ DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"),
DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"),
DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"),
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 741e4fa3e47..cafcc49d099 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -275,7 +275,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
fib_res_put(&res);
if (no_addr)
goto last_resort;
- if (rpf)
+ if (rpf == 1)
goto e_inval;
fl.oif = dev->ifindex;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 4817dea3bc7..f831df50090 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -322,8 +322,9 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, info->nl_net, info->pid, RTNLGRP_IPV4_ROUTE,
- info->nlh, GFP_KERNEL);
+ rtnl_notify(skb, info->nl_net, info->pid, RTNLGRP_IPV4_ROUTE,
+ info->nlh, GFP_KERNEL);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index fc562d29cc4..3f50807237e 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -375,6 +375,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
inet->tos = ip_hdr(skb)->tos;
daddr = ipc.addr = rt->rt_src;
ipc.opt = NULL;
+ ipc.shtx.flags = 0;
if (icmp_param->replyopts.optlen) {
ipc.opt = &icmp_param->replyopts;
if (ipc.opt->srr)
@@ -532,6 +533,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
inet_sk(sk)->tos = tos;
ipc.addr = iph->saddr;
ipc.opt = &icmp_param.replyopts;
+ ipc.shtx.flags = 0;
{
struct flowi fl = {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f26ab38680d..22cd19ee44e 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -93,24 +93,40 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
struct inet_bind_hashbucket *head;
struct hlist_node *node;
struct inet_bind_bucket *tb;
- int ret;
+ int ret, attempts = 5;
struct net *net = sock_net(sk);
+ int smallest_size = -1, smallest_rover;
local_bh_disable();
if (!snum) {
int remaining, rover, low, high;
+again:
inet_get_local_port_range(&low, &high);
remaining = (high - low) + 1;
- rover = net_random() % remaining + low;
+ smallest_rover = rover = net_random() % remaining + low;
+ smallest_size = -1;
do {
head = &hashinfo->bhash[inet_bhashfn(net, rover,
hashinfo->bhash_size)];
spin_lock(&head->lock);
inet_bind_bucket_for_each(tb, node, &head->chain)
- if (ib_net(tb) == net && tb->port == rover)
+ if (ib_net(tb) == net && tb->port == rover) {
+ if (tb->fastreuse > 0 &&
+ sk->sk_reuse &&
+ sk->sk_state != TCP_LISTEN &&
+ (tb->num_owners < smallest_size || smallest_size == -1)) {
+ smallest_size = tb->num_owners;
+ smallest_rover = rover;
+ if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) {
+ spin_unlock(&head->lock);
+ snum = smallest_rover;
+ goto have_snum;
+ }
+ }
goto next;
+ }
break;
next:
spin_unlock(&head->lock);
@@ -125,14 +141,19 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
* the top level, not from the 'break;' statement.
*/
ret = 1;
- if (remaining <= 0)
+ if (remaining <= 0) {
+ if (smallest_size != -1) {
+ snum = smallest_rover;
+ goto have_snum;
+ }
goto fail;
-
+ }
/* OK, here is the one we will use. HEAD is
* non-NULL and we hold it's mutex.
*/
snum = rover;
} else {
+have_snum:
head = &hashinfo->bhash[inet_bhashfn(net, snum,
hashinfo->bhash_size)];
spin_lock(&head->lock);
@@ -145,12 +166,19 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
tb_found:
if (!hlist_empty(&tb->owners)) {
if (tb->fastreuse > 0 &&
- sk->sk_reuse && sk->sk_state != TCP_LISTEN) {
+ sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
+ smallest_size == -1) {
goto success;
} else {
ret = 1;
- if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb))
+ if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
+ if (sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
+ smallest_size != -1 && --attempts >= 0) {
+ spin_unlock(&head->lock);
+ goto again;
+ }
goto fail_unlock;
+ }
}
}
tb_not_found:
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 6c52e08f786..eaf3e2c8646 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -267,6 +267,7 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
struct inet_frags *f, void *key, unsigned int hash)
+ __releases(&f->lock)
{
struct inet_frag_queue *q;
struct hlist_node *n;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 6a1045da48d..625cc5f64c9 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -38,6 +38,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
write_pnet(&tb->ib_net, hold_net(net));
tb->port = snum;
tb->fastreuse = 0;
+ tb->num_owners = 0;
INIT_HLIST_HEAD(&tb->owners);
hlist_add_head(&tb->node, &head->chain);
}
@@ -59,8 +60,13 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket
void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
const unsigned short snum)
{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+
+ atomic_inc(&hashinfo->bsockets);
+
inet_sk(sk)->num = snum;
sk_add_bind_node(sk, &tb->owners);
+ tb->num_owners++;
inet_csk(sk)->icsk_bind_hash = tb;
}
@@ -75,9 +81,12 @@ static void __inet_put_port(struct sock *sk)
struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash];
struct inet_bind_bucket *tb;
+ atomic_dec(&hashinfo->bsockets);
+
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
__sk_del_bind_node(sk);
+ tb->num_owners--;
inet_csk(sk)->icsk_bind_hash = NULL;
inet_sk(sk)->num = 0;
inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
@@ -444,9 +453,9 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
*/
inet_bind_bucket_for_each(tb, node, &head->chain) {
if (ib_net(tb) == net && tb->port == port) {
- WARN_ON(hlist_empty(&tb->owners));
if (tb->fastreuse >= 0)
goto next_port;
+ WARN_ON(hlist_empty(&tb->owners));
if (!check_established(death_row, sk,
port, &tw))
goto ok;
@@ -523,6 +532,7 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
{
int i;
+ atomic_set(&h->bsockets, 0);
for (i = 0; i < INET_LHTABLE_SIZE; i++) {
spin_lock_init(&h->listening_hash[i].lock);
INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].head,
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 6659ac000ee..7985346653b 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -463,6 +463,7 @@ err:
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev)
{
+ struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = qp->q.fragments;
int len;
@@ -548,7 +549,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
iph = ip_hdr(head);
iph->frag_off = 0;
iph->tot_len = htons(len);
- IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_REASMOKS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
return 0;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0101521f366..e62510d5ea5 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -164,67 +164,124 @@ static DEFINE_RWLOCK(ipgre_lock);
/* Given src, dst and key, find appropriate for input tunnel. */
-static struct ip_tunnel * ipgre_tunnel_lookup(struct net *net,
+static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
__be32 remote, __be32 local,
__be32 key, __be16 gre_proto)
{
+ struct net *net = dev_net(dev);
+ int link = dev->ifindex;
unsigned h0 = HASH(remote);
unsigned h1 = HASH(key);
- struct ip_tunnel *t;
- struct ip_tunnel *t2 = NULL;
+ struct ip_tunnel *t, *cand = NULL;
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
ARPHRD_ETHER : ARPHRD_IPGRE;
+ int score, cand_score = 4;
for (t = ign->tunnels_r_l[h0^h1]; t; t = t->next) {
- if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) {
- if (t->parms.i_key == key && t->dev->flags & IFF_UP) {
- if (t->dev->type == dev_type)
- return t;
- if (t->dev->type == ARPHRD_IPGRE && !t2)
- t2 = t;
- }
+ if (local != t->parms.iph.saddr ||
+ remote != t->parms.iph.daddr ||
+ key != t->parms.i_key ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (t->dev->type != ARPHRD_IPGRE &&
+ t->dev->type != dev_type)
+ continue;
+
+ score = 0;
+ if (t->parms.link != link)
+ score |= 1;
+ if (t->dev->type != dev_type)
+ score |= 2;
+ if (score == 0)
+ return t;
+
+ if (score < cand_score) {
+ cand = t;
+ cand_score = score;
}
}
for (t = ign->tunnels_r[h0^h1]; t; t = t->next) {
- if (remote == t->parms.iph.daddr) {
- if (t->parms.i_key == key && t->dev->flags & IFF_UP) {
- if (t->dev->type == dev_type)
- return t;
- if (t->dev->type == ARPHRD_IPGRE && !t2)
- t2 = t;
- }
+ if (remote != t->parms.iph.daddr ||
+ key != t->parms.i_key ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (t->dev->type != ARPHRD_IPGRE &&
+ t->dev->type != dev_type)
+ continue;
+
+ score = 0;
+ if (t->parms.link != link)
+ score |= 1;
+ if (t->dev->type != dev_type)
+ score |= 2;
+ if (score == 0)
+ return t;
+
+ if (score < cand_score) {
+ cand = t;
+ cand_score = score;
}
}
for (t = ign->tunnels_l[h1]; t; t = t->next) {
- if (local == t->parms.iph.saddr ||
- (local == t->parms.iph.daddr &&
- ipv4_is_multicast(local))) {
- if (t->parms.i_key == key && t->dev->flags & IFF_UP) {
- if (t->dev->type == dev_type)
- return t;
- if (t->dev->type == ARPHRD_IPGRE && !t2)
- t2 = t;
- }
+ if ((local != t->parms.iph.saddr &&
+ (local != t->parms.iph.daddr ||
+ !ipv4_is_multicast(local))) ||
+ key != t->parms.i_key ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (t->dev->type != ARPHRD_IPGRE &&
+ t->dev->type != dev_type)
+ continue;
+
+ score = 0;
+ if (t->parms.link != link)
+ score |= 1;
+ if (t->dev->type != dev_type)
+ score |= 2;
+ if (score == 0)
+ return t;
+
+ if (score < cand_score) {
+ cand = t;
+ cand_score = score;
}
}
for (t = ign->tunnels_wc[h1]; t; t = t->next) {
- if (t->parms.i_key == key && t->dev->flags & IFF_UP) {
- if (t->dev->type == dev_type)
- return t;
- if (t->dev->type == ARPHRD_IPGRE && !t2)
- t2 = t;
+ if (t->parms.i_key != key ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (t->dev->type != ARPHRD_IPGRE &&
+ t->dev->type != dev_type)
+ continue;
+
+ score = 0;
+ if (t->parms.link != link)
+ score |= 1;
+ if (t->dev->type != dev_type)
+ score |= 2;
+ if (score == 0)
+ return t;
+
+ if (score < cand_score) {
+ cand = t;
+ cand_score = score;
}
}
- if (t2)
- return t2;
+ if (cand != NULL)
+ return cand;
- if (ign->fb_tunnel_dev->flags&IFF_UP)
+ if (ign->fb_tunnel_dev->flags & IFF_UP)
return netdev_priv(ign->fb_tunnel_dev);
+
return NULL;
}
@@ -284,6 +341,7 @@ static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
__be32 key = parms->i_key;
+ int link = parms->link;
struct ip_tunnel *t, **tp;
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
@@ -291,6 +349,7 @@ static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
key == t->parms.i_key &&
+ link == t->parms.link &&
type == t->dev->type)
break;
@@ -421,7 +480,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
}
read_lock(&ipgre_lock);
- t = ipgre_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr,
+ t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
flags & GRE_KEY ?
*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
p[1]);
@@ -432,7 +491,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
goto out;
- if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
+ if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
t->err_count++;
else
t->err_count = 1;
@@ -518,7 +577,7 @@ static int ipgre_rcv(struct sk_buff *skb)
gre_proto = *(__be16 *)(h + 2);
read_lock(&ipgre_lock);
- if ((tunnel = ipgre_tunnel_lookup(dev_net(skb->dev),
+ if ((tunnel = ipgre_tunnel_lookup(skb->dev,
iph->saddr, iph->daddr, key,
gre_proto))) {
struct net_device_stats *stats = &tunnel->dev->stats;
@@ -744,7 +803,8 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
#endif
if (tunnel->err_count > 0) {
- if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
+ if (time_before(jiffies,
+ tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8ebe86dd72a..3e7e910c7c0 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -935,6 +935,10 @@ alloc_new_skb:
sk->sk_allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
+ else
+ /* only the initial fragment is
+ time stamped */
+ ipc->shtx.flags = 0;
}
if (skb == NULL)
goto error;
@@ -945,6 +949,7 @@ alloc_new_skb:
skb->ip_summed = csummode;
skb->csum = 0;
skb_reserve(skb, hh_len);
+ *skb_tx(skb) = ipc->shtx;
/*
* Find where to start putting bytes.
@@ -1364,6 +1369,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
daddr = ipc.addr = rt->rt_src;
ipc.opt = NULL;
+ ipc.shtx.flags = 0;
if (replyopts.opt.optlen) {
ipc.opt = &replyopts.opt;
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index d722013c1ca..90d22ae0a41 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -100,8 +100,8 @@
#define CONF_NAMESERVERS_MAX 3 /* Maximum number of nameservers
- '3' from resolv.h */
-#define NONE __constant_htonl(INADDR_NONE)
-#define ANY __constant_htonl(INADDR_ANY)
+#define NONE cpu_to_be32(INADDR_NONE)
+#define ANY cpu_to_be32(INADDR_ANY)
/*
* Public IP configuration
@@ -406,7 +406,7 @@ static int __init ic_defaults(void)
static int ic_rarp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev);
static struct packet_type rarp_packet_type __initdata = {
- .type = __constant_htons(ETH_P_RARP),
+ .type = cpu_to_be16(ETH_P_RARP),
.func = ic_rarp_recv,
};
@@ -568,7 +568,7 @@ struct bootp_pkt { /* BOOTP packet format */
static int ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev);
static struct packet_type bootp_packet_type __initdata = {
- .type = __constant_htons(ETH_P_IP),
+ .type = cpu_to_be16(ETH_P_IP),
.func = ic_bootp_recv,
};
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 5079dfbc6f3..9054139795a 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -327,7 +327,7 @@ static int ipip_err(struct sk_buff *skb, u32 info)
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
goto out;
- if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
+ if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
t->err_count++;
else
t->err_count = 1;
@@ -466,7 +466,8 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
}
if (tunnel->err_count > 0) {
- if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
+ if (time_before(jiffies,
+ tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
@@ -750,7 +751,7 @@ static struct xfrm_tunnel ipip_handler = {
.priority = 1,
};
-static char banner[] __initdata =
+static const char banner[] __initconst =
KERN_INFO "IPv4 over IPv4 tunneling driver\n";
static void ipip_destroy_tunnels(struct ipip_net *ipn)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 14666449dc1..13e9dd3012b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -67,9 +67,6 @@
#define CONFIG_IP_PIMSM 1
#endif
-static struct sock *mroute_socket;
-
-
/* Big lock, protecting vif table, mrt cache and mroute socket state.
Note that the changes are semaphored via rtnl_lock.
*/
@@ -80,18 +77,9 @@ static DEFINE_RWLOCK(mrt_lock);
* Multicast router control variables
*/
-static struct vif_device vif_table[MAXVIFS]; /* Devices */
-static int maxvif;
-
-#define VIF_EXISTS(idx) (vif_table[idx].dev != NULL)
-
-static int mroute_do_assert; /* Set in PIM assert */
-static int mroute_do_pim;
-
-static struct mfc_cache *mfc_cache_array[MFC_LINES]; /* Forwarding cache */
+#define VIF_EXISTS(_net, _idx) ((_net)->ipv4.vif_table[_idx].dev != NULL)
static struct mfc_cache *mfc_unres_queue; /* Queue of unresolved entries */
-static atomic_t cache_resolve_queue_len; /* Size of unresolved */
/* Special spinlock for queue of unresolved entries */
static DEFINE_SPINLOCK(mfc_unres_lock);
@@ -107,7 +95,8 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
static struct kmem_cache *mrt_cachep __read_mostly;
static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local);
-static int ipmr_cache_report(struct sk_buff *pkt, vifi_t vifi, int assert);
+static int ipmr_cache_report(struct net *net,
+ struct sk_buff *pkt, vifi_t vifi, int assert);
static int ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm);
#ifdef CONFIG_IP_PIMSM_V2
@@ -120,9 +109,11 @@ static struct timer_list ipmr_expire_timer;
static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v)
{
+ struct net *net = dev_net(dev);
+
dev_close(dev);
- dev = __dev_get_by_name(&init_net, "tunl0");
+ dev = __dev_get_by_name(net, "tunl0");
if (dev) {
const struct net_device_ops *ops = dev->netdev_ops;
struct ifreq ifr;
@@ -148,11 +139,11 @@ static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v)
}
static
-struct net_device *ipmr_new_tunnel(struct vifctl *v)
+struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v)
{
struct net_device *dev;
- dev = __dev_get_by_name(&init_net, "tunl0");
+ dev = __dev_get_by_name(net, "tunl0");
if (dev) {
const struct net_device_ops *ops = dev->netdev_ops;
@@ -181,7 +172,8 @@ struct net_device *ipmr_new_tunnel(struct vifctl *v)
dev = NULL;
- if (err == 0 && (dev = __dev_get_by_name(&init_net, p.name)) != NULL) {
+ if (err == 0 &&
+ (dev = __dev_get_by_name(net, p.name)) != NULL) {
dev->flags |= IFF_MULTICAST;
in_dev = __in_dev_get_rtnl(dev);
@@ -209,14 +201,15 @@ failure:
#ifdef CONFIG_IP_PIMSM
-static int reg_vif_num = -1;
-
static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
{
+ struct net *net = dev_net(dev);
+
read_lock(&mrt_lock);
dev->stats.tx_bytes += skb->len;
dev->stats.tx_packets++;
- ipmr_cache_report(skb, reg_vif_num, IGMPMSG_WHOLEPKT);
+ ipmr_cache_report(net, skb, net->ipv4.mroute_reg_vif_num,
+ IGMPMSG_WHOLEPKT);
read_unlock(&mrt_lock);
kfree_skb(skb);
return 0;
@@ -283,16 +276,16 @@ failure:
* @notify: Set to 1, if the caller is a notifier_call
*/
-static int vif_delete(int vifi, int notify)
+static int vif_delete(struct net *net, int vifi, int notify)
{
struct vif_device *v;
struct net_device *dev;
struct in_device *in_dev;
- if (vifi < 0 || vifi >= maxvif)
+ if (vifi < 0 || vifi >= net->ipv4.maxvif)
return -EADDRNOTAVAIL;
- v = &vif_table[vifi];
+ v = &net->ipv4.vif_table[vifi];
write_lock_bh(&mrt_lock);
dev = v->dev;
@@ -304,17 +297,17 @@ static int vif_delete(int vifi, int notify)
}
#ifdef CONFIG_IP_PIMSM
- if (vifi == reg_vif_num)
- reg_vif_num = -1;
+ if (vifi == net->ipv4.mroute_reg_vif_num)
+ net->ipv4.mroute_reg_vif_num = -1;
#endif
- if (vifi+1 == maxvif) {
+ if (vifi+1 == net->ipv4.maxvif) {
int tmp;
for (tmp=vifi-1; tmp>=0; tmp--) {
- if (VIF_EXISTS(tmp))
+ if (VIF_EXISTS(net, tmp))
break;
}
- maxvif = tmp+1;
+ net->ipv4.maxvif = tmp+1;
}
write_unlock_bh(&mrt_lock);
@@ -333,6 +326,12 @@ static int vif_delete(int vifi, int notify)
return 0;
}
+static inline void ipmr_cache_free(struct mfc_cache *c)
+{
+ release_net(mfc_net(c));
+ kmem_cache_free(mrt_cachep, c);
+}
+
/* Destroy an unresolved cache entry, killing queued skbs
and reporting error to netlink readers.
*/
@@ -341,8 +340,9 @@ static void ipmr_destroy_unres(struct mfc_cache *c)
{
struct sk_buff *skb;
struct nlmsgerr *e;
+ struct net *net = mfc_net(c);
- atomic_dec(&cache_resolve_queue_len);
+ atomic_dec(&net->ipv4.cache_resolve_queue_len);
while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) {
if (ip_hdr(skb)->version == 0) {
@@ -354,12 +354,12 @@ static void ipmr_destroy_unres(struct mfc_cache *c)
e->error = -ETIMEDOUT;
memset(&e->msg, 0, sizeof(e->msg));
- rtnl_unicast(skb, &init_net, NETLINK_CB(skb).pid);
+ rtnl_unicast(skb, net, NETLINK_CB(skb).pid);
} else
kfree_skb(skb);
}
- kmem_cache_free(mrt_cachep, c);
+ ipmr_cache_free(c);
}
@@ -376,7 +376,7 @@ static void ipmr_expire_process(unsigned long dummy)
return;
}
- if (atomic_read(&cache_resolve_queue_len) == 0)
+ if (mfc_unres_queue == NULL)
goto out;
now = jiffies;
@@ -397,7 +397,7 @@ static void ipmr_expire_process(unsigned long dummy)
ipmr_destroy_unres(c);
}
- if (atomic_read(&cache_resolve_queue_len))
+ if (mfc_unres_queue != NULL)
mod_timer(&ipmr_expire_timer, jiffies + expires);
out:
@@ -409,13 +409,15 @@ out:
static void ipmr_update_thresholds(struct mfc_cache *cache, unsigned char *ttls)
{
int vifi;
+ struct net *net = mfc_net(cache);
cache->mfc_un.res.minvif = MAXVIFS;
cache->mfc_un.res.maxvif = 0;
memset(cache->mfc_un.res.ttls, 255, MAXVIFS);
- for (vifi=0; vifi<maxvif; vifi++) {
- if (VIF_EXISTS(vifi) && ttls[vifi] && ttls[vifi] < 255) {
+ for (vifi = 0; vifi < net->ipv4.maxvif; vifi++) {
+ if (VIF_EXISTS(net, vifi) &&
+ ttls[vifi] && ttls[vifi] < 255) {
cache->mfc_un.res.ttls[vifi] = ttls[vifi];
if (cache->mfc_un.res.minvif > vifi)
cache->mfc_un.res.minvif = vifi;
@@ -425,16 +427,16 @@ static void ipmr_update_thresholds(struct mfc_cache *cache, unsigned char *ttls)
}
}
-static int vif_add(struct vifctl *vifc, int mrtsock)
+static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock)
{
int vifi = vifc->vifc_vifi;
- struct vif_device *v = &vif_table[vifi];
+ struct vif_device *v = &net->ipv4.vif_table[vifi];
struct net_device *dev;
struct in_device *in_dev;
int err;
/* Is vif busy ? */
- if (VIF_EXISTS(vifi))
+ if (VIF_EXISTS(net, vifi))
return -EADDRINUSE;
switch (vifc->vifc_flags) {
@@ -444,7 +446,7 @@ static int vif_add(struct vifctl *vifc, int mrtsock)
* Special Purpose VIF in PIM
* All the packets will be sent to the daemon
*/
- if (reg_vif_num >= 0)
+ if (net->ipv4.mroute_reg_vif_num >= 0)
return -EADDRINUSE;
dev = ipmr_reg_vif();
if (!dev)
@@ -458,7 +460,7 @@ static int vif_add(struct vifctl *vifc, int mrtsock)
break;
#endif
case VIFF_TUNNEL:
- dev = ipmr_new_tunnel(vifc);
+ dev = ipmr_new_tunnel(net, vifc);
if (!dev)
return -ENOBUFS;
err = dev_set_allmulti(dev, 1);
@@ -469,7 +471,7 @@ static int vif_add(struct vifctl *vifc, int mrtsock)
}
break;
case 0:
- dev = ip_dev_find(&init_net, vifc->vifc_lcl_addr.s_addr);
+ dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr);
if (!dev)
return -EADDRNOTAVAIL;
err = dev_set_allmulti(dev, 1);
@@ -510,20 +512,22 @@ static int vif_add(struct vifctl *vifc, int mrtsock)
v->dev = dev;
#ifdef CONFIG_IP_PIMSM
if (v->flags&VIFF_REGISTER)
- reg_vif_num = vifi;
+ net->ipv4.mroute_reg_vif_num = vifi;
#endif
- if (vifi+1 > maxvif)
- maxvif = vifi+1;
+ if (vifi+1 > net->ipv4.maxvif)
+ net->ipv4.maxvif = vifi+1;
write_unlock_bh(&mrt_lock);
return 0;
}
-static struct mfc_cache *ipmr_cache_find(__be32 origin, __be32 mcastgrp)
+static struct mfc_cache *ipmr_cache_find(struct net *net,
+ __be32 origin,
+ __be32 mcastgrp)
{
int line = MFC_HASH(mcastgrp, origin);
struct mfc_cache *c;
- for (c=mfc_cache_array[line]; c; c = c->next) {
+ for (c = net->ipv4.mfc_cache_array[line]; c; c = c->next) {
if (c->mfc_origin==origin && c->mfc_mcastgrp==mcastgrp)
break;
}
@@ -533,22 +537,24 @@ static struct mfc_cache *ipmr_cache_find(__be32 origin, __be32 mcastgrp)
/*
* Allocate a multicast cache entry
*/
-static struct mfc_cache *ipmr_cache_alloc(void)
+static struct mfc_cache *ipmr_cache_alloc(struct net *net)
{
struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
if (c == NULL)
return NULL;
c->mfc_un.res.minvif = MAXVIFS;
+ mfc_net_set(c, net);
return c;
}
-static struct mfc_cache *ipmr_cache_alloc_unres(void)
+static struct mfc_cache *ipmr_cache_alloc_unres(struct net *net)
{
struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
if (c == NULL)
return NULL;
skb_queue_head_init(&c->mfc_un.unres.unresolved);
c->mfc_un.unres.expires = jiffies + 10*HZ;
+ mfc_net_set(c, net);
return c;
}
@@ -581,7 +587,7 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
memset(&e->msg, 0, sizeof(e->msg));
}
- rtnl_unicast(skb, &init_net, NETLINK_CB(skb).pid);
+ rtnl_unicast(skb, mfc_net(c), NETLINK_CB(skb).pid);
} else
ip_mr_forward(skb, c, 0);
}
@@ -594,7 +600,8 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
* Called under mrt_lock.
*/
-static int ipmr_cache_report(struct sk_buff *pkt, vifi_t vifi, int assert)
+static int ipmr_cache_report(struct net *net,
+ struct sk_buff *pkt, vifi_t vifi, int assert)
{
struct sk_buff *skb;
const int ihl = ip_hdrlen(pkt);
@@ -626,7 +633,7 @@ static int ipmr_cache_report(struct sk_buff *pkt, vifi_t vifi, int assert)
memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr));
msg->im_msgtype = IGMPMSG_WHOLEPKT;
msg->im_mbz = 0;
- msg->im_vif = reg_vif_num;
+ msg->im_vif = net->ipv4.mroute_reg_vif_num;
ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2;
ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) +
sizeof(struct iphdr));
@@ -658,7 +665,7 @@ static int ipmr_cache_report(struct sk_buff *pkt, vifi_t vifi, int assert)
skb->transport_header = skb->network_header;
}
- if (mroute_socket == NULL) {
+ if (net->ipv4.mroute_sk == NULL) {
kfree_skb(skb);
return -EINVAL;
}
@@ -666,7 +673,8 @@ static int ipmr_cache_report(struct sk_buff *pkt, vifi_t vifi, int assert)
/*
* Deliver to mrouted
*/
- if ((ret = sock_queue_rcv_skb(mroute_socket, skb))<0) {
+ ret = sock_queue_rcv_skb(net->ipv4.mroute_sk, skb);
+ if (ret < 0) {
if (net_ratelimit())
printk(KERN_WARNING "mroute: pending queue full, dropping entries.\n");
kfree_skb(skb);
@@ -680,7 +688,7 @@ static int ipmr_cache_report(struct sk_buff *pkt, vifi_t vifi, int assert)
*/
static int
-ipmr_cache_unresolved(vifi_t vifi, struct sk_buff *skb)
+ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
{
int err;
struct mfc_cache *c;
@@ -688,7 +696,8 @@ ipmr_cache_unresolved(vifi_t vifi, struct sk_buff *skb)
spin_lock_bh(&mfc_unres_lock);
for (c=mfc_unres_queue; c; c=c->next) {
- if (c->mfc_mcastgrp == iph->daddr &&
+ if (net_eq(mfc_net(c), net) &&
+ c->mfc_mcastgrp == iph->daddr &&
c->mfc_origin == iph->saddr)
break;
}
@@ -698,8 +707,8 @@ ipmr_cache_unresolved(vifi_t vifi, struct sk_buff *skb)
* Create a new entry if allowable
*/
- if (atomic_read(&cache_resolve_queue_len) >= 10 ||
- (c=ipmr_cache_alloc_unres())==NULL) {
+ if (atomic_read(&net->ipv4.cache_resolve_queue_len) >= 10 ||
+ (c = ipmr_cache_alloc_unres(net)) == NULL) {
spin_unlock_bh(&mfc_unres_lock);
kfree_skb(skb);
@@ -716,18 +725,19 @@ ipmr_cache_unresolved(vifi_t vifi, struct sk_buff *skb)
/*
* Reflect first query at mrouted.
*/
- if ((err = ipmr_cache_report(skb, vifi, IGMPMSG_NOCACHE))<0) {
+ err = ipmr_cache_report(net, skb, vifi, IGMPMSG_NOCACHE);
+ if (err < 0) {
/* If the report failed throw the cache entry
out - Brad Parker
*/
spin_unlock_bh(&mfc_unres_lock);
- kmem_cache_free(mrt_cachep, c);
+ ipmr_cache_free(c);
kfree_skb(skb);
return err;
}
- atomic_inc(&cache_resolve_queue_len);
+ atomic_inc(&net->ipv4.cache_resolve_queue_len);
c->next = mfc_unres_queue;
mfc_unres_queue = c;
@@ -753,35 +763,37 @@ ipmr_cache_unresolved(vifi_t vifi, struct sk_buff *skb)
* MFC cache manipulation by user space mroute daemon
*/
-static int ipmr_mfc_delete(struct mfcctl *mfc)
+static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc)
{
int line;
struct mfc_cache *c, **cp;
line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
- for (cp=&mfc_cache_array[line]; (c=*cp) != NULL; cp = &c->next) {
+ for (cp = &net->ipv4.mfc_cache_array[line];
+ (c = *cp) != NULL; cp = &c->next) {
if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
write_lock_bh(&mrt_lock);
*cp = c->next;
write_unlock_bh(&mrt_lock);
- kmem_cache_free(mrt_cachep, c);
+ ipmr_cache_free(c);
return 0;
}
}
return -ENOENT;
}
-static int ipmr_mfc_add(struct mfcctl *mfc, int mrtsock)
+static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
{
int line;
struct mfc_cache *uc, *c, **cp;
line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
- for (cp=&mfc_cache_array[line]; (c=*cp) != NULL; cp = &c->next) {
+ for (cp = &net->ipv4.mfc_cache_array[line];
+ (c = *cp) != NULL; cp = &c->next) {
if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr)
break;
@@ -800,7 +812,7 @@ static int ipmr_mfc_add(struct mfcctl *mfc, int mrtsock)
if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr))
return -EINVAL;
- c = ipmr_cache_alloc();
+ c = ipmr_cache_alloc(net);
if (c == NULL)
return -ENOMEM;
@@ -812,8 +824,8 @@ static int ipmr_mfc_add(struct mfcctl *mfc, int mrtsock)
c->mfc_flags |= MFC_STATIC;
write_lock_bh(&mrt_lock);
- c->next = mfc_cache_array[line];
- mfc_cache_array[line] = c;
+ c->next = net->ipv4.mfc_cache_array[line];
+ net->ipv4.mfc_cache_array[line] = c;
write_unlock_bh(&mrt_lock);
/*
@@ -823,19 +835,21 @@ static int ipmr_mfc_add(struct mfcctl *mfc, int mrtsock)
spin_lock_bh(&mfc_unres_lock);
for (cp = &mfc_unres_queue; (uc=*cp) != NULL;
cp = &uc->next) {
- if (uc->mfc_origin == c->mfc_origin &&
+ if (net_eq(mfc_net(uc), net) &&
+ uc->mfc_origin == c->mfc_origin &&
uc->mfc_mcastgrp == c->mfc_mcastgrp) {
*cp = uc->next;
- if (atomic_dec_and_test(&cache_resolve_queue_len))
- del_timer(&ipmr_expire_timer);
+ atomic_dec(&net->ipv4.cache_resolve_queue_len);
break;
}
}
+ if (mfc_unres_queue == NULL)
+ del_timer(&ipmr_expire_timer);
spin_unlock_bh(&mfc_unres_lock);
if (uc) {
ipmr_cache_resolve(uc, c);
- kmem_cache_free(mrt_cachep, uc);
+ ipmr_cache_free(uc);
}
return 0;
}
@@ -844,16 +858,16 @@ static int ipmr_mfc_add(struct mfcctl *mfc, int mrtsock)
* Close the multicast socket, and clear the vif tables etc
*/
-static void mroute_clean_tables(struct sock *sk)
+static void mroute_clean_tables(struct net *net)
{
int i;
/*
* Shut down all active vif entries
*/
- for (i=0; i<maxvif; i++) {
- if (!(vif_table[i].flags&VIFF_STATIC))
- vif_delete(i, 0);
+ for (i = 0; i < net->ipv4.maxvif; i++) {
+ if (!(net->ipv4.vif_table[i].flags&VIFF_STATIC))
+ vif_delete(net, i, 0);
}
/*
@@ -862,7 +876,7 @@ static void mroute_clean_tables(struct sock *sk)
for (i=0; i<MFC_LINES; i++) {
struct mfc_cache *c, **cp;
- cp = &mfc_cache_array[i];
+ cp = &net->ipv4.mfc_cache_array[i];
while ((c = *cp) != NULL) {
if (c->mfc_flags&MFC_STATIC) {
cp = &c->next;
@@ -872,22 +886,23 @@ static void mroute_clean_tables(struct sock *sk)
*cp = c->next;
write_unlock_bh(&mrt_lock);
- kmem_cache_free(mrt_cachep, c);
+ ipmr_cache_free(c);
}
}
- if (atomic_read(&cache_resolve_queue_len) != 0) {
- struct mfc_cache *c;
+ if (atomic_read(&net->ipv4.cache_resolve_queue_len) != 0) {
+ struct mfc_cache *c, **cp;
spin_lock_bh(&mfc_unres_lock);
- while (mfc_unres_queue != NULL) {
- c = mfc_unres_queue;
- mfc_unres_queue = c->next;
- spin_unlock_bh(&mfc_unres_lock);
+ cp = &mfc_unres_queue;
+ while ((c = *cp) != NULL) {
+ if (!net_eq(mfc_net(c), net)) {
+ cp = &c->next;
+ continue;
+ }
+ *cp = c->next;
ipmr_destroy_unres(c);
-
- spin_lock_bh(&mfc_unres_lock);
}
spin_unlock_bh(&mfc_unres_lock);
}
@@ -895,15 +910,17 @@ static void mroute_clean_tables(struct sock *sk)
static void mrtsock_destruct(struct sock *sk)
{
+ struct net *net = sock_net(sk);
+
rtnl_lock();
- if (sk == mroute_socket) {
- IPV4_DEVCONF_ALL(sock_net(sk), MC_FORWARDING)--;
+ if (sk == net->ipv4.mroute_sk) {
+ IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
write_lock_bh(&mrt_lock);
- mroute_socket = NULL;
+ net->ipv4.mroute_sk = NULL;
write_unlock_bh(&mrt_lock);
- mroute_clean_tables(sk);
+ mroute_clean_tables(net);
}
rtnl_unlock();
}
@@ -920,9 +937,10 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int
int ret;
struct vifctl vif;
struct mfcctl mfc;
+ struct net *net = sock_net(sk);
if (optname != MRT_INIT) {
- if (sk != mroute_socket && !capable(CAP_NET_ADMIN))
+ if (sk != net->ipv4.mroute_sk && !capable(CAP_NET_ADMIN))
return -EACCES;
}
@@ -935,7 +953,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int
return -ENOPROTOOPT;
rtnl_lock();
- if (mroute_socket) {
+ if (net->ipv4.mroute_sk) {
rtnl_unlock();
return -EADDRINUSE;
}
@@ -943,15 +961,15 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int
ret = ip_ra_control(sk, 1, mrtsock_destruct);
if (ret == 0) {
write_lock_bh(&mrt_lock);
- mroute_socket = sk;
+ net->ipv4.mroute_sk = sk;
write_unlock_bh(&mrt_lock);
- IPV4_DEVCONF_ALL(sock_net(sk), MC_FORWARDING)++;
+ IPV4_DEVCONF_ALL(net, MC_FORWARDING)++;
}
rtnl_unlock();
return ret;
case MRT_DONE:
- if (sk != mroute_socket)
+ if (sk != net->ipv4.mroute_sk)
return -EACCES;
return ip_ra_control(sk, 0, NULL);
case MRT_ADD_VIF:
@@ -964,9 +982,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int
return -ENFILE;
rtnl_lock();
if (optname == MRT_ADD_VIF) {
- ret = vif_add(&vif, sk==mroute_socket);
+ ret = vif_add(net, &vif, sk == net->ipv4.mroute_sk);
} else {
- ret = vif_delete(vif.vifc_vifi, 0);
+ ret = vif_delete(net, vif.vifc_vifi, 0);
}
rtnl_unlock();
return ret;
@@ -983,9 +1001,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int
return -EFAULT;
rtnl_lock();
if (optname == MRT_DEL_MFC)
- ret = ipmr_mfc_delete(&mfc);
+ ret = ipmr_mfc_delete(net, &mfc);
else
- ret = ipmr_mfc_add(&mfc, sk==mroute_socket);
+ ret = ipmr_mfc_add(net, &mfc, sk == net->ipv4.mroute_sk);
rtnl_unlock();
return ret;
/*
@@ -996,7 +1014,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int
int v;
if (get_user(v,(int __user *)optval))
return -EFAULT;
- mroute_do_assert=(v)?1:0;
+ net->ipv4.mroute_do_assert = (v) ? 1 : 0;
return 0;
}
#ifdef CONFIG_IP_PIMSM
@@ -1010,11 +1028,11 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int
rtnl_lock();
ret = 0;
- if (v != mroute_do_pim) {
- mroute_do_pim = v;
- mroute_do_assert = v;
+ if (v != net->ipv4.mroute_do_pim) {
+ net->ipv4.mroute_do_pim = v;
+ net->ipv4.mroute_do_assert = v;
#ifdef CONFIG_IP_PIMSM_V2
- if (mroute_do_pim)
+ if (net->ipv4.mroute_do_pim)
ret = inet_add_protocol(&pim_protocol,
IPPROTO_PIM);
else
@@ -1045,6 +1063,7 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
{
int olr;
int val;
+ struct net *net = sock_net(sk);
if (optname != MRT_VERSION &&
#ifdef CONFIG_IP_PIMSM
@@ -1066,10 +1085,10 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
val = 0x0305;
#ifdef CONFIG_IP_PIMSM
else if (optname == MRT_PIM)
- val = mroute_do_pim;
+ val = net->ipv4.mroute_do_pim;
#endif
else
- val = mroute_do_assert;
+ val = net->ipv4.mroute_do_assert;
if (copy_to_user(optval, &val, olr))
return -EFAULT;
return 0;
@@ -1085,16 +1104,17 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
struct sioc_vif_req vr;
struct vif_device *vif;
struct mfc_cache *c;
+ struct net *net = sock_net(sk);
switch (cmd) {
case SIOCGETVIFCNT:
if (copy_from_user(&vr, arg, sizeof(vr)))
return -EFAULT;
- if (vr.vifi >= maxvif)
+ if (vr.vifi >= net->ipv4.maxvif)
return -EINVAL;
read_lock(&mrt_lock);
- vif=&vif_table[vr.vifi];
- if (VIF_EXISTS(vr.vifi)) {
+ vif = &net->ipv4.vif_table[vr.vifi];
+ if (VIF_EXISTS(net, vr.vifi)) {
vr.icount = vif->pkt_in;
vr.ocount = vif->pkt_out;
vr.ibytes = vif->bytes_in;
@@ -1112,7 +1132,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
return -EFAULT;
read_lock(&mrt_lock);
- c = ipmr_cache_find(sr.src.s_addr, sr.grp.s_addr);
+ c = ipmr_cache_find(net, sr.src.s_addr, sr.grp.s_addr);
if (c) {
sr.pktcnt = c->mfc_un.res.pkt;
sr.bytecnt = c->mfc_un.res.bytes;
@@ -1134,18 +1154,19 @@ int ipmr_ioctl(struct sock *sk, 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 *net = dev_net(dev);
struct vif_device *v;
int ct;
- if (!net_eq(dev_net(dev), &init_net))
+ if (!net_eq(dev_net(dev), net))
return NOTIFY_DONE;
if (event != NETDEV_UNREGISTER)
return NOTIFY_DONE;
- v=&vif_table[0];
- for (ct=0; ct<maxvif; ct++,v++) {
+ v = &net->ipv4.vif_table[0];
+ for (ct = 0; ct < net->ipv4.maxvif; ct++, v++) {
if (v->dev == dev)
- vif_delete(ct, 1);
+ vif_delete(net, ct, 1);
}
return NOTIFY_DONE;
}
@@ -1205,8 +1226,9 @@ static inline int ipmr_forward_finish(struct sk_buff *skb)
static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi)
{
+ struct net *net = mfc_net(c);
const struct iphdr *iph = ip_hdr(skb);
- struct vif_device *vif = &vif_table[vifi];
+ struct vif_device *vif = &net->ipv4.vif_table[vifi];
struct net_device *dev;
struct rtable *rt;
int encap = 0;
@@ -1220,9 +1242,8 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi)
vif->bytes_out += skb->len;
vif->dev->stats.tx_bytes += skb->len;
vif->dev->stats.tx_packets++;
- ipmr_cache_report(skb, vifi, IGMPMSG_WHOLEPKT);
- kfree_skb(skb);
- return;
+ ipmr_cache_report(net, skb, vifi, IGMPMSG_WHOLEPKT);
+ goto out_free;
}
#endif
@@ -1233,7 +1254,7 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi)
.saddr = vif->local,
.tos = RT_TOS(iph->tos) } },
.proto = IPPROTO_IPIP };
- if (ip_route_output_key(&init_net, &rt, &fl))
+ if (ip_route_output_key(net, &rt, &fl))
goto out_free;
encap = sizeof(struct iphdr);
} else {
@@ -1242,7 +1263,7 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi)
{ .daddr = iph->daddr,
.tos = RT_TOS(iph->tos) } },
.proto = IPPROTO_IPIP };
- if (ip_route_output_key(&init_net, &rt, &fl))
+ if (ip_route_output_key(net, &rt, &fl))
goto out_free;
}
@@ -1306,9 +1327,10 @@ out_free:
static int ipmr_find_vif(struct net_device *dev)
{
+ struct net *net = dev_net(dev);
int ct;
- for (ct=maxvif-1; ct>=0; ct--) {
- if (vif_table[ct].dev == dev)
+ for (ct = net->ipv4.maxvif-1; ct >= 0; ct--) {
+ if (net->ipv4.vif_table[ct].dev == dev)
break;
}
return ct;
@@ -1320,6 +1342,7 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local
{
int psend = -1;
int vif, ct;
+ struct net *net = mfc_net(cache);
vif = cache->mfc_parent;
cache->mfc_un.res.pkt++;
@@ -1328,7 +1351,7 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local
/*
* Wrong interface: drop packet and (maybe) send PIM assert.
*/
- if (vif_table[vif].dev != skb->dev) {
+ if (net->ipv4.vif_table[vif].dev != skb->dev) {
int true_vifi;
if (skb->rtable->fl.iif == 0) {
@@ -1349,23 +1372,24 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local
cache->mfc_un.res.wrong_if++;
true_vifi = ipmr_find_vif(skb->dev);
- if (true_vifi >= 0 && mroute_do_assert &&
+ if (true_vifi >= 0 && net->ipv4.mroute_do_assert &&
/* pimsm uses asserts, when switching from RPT to SPT,
so that we cannot check that packet arrived on an oif.
It is bad, but otherwise we would need to move pretty
large chunk of pimd to kernel. Ough... --ANK
*/
- (mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) &&
+ (net->ipv4.mroute_do_pim ||
+ cache->mfc_un.res.ttls[true_vifi] < 255) &&
time_after(jiffies,
cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) {
cache->mfc_un.res.last_assert = jiffies;
- ipmr_cache_report(skb, true_vifi, IGMPMSG_WRONGVIF);
+ ipmr_cache_report(net, skb, true_vifi, IGMPMSG_WRONGVIF);
}
goto dont_forward;
}
- vif_table[vif].pkt_in++;
- vif_table[vif].bytes_in += skb->len;
+ net->ipv4.vif_table[vif].pkt_in++;
+ net->ipv4.vif_table[vif].bytes_in += skb->len;
/*
* Forward the frame
@@ -1405,6 +1429,7 @@ dont_forward:
int ip_mr_input(struct sk_buff *skb)
{
struct mfc_cache *cache;
+ struct net *net = dev_net(skb->dev);
int local = skb->rtable->rt_flags&RTCF_LOCAL;
/* Packet is looped back after forward, it should not be
@@ -1425,9 +1450,9 @@ int ip_mr_input(struct sk_buff *skb)
that we can forward NO IGMP messages.
*/
read_lock(&mrt_lock);
- if (mroute_socket) {
+ if (net->ipv4.mroute_sk) {
nf_reset(skb);
- raw_rcv(mroute_socket, skb);
+ raw_rcv(net->ipv4.mroute_sk, skb);
read_unlock(&mrt_lock);
return 0;
}
@@ -1436,7 +1461,7 @@ int ip_mr_input(struct sk_buff *skb)
}
read_lock(&mrt_lock);
- cache = ipmr_cache_find(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr);
+ cache = ipmr_cache_find(net, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr);
/*
* No usable cache entry
@@ -1456,7 +1481,7 @@ int ip_mr_input(struct sk_buff *skb)
vif = ipmr_find_vif(skb->dev);
if (vif >= 0) {
- int err = ipmr_cache_unresolved(vif, skb);
+ int err = ipmr_cache_unresolved(net, vif, skb);
read_unlock(&mrt_lock);
return err;
@@ -1487,6 +1512,7 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen)
{
struct net_device *reg_dev = NULL;
struct iphdr *encap;
+ struct net *net = dev_net(skb->dev);
encap = (struct iphdr *)(skb_transport_header(skb) + pimlen);
/*
@@ -1501,8 +1527,8 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen)
return 1;
read_lock(&mrt_lock);
- if (reg_vif_num >= 0)
- reg_dev = vif_table[reg_vif_num].dev;
+ if (net->ipv4.mroute_reg_vif_num >= 0)
+ reg_dev = net->ipv4.vif_table[net->ipv4.mroute_reg_vif_num].dev;
if (reg_dev)
dev_hold(reg_dev);
read_unlock(&mrt_lock);
@@ -1537,13 +1563,14 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen)
int pim_rcv_v1(struct sk_buff * skb)
{
struct igmphdr *pim;
+ struct net *net = dev_net(skb->dev);
if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr)))
goto drop;
pim = igmp_hdr(skb);
- if (!mroute_do_pim ||
+ if (!net->ipv4.mroute_do_pim ||
pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER)
goto drop;
@@ -1583,7 +1610,8 @@ ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm)
{
int ct;
struct rtnexthop *nhp;
- struct net_device *dev = vif_table[c->mfc_parent].dev;
+ struct net *net = mfc_net(c);
+ struct net_device *dev = net->ipv4.vif_table[c->mfc_parent].dev;
u8 *b = skb_tail_pointer(skb);
struct rtattr *mp_head;
@@ -1599,7 +1627,7 @@ ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm)
nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp)));
nhp->rtnh_flags = 0;
nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
- nhp->rtnh_ifindex = vif_table[ct].dev->ifindex;
+ nhp->rtnh_ifindex = net->ipv4.vif_table[ct].dev->ifindex;
nhp->rtnh_len = sizeof(*nhp);
}
}
@@ -1613,14 +1641,15 @@ rtattr_failure:
return -EMSGSIZE;
}
-int ipmr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait)
+int ipmr_get_route(struct net *net,
+ struct sk_buff *skb, struct rtmsg *rtm, int nowait)
{
int err;
struct mfc_cache *cache;
struct rtable *rt = skb->rtable;
read_lock(&mrt_lock);
- cache = ipmr_cache_find(rt->rt_src, rt->rt_dst);
+ cache = ipmr_cache_find(net, rt->rt_src, rt->rt_dst);
if (cache == NULL) {
struct sk_buff *skb2;
@@ -1651,7 +1680,7 @@ int ipmr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait)
iph->saddr = rt->rt_src;
iph->daddr = rt->rt_dst;
iph->version = 0;
- err = ipmr_cache_unresolved(vif, skb2);
+ err = ipmr_cache_unresolved(net, vif, skb2);
read_unlock(&mrt_lock);
return err;
}
@@ -1668,17 +1697,19 @@ int ipmr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait)
* The /proc interfaces to multicast routing /proc/ip_mr_cache /proc/ip_mr_vif
*/
struct ipmr_vif_iter {
+ struct seq_net_private p;
int ct;
};
-static struct vif_device *ipmr_vif_seq_idx(struct ipmr_vif_iter *iter,
+static struct vif_device *ipmr_vif_seq_idx(struct net *net,
+ struct ipmr_vif_iter *iter,
loff_t pos)
{
- for (iter->ct = 0; iter->ct < maxvif; ++iter->ct) {
- if (!VIF_EXISTS(iter->ct))
+ for (iter->ct = 0; iter->ct < net->ipv4.maxvif; ++iter->ct) {
+ if (!VIF_EXISTS(net, iter->ct))
continue;
if (pos-- == 0)
- return &vif_table[iter->ct];
+ return &net->ipv4.vif_table[iter->ct];
}
return NULL;
}
@@ -1686,23 +1717,26 @@ static struct vif_device *ipmr_vif_seq_idx(struct ipmr_vif_iter *iter,
static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(mrt_lock)
{
+ struct net *net = seq_file_net(seq);
+
read_lock(&mrt_lock);
- return *pos ? ipmr_vif_seq_idx(seq->private, *pos - 1)
+ return *pos ? ipmr_vif_seq_idx(net, seq->private, *pos - 1)
: SEQ_START_TOKEN;
}
static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct ipmr_vif_iter *iter = seq->private;
+ struct net *net = seq_file_net(seq);
++*pos;
if (v == SEQ_START_TOKEN)
- return ipmr_vif_seq_idx(iter, 0);
+ return ipmr_vif_seq_idx(net, iter, 0);
- while (++iter->ct < maxvif) {
- if (!VIF_EXISTS(iter->ct))
+ while (++iter->ct < net->ipv4.maxvif) {
+ if (!VIF_EXISTS(net, iter->ct))
continue;
- return &vif_table[iter->ct];
+ return &net->ipv4.vif_table[iter->ct];
}
return NULL;
}
@@ -1715,6 +1749,8 @@ static void ipmr_vif_seq_stop(struct seq_file *seq, void *v)
static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
{
+ struct net *net = seq_file_net(seq);
+
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
"Interface BytesIn PktsIn BytesOut PktsOut Flags Local Remote\n");
@@ -1724,7 +1760,7 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
seq_printf(seq,
"%2Zd %-10s %8ld %7ld %8ld %7ld %05X %08X %08X\n",
- vif - vif_table,
+ vif - net->ipv4.vif_table,
name, vif->bytes_in, vif->pkt_in,
vif->bytes_out, vif->pkt_out,
vif->flags, vif->local, vif->remote);
@@ -1741,8 +1777,8 @@ static const struct seq_operations ipmr_vif_seq_ops = {
static int ipmr_vif_open(struct inode *inode, struct file *file)
{
- return seq_open_private(file, &ipmr_vif_seq_ops,
- sizeof(struct ipmr_vif_iter));
+ return seq_open_net(inode, file, &ipmr_vif_seq_ops,
+ sizeof(struct ipmr_vif_iter));
}
static const struct file_operations ipmr_vif_fops = {
@@ -1750,23 +1786,26 @@ static const struct file_operations ipmr_vif_fops = {
.open = ipmr_vif_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = seq_release_net,
};
struct ipmr_mfc_iter {
+ struct seq_net_private p;
struct mfc_cache **cache;
int ct;
};
-static struct mfc_cache *ipmr_mfc_seq_idx(struct ipmr_mfc_iter *it, loff_t pos)
+static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net,
+ struct ipmr_mfc_iter *it, loff_t pos)
{
struct mfc_cache *mfc;
- it->cache = mfc_cache_array;
+ it->cache = net->ipv4.mfc_cache_array;
read_lock(&mrt_lock);
for (it->ct = 0; it->ct < MFC_LINES; it->ct++)
- for (mfc = mfc_cache_array[it->ct]; mfc; mfc = mfc->next)
+ for (mfc = net->ipv4.mfc_cache_array[it->ct];
+ mfc; mfc = mfc->next)
if (pos-- == 0)
return mfc;
read_unlock(&mrt_lock);
@@ -1774,7 +1813,8 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct ipmr_mfc_iter *it, loff_t pos)
it->cache = &mfc_unres_queue;
spin_lock_bh(&mfc_unres_lock);
for (mfc = mfc_unres_queue; mfc; mfc = mfc->next)
- if (pos-- == 0)
+ if (net_eq(mfc_net(mfc), net) &&
+ pos-- == 0)
return mfc;
spin_unlock_bh(&mfc_unres_lock);
@@ -1786,9 +1826,11 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct ipmr_mfc_iter *it, loff_t pos)
static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
{
struct ipmr_mfc_iter *it = seq->private;
+ struct net *net = seq_file_net(seq);
+
it->cache = NULL;
it->ct = 0;
- return *pos ? ipmr_mfc_seq_idx(seq->private, *pos - 1)
+ return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1)
: SEQ_START_TOKEN;
}
@@ -1796,11 +1838,12 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct mfc_cache *mfc = v;
struct ipmr_mfc_iter *it = seq->private;
+ struct net *net = seq_file_net(seq);
++*pos;
if (v == SEQ_START_TOKEN)
- return ipmr_mfc_seq_idx(seq->private, 0);
+ return ipmr_mfc_seq_idx(net, seq->private, 0);
if (mfc->next)
return mfc->next;
@@ -1808,10 +1851,10 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
if (it->cache == &mfc_unres_queue)
goto end_of_list;
- BUG_ON(it->cache != mfc_cache_array);
+ BUG_ON(it->cache != net->ipv4.mfc_cache_array);
while (++it->ct < MFC_LINES) {
- mfc = mfc_cache_array[it->ct];
+ mfc = net->ipv4.mfc_cache_array[it->ct];
if (mfc)
return mfc;
}
@@ -1823,6 +1866,8 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
spin_lock_bh(&mfc_unres_lock);
mfc = mfc_unres_queue;
+ while (mfc && !net_eq(mfc_net(mfc), net))
+ mfc = mfc->next;
if (mfc)
return mfc;
@@ -1836,16 +1881,18 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
{
struct ipmr_mfc_iter *it = seq->private;
+ struct net *net = seq_file_net(seq);
if (it->cache == &mfc_unres_queue)
spin_unlock_bh(&mfc_unres_lock);
- else if (it->cache == mfc_cache_array)
+ else if (it->cache == net->ipv4.mfc_cache_array)
read_unlock(&mrt_lock);
}
static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
{
int n;
+ struct net *net = seq_file_net(seq);
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
@@ -1866,9 +1913,9 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
mfc->mfc_un.res.wrong_if);
for (n = mfc->mfc_un.res.minvif;
n < mfc->mfc_un.res.maxvif; n++ ) {
- if (VIF_EXISTS(n)
- && mfc->mfc_un.res.ttls[n] < 255)
- seq_printf(seq,
+ if (VIF_EXISTS(net, n) &&
+ mfc->mfc_un.res.ttls[n] < 255)
+ seq_printf(seq,
" %2d:%-3d",
n, mfc->mfc_un.res.ttls[n]);
}
@@ -1892,8 +1939,8 @@ static const struct seq_operations ipmr_mfc_seq_ops = {
static int ipmr_mfc_open(struct inode *inode, struct file *file)
{
- return seq_open_private(file, &ipmr_mfc_seq_ops,
- sizeof(struct ipmr_mfc_iter));
+ return seq_open_net(inode, file, &ipmr_mfc_seq_ops,
+ sizeof(struct ipmr_mfc_iter));
}
static const struct file_operations ipmr_mfc_fops = {
@@ -1901,7 +1948,7 @@ static const struct file_operations ipmr_mfc_fops = {
.open = ipmr_mfc_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = seq_release_net,
};
#endif
@@ -1915,6 +1962,65 @@ static struct net_protocol pim_protocol = {
/*
* Setup for IP multicast routing
*/
+static int __net_init ipmr_net_init(struct net *net)
+{
+ int err = 0;
+
+ net->ipv4.vif_table = kcalloc(MAXVIFS, sizeof(struct vif_device),
+ GFP_KERNEL);
+ if (!net->ipv4.vif_table) {
+ err = -ENOMEM;
+ goto fail;
+ }
+
+ /* Forwarding cache */
+ net->ipv4.mfc_cache_array = kcalloc(MFC_LINES,
+ sizeof(struct mfc_cache *),
+ GFP_KERNEL);
+ if (!net->ipv4.mfc_cache_array) {
+ err = -ENOMEM;
+ goto fail_mfc_cache;
+ }
+
+#ifdef CONFIG_IP_PIMSM
+ net->ipv4.mroute_reg_vif_num = -1;
+#endif
+
+#ifdef CONFIG_PROC_FS
+ err = -ENOMEM;
+ if (!proc_net_fops_create(net, "ip_mr_vif", 0, &ipmr_vif_fops))
+ goto proc_vif_fail;
+ if (!proc_net_fops_create(net, "ip_mr_cache", 0, &ipmr_mfc_fops))
+ goto proc_cache_fail;
+#endif
+ return 0;
+
+#ifdef CONFIG_PROC_FS
+proc_cache_fail:
+ proc_net_remove(net, "ip_mr_vif");
+proc_vif_fail:
+ kfree(net->ipv4.mfc_cache_array);
+#endif
+fail_mfc_cache:
+ kfree(net->ipv4.vif_table);
+fail:
+ return err;
+}
+
+static void __net_exit ipmr_net_exit(struct net *net)
+{
+#ifdef CONFIG_PROC_FS
+ proc_net_remove(net, "ip_mr_cache");
+ proc_net_remove(net, "ip_mr_vif");
+#endif
+ kfree(net->ipv4.mfc_cache_array);
+ kfree(net->ipv4.vif_table);
+}
+
+static struct pernet_operations ipmr_net_ops = {
+ .init = ipmr_net_init,
+ .exit = ipmr_net_exit,
+};
int __init ip_mr_init(void)
{
@@ -1927,26 +2033,20 @@ int __init ip_mr_init(void)
if (!mrt_cachep)
return -ENOMEM;
+ err = register_pernet_subsys(&ipmr_net_ops);
+ if (err)
+ goto reg_pernet_fail;
+
setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0);
err = register_netdevice_notifier(&ip_mr_notifier);
if (err)
goto reg_notif_fail;
-#ifdef CONFIG_PROC_FS
- err = -ENOMEM;
- if (!proc_net_fops_create(&init_net, "ip_mr_vif", 0, &ipmr_vif_fops))
- goto proc_vif_fail;
- if (!proc_net_fops_create(&init_net, "ip_mr_cache", 0, &ipmr_mfc_fops))
- goto proc_cache_fail;
-#endif
return 0;
-#ifdef CONFIG_PROC_FS
-proc_cache_fail:
- proc_net_remove(&init_net, "ip_mr_vif");
-proc_vif_fail:
- unregister_netdevice_notifier(&ip_mr_notifier);
-#endif
+
reg_notif_fail:
del_timer(&ipmr_expire_timer);
+ unregister_pernet_subsys(&ipmr_net_ops);
+reg_pernet_fail:
kmem_cache_destroy(mrt_cachep);
return err;
}
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 3816e1dc929..1833bdbf980 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -31,7 +31,7 @@ config NF_CONNTRACK_PROC_COMPAT
default y
help
This option enables /proc and sysctl compatibility with the old
- layer 3 dependant connection tracking. This is needed to keep
+ layer 3 dependent connection tracking. This is needed to keep
old programs that have not been adapted to the new names working.
If unsure, say Y.
@@ -95,11 +95,11 @@ config IP_NF_MATCH_ECN
config IP_NF_MATCH_TTL
tristate '"ttl" match support'
depends on NETFILTER_ADVANCED
- help
- This adds CONFIG_IP_NF_MATCH_TTL option, which enabled the user
- to match packets by their TTL value.
-
- To compile it as a module, choose M here. If unsure, say N.
+ select NETFILTER_XT_MATCH_HL
+ ---help---
+ This is a backwards-compat option for the user's convenience
+ (e.g. when running oldconfig). It selects
+ CONFIG_NETFILTER_XT_MATCH_HL.
# `filter', generic and specific targets
config IP_NF_FILTER
@@ -323,19 +323,13 @@ config IP_NF_TARGET_ECN
To compile it as a module, choose M here. If unsure, say N.
config IP_NF_TARGET_TTL
- tristate 'TTL target support'
- depends on IP_NF_MANGLE
+ tristate '"TTL" target support'
depends on NETFILTER_ADVANCED
- help
- This option adds a `TTL' target, which enables the user to modify
- the TTL value of the IP header.
-
- While it is safe to decrement/lower the TTL, this target also enables
- functionality to increment and set the TTL value of the IP header to
- arbitrary values. This is EXTREMELY DANGEROUS since you can easily
- create immortal packets that loop forever on the network.
-
- To compile it as a module, choose M here. If unsure, say N.
+ select NETFILTER_XT_TARGET_HL
+ ---help---
+ This is a backwards-compat option for the user's convenience
+ (e.g. when running oldconfig). It selects
+ CONFIG_NETFILTER_XT_TARGET_HL.
# raw + specific targets
config IP_NF_RAW
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 5f9b650d90f..48111594ee9 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -51,7 +51,6 @@ obj-$(CONFIG_IP_NF_SECURITY) += iptable_security.o
obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o
obj-$(CONFIG_IP_NF_MATCH_AH) += ipt_ah.o
obj-$(CONFIG_IP_NF_MATCH_ECN) += ipt_ecn.o
-obj-$(CONFIG_IP_NF_MATCH_TTL) += ipt_ttl.o
# targets
obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o
@@ -61,7 +60,6 @@ obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o
obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o
obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o
obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o
-obj-$(CONFIG_IP_NF_TARGET_TTL) += ipt_TTL.o
obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o
# generic ARP tables
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 7ea88b61cb0..35c5f6a5cb7 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -73,6 +73,28 @@ static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap,
return (ret != 0);
}
+/*
+ * Unfortunatly, _b and _mask are not aligned to an int (or long int)
+ * Some arches dont care, unrolling the loop is a win on them.
+ * For other arches, we only have a 16bit alignement.
+ */
+static unsigned long ifname_compare(const char *_a, const char *_b, const char *_mask)
+{
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ unsigned long ret = ifname_compare_aligned(_a, _b, _mask);
+#else
+ unsigned long ret = 0;
+ const u16 *a = (const u16 *)_a;
+ const u16 *b = (const u16 *)_b;
+ const u16 *mask = (const u16 *)_mask;
+ int i;
+
+ for (i = 0; i < IFNAMSIZ/sizeof(u16); i++)
+ ret |= (a[i] ^ b[i]) & mask[i];
+#endif
+ return ret;
+}
+
/* Returns whether packet matches rule or not. */
static inline int arp_packet_match(const struct arphdr *arphdr,
struct net_device *dev,
@@ -83,7 +105,7 @@ static inline int arp_packet_match(const struct arphdr *arphdr,
const char *arpptr = (char *)(arphdr + 1);
const char *src_devaddr, *tgt_devaddr;
__be32 src_ipaddr, tgt_ipaddr;
- int i, ret;
+ long ret;
#define FWINV(bool, invflg) ((bool) ^ !!(arpinfo->invflags & (invflg)))
@@ -156,10 +178,7 @@ static inline int arp_packet_match(const struct arphdr *arphdr,
}
/* Look for ifname matches. */
- for (i = 0, ret = 0; i < IFNAMSIZ; i++) {
- ret |= (indev[i] ^ arpinfo->iniface[i])
- & arpinfo->iniface_mask[i];
- }
+ ret = ifname_compare(indev, arpinfo->iniface, arpinfo->iniface_mask);
if (FWINV(ret != 0, ARPT_INV_VIA_IN)) {
dprintf("VIA in mismatch (%s vs %s).%s\n",
@@ -168,10 +187,7 @@ static inline int arp_packet_match(const struct arphdr *arphdr,
return 0;
}
- for (i = 0, ret = 0; i < IFNAMSIZ; i++) {
- ret |= (outdev[i] ^ arpinfo->outiface[i])
- & arpinfo->outiface_mask[i];
- }
+ ret = ifname_compare(outdev, arpinfo->outiface, arpinfo->outiface_mask);
if (FWINV(ret != 0, ARPT_INV_VIA_OUT)) {
dprintf("VIA out mismatch (%s vs %s).%s\n",
@@ -221,7 +237,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
const struct net_device *out,
struct xt_table *table)
{
- static const char nulldevname[IFNAMSIZ];
+ static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
unsigned int verdict = NF_DROP;
const struct arphdr *arp;
bool hotdrop = false;
@@ -237,9 +253,10 @@ unsigned int arpt_do_table(struct sk_buff *skb,
indev = in ? in->name : nulldevname;
outdev = out ? out->name : nulldevname;
- read_lock_bh(&table->lock);
- private = table->private;
- table_base = (void *)private->entries[smp_processor_id()];
+ rcu_read_lock();
+ private = rcu_dereference(table->private);
+ table_base = rcu_dereference(private->entries[smp_processor_id()]);
+
e = get_entry(table_base, private->hook_entry[hook]);
back = get_entry(table_base, private->underflow[hook]);
@@ -311,7 +328,8 @@ unsigned int arpt_do_table(struct sk_buff *skb,
e = (void *)e + e->next_offset;
}
} while (!hotdrop);
- read_unlock_bh(&table->lock);
+
+ rcu_read_unlock();
if (hotdrop)
return NF_DROP;
@@ -374,7 +392,9 @@ static int mark_source_chains(struct xt_table_info *newinfo,
&& unconditional(&e->arp)) || visited) {
unsigned int oldpos, size;
- if (t->verdict < -NF_MAX_VERDICT - 1) {
+ if ((strcmp(t->target.u.user.name,
+ ARPT_STANDARD_TARGET) == 0) &&
+ t->verdict < -NF_MAX_VERDICT - 1) {
duprintf("mark_source_chains: bad "
"negative verdict (%i)\n",
t->verdict);
@@ -714,11 +734,65 @@ static void get_counters(const struct xt_table_info *t,
}
}
-static inline struct xt_counters *alloc_counters(struct xt_table *table)
+
+/* We're lazy, and add to the first CPU; overflow works its fey magic
+ * and everything is OK. */
+static int
+add_counter_to_entry(struct arpt_entry *e,
+ const struct xt_counters addme[],
+ unsigned int *i)
+{
+ ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
+
+ (*i)++;
+ return 0;
+}
+
+/* Take values from counters and add them back onto the current cpu */
+static void put_counters(struct xt_table_info *t,
+ const struct xt_counters counters[])
+{
+ unsigned int i, cpu;
+
+ local_bh_disable();
+ cpu = smp_processor_id();
+ i = 0;
+ ARPT_ENTRY_ITERATE(t->entries[cpu],
+ t->size,
+ add_counter_to_entry,
+ counters,
+ &i);
+ local_bh_enable();
+}
+
+static inline int
+zero_entry_counter(struct arpt_entry *e, void *arg)
+{
+ e->counters.bcnt = 0;
+ e->counters.pcnt = 0;
+ return 0;
+}
+
+static void
+clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info)
+{
+ unsigned int cpu;
+ const void *loc_cpu_entry = info->entries[raw_smp_processor_id()];
+
+ memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
+ for_each_possible_cpu(cpu) {
+ memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size);
+ ARPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size,
+ zero_entry_counter, NULL);
+ }
+}
+
+static struct xt_counters *alloc_counters(struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ struct xt_table_info *private = table->private;
+ struct xt_table_info *info;
/* We need atomic snapshot of counters: rest doesn't change
* (other than comefrom, which userspace doesn't care
@@ -728,14 +802,30 @@ static inline struct xt_counters *alloc_counters(struct xt_table *table)
counters = vmalloc_node(countersize, numa_node_id());
if (counters == NULL)
- return ERR_PTR(-ENOMEM);
+ goto nomem;
+
+ info = xt_alloc_table_info(private->size);
+ if (!info)
+ goto free_counters;
+
+ clone_counters(info, private);
+
+ mutex_lock(&table->lock);
+ xt_table_entry_swap_rcu(private, info);
+ synchronize_net(); /* Wait until smoke has cleared */
+
+ get_counters(info, counters);
+ put_counters(private, counters);
+ mutex_unlock(&table->lock);
- /* First, sum counters... */
- write_lock_bh(&table->lock);
- get_counters(private, counters);
- write_unlock_bh(&table->lock);
+ xt_free_table_info(info);
return counters;
+
+ free_counters:
+ vfree(counters);
+ nomem:
+ return ERR_PTR(-ENOMEM);
}
static int copy_entries_to_user(unsigned int total_size,
@@ -1075,20 +1165,6 @@ static int do_replace(struct net *net, void __user *user, unsigned int len)
return ret;
}
-/* We're lazy, and add to the first CPU; overflow works its fey magic
- * and everything is OK.
- */
-static inline int add_counter_to_entry(struct arpt_entry *e,
- const struct xt_counters addme[],
- unsigned int *i)
-{
-
- ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
-
- (*i)++;
- return 0;
-}
-
static int do_add_counters(struct net *net, void __user *user, unsigned int len,
int compat)
{
@@ -1148,13 +1224,14 @@ static int do_add_counters(struct net *net, void __user *user, unsigned int len,
goto free;
}
- write_lock_bh(&t->lock);
+ mutex_lock(&t->lock);
private = t->private;
if (private->number != num_counters) {
ret = -EINVAL;
goto unlock_up_free;
}
+ preempt_disable();
i = 0;
/* Choose the copy that is on our node */
loc_cpu_entry = private->entries[smp_processor_id()];
@@ -1163,8 +1240,10 @@ static int do_add_counters(struct net *net, void __user *user, unsigned int len,
add_counter_to_entry,
paddc,
&i);
+ preempt_enable();
unlock_up_free:
- write_unlock_bh(&t->lock);
+ mutex_unlock(&t->lock);
+
xt_table_unlock(t);
module_put(t->me);
free:
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index e091187e864..6ecfdae7c58 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -48,8 +48,6 @@ static struct
static struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(packet_filter.lock),
- .private = NULL,
.me = THIS_MODULE,
.af = NFPROTO_ARP,
};
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index 432ce9d1c11..5f22c91c6e1 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -24,6 +24,7 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/security.h>
+#include <linux/net.h>
#include <linux/mutex.h>
#include <net/net_namespace.h>
#include <net/sock.h>
@@ -640,6 +641,7 @@ static void __exit ip_queue_fini(void)
MODULE_DESCRIPTION("IPv4 packet queue handler");
MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_FIREWALL);
module_init(ip_queue_init);
module_exit(ip_queue_fini);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index ef8b6ca068b..82ee7c9049f 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -83,7 +83,6 @@ ip_packet_match(const struct iphdr *ip,
const struct ipt_ip *ipinfo,
int isfrag)
{
- size_t i;
unsigned long ret;
#define FWINV(bool, invflg) ((bool) ^ !!(ipinfo->invflags & (invflg)))
@@ -103,12 +102,7 @@ ip_packet_match(const struct iphdr *ip,
return false;
}
- /* Look for ifname matches; this should unroll nicely. */
- for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
- ret |= (((const unsigned long *)indev)[i]
- ^ ((const unsigned long *)ipinfo->iniface)[i])
- & ((const unsigned long *)ipinfo->iniface_mask)[i];
- }
+ ret = ifname_compare_aligned(indev, ipinfo->iniface, ipinfo->iniface_mask);
if (FWINV(ret != 0, IPT_INV_VIA_IN)) {
dprintf("VIA in mismatch (%s vs %s).%s\n",
@@ -117,11 +111,7 @@ ip_packet_match(const struct iphdr *ip,
return false;
}
- for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
- ret |= (((const unsigned long *)outdev)[i]
- ^ ((const unsigned long *)ipinfo->outiface)[i])
- & ((const unsigned long *)ipinfo->outiface_mask)[i];
- }
+ ret = ifname_compare_aligned(outdev, ipinfo->outiface, ipinfo->outiface_mask);
if (FWINV(ret != 0, IPT_INV_VIA_OUT)) {
dprintf("VIA out mismatch (%s vs %s).%s\n",
@@ -347,10 +337,12 @@ ipt_do_table(struct sk_buff *skb,
mtpar.family = tgpar.family = NFPROTO_IPV4;
tgpar.hooknum = hook;
- read_lock_bh(&table->lock);
IP_NF_ASSERT(table->valid_hooks & (1 << hook));
- private = table->private;
- table_base = (void *)private->entries[smp_processor_id()];
+
+ rcu_read_lock();
+ private = rcu_dereference(table->private);
+ table_base = rcu_dereference(private->entries[smp_processor_id()]);
+
e = get_entry(table_base, private->hook_entry[hook]);
/* For return from builtin chain */
@@ -445,7 +437,7 @@ ipt_do_table(struct sk_buff *skb,
}
} while (!hotdrop);
- read_unlock_bh(&table->lock);
+ rcu_read_unlock();
#ifdef DEBUG_ALLOW_ALL
return NF_ACCEPT;
@@ -496,7 +488,9 @@ mark_source_chains(struct xt_table_info *newinfo,
&& unconditional(&e->ip)) || visited) {
unsigned int oldpos, size;
- if (t->verdict < -NF_MAX_VERDICT - 1) {
+ if ((strcmp(t->target.u.user.name,
+ IPT_STANDARD_TARGET) == 0) &&
+ t->verdict < -NF_MAX_VERDICT - 1) {
duprintf("mark_source_chains: bad "
"negative verdict (%i)\n",
t->verdict);
@@ -924,13 +918,68 @@ get_counters(const struct xt_table_info *t,
counters,
&i);
}
+
+}
+
+/* We're lazy, and add to the first CPU; overflow works its fey magic
+ * and everything is OK. */
+static int
+add_counter_to_entry(struct ipt_entry *e,
+ const struct xt_counters addme[],
+ unsigned int *i)
+{
+ ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
+
+ (*i)++;
+ return 0;
+}
+
+/* Take values from counters and add them back onto the current cpu */
+static void put_counters(struct xt_table_info *t,
+ const struct xt_counters counters[])
+{
+ unsigned int i, cpu;
+
+ local_bh_disable();
+ cpu = smp_processor_id();
+ i = 0;
+ IPT_ENTRY_ITERATE(t->entries[cpu],
+ t->size,
+ add_counter_to_entry,
+ counters,
+ &i);
+ local_bh_enable();
+}
+
+
+static inline int
+zero_entry_counter(struct ipt_entry *e, void *arg)
+{
+ e->counters.bcnt = 0;
+ e->counters.pcnt = 0;
+ return 0;
+}
+
+static void
+clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info)
+{
+ unsigned int cpu;
+ const void *loc_cpu_entry = info->entries[raw_smp_processor_id()];
+
+ memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
+ for_each_possible_cpu(cpu) {
+ memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size);
+ IPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size,
+ zero_entry_counter, NULL);
+ }
}
static struct xt_counters * alloc_counters(struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ struct xt_table_info *private = table->private;
+ struct xt_table_info *info;
/* We need atomic snapshot of counters: rest doesn't change
(other than comefrom, which userspace doesn't care
@@ -939,14 +988,30 @@ static struct xt_counters * alloc_counters(struct xt_table *table)
counters = vmalloc_node(countersize, numa_node_id());
if (counters == NULL)
- return ERR_PTR(-ENOMEM);
+ goto nomem;
+
+ info = xt_alloc_table_info(private->size);
+ if (!info)
+ goto free_counters;
+
+ clone_counters(info, private);
- /* First, sum counters... */
- write_lock_bh(&table->lock);
- get_counters(private, counters);
- write_unlock_bh(&table->lock);
+ mutex_lock(&table->lock);
+ xt_table_entry_swap_rcu(private, info);
+ synchronize_net(); /* Wait until smoke has cleared */
+
+ get_counters(info, counters);
+ put_counters(private, counters);
+ mutex_unlock(&table->lock);
+
+ xt_free_table_info(info);
return counters;
+
+ free_counters:
+ vfree(counters);
+ nomem:
+ return ERR_PTR(-ENOMEM);
}
static int
@@ -1312,27 +1377,6 @@ do_replace(struct net *net, void __user *user, unsigned int len)
return ret;
}
-/* We're lazy, and add to the first CPU; overflow works its fey magic
- * and everything is OK. */
-static int
-add_counter_to_entry(struct ipt_entry *e,
- const struct xt_counters addme[],
- unsigned int *i)
-{
-#if 0
- duprintf("add_counter: Entry %u %lu/%lu + %lu/%lu\n",
- *i,
- (long unsigned int)e->counters.pcnt,
- (long unsigned int)e->counters.bcnt,
- (long unsigned int)addme[*i].pcnt,
- (long unsigned int)addme[*i].bcnt);
-#endif
-
- ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
-
- (*i)++;
- return 0;
-}
static int
do_add_counters(struct net *net, void __user *user, unsigned int len, int compat)
@@ -1393,13 +1437,14 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, int compat
goto free;
}
- write_lock_bh(&t->lock);
+ mutex_lock(&t->lock);
private = t->private;
if (private->number != num_counters) {
ret = -EINVAL;
goto unlock_up_free;
}
+ preempt_disable();
i = 0;
/* Choose the copy that is on our node */
loc_cpu_entry = private->entries[raw_smp_processor_id()];
@@ -1408,8 +1453,9 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, int compat
add_counter_to_entry,
paddc,
&i);
+ preempt_enable();
unlock_up_free:
- write_unlock_bh(&t->lock);
+ mutex_unlock(&t->lock);
xt_table_unlock(t);
module_put(t->me);
free:
diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c
index 27a78fbbd92..acc44c69eb6 100644
--- a/net/ipv4/netfilter/ipt_LOG.c
+++ b/net/ipv4/netfilter/ipt_LOG.c
@@ -464,7 +464,7 @@ static struct xt_target log_tg_reg __read_mostly = {
.me = THIS_MODULE,
};
-static const struct nf_logger ipt_log_logger ={
+static struct nf_logger ipt_log_logger __read_mostly = {
.name = "ipt_LOG",
.logfn = &ipt_log_packet,
.me = THIS_MODULE,
diff --git a/net/ipv4/netfilter/ipt_TTL.c b/net/ipv4/netfilter/ipt_TTL.c
deleted file mode 100644
index 6d76aae90cc..00000000000
--- a/net/ipv4/netfilter/ipt_TTL.c
+++ /dev/null
@@ -1,97 +0,0 @@
-/* TTL modification target for IP tables
- * (C) 2000,2005 by Harald Welte <laforge@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/ip.h>
-#include <net/checksum.h>
-
-#include <linux/netfilter/x_tables.h>
-#include <linux/netfilter_ipv4/ipt_TTL.h>
-
-MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
-MODULE_DESCRIPTION("Xtables: IPv4 TTL field modification target");
-MODULE_LICENSE("GPL");
-
-static unsigned int
-ttl_tg(struct sk_buff *skb, const struct xt_target_param *par)
-{
- struct iphdr *iph;
- const struct ipt_TTL_info *info = par->targinfo;
- int new_ttl;
-
- if (!skb_make_writable(skb, skb->len))
- return NF_DROP;
-
- iph = ip_hdr(skb);
-
- switch (info->mode) {
- case IPT_TTL_SET:
- new_ttl = info->ttl;
- break;
- case IPT_TTL_INC:
- new_ttl = iph->ttl + info->ttl;
- if (new_ttl > 255)
- new_ttl = 255;
- break;
- case IPT_TTL_DEC:
- new_ttl = iph->ttl - info->ttl;
- if (new_ttl < 0)
- new_ttl = 0;
- break;
- default:
- new_ttl = iph->ttl;
- break;
- }
-
- if (new_ttl != iph->ttl) {
- csum_replace2(&iph->check, htons(iph->ttl << 8),
- htons(new_ttl << 8));
- iph->ttl = new_ttl;
- }
-
- return XT_CONTINUE;
-}
-
-static bool ttl_tg_check(const struct xt_tgchk_param *par)
-{
- const struct ipt_TTL_info *info = par->targinfo;
-
- if (info->mode > IPT_TTL_MAXMODE) {
- printk(KERN_WARNING "ipt_TTL: invalid or unknown Mode %u\n",
- info->mode);
- return false;
- }
- if (info->mode != IPT_TTL_SET && info->ttl == 0)
- return false;
- return true;
-}
-
-static struct xt_target ttl_tg_reg __read_mostly = {
- .name = "TTL",
- .family = NFPROTO_IPV4,
- .target = ttl_tg,
- .targetsize = sizeof(struct ipt_TTL_info),
- .table = "mangle",
- .checkentry = ttl_tg_check,
- .me = THIS_MODULE,
-};
-
-static int __init ttl_tg_init(void)
-{
- return xt_register_target(&ttl_tg_reg);
-}
-
-static void __exit ttl_tg_exit(void)
-{
- xt_unregister_target(&ttl_tg_reg);
-}
-
-module_init(ttl_tg_init);
-module_exit(ttl_tg_exit);
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index 18a2826b57c..d32cc4bb328 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -379,7 +379,7 @@ static struct xt_target ulog_tg_reg __read_mostly = {
.me = THIS_MODULE,
};
-static struct nf_logger ipt_ulog_logger = {
+static struct nf_logger ipt_ulog_logger __read_mostly = {
.name = "ipt_ULOG",
.logfn = ipt_logfn,
.me = THIS_MODULE,
diff --git a/net/ipv4/netfilter/ipt_ttl.c b/net/ipv4/netfilter/ipt_ttl.c
deleted file mode 100644
index 297f1cbf4ff..00000000000
--- a/net/ipv4/netfilter/ipt_ttl.c
+++ /dev/null
@@ -1,63 +0,0 @@
-/* IP tables module for matching the value of the TTL
- *
- * (C) 2000,2001 by Harald Welte <laforge@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/ip.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-
-#include <linux/netfilter_ipv4/ipt_ttl.h>
-#include <linux/netfilter/x_tables.h>
-
-MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
-MODULE_DESCRIPTION("Xtables: IPv4 TTL field match");
-MODULE_LICENSE("GPL");
-
-static bool ttl_mt(const struct sk_buff *skb, const struct xt_match_param *par)
-{
- const struct ipt_ttl_info *info = par->matchinfo;
- const u8 ttl = ip_hdr(skb)->ttl;
-
- switch (info->mode) {
- case IPT_TTL_EQ:
- return ttl == info->ttl;
- case IPT_TTL_NE:
- return ttl != info->ttl;
- case IPT_TTL_LT:
- return ttl < info->ttl;
- case IPT_TTL_GT:
- return ttl > info->ttl;
- default:
- printk(KERN_WARNING "ipt_ttl: unknown mode %d\n",
- info->mode);
- return false;
- }
-
- return false;
-}
-
-static struct xt_match ttl_mt_reg __read_mostly = {
- .name = "ttl",
- .family = NFPROTO_IPV4,
- .match = ttl_mt,
- .matchsize = sizeof(struct ipt_ttl_info),
- .me = THIS_MODULE,
-};
-
-static int __init ttl_mt_init(void)
-{
- return xt_register_match(&ttl_mt_reg);
-}
-
-static void __exit ttl_mt_exit(void)
-{
- xt_unregister_match(&ttl_mt_reg);
-}
-
-module_init(ttl_mt_init);
-module_exit(ttl_mt_exit);
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index 52cb6939d09..c30a969724f 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -56,7 +56,6 @@ static struct
static struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(packet_filter.lock),
.me = THIS_MODULE,
.af = AF_INET,
};
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index 3929d20b9e4..4087614d951 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -67,7 +67,6 @@ static struct
static struct xt_table packet_mangler = {
.name = "mangle",
.valid_hooks = MANGLE_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(packet_mangler.lock),
.me = THIS_MODULE,
.af = AF_INET,
};
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 7f65d18333e..e5356da1fb5 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -39,7 +39,6 @@ static struct
static struct xt_table packet_raw = {
.name = "raw",
.valid_hooks = RAW_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(packet_raw.lock),
.me = THIS_MODULE,
.af = AF_INET,
};
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index a52a35f4a58..29ab630f240 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -60,7 +60,6 @@ static struct
static struct xt_table security_table = {
.name = "security",
.valid_hooks = SECURITY_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(security_table.lock),
.me = THIS_MODULE,
.af = AF_INET,
};
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 4beb04fac58..7d2ead7228a 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -120,8 +120,10 @@ static unsigned int ipv4_confirm(unsigned int hooknum,
typeof(nf_nat_seq_adjust_hook) seq_adjust;
seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
- if (!seq_adjust || !seq_adjust(skb, ct, ctinfo))
+ if (!seq_adjust || !seq_adjust(skb, ct, ctinfo)) {
+ NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
return NF_DROP;
+ }
}
out:
/* We've seen it coming out the other side: confirm it */
@@ -326,6 +328,11 @@ static int ipv4_nlattr_to_tuple(struct nlattr *tb[],
return 0;
}
+
+static int ipv4_nlattr_tuple_size(void)
+{
+ return nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1);
+}
#endif
static struct nf_sockopt_ops so_getorigdst = {
@@ -345,6 +352,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
.get_l4proto = ipv4_get_l4proto,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.tuple_to_nlattr = ipv4_tuple_to_nlattr,
+ .nlattr_tuple_size = ipv4_nlattr_tuple_size,
.nlattr_to_tuple = ipv4_nlattr_to_tuple,
.nla_policy = ipv4_nla_policy,
#endif
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 6ba5c557690..8668a3defda 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -25,40 +25,42 @@ struct ct_iter_state {
unsigned int bucket;
};
-static struct hlist_node *ct_get_first(struct seq_file *seq)
+static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
{
struct net *net = seq_file_net(seq);
struct ct_iter_state *st = seq->private;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
for (st->bucket = 0;
st->bucket < nf_conntrack_htable_size;
st->bucket++) {
n = rcu_dereference(net->ct.hash[st->bucket].first);
- if (n)
+ if (!is_a_nulls(n))
return n;
}
return NULL;
}
-static struct hlist_node *ct_get_next(struct seq_file *seq,
- struct hlist_node *head)
+static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
+ struct hlist_nulls_node *head)
{
struct net *net = seq_file_net(seq);
struct ct_iter_state *st = seq->private;
head = rcu_dereference(head->next);
- while (head == NULL) {
- if (++st->bucket >= nf_conntrack_htable_size)
- return NULL;
+ while (is_a_nulls(head)) {
+ if (likely(get_nulls_value(head) == st->bucket)) {
+ if (++st->bucket >= nf_conntrack_htable_size)
+ return NULL;
+ }
head = rcu_dereference(net->ct.hash[st->bucket].first);
}
return head;
}
-static struct hlist_node *ct_get_idx(struct seq_file *seq, loff_t pos)
+static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos)
{
- struct hlist_node *head = ct_get_first(seq);
+ struct hlist_nulls_node *head = ct_get_first(seq);
if (head)
while (pos && (head = ct_get_next(seq, head)))
@@ -87,69 +89,76 @@ static void ct_seq_stop(struct seq_file *s, void *v)
static int ct_seq_show(struct seq_file *s, void *v)
{
- const struct nf_conntrack_tuple_hash *hash = v;
- const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash);
+ struct nf_conntrack_tuple_hash *hash = v;
+ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash);
const struct nf_conntrack_l3proto *l3proto;
const struct nf_conntrack_l4proto *l4proto;
+ int ret = 0;
NF_CT_ASSERT(ct);
+ if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
+ return 0;
+
/* we only want to print DIR_ORIGINAL */
if (NF_CT_DIRECTION(hash))
- return 0;
+ goto release;
if (nf_ct_l3num(ct) != AF_INET)
- return 0;
+ goto release;
l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
NF_CT_ASSERT(l3proto);
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
NF_CT_ASSERT(l4proto);
+ ret = -ENOSPC;
if (seq_printf(s, "%-8s %u %ld ",
l4proto->name, nf_ct_protonum(ct),
timer_pending(&ct->timeout)
? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0)
- return -ENOSPC;
+ goto release;
if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct))
- return -ENOSPC;
+ goto release;
if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
l3proto, l4proto))
- return -ENOSPC;
+ goto release;
if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL))
- return -ENOSPC;
+ goto release;
if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status)))
if (seq_printf(s, "[UNREPLIED] "))
- return -ENOSPC;
+ goto release;
if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
l3proto, l4proto))
- return -ENOSPC;
+ goto release;
if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
- return -ENOSPC;
+ goto release;
if (test_bit(IPS_ASSURED_BIT, &ct->status))
if (seq_printf(s, "[ASSURED] "))
- return -ENOSPC;
+ goto release;
#ifdef CONFIG_NF_CONNTRACK_MARK
if (seq_printf(s, "mark=%u ", ct->mark))
- return -ENOSPC;
+ goto release;
#endif
#ifdef CONFIG_NF_CONNTRACK_SECMARK
if (seq_printf(s, "secmark=%u ", ct->secmark))
- return -ENOSPC;
+ goto release;
#endif
if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
- return -ENOSPC;
-
- return 0;
+ goto release;
+ ret = 0;
+release:
+ nf_ct_put(ct);
+ return ret;
}
static const struct seq_operations ct_seq_ops = {
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 2a8bee26f43..23b2c2ee869 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -262,6 +262,11 @@ static int icmp_nlattr_to_tuple(struct nlattr *tb[],
return 0;
}
+
+static int icmp_nlattr_tuple_size(void)
+{
+ return nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1);
+}
#endif
#ifdef CONFIG_SYSCTL
@@ -309,6 +314,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly =
.me = NULL,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.tuple_to_nlattr = icmp_tuple_to_nlattr,
+ .nlattr_tuple_size = icmp_nlattr_tuple_size,
.nlattr_to_tuple = icmp_nlattr_to_tuple,
.nla_policy = icmp_nla_policy,
#endif
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index a65cf692359..fe65187810f 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -679,7 +679,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct,
static int __net_init nf_nat_net_init(struct net *net)
{
net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size,
- &net->ipv4.nat_vmalloced);
+ &net->ipv4.nat_vmalloced, 0);
if (!net->ipv4.nat_bysource)
return -ENOMEM;
return 0;
diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c
index a7eb0471904..6348a793936 100644
--- a/net/ipv4/netfilter/nf_nat_rule.c
+++ b/net/ipv4/netfilter/nf_nat_rule.c
@@ -61,7 +61,6 @@ static struct
static struct xt_table nat_table = {
.name = "nat",
.valid_hooks = NAT_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(nat_table.lock),
.me = THIS_MODULE,
.af = AF_INET,
};
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index 182f845de92..d9521f6f9ed 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -1292,7 +1292,7 @@ static struct nf_conntrack_helper snmp_helper __read_mostly = {
.expect_policy = &snmp_exp_policy,
.name = "snmp",
.tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = __constant_htons(SNMP_PORT),
+ .tuple.src.u.udp.port = cpu_to_be16(SNMP_PORT),
.tuple.dst.protonum = IPPROTO_UDP,
};
@@ -1302,7 +1302,7 @@ static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
.expect_policy = &snmp_exp_policy,
.name = "snmp_trap",
.tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = __constant_htons(SNMP_TRAP_PORT),
+ .tuple.src.u.udp.port = cpu_to_be16(SNMP_TRAP_PORT),
.tuple.dst.protonum = IPPROTO_UDP,
};
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index eb62e58bff7..cf0cdeeb1db 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -54,8 +54,8 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
int orphans, sockets;
local_bh_disable();
- orphans = percpu_counter_sum_positive(&tcp_orphan_count),
- sockets = percpu_counter_sum_positive(&tcp_sockets_allocated),
+ orphans = percpu_counter_sum_positive(&tcp_orphan_count);
+ sockets = percpu_counter_sum_positive(&tcp_sockets_allocated);
local_bh_enable();
socket_seq_show(seq);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index dff8bc4e0fa..f774651f0a4 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -493,6 +493,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.addr = inet->saddr;
ipc.opt = NULL;
+ ipc.shtx.flags = 0;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index bf895401218..c40debe51b3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -151,7 +151,7 @@ static void rt_emergency_hash_rebuild(struct net *net);
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
- .protocol = __constant_htons(ETH_P_IP),
+ .protocol = cpu_to_be16(ETH_P_IP),
.gc = rt_garbage_collect,
.check = ipv4_dst_check,
.destroy = ipv4_dst_destroy,
@@ -2696,7 +2696,7 @@ static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
static struct dst_ops ipv4_dst_blackhole_ops = {
.family = AF_INET,
- .protocol = __constant_htons(ETH_P_IP),
+ .protocol = cpu_to_be16(ETH_P_IP),
.destroy = ipv4_dst_destroy,
.check = ipv4_dst_check,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
@@ -2779,7 +2779,8 @@ int ip_route_output_key(struct net *net, struct rtable **rp, struct flowi *flp)
return ip_route_output_flow(net, rp, flp, NULL, 0);
}
-static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
+static int rt_fill_info(struct net *net,
+ struct sk_buff *skb, u32 pid, u32 seq, int event,
int nowait, unsigned int flags)
{
struct rtable *rt = skb->rtable;
@@ -2844,8 +2845,8 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
__be32 dst = rt->rt_dst;
if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
- IPV4_DEVCONF_ALL(&init_net, MC_FORWARDING)) {
- int err = ipmr_get_route(skb, r, nowait);
+ IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
+ int err = ipmr_get_route(net, skb, r, nowait);
if (err <= 0) {
if (!nowait) {
if (err == 0)
@@ -2950,7 +2951,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
- err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
+ err = rt_fill_info(net, skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
RTM_NEWROUTE, 0, 0);
if (err <= 0)
goto errout_free;
@@ -2988,7 +2989,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
if (rt_is_expired(rt))
continue;
skb->dst = dst_clone(&rt->u.dst);
- if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid,
+ if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, RTM_NEWROUTE,
1, NLM_F_MULTI) <= 0) {
dst_release(xchg(&skb->dst, NULL));
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index d346c22aa6a..b35a950d2e0 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -288,10 +288,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
if (!req)
goto out;
- if (security_inet_conn_request(sk, skb, req)) {
- reqsk_free(req);
- goto out;
- }
ireq = inet_rsk(req);
treq = tcp_rsk(req);
treq->rcv_isn = ntohl(th->seq) - 1;
@@ -322,6 +318,11 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
}
}
+ if (security_inet_conn_request(sk, skb, req)) {
+ reqsk_free(req);
+ goto out;
+ }
+
req->expires = 0UL;
req->retrans = 0;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 76b148bcb0d..2451aeb5ac2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -661,6 +661,47 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
return NULL;
}
+static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
+ int large_allowed)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 xmit_size_goal, old_size_goal;
+
+ xmit_size_goal = mss_now;
+
+ if (large_allowed && sk_can_gso(sk)) {
+ xmit_size_goal = ((sk->sk_gso_max_size - 1) -
+ inet_csk(sk)->icsk_af_ops->net_header_len -
+ inet_csk(sk)->icsk_ext_hdr_len -
+ tp->tcp_header_len);
+
+ xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
+
+ /* We try hard to avoid divides here */
+ old_size_goal = tp->xmit_size_goal_segs * mss_now;
+
+ if (likely(old_size_goal <= xmit_size_goal &&
+ old_size_goal + mss_now > xmit_size_goal)) {
+ xmit_size_goal = old_size_goal;
+ } else {
+ tp->xmit_size_goal_segs = xmit_size_goal / mss_now;
+ xmit_size_goal = tp->xmit_size_goal_segs * mss_now;
+ }
+ }
+
+ return max(xmit_size_goal, mss_now);
+}
+
+static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
+{
+ int mss_now;
+
+ mss_now = tcp_current_mss(sk);
+ *size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB));
+
+ return mss_now;
+}
+
static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffset,
size_t psize, int flags)
{
@@ -677,13 +718,12 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse
clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
- mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
- size_goal = tp->xmit_size_goal;
+ mss_now = tcp_send_mss(sk, &size_goal, flags);
copied = 0;
err = -EPIPE;
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
- goto do_error;
+ goto out_err;
while (psize > 0) {
struct sk_buff *skb = tcp_write_queue_tail(sk);
@@ -761,8 +801,7 @@ wait_for_memory:
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
goto do_error;
- mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
- size_goal = tp->xmit_size_goal;
+ mss_now = tcp_send_mss(sk, &size_goal, flags);
}
out:
@@ -844,8 +883,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
/* This should be in poll */
clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
- mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
- size_goal = tp->xmit_size_goal;
+ mss_now = tcp_send_mss(sk, &size_goal, flags);
/* Ok commence sending. */
iovlen = msg->msg_iovlen;
@@ -854,7 +892,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
err = -EPIPE;
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
- goto do_error;
+ goto out_err;
while (--iovlen >= 0) {
int seglen = iov->iov_len;
@@ -1007,8 +1045,7 @@ wait_for_memory:
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
goto do_error;
- mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
- size_goal = tp->xmit_size_goal;
+ mss_now = tcp_send_mss(sk, &size_goal, flags);
}
}
@@ -1045,8 +1082,7 @@ out_err:
*/
static int tcp_recv_urg(struct sock *sk, long timeo,
- struct msghdr *msg, int len, int flags,
- int *addr_len)
+ struct msghdr *msg, int len, int flags)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -1661,7 +1697,7 @@ out:
return err;
recv_urg:
- err = tcp_recv_urg(sk, timeo, msg, len, flags, addr_len);
+ err = tcp_recv_urg(sk, timeo, msg, len, flags);
goto out;
}
@@ -2478,23 +2514,23 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
struct tcphdr *th2;
unsigned int thlen;
unsigned int flags;
- unsigned int total;
unsigned int mss = 1;
int flush = 1;
+ int i;
- if (!pskb_may_pull(skb, sizeof(*th)))
+ th = skb_gro_header(skb, sizeof(*th));
+ if (unlikely(!th))
goto out;
- th = tcp_hdr(skb);
thlen = th->doff * 4;
if (thlen < sizeof(*th))
goto out;
- if (!pskb_may_pull(skb, thlen))
+ th = skb_gro_header(skb, thlen);
+ if (unlikely(!th))
goto out;
- th = tcp_hdr(skb);
- __skb_pull(skb, thlen);
+ skb_gro_pull(skb, thlen);
flags = tcp_flag_word(th);
@@ -2504,7 +2540,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
th2 = tcp_hdr(p);
- if (th->source != th2->source || th->dest != th2->dest) {
+ if ((th->source ^ th2->source) | (th->dest ^ th2->dest)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
@@ -2519,14 +2555,15 @@ found:
flush |= flags & TCP_FLAG_CWR;
flush |= (flags ^ tcp_flag_word(th2)) &
~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH);
- flush |= th->ack_seq != th2->ack_seq || th->window != th2->window;
- flush |= memcmp(th + 1, th2 + 1, thlen - sizeof(*th));
+ flush |= (th->ack_seq ^ th2->ack_seq) | (th->window ^ th2->window);
+ for (i = sizeof(*th); !flush && i < thlen; i += 4)
+ flush |= *(u32 *)((u8 *)th + i) ^
+ *(u32 *)((u8 *)th2 + i);
- total = p->len;
mss = skb_shinfo(p)->gso_size;
- flush |= skb->len > mss || skb->len <= 0;
- flush |= ntohl(th2->seq) + total != ntohl(th->seq);
+ flush |= (skb_gro_len(skb) > mss) | !skb_gro_len(skb);
+ flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
if (flush || skb_gro_receive(head, skb)) {
mss = 1;
@@ -2538,7 +2575,7 @@ found:
tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
out_check_final:
- flush = skb->len < mss;
+ flush = skb_gro_len(skb) < mss;
flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST |
TCP_FLAG_SYN | TCP_FLAG_FIN);
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index 7eb7636db0d..3b53fd1af23 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -149,16 +149,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
tcp_slow_start(tp);
else {
bictcp_update(ca, tp->snd_cwnd);
-
- /* In dangerous area, increase slowly.
- * In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd
- */
- if (tp->snd_cwnd_cnt >= ca->cnt) {
- if (tp->snd_cwnd < tp->snd_cwnd_clamp)
- tp->snd_cwnd++;
- tp->snd_cwnd_cnt = 0;
- } else
- tp->snd_cwnd_cnt++;
+ tcp_cong_avoid_ai(tp, ca->cnt);
}
}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 4ec5b4e97c4..e92beb9e55e 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -336,6 +336,19 @@ void tcp_slow_start(struct tcp_sock *tp)
}
EXPORT_SYMBOL_GPL(tcp_slow_start);
+/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w)
+{
+ if (tp->snd_cwnd_cnt >= w) {
+ if (tp->snd_cwnd < tp->snd_cwnd_clamp)
+ tp->snd_cwnd++;
+ tp->snd_cwnd_cnt = 0;
+ } else {
+ tp->snd_cwnd_cnt++;
+ }
+}
+EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
+
/*
* TCP Reno congestion control
* This is special case used for fallback as well.
@@ -365,13 +378,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
tp->snd_cwnd++;
}
} else {
- /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd */
- if (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
- if (tp->snd_cwnd < tp->snd_cwnd_clamp)
- tp->snd_cwnd++;
- tp->snd_cwnd_cnt = 0;
- } else
- tp->snd_cwnd_cnt++;
+ tcp_cong_avoid_ai(tp, tp->snd_cwnd);
}
}
EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index ee467ec40c4..71d5f2f29fa 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -294,16 +294,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
tcp_slow_start(tp);
} else {
bictcp_update(ca, tp->snd_cwnd);
-
- /* In dangerous area, increase slowly.
- * In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd
- */
- if (tp->snd_cwnd_cnt >= ca->cnt) {
- if (tp->snd_cwnd < tp->snd_cwnd_clamp)
- tp->snd_cwnd++;
- tp->snd_cwnd_cnt = 0;
- } else
- tp->snd_cwnd_cnt++;
+ tcp_cong_avoid_ai(tp, ca->cnt);
}
}
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 937549b8a92..26d5c7fc7de 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -115,8 +115,7 @@ static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, s32 rtt
return;
/* achieved throughput calculations */
- if (icsk->icsk_ca_state != TCP_CA_Open &&
- icsk->icsk_ca_state != TCP_CA_Disorder) {
+ if (!((1 << icsk->icsk_ca_state) & (TCPF_CA_Open | TCPF_CA_Disorder))) {
ca->packetcount = 0;
ca->lasttime = now;
return;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c28976a7e59..2bc8e27a163 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -64,6 +64,7 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sysctl.h>
+#include <linux/kernel.h>
#include <net/dst.h>
#include <net/tcp.h>
#include <net/inet_common.h>
@@ -1178,10 +1179,18 @@ static void tcp_mark_lost_retrans(struct sock *sk)
if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS))
continue;
- if (after(received_upto, ack_seq) &&
- (tcp_is_fack(tp) ||
- !before(received_upto,
- ack_seq + tp->reordering * tp->mss_cache))) {
+ /* TODO: We would like to get rid of tcp_is_fack(tp) only
+ * constraint here (see above) but figuring out that at
+ * least tp->reordering SACK blocks reside between ack_seq
+ * and received_upto is not easy task to do cheaply with
+ * the available datastructures.
+ *
+ * Whether FACK should check here for tp->reordering segs
+ * in-between one could argue for either way (it would be
+ * rather simple to implement as we could count fack_count
+ * during the walk and do tp->fackets_out - fack_count).
+ */
+ if (after(received_upto, ack_seq)) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
@@ -1794,11 +1803,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb,
for (i = used_sacks - 1; i > 0; i--) {
for (j = 0; j < i; j++) {
if (after(sp[j].start_seq, sp[j + 1].start_seq)) {
- struct tcp_sack_block tmp;
-
- tmp = sp[j];
- sp[j] = sp[j + 1];
- sp[j + 1] = tmp;
+ swap(sp[j], sp[j + 1]);
/* Track where the first SACK block goes to */
if (j == first_sack_index)
@@ -2453,6 +2458,44 @@ static int tcp_time_to_recover(struct sock *sk)
return 0;
}
+/* 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);
+}
+
/* Mark head of queue up as lost. With RFC3517 SACK, the packets is
* is against sacked "cnt", otherwise it's against facked "cnt"
*/
@@ -2525,30 +2568,7 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit)
tcp_mark_head_lost(sk, sacked_upto);
}
- /* 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.
- */
- if (tcp_is_fack(tp) && tcp_head_timedout(sk)) {
- struct sk_buff *skb;
-
- skb = tp->scoreboard_skb_hint ? tp->scoreboard_skb_hint
- : 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);
- }
+ tcp_timeout_skbs(sk);
}
/* CWND moderation, preventing bursts due to too big ACKs
@@ -2813,7 +2833,7 @@ static void tcp_mtup_probe_failed(struct sock *sk)
icsk->icsk_mtup.probe_size = 0;
}
-static void tcp_mtup_probe_success(struct sock *sk, struct sk_buff *skb)
+static void tcp_mtup_probe_success(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -2841,7 +2861,7 @@ void tcp_simple_retransmit(struct sock *sk)
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- unsigned int mss = tcp_current_mss(sk, 0);
+ unsigned int mss = tcp_current_mss(sk);
u32 prior_lost = tp->lost_out;
tcp_for_write_queue(skb, sk) {
@@ -3178,7 +3198,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
- u32 end_seq;
u32 acked_pcount;
u8 sacked = scb->sacked;
@@ -3193,16 +3212,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
break;
fully_acked = 0;
- end_seq = tp->snd_una;
} else {
acked_pcount = tcp_skb_pcount(skb);
- end_seq = scb->end_seq;
- }
-
- /* MTU probing checks */
- if (fully_acked && icsk->icsk_mtup.probe_size &&
- !after(tp->mtu_probe.probe_seq_end, scb->end_seq)) {
- tcp_mtup_probe_success(sk, skb);
}
if (sacked & TCPCB_RETRANS) {
@@ -3267,24 +3278,26 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
const struct tcp_congestion_ops *ca_ops
= inet_csk(sk)->icsk_ca_ops;
+ if (unlikely(icsk->icsk_mtup.probe_size &&
+ !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) {
+ tcp_mtup_probe_success(sk);
+ }
+
tcp_ack_update_rtt(sk, flag, seq_rtt);
tcp_rearm_rto(sk);
if (tcp_is_reno(tp)) {
tcp_remove_reno_sacks(sk, pkts_acked);
} else {
+ int delta;
+
/* Non-retransmitted hole got filled? That's reordering */
if (reord < prior_fackets)
tcp_update_reordering(sk, tp->fackets_out - reord, 0);
- /* No need to care for underflows here because
- * the lost_skb_hint gets NULLed if we're past it
- * (or something non-trivial happened)
- */
- if (tcp_is_fack(tp))
- tp->lost_cnt_hint -= pkts_acked;
- else
- tp->lost_cnt_hint -= prior_sacked - tp->sacked_out;
+ delta = tcp_is_fack(tp) ? pkts_acked :
+ prior_sacked - tp->sacked_out;
+ tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
}
tp->fackets_out -= min(pkts_acked, tp->fackets_out);
@@ -3396,7 +3409,7 @@ static int tcp_ack_update_window(struct sock *sk, struct sk_buff *skb, u32 ack,
if (tcp_may_update_window(tp, ack, ack_seq, nwin)) {
flag |= FLAG_WIN_UPDATE;
- tcp_update_wl(tp, ack, ack_seq);
+ tcp_update_wl(tp, ack_seq);
if (tp->snd_wnd != nwin) {
tp->snd_wnd = nwin;
@@ -3572,15 +3585,18 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
int prior_packets;
int frto_cwnd = 0;
- /* If the ack is newer than sent or older than previous acks
+ /* If the ack is older than previous acks
* then we can probably ignore it.
*/
- if (after(ack, tp->snd_nxt))
- goto uninteresting_ack;
-
if (before(ack, prior_snd_una))
goto old_ack;
+ /* If the ack includes data we haven't sent yet, discard
+ * this segment (RFC793 Section 3.9).
+ */
+ if (after(ack, tp->snd_nxt))
+ goto invalid_ack;
+
if (after(ack, prior_snd_una))
flag |= FLAG_SND_UNA_ADVANCED;
@@ -3601,7 +3617,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
* No more checks are required.
* Note, we use the fact that SND.UNA>=SND.WL2.
*/
- tcp_update_wl(tp, ack, ack_seq);
+ tcp_update_wl(tp, ack_seq);
tp->snd_una = ack;
flag |= FLAG_WIN_UPDATE;
@@ -3670,6 +3686,10 @@ no_queue:
tcp_ack_probe(sk);
return 1;
+invalid_ack:
+ SOCK_DEBUG(sk, "Ack %u after %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
+ return -1;
+
old_ack:
if (TCP_SKB_CB(skb)->sacked) {
tcp_sacktag_write_queue(sk, skb, prior_snd_una);
@@ -3677,8 +3697,7 @@ old_ack:
tcp_try_keep_open(sk);
}
-uninteresting_ack:
- SOCK_DEBUG(sk, "Ack %u out of %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
+ SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
return 0;
}
@@ -3866,8 +3885,7 @@ static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
* Not only, also it occurs for expired timestamps.
*/
- if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) >= 0 ||
- get_seconds() >= tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS)
+ if (tcp_paws_check(&tp->rx_opt, 0))
tcp_store_ts_recent(tp);
}
}
@@ -3919,9 +3937,9 @@ static inline int tcp_paws_discard(const struct sock *sk,
const struct sk_buff *skb)
{
const struct tcp_sock *tp = tcp_sk(sk);
- return ((s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) > TCP_PAWS_WINDOW &&
- get_seconds() < tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS &&
- !tcp_disordered_ack(sk, skb));
+
+ return !tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW) &&
+ !tcp_disordered_ack(sk, skb);
}
/* Check segment sequence number for validity.
@@ -4079,7 +4097,6 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
tp->rx_opt.dsack = 1;
tp->duplicate_sack[0].start_seq = seq;
tp->duplicate_sack[0].end_seq = end_seq;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks + 1;
}
}
@@ -4134,8 +4151,6 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
* Decrease num_sacks.
*/
tp->rx_opt.num_sacks--;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks +
- tp->rx_opt.dsack;
for (i = this_sack; i < tp->rx_opt.num_sacks; i++)
sp[i] = sp[i + 1];
continue;
@@ -4144,20 +4159,6 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
}
}
-static inline void tcp_sack_swap(struct tcp_sack_block *sack1,
- struct tcp_sack_block *sack2)
-{
- __u32 tmp;
-
- tmp = sack1->start_seq;
- sack1->start_seq = sack2->start_seq;
- sack2->start_seq = tmp;
-
- tmp = sack1->end_seq;
- sack1->end_seq = sack2->end_seq;
- sack2->end_seq = tmp;
-}
-
static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -4172,7 +4173,7 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
if (tcp_sack_extend(sp, seq, end_seq)) {
/* Rotate this_sack to the first one. */
for (; this_sack > 0; this_sack--, sp--)
- tcp_sack_swap(sp, sp - 1);
+ swap(*sp, *(sp - 1));
if (cur_sacks > 1)
tcp_sack_maybe_coalesce(tp);
return;
@@ -4198,7 +4199,6 @@ new_sack:
sp->start_seq = seq;
sp->end_seq = end_seq;
tp->rx_opt.num_sacks++;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
}
/* RCV.NXT advances, some SACKs should be eaten. */
@@ -4212,7 +4212,6 @@ static void tcp_sack_remove(struct tcp_sock *tp)
/* Empty ofo queue, hence, all the SACKs are eaten. Clear. */
if (skb_queue_empty(&tp->out_of_order_queue)) {
tp->rx_opt.num_sacks = 0;
- tp->rx_opt.eff_sacks = tp->rx_opt.dsack;
return;
}
@@ -4233,11 +4232,7 @@ static void tcp_sack_remove(struct tcp_sock *tp)
this_sack++;
sp++;
}
- if (num_sacks != tp->rx_opt.num_sacks) {
- tp->rx_opt.num_sacks = num_sacks;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks +
- tp->rx_opt.dsack;
- }
+ tp->rx_opt.num_sacks = num_sacks;
}
/* This one checks to see if we can put data from the
@@ -4313,10 +4308,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
TCP_ECN_accept_cwr(tp, skb);
- if (tp->rx_opt.dsack) {
- tp->rx_opt.dsack = 0;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks;
- }
+ tp->rx_opt.dsack = 0;
/* Queue data for delivery to the user.
* Packets in sequence go to the receive queue.
@@ -4435,8 +4427,6 @@ drop:
/* Initial out of order segment, build 1 SACK. */
if (tcp_is_sack(tp)) {
tp->rx_opt.num_sacks = 1;
- tp->rx_opt.dsack = 0;
- tp->rx_opt.eff_sacks = 1;
tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq;
tp->selective_acks[0].end_seq =
TCP_SKB_CB(skb)->end_seq;
@@ -5157,7 +5147,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
*/
if ((tcp_flag_word(th) & TCP_HP_BITS) == tp->pred_flags &&
- TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
+ TCP_SKB_CB(skb)->seq == tp->rcv_nxt &&
+ !after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
int tcp_header_len = tp->tcp_header_len;
/* Timestamp header prediction: tcp_header_len
@@ -5310,8 +5301,8 @@ slow_path:
return -res;
step5:
- if (th->ack)
- tcp_ack(sk, skb, FLAG_SLOWPATH);
+ if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0)
+ goto discard;
tcp_rcv_rtt_measure_ts(sk, skb);
@@ -5409,7 +5400,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
* never scaled.
*/
tp->snd_wnd = ntohs(th->window);
- tcp_init_wl(tp, TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(skb)->seq);
+ tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
if (!tp->rx_opt.wscale_ok) {
tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0;
@@ -5510,7 +5501,7 @@ discard:
/* PAWS check. */
if (tp->rx_opt.ts_recent_stamp && tp->rx_opt.saw_tstamp &&
- tcp_paws_check(&tp->rx_opt, 0))
+ tcp_paws_reject(&tp->rx_opt, 0))
goto discard_and_undo;
if (th->syn) {
@@ -5648,7 +5639,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
/* step 5: check the ACK field */
if (th->ack) {
- int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH);
+ int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0;
switch (sk->sk_state) {
case TCP_SYN_RECV:
@@ -5670,8 +5661,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
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)->ack_seq,
- TCP_SKB_CB(skb)->seq);
+ tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
/* tcp_ack considers this ACK as duplicate
* and does not calculate rtt.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cf74c416831..5d427f86b41 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1226,27 +1226,19 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
- if (tmp_opt.saw_tstamp && !tmp_opt.rcv_tsval) {
- /* Some OSes (unknown ones, but I see them on web server, which
- * contains information interesting only for windows'
- * users) do not send their stamp in SYN. It is easy case.
- * We simply do not advertise TS support.
- */
- tmp_opt.saw_tstamp = 0;
- tmp_opt.tstamp_ok = 0;
- }
tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
tcp_openreq_init(req, &tmp_opt, skb);
- if (security_inet_conn_request(sk, skb, req))
- goto drop_and_free;
-
ireq = inet_rsk(req);
ireq->loc_addr = daddr;
ireq->rmt_addr = saddr;
ireq->no_srccheck = inet_sk(sk)->transparent;
ireq->opt = tcp_v4_save_options(sk, skb);
+
+ if (security_inet_conn_request(sk, skb, req))
+ goto drop_and_free;
+
if (!want_cookie)
TCP_ECN_create_request(req, tcp_hdr(skb));
@@ -2355,7 +2347,7 @@ struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
- if (!tcp_v4_check(skb->len, iph->saddr, iph->daddr,
+ if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
skb->csum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index f67effbb102..43bbba7926e 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -107,7 +107,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
tmp_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
- paws_reject = tcp_paws_check(&tmp_opt, th->rst);
+ paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
}
}
@@ -399,7 +399,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
tcp_prequeue_init(newtp);
- tcp_init_wl(newtp, treq->snt_isn, treq->rcv_isn);
+ tcp_init_wl(newtp, treq->rcv_isn);
newtp->srtt = 0;
newtp->mdev = TCP_TIMEOUT_INIT;
@@ -434,9 +434,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->rx_opt.saw_tstamp = 0;
newtp->rx_opt.dsack = 0;
- newtp->rx_opt.eff_sacks = 0;
-
newtp->rx_opt.num_sacks = 0;
+
newtp->urg_data = 0;
if (sock_flag(newsk, SOCK_KEEPOPEN))
@@ -512,7 +511,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
* from another data.
*/
tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->retrans);
- paws_reject = tcp_paws_check(&tmp_opt, th->rst);
+ paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
}
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index da2c3b8794f..c1f259d2d33 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -441,10 +441,7 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
*ptr++ = htonl(sp[this_sack].end_seq);
}
- if (tp->rx_opt.dsack) {
- tp->rx_opt.dsack = 0;
- tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks;
- }
+ tp->rx_opt.dsack = 0;
}
}
@@ -550,6 +547,7 @@ static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb,
struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL;
struct tcp_sock *tp = tcp_sk(sk);
unsigned size = 0;
+ unsigned int eff_sacks;
#ifdef CONFIG_TCP_MD5SIG
*md5 = tp->af_specific->md5_lookup(sk, sk);
@@ -568,10 +566,11 @@ static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb,
size += TCPOLEN_TSTAMP_ALIGNED;
}
- if (unlikely(tp->rx_opt.eff_sacks)) {
+ eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
+ if (unlikely(eff_sacks)) {
const unsigned remaining = MAX_TCP_OPTION_SPACE - size;
opts->num_sack_blocks =
- min_t(unsigned, tp->rx_opt.eff_sacks,
+ min_t(unsigned, eff_sacks,
(remaining - TCPOLEN_SACK_BASE_ALIGNED) /
TCPOLEN_SACK_PERBLOCK);
size += TCPOLEN_SACK_BASE_ALIGNED +
@@ -663,10 +662,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
th->urg_ptr = 0;
/* The urg_mode check is necessary during a below snd_una win probe */
- if (unlikely(tcp_urg_mode(tp) &&
- between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF))) {
- th->urg_ptr = htons(tp->snd_up - tcb->seq);
- th->urg = 1;
+ if (unlikely(tcp_urg_mode(tp) && before(tcb->seq, tp->snd_up))) {
+ if (before(tp->snd_up, tcb->seq + 0x10000)) {
+ th->urg_ptr = htons(tp->snd_up - tcb->seq);
+ th->urg = 1;
+ } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {
+ th->urg_ptr = 0xFFFF;
+ th->urg = 1;
+ }
}
tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
@@ -763,11 +766,10 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
struct sk_buff *buff;
int nsize, old_factor;
int nlen;
- u16 flags;
+ u8 flags;
BUG_ON(len > skb->len);
- tcp_clear_retrans_hints_partial(tp);
nsize = skb_headlen(skb) - len;
if (nsize < 0)
nsize = 0;
@@ -850,6 +852,12 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
tcp_verify_left_out(tp);
}
tcp_adjust_fackets_out(sk, skb, diff);
+
+ if (tp->lost_skb_hint &&
+ before(TCP_SKB_CB(skb)->seq,
+ TCP_SKB_CB(tp->lost_skb_hint)->seq) &&
+ (tcp_is_fack(tp) || TCP_SKB_CB(skb)->sacked))
+ tp->lost_cnt_hint -= diff;
}
/* Link BUFF into the send queue. */
@@ -913,7 +921,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
* factor and mss.
*/
if (tcp_skb_pcount(skb) > 1)
- tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk, 1));
+ tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk));
return 0;
}
@@ -974,15 +982,6 @@ void tcp_mtup_init(struct sock *sk)
icsk->icsk_mtup.probe_size = 0;
}
-/* Bound MSS / TSO packet size with the half of the window */
-static int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
-{
- if (tp->max_window && pktsize > (tp->max_window >> 1))
- return max(tp->max_window >> 1, 68U - tp->tcp_header_len);
- else
- return pktsize;
-}
-
/* This function synchronize snd mss to current pmtu/exthdr set.
tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts
@@ -1029,22 +1028,17 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
/* Compute the current effective MSS, taking SACKs and IP options,
* and even PMTU discovery events into account.
*/
-unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
+unsigned int tcp_current_mss(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
u32 mss_now;
- u16 xmit_size_goal;
- int doing_tso = 0;
unsigned header_len;
struct tcp_out_options opts;
struct tcp_md5sig_key *md5;
mss_now = tp->mss_cache;
- if (large_allowed && sk_can_gso(sk))
- doing_tso = 1;
-
if (dst) {
u32 mtu = dst_mtu(dst);
if (mtu != inet_csk(sk)->icsk_pmtu_cookie)
@@ -1062,19 +1056,6 @@ unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
mss_now -= delta;
}
- xmit_size_goal = mss_now;
-
- if (doing_tso) {
- xmit_size_goal = ((sk->sk_gso_max_size - 1) -
- inet_csk(sk)->icsk_af_ops->net_header_len -
- inet_csk(sk)->icsk_ext_hdr_len -
- tp->tcp_header_len);
-
- xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
- xmit_size_goal -= (xmit_size_goal % mss_now);
- }
- tp->xmit_size_goal = xmit_size_goal;
-
return mss_now;
}
@@ -1256,7 +1237,7 @@ int tcp_may_send_now(struct sock *sk)
struct sk_buff *skb = tcp_send_head(sk);
return (skb &&
- tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
+ tcp_snd_test(sk, skb, tcp_current_mss(sk),
(tcp_skb_is_last(sk, skb) ?
tp->nonagle : TCP_NAGLE_PUSH)));
}
@@ -1273,7 +1254,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
{
struct sk_buff *buff;
int nlen = skb->len - len;
- u16 flags;
+ u8 flags;
/* All of a TSO frame must be composed of paged data. */
if (skb->len != skb->data_len)
@@ -1352,6 +1333,10 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
if (limit >= sk->sk_gso_max_size)
goto send_now;
+ /* Middle in queue won't get any more data, full sendable already? */
+ if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
+ goto send_now;
+
if (sysctl_tcp_tso_win_divisor) {
u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
@@ -1405,11 +1390,11 @@ static int tcp_mtu_probe(struct sock *sk)
icsk->icsk_mtup.probe_size ||
inet_csk(sk)->icsk_ca_state != TCP_CA_Open ||
tp->snd_cwnd < 11 ||
- tp->rx_opt.eff_sacks)
+ tp->rx_opt.num_sacks || tp->rx_opt.dsack)
return -1;
/* Very simple search strategy: just double the MSS. */
- mss_now = tcp_current_mss(sk, 0);
+ mss_now = tcp_current_mss(sk);
probe_size = 2 * tp->mss_cache;
size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) {
@@ -1754,11 +1739,9 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *next_skb = tcp_write_queue_next(sk, skb);
int skb_size, next_skb_size;
- u16 flags;
skb_size = skb->len;
next_skb_size = next_skb->len;
- flags = TCP_SKB_CB(skb)->flags;
BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1);
@@ -1778,9 +1761,8 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
/* Update sequence range on original skb. */
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq;
- /* Merge over control information. */
- flags |= TCP_SKB_CB(next_skb)->flags; /* This moves PSH/FIN etc. over */
- TCP_SKB_CB(skb)->flags = flags;
+ /* Merge over control information. This moves PSH/FIN etc. over */
+ TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(next_skb)->flags;
/* All done, get rid of second SKB and account for it so
* packet counting does not break.
@@ -1894,7 +1876,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
return -EHOSTUNREACH; /* Routing failure or similar. */
- cur_mss = tcp_current_mss(sk, 0);
+ cur_mss = tcp_current_mss(sk);
/* If receiver has shrunk his window, and skb is out of
* new window, do not retransmit it. The exception is the
@@ -1908,6 +1890,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
if (skb->len > cur_mss) {
if (tcp_fragment(sk, skb, cur_mss, cur_mss))
return -ENOMEM; /* We'll try again later. */
+ } else {
+ tcp_init_tso_segs(sk, skb, cur_mss);
}
tcp_retrans_try_collapse(sk, skb, cur_mss);
@@ -2061,7 +2045,7 @@ begin_fwd:
goto begin_fwd;
} else if (!(sacked & TCPCB_LOST)) {
- if (hole == NULL && !(sacked & TCPCB_SACKED_RETRANS))
+ if (hole == NULL && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED)))
hole = skb;
continue;
@@ -2100,7 +2084,7 @@ void tcp_send_fin(struct sock *sk)
* unsent frames. But be careful about outgoing SACKS
* and IP options.
*/
- mss_now = tcp_current_mss(sk, 1);
+ mss_now = tcp_current_mss(sk);
if (tcp_send_head(sk) != NULL) {
TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_FIN;
@@ -2325,7 +2309,7 @@ static void tcp_connect_init(struct sock *sk)
sk->sk_err = 0;
sock_reset_flag(sk, SOCK_DONE);
tp->snd_wnd = 0;
- tcp_init_wl(tp, tp->write_seq, 0);
+ tcp_init_wl(tp, 0);
tp->snd_una = tp->write_seq;
tp->snd_sml = tp->write_seq;
tp->snd_up = tp->write_seq;
@@ -2512,7 +2496,7 @@ int tcp_write_wakeup(struct sock *sk)
if ((skb = tcp_send_head(sk)) != NULL &&
before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) {
int err;
- unsigned int mss = tcp_current_mss(sk, 0);
+ unsigned int mss = tcp_current_mss(sk);
unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq))
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 25524d4e372..59f5b5e7c56 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -165,9 +165,10 @@ static int tcpprobe_sprint(char *tbuf, int n)
static ssize_t tcpprobe_read(struct file *file, char __user *buf,
size_t len, loff_t *ppos)
{
- int error = 0, cnt = 0;
+ int error = 0;
+ size_t cnt = 0;
- if (!buf || len < 0)
+ if (!buf)
return -EINVAL;
while (cnt < len) {
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 4660b088a8c..a76513779e2 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -24,14 +24,8 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
if (tp->snd_cwnd <= tp->snd_ssthresh)
tcp_slow_start(tp);
- else {
- tp->snd_cwnd_cnt++;
- if (tp->snd_cwnd_cnt > min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT)){
- if (tp->snd_cwnd < tp->snd_cwnd_clamp)
- tp->snd_cwnd++;
- tp->snd_cwnd_cnt = 0;
- }
- }
+ else
+ tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT));
}
static u32 tcp_scalable_ssthresh(struct sock *sk)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 0170e914f1b..b144a26359b 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -328,19 +328,16 @@ static void tcp_retransmit_timer(struct sock *sk)
if (icsk->icsk_retransmits == 0) {
int mib_idx;
- if (icsk->icsk_ca_state == TCP_CA_Disorder ||
- icsk->icsk_ca_state == TCP_CA_Recovery) {
- if (tcp_is_sack(tp)) {
- if (icsk->icsk_ca_state == TCP_CA_Recovery)
- mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL;
- else
- mib_idx = LINUX_MIB_TCPSACKFAILURES;
- } else {
- if (icsk->icsk_ca_state == TCP_CA_Recovery)
- mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL;
- else
- mib_idx = LINUX_MIB_TCPRENOFAILURES;
- }
+ if (icsk->icsk_ca_state == TCP_CA_Disorder) {
+ if (tcp_is_sack(tp))
+ mib_idx = LINUX_MIB_TCPSACKFAILURES;
+ else
+ mib_idx = LINUX_MIB_TCPRENOFAILURES;
+ } else if (icsk->icsk_ca_state == TCP_CA_Recovery) {
+ if (tcp_is_sack(tp))
+ mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL;
+ else
+ mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL;
} else if (icsk->icsk_ca_state == TCP_CA_Loss) {
mib_idx = LINUX_MIB_TCPLOSSFAILURES;
} else {
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index d08b2e855c2..e9bbff74648 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -159,12 +159,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
/* In the "non-congestive state", increase cwnd
* every rtt.
*/
- if (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
- if (tp->snd_cwnd < tp->snd_cwnd_clamp)
- tp->snd_cwnd++;
- tp->snd_cwnd_cnt = 0;
- } else
- tp->snd_cwnd_cnt++;
+ tcp_cong_avoid_ai(tp, tp->snd_cwnd);
} else {
/* In the "congestive state", increase cwnd
* every other rtt.
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 9ec843a9bbb..66b6821b984 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -94,14 +94,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
} else {
/* Reno */
-
- if (tp->snd_cwnd_cnt < tp->snd_cwnd)
- tp->snd_cwnd_cnt++;
-
- if (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
- tp->snd_cwnd++;
- tp->snd_cwnd_cnt = 0;
- }
+ tcp_cong_avoid_ai(tp, tp->snd_cwnd);
}
/* The key players are v_vegas.beg_snd_una and v_beg_snd_nxt.
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c47c989cb1f..bda08a09357 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -222,7 +222,7 @@ fail:
return error;
}
-static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
+int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
{
struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
@@ -596,6 +596,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
return -EOPNOTSUPP;
ipc.opt = NULL;
+ ipc.shtx.flags = 0;
if (up->pending) {
/*
@@ -643,6 +644,9 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.addr = inet->saddr;
ipc.oif = sk->sk_bound_dev_if;
+ err = sock_tx_timestamp(msg, sk, &ipc.shtx);
+ if (err)
+ return err;
if (msg->msg_controllen) {
err = ip_cmsg_send(sock_net(sk), msg, &ipc);
if (err)
@@ -1180,7 +1184,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
sk = sknext;
} while (sknext);
} else
- kfree_skb(skb);
+ consume_skb(skb);
spin_unlock(&hslot->lock);
return 0;
}
@@ -1614,7 +1618,8 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
} while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family));
if (!sk) {
- spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
+ if (state->bucket < UDP_HTABLE_SIZE)
+ spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
return udp_get_first(seq, state->bucket + 1);
}
return sk;
@@ -1632,6 +1637,9 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos)
static void *udp_seq_start(struct seq_file *seq, loff_t *pos)
{
+ struct udp_iter_state *state = seq->private;
+ state->bucket = UDP_HTABLE_SIZE;
+
return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
}
@@ -1815,6 +1823,7 @@ EXPORT_SYMBOL(udp_lib_getsockopt);
EXPORT_SYMBOL(udp_lib_setsockopt);
EXPORT_SYMBOL(udp_poll);
EXPORT_SYMBOL(udp_lib_get_port);
+EXPORT_SYMBOL(ipv4_rcv_saddr_equal);
#ifdef CONFIG_PROC_FS
EXPORT_SYMBOL(udp_proc_register);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 2ad24ba31f9..60d918c96a4 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -241,7 +241,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
static struct dst_ops xfrm4_dst_ops = {
.family = AF_INET,
- .protocol = __constant_htons(ETH_P_IP),
+ .protocol = cpu_to_be16(ETH_P_IP),
.gc = xfrm4_garbage_collect,
.update_pmtu = xfrm4_update_pmtu,
.destroy = xfrm4_dst_destroy,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1220e2c7831..a8218bc1806 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -40,6 +40,7 @@
#include <linux/errno.h>
#include <linux/types.h>
+#include <linux/kernel.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
@@ -590,6 +591,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
{
struct inet6_ifaddr *ifa = NULL;
struct rt6_info *rt;
+ struct net *net = dev_net(idev->dev);
int hash;
int err = 0;
int addr_type = ipv6_addr_type(addr);
@@ -606,6 +608,11 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
goto out2;
}
+ if (idev->cnf.disable_ipv6 || net->ipv6.devconf_all->disable_ipv6) {
+ err = -EACCES;
+ goto out2;
+ }
+
write_lock(&addrconf_hash_lock);
/* Ignore adding duplicate addresses on an interface */
@@ -1209,16 +1216,12 @@ int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev,
}
break;
} else if (minihiscore < miniscore) {
- struct ipv6_saddr_score *tmp;
-
if (hiscore->ifa)
in6_ifa_put(hiscore->ifa);
in6_ifa_hold(score->ifa);
- tmp = hiscore;
- hiscore = score;
- score = tmp;
+ swap(hiscore, score);
/* restore our iterator */
score->ifa = hiscore->ifa;
@@ -1367,40 +1370,6 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
return ifp;
}
-int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
-{
- const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
- const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
- __be32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr;
- __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
- int sk_ipv6only = ipv6_only_sock(sk);
- int sk2_ipv6only = inet_v6_ipv6only(sk2);
- int addr_type = ipv6_addr_type(sk_rcv_saddr6);
- int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
-
- if (!sk2_rcv_saddr && !sk_ipv6only)
- return 1;
-
- if (addr_type2 == IPV6_ADDR_ANY &&
- !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
- return 1;
-
- if (addr_type == IPV6_ADDR_ANY &&
- !(sk_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
- return 1;
-
- if (sk2_rcv_saddr6 &&
- ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6))
- return 1;
-
- if (addr_type == IPV6_ADDR_MAPPED &&
- !sk2_ipv6only &&
- (!sk2_rcv_saddr || !sk_rcv_saddr || sk_rcv_saddr == sk2_rcv_saddr))
- return 1;
-
- return 0;
-}
-
/* Gets referenced address, destroys ifaddr */
static void addrconf_dad_stop(struct inet6_ifaddr *ifp)
@@ -1433,6 +1402,11 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp)
void addrconf_dad_failure(struct inet6_ifaddr *ifp)
{
struct inet6_dev *idev = ifp->idev;
+
+ if (net_ratelimit())
+ printk(KERN_INFO "%s: IPv6 duplicate address detected!\n",
+ ifp->idev->dev->name);
+
if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) {
struct in6_addr addr;
@@ -1443,11 +1417,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
ipv6_addr_equal(&ifp->addr, &addr)) {
/* DAD failed for link-local based on MAC address */
idev->cnf.disable_ipv6 = 1;
+
+ printk(KERN_INFO "%s: IPv6 being disabled!\n",
+ ifp->idev->dev->name);
}
}
- if (net_ratelimit())
- printk(KERN_INFO "%s: duplicate address detected!\n", ifp->idev->dev->name);
addrconf_dad_stop(ifp);
}
@@ -2227,10 +2202,24 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg)
return err;
}
+static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
+ int plen, int scope)
+{
+ struct inet6_ifaddr *ifp;
+
+ ifp = ipv6_add_addr(idev, addr, plen, scope, IFA_F_PERMANENT);
+ if (!IS_ERR(ifp)) {
+ spin_lock_bh(&ifp->lock);
+ ifp->flags &= ~IFA_F_TENTATIVE;
+ spin_unlock_bh(&ifp->lock);
+ ipv6_ifa_notify(RTM_NEWADDR, ifp);
+ in6_ifa_put(ifp);
+ }
+}
+
#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
static void sit_add_v4_addrs(struct inet6_dev *idev)
{
- struct inet6_ifaddr * ifp;
struct in6_addr addr;
struct net_device *dev;
struct net *net = dev_net(idev->dev);
@@ -2249,14 +2238,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
}
if (addr.s6_addr32[3]) {
- ifp = ipv6_add_addr(idev, &addr, 128, scope, IFA_F_PERMANENT);
- if (!IS_ERR(ifp)) {
- spin_lock_bh(&ifp->lock);
- ifp->flags &= ~IFA_F_TENTATIVE;
- spin_unlock_bh(&ifp->lock);
- ipv6_ifa_notify(RTM_NEWADDR, ifp);
- in6_ifa_put(ifp);
- }
+ add_addr(idev, &addr, 128, scope);
return;
}
@@ -2284,15 +2266,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
else
plen = 96;
- ifp = ipv6_add_addr(idev, &addr, plen, flag,
- IFA_F_PERMANENT);
- if (!IS_ERR(ifp)) {
- spin_lock_bh(&ifp->lock);
- ifp->flags &= ~IFA_F_TENTATIVE;
- spin_unlock_bh(&ifp->lock);
- ipv6_ifa_notify(RTM_NEWADDR, ifp);
- in6_ifa_put(ifp);
- }
+ add_addr(idev, &addr, plen, flag);
}
}
}
@@ -2302,7 +2276,6 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
static void init_loopback(struct net_device *dev)
{
struct inet6_dev *idev;
- struct inet6_ifaddr * ifp;
/* ::1 */
@@ -2313,14 +2286,7 @@ static void init_loopback(struct net_device *dev)
return;
}
- ifp = ipv6_add_addr(idev, &in6addr_loopback, 128, IFA_HOST, IFA_F_PERMANENT);
- if (!IS_ERR(ifp)) {
- spin_lock_bh(&ifp->lock);
- ifp->flags &= ~IFA_F_TENTATIVE;
- spin_unlock_bh(&ifp->lock);
- ipv6_ifa_notify(RTM_NEWADDR, ifp);
- in6_ifa_put(ifp);
- }
+ add_addr(idev, &in6addr_loopback, 128, IFA_HOST);
}
static void addrconf_add_linklocal(struct inet6_dev *idev, struct in6_addr *addr)
@@ -2832,11 +2798,6 @@ static void addrconf_dad_timer(unsigned long data)
read_unlock_bh(&idev->lock);
goto out;
}
- if (idev->cnf.accept_dad > 1 && idev->cnf.disable_ipv6) {
- read_unlock_bh(&idev->lock);
- addrconf_dad_failure(ifp);
- return;
- }
spin_lock_bh(&ifp->lock);
if (ifp->probes == 0) {
/*
@@ -3647,7 +3608,8 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa)
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
+ rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err);
@@ -3858,7 +3820,8 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev)
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
+ rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err);
@@ -3928,7 +3891,8 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev,
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC);
+ rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC);
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index da944eca2ca..61f55386a23 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -276,11 +276,26 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
/* Check if the address belongs to the host. */
if (addr_type == IPV6_ADDR_MAPPED) {
- v4addr = addr->sin6_addr.s6_addr32[3];
- if (inet_addr_type(net, v4addr) != RTN_LOCAL) {
- err = -EADDRNOTAVAIL;
+ int chk_addr_ret;
+
+ /* Binding to v4-mapped address on a v6-only socket
+ * makes no sense
+ */
+ if (np->ipv6only) {
+ err = -EINVAL;
goto out;
}
+
+ /* Reproduce AF_INET checks to make the bindings consitant */
+ v4addr = addr->sin6_addr.s6_addr32[3];
+ chk_addr_ret = inet_addr_type(net, v4addr);
+ if (!sysctl_ip_nonlocal_bind &&
+ !(inet->freebind || inet->transparent) &&
+ v4addr != htonl(INADDR_ANY) &&
+ chk_addr_ret != RTN_LOCAL &&
+ chk_addr_ret != RTN_MULTICAST &&
+ chk_addr_ret != RTN_BROADCAST)
+ goto out;
} else {
if (addr_type != IPV6_ADDR_ANY) {
struct net_device *dev = NULL;
@@ -339,8 +354,11 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
goto out;
}
- if (addr_type != IPV6_ADDR_ANY)
+ if (addr_type != IPV6_ADDR_ANY) {
sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
+ if (addr_type != IPV6_ADDR_MAPPED)
+ np->ipv6only = 1;
+ }
if (snum)
sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
inet->sport = htons(inet->num);
@@ -803,24 +821,34 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
int proto;
__wsum csum;
- if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
+ iph = skb_gro_header(skb, sizeof(*iph));
+ if (unlikely(!iph))
goto out;
- iph = ipv6_hdr(skb);
- __skb_pull(skb, sizeof(*iph));
+ skb_gro_pull(skb, sizeof(*iph));
+ skb_set_transport_header(skb, skb_gro_offset(skb));
- flush += ntohs(iph->payload_len) != skb->len;
+ flush += ntohs(iph->payload_len) != skb_gro_len(skb);
rcu_read_lock();
- proto = ipv6_gso_pull_exthdrs(skb, iph->nexthdr);
- iph = ipv6_hdr(skb);
- IPV6_GRO_CB(skb)->proto = proto;
+ proto = iph->nexthdr;
ops = rcu_dereference(inet6_protos[proto]);
- if (!ops || !ops->gro_receive)
- goto out_unlock;
+ if (!ops || !ops->gro_receive) {
+ __pskb_pull(skb, skb_gro_offset(skb));
+ proto = ipv6_gso_pull_exthdrs(skb, proto);
+ skb_gro_pull(skb, -skb_transport_offset(skb));
+ skb_reset_transport_header(skb);
+ __skb_push(skb, skb_gro_offset(skb));
+
+ if (!ops || !ops->gro_receive)
+ goto out_unlock;
+
+ iph = ipv6_hdr(skb);
+ }
+
+ IPV6_GRO_CB(skb)->proto = proto;
flush--;
- skb_reset_transport_header(skb);
nlen = skb_network_header_len(skb);
for (p = *head; p; p = p->next) {
@@ -883,8 +911,8 @@ out_unlock:
return err;
}
-static struct packet_type ipv6_packet_type = {
- .type = __constant_htons(ETH_P_IPV6),
+static struct packet_type ipv6_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_IPV6),
.func = ipv6_rcv,
.gso_send_check = ipv6_gso_send_check,
.gso_segment = ipv6_gso_segment,
@@ -1192,6 +1220,9 @@ module_init(inet6_init);
static void __exit inet6_exit(void)
{
+ if (disable_ipv6)
+ return;
+
/* First of all disallow new sockets creation. */
sock_unregister(PF_INET6);
/* Disallow any further netlink messages */
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index f171e8dbac9..8f04bd9da27 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -75,8 +75,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
!idev || unlikely(idev->cnf.disable_ipv6)) {
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS);
- rcu_read_unlock();
- goto out;
+ goto drop;
}
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
@@ -147,7 +146,6 @@ err:
drop:
rcu_read_unlock();
kfree_skb(skb);
-out:
return 0;
}
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 40f324655e2..d31df0f4bc9 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -218,8 +218,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
pktopt = xchg(&np->pktoptions, NULL);
- if (pktopt)
- kfree_skb(pktopt);
+ kfree_skb(pktopt);
sk->sk_destruct = inet_sock_destruct;
/*
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 3e2970841bd..9f061d1adbc 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1095,11 +1095,7 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt)
&ipv6_hdr(ra)->saddr);
nlmsg_end(skb, nlh);
- err = rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL,
- GFP_ATOMIC);
- if (err < 0)
- goto errout;
-
+ rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL, GFP_ATOMIC);
return;
nla_put_failure:
@@ -1538,13 +1534,10 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
if (rt->rt6i_flags & RTF_GATEWAY) {
ND_PRINTK2(KERN_WARNING
"ICMPv6 Redirect: destination is not a neighbour.\n");
- dst_release(dst);
- return;
- }
- if (!xrlim_allow(dst, 1*HZ)) {
- dst_release(dst);
- return;
+ goto release;
}
+ if (!xrlim_allow(dst, 1*HZ))
+ goto release;
if (dev->addr_len) {
read_lock_bh(&neigh->lock);
@@ -1570,8 +1563,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
ND_PRINTK0(KERN_ERR
"ICMPv6 Redirect: %s() failed to allocate an skb.\n",
__func__);
- dst_release(dst);
- return;
+ goto release;
}
skb_reserve(buff, LL_RESERVED_SPACE(dev));
@@ -1631,6 +1623,10 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
if (likely(idev != NULL))
in6_dev_put(idev);
+ return;
+
+release:
+ dst_release(dst);
}
static void pndisc_redo(struct sk_buff *skb)
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 53ea512c460..29d643bcafa 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -95,13 +95,13 @@ config IP6_NF_MATCH_OPTS
To compile it as a module, choose M here. If unsure, say N.
config IP6_NF_MATCH_HL
- tristate '"hl" match support'
+ tristate '"hl" hoplimit match support'
depends on NETFILTER_ADVANCED
- help
- HL matching allows you to match packets based on the hop
- limit of the packet.
-
- To compile it as a module, choose M here. If unsure, say N.
+ select NETFILTER_XT_MATCH_HL
+ ---help---
+ This is a backwards-compat option for the user's convenience
+ (e.g. when running oldconfig). It selects
+ CONFIG_NETFILTER_XT_MATCH_HL.
config IP6_NF_MATCH_IPV6HEADER
tristate '"ipv6header" IPv6 Extension Headers Match'
@@ -130,6 +130,15 @@ config IP6_NF_MATCH_RT
To compile it as a module, choose M here. If unsure, say N.
# The targets
+config IP6_NF_TARGET_HL
+ tristate '"HL" hoplimit target support'
+ depends on NETFILTER_ADVANCED
+ select NETFILTER_XT_TARGET_HL
+ ---help---
+ This is a backwards-compat option for the user's convenience
+ (e.g. when running oldconfig). It selects
+ CONFIG_NETFILTER_XT_TARGET_HL.
+
config IP6_NF_TARGET_LOG
tristate "LOG target support"
default m if NETFILTER_ADVANCED=n
@@ -170,23 +179,6 @@ config IP6_NF_MANGLE
To compile it as a module, choose M here. If unsure, say N.
-config IP6_NF_TARGET_HL
- tristate 'HL (hoplimit) target support'
- depends on IP6_NF_MANGLE
- depends on NETFILTER_ADVANCED
- help
- This option adds a `HL' target, which enables the user to decrement
- the hoplimit value of the IPv6 header or set it to a given (lower)
- value.
-
- While it is safe to decrement the hoplimit value, this option also
- enables functionality to increment and set the hoplimit value of the
- IPv6 header to arbitrary values. This is EXTREMELY DANGEROUS since
- you can easily create immortal packets that loop forever on the
- network.
-
- To compile it as a module, choose M here. If unsure, say N.
-
config IP6_NF_RAW
tristate 'raw table support (required for TRACE)'
depends on NETFILTER_ADVANCED
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 3f17c948eef..aafbba30c89 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -20,13 +20,11 @@ obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o
obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o
obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o
-obj-$(CONFIG_IP6_NF_MATCH_HL) += ip6t_hl.o
obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o
obj-$(CONFIG_IP6_NF_MATCH_MH) += ip6t_mh.o
obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o
obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o
# targets
-obj-$(CONFIG_IP6_NF_TARGET_HL) += ip6t_HL.o
obj-$(CONFIG_IP6_NF_TARGET_LOG) += ip6t_LOG.o
obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o
diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c
index 5859c046cbc..b693f841aeb 100644
--- a/net/ipv6/netfilter/ip6_queue.c
+++ b/net/ipv6/netfilter/ip6_queue.c
@@ -643,6 +643,7 @@ static void __exit ip6_queue_fini(void)
MODULE_DESCRIPTION("IPv6 packet queue handler");
MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_IP6_FW);
module_init(ip6_queue_init);
module_exit(ip6_queue_fini);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index a33485dc81c..e89cfa3a8f2 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -99,7 +99,6 @@ ip6_packet_match(const struct sk_buff *skb,
unsigned int *protoff,
int *fragoff, bool *hotdrop)
{
- size_t i;
unsigned long ret;
const struct ipv6hdr *ipv6 = ipv6_hdr(skb);
@@ -120,12 +119,7 @@ ip6_packet_match(const struct sk_buff *skb,
return false;
}
- /* Look for ifname matches; this should unroll nicely. */
- for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
- ret |= (((const unsigned long *)indev)[i]
- ^ ((const unsigned long *)ip6info->iniface)[i])
- & ((const unsigned long *)ip6info->iniface_mask)[i];
- }
+ ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask);
if (FWINV(ret != 0, IP6T_INV_VIA_IN)) {
dprintf("VIA in mismatch (%s vs %s).%s\n",
@@ -134,11 +128,7 @@ ip6_packet_match(const struct sk_buff *skb,
return false;
}
- for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
- ret |= (((const unsigned long *)outdev)[i]
- ^ ((const unsigned long *)ip6info->outiface)[i])
- & ((const unsigned long *)ip6info->outiface_mask)[i];
- }
+ ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask);
if (FWINV(ret != 0, IP6T_INV_VIA_OUT)) {
dprintf("VIA out mismatch (%s vs %s).%s\n",
@@ -373,10 +363,12 @@ ip6t_do_table(struct sk_buff *skb,
mtpar.family = tgpar.family = NFPROTO_IPV6;
tgpar.hooknum = hook;
- read_lock_bh(&table->lock);
IP_NF_ASSERT(table->valid_hooks & (1 << hook));
- private = table->private;
- table_base = (void *)private->entries[smp_processor_id()];
+
+ rcu_read_lock();
+ private = rcu_dereference(table->private);
+ table_base = rcu_dereference(private->entries[smp_processor_id()]);
+
e = get_entry(table_base, private->hook_entry[hook]);
/* For return from builtin chain */
@@ -474,7 +466,7 @@ ip6t_do_table(struct sk_buff *skb,
#ifdef CONFIG_NETFILTER_DEBUG
((struct ip6t_entry *)table_base)->comefrom = NETFILTER_LINK_POISON;
#endif
- read_unlock_bh(&table->lock);
+ rcu_read_unlock();
#ifdef DEBUG_ALLOW_ALL
return NF_ACCEPT;
@@ -525,7 +517,9 @@ mark_source_chains(struct xt_table_info *newinfo,
&& unconditional(&e->ipv6)) || visited) {
unsigned int oldpos, size;
- if (t->verdict < -NF_MAX_VERDICT - 1) {
+ if ((strcmp(t->target.u.user.name,
+ IP6T_STANDARD_TARGET) == 0) &&
+ t->verdict < -NF_MAX_VERDICT - 1) {
duprintf("mark_source_chains: bad "
"negative verdict (%i)\n",
t->verdict);
@@ -955,11 +949,64 @@ get_counters(const struct xt_table_info *t,
}
}
+/* We're lazy, and add to the first CPU; overflow works its fey magic
+ * and everything is OK. */
+static int
+add_counter_to_entry(struct ip6t_entry *e,
+ const struct xt_counters addme[],
+ unsigned int *i)
+{
+ ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
+
+ (*i)++;
+ return 0;
+}
+
+/* Take values from counters and add them back onto the current cpu */
+static void put_counters(struct xt_table_info *t,
+ const struct xt_counters counters[])
+{
+ unsigned int i, cpu;
+
+ local_bh_disable();
+ cpu = smp_processor_id();
+ i = 0;
+ IP6T_ENTRY_ITERATE(t->entries[cpu],
+ t->size,
+ add_counter_to_entry,
+ counters,
+ &i);
+ local_bh_enable();
+}
+
+static inline int
+zero_entry_counter(struct ip6t_entry *e, void *arg)
+{
+ e->counters.bcnt = 0;
+ e->counters.pcnt = 0;
+ return 0;
+}
+
+static void
+clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info)
+{
+ unsigned int cpu;
+ const void *loc_cpu_entry = info->entries[raw_smp_processor_id()];
+
+ memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
+ for_each_possible_cpu(cpu) {
+ memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size);
+ IP6T_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size,
+ zero_entry_counter, NULL);
+ }
+}
+
static struct xt_counters *alloc_counters(struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ struct xt_table_info *private = table->private;
+ struct xt_table_info *info;
/* We need atomic snapshot of counters: rest doesn't change
(other than comefrom, which userspace doesn't care
@@ -968,14 +1015,28 @@ static struct xt_counters *alloc_counters(struct xt_table *table)
counters = vmalloc_node(countersize, numa_node_id());
if (counters == NULL)
- return ERR_PTR(-ENOMEM);
+ goto nomem;
- /* First, sum counters... */
- write_lock_bh(&table->lock);
- get_counters(private, counters);
- write_unlock_bh(&table->lock);
+ info = xt_alloc_table_info(private->size);
+ if (!info)
+ goto free_counters;
+
+ clone_counters(info, private);
+
+ mutex_lock(&table->lock);
+ xt_table_entry_swap_rcu(private, info);
+ synchronize_net(); /* Wait until smoke has cleared */
+
+ get_counters(info, counters);
+ put_counters(private, counters);
+ mutex_unlock(&table->lock);
- return counters;
+ xt_free_table_info(info);
+
+ free_counters:
+ vfree(counters);
+ nomem:
+ return ERR_PTR(-ENOMEM);
}
static int
@@ -1342,28 +1403,6 @@ do_replace(struct net *net, void __user *user, unsigned int len)
return ret;
}
-/* We're lazy, and add to the first CPU; overflow works its fey magic
- * and everything is OK. */
-static inline int
-add_counter_to_entry(struct ip6t_entry *e,
- const struct xt_counters addme[],
- unsigned int *i)
-{
-#if 0
- duprintf("add_counter: Entry %u %lu/%lu + %lu/%lu\n",
- *i,
- (long unsigned int)e->counters.pcnt,
- (long unsigned int)e->counters.bcnt,
- (long unsigned int)addme[*i].pcnt,
- (long unsigned int)addme[*i].bcnt);
-#endif
-
- ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
-
- (*i)++;
- return 0;
-}
-
static int
do_add_counters(struct net *net, void __user *user, unsigned int len,
int compat)
@@ -1424,13 +1463,14 @@ do_add_counters(struct net *net, void __user *user, unsigned int len,
goto free;
}
- write_lock_bh(&t->lock);
+ mutex_lock(&t->lock);
private = t->private;
if (private->number != num_counters) {
ret = -EINVAL;
goto unlock_up_free;
}
+ preempt_disable();
i = 0;
/* Choose the copy that is on our node */
loc_cpu_entry = private->entries[raw_smp_processor_id()];
@@ -1439,8 +1479,9 @@ do_add_counters(struct net *net, void __user *user, unsigned int len,
add_counter_to_entry,
paddc,
&i);
+ preempt_enable();
unlock_up_free:
- write_unlock_bh(&t->lock);
+ mutex_unlock(&t->lock);
xt_table_unlock(t);
module_put(t->me);
free:
diff --git a/net/ipv6/netfilter/ip6t_HL.c b/net/ipv6/netfilter/ip6t_HL.c
deleted file mode 100644
index 27b5adf670a..00000000000
--- a/net/ipv6/netfilter/ip6t_HL.c
+++ /dev/null
@@ -1,95 +0,0 @@
-/*
- * Hop Limit modification target for ip6tables
- * Maciej Soltysiak <solt@dns.toxicfilms.tv>
- * Based on HW's TTL module
- *
- * This software is distributed under the terms of GNU GPL
- */
-
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-
-#include <linux/netfilter/x_tables.h>
-#include <linux/netfilter_ipv6/ip6t_HL.h>
-
-MODULE_AUTHOR("Maciej Soltysiak <solt@dns.toxicfilms.tv>");
-MODULE_DESCRIPTION("Xtables: IPv6 Hop Limit field modification target");
-MODULE_LICENSE("GPL");
-
-static unsigned int
-hl_tg6(struct sk_buff *skb, const struct xt_target_param *par)
-{
- struct ipv6hdr *ip6h;
- const struct ip6t_HL_info *info = par->targinfo;
- int new_hl;
-
- if (!skb_make_writable(skb, skb->len))
- return NF_DROP;
-
- ip6h = ipv6_hdr(skb);
-
- switch (info->mode) {
- case IP6T_HL_SET:
- new_hl = info->hop_limit;
- break;
- case IP6T_HL_INC:
- new_hl = ip6h->hop_limit + info->hop_limit;
- if (new_hl > 255)
- new_hl = 255;
- break;
- case IP6T_HL_DEC:
- new_hl = ip6h->hop_limit - info->hop_limit;
- if (new_hl < 0)
- new_hl = 0;
- break;
- default:
- new_hl = ip6h->hop_limit;
- break;
- }
-
- ip6h->hop_limit = new_hl;
-
- return XT_CONTINUE;
-}
-
-static bool hl_tg6_check(const struct xt_tgchk_param *par)
-{
- const struct ip6t_HL_info *info = par->targinfo;
-
- if (info->mode > IP6T_HL_MAXMODE) {
- printk(KERN_WARNING "ip6t_HL: invalid or unknown Mode %u\n",
- info->mode);
- return false;
- }
- if (info->mode != IP6T_HL_SET && info->hop_limit == 0) {
- printk(KERN_WARNING "ip6t_HL: increment/decrement doesn't "
- "make sense with value 0\n");
- return false;
- }
- return true;
-}
-
-static struct xt_target hl_tg6_reg __read_mostly = {
- .name = "HL",
- .family = NFPROTO_IPV6,
- .target = hl_tg6,
- .targetsize = sizeof(struct ip6t_HL_info),
- .table = "mangle",
- .checkentry = hl_tg6_check,
- .me = THIS_MODULE
-};
-
-static int __init hl_tg6_init(void)
-{
- return xt_register_target(&hl_tg6_reg);
-}
-
-static void __exit hl_tg6_exit(void)
-{
- xt_unregister_target(&hl_tg6_reg);
-}
-
-module_init(hl_tg6_init);
-module_exit(hl_tg6_exit);
diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c
index 37adf5abc51..7018cac4fdd 100644
--- a/net/ipv6/netfilter/ip6t_LOG.c
+++ b/net/ipv6/netfilter/ip6t_LOG.c
@@ -477,7 +477,7 @@ static struct xt_target log_tg6_reg __read_mostly = {
.me = THIS_MODULE,
};
-static const struct nf_logger ip6t_logger = {
+static struct nf_logger ip6t_logger __read_mostly = {
.name = "ip6t_LOG",
.logfn = &ip6t_log_packet,
.me = THIS_MODULE,
diff --git a/net/ipv6/netfilter/ip6t_hl.c b/net/ipv6/netfilter/ip6t_hl.c
deleted file mode 100644
index c964dca1132..00000000000
--- a/net/ipv6/netfilter/ip6t_hl.c
+++ /dev/null
@@ -1,68 +0,0 @@
-/* Hop Limit matching module */
-
-/* (C) 2001-2002 Maciej Soltysiak <solt@dns.toxicfilms.tv>
- * Based on HW's ttl module
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/ipv6.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-
-#include <linux/netfilter_ipv6/ip6t_hl.h>
-#include <linux/netfilter/x_tables.h>
-
-MODULE_AUTHOR("Maciej Soltysiak <solt@dns.toxicfilms.tv>");
-MODULE_DESCRIPTION("Xtables: IPv6 Hop Limit field match");
-MODULE_LICENSE("GPL");
-
-static bool hl_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
-{
- const struct ip6t_hl_info *info = par->matchinfo;
- const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-
- switch (info->mode) {
- case IP6T_HL_EQ:
- return ip6h->hop_limit == info->hop_limit;
- break;
- case IP6T_HL_NE:
- return ip6h->hop_limit != info->hop_limit;
- break;
- case IP6T_HL_LT:
- return ip6h->hop_limit < info->hop_limit;
- break;
- case IP6T_HL_GT:
- return ip6h->hop_limit > info->hop_limit;
- break;
- default:
- printk(KERN_WARNING "ip6t_hl: unknown mode %d\n",
- info->mode);
- return false;
- }
-
- return false;
-}
-
-static struct xt_match hl_mt6_reg __read_mostly = {
- .name = "hl",
- .family = NFPROTO_IPV6,
- .match = hl_mt6,
- .matchsize = sizeof(struct ip6t_hl_info),
- .me = THIS_MODULE,
-};
-
-static int __init hl_mt6_init(void)
-{
- return xt_register_match(&hl_mt6_reg);
-}
-
-static void __exit hl_mt6_exit(void)
-{
- xt_unregister_match(&hl_mt6_reg);
-}
-
-module_init(hl_mt6_init);
-module_exit(hl_mt6_exit);
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index 40d2e36d8fa..ef5a0a32bf8 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -54,7 +54,6 @@ static struct
static struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(packet_filter.lock),
.me = THIS_MODULE,
.af = AF_INET6,
};
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index d0b31b259d4..ab0d398a2ba 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -60,7 +60,6 @@ static struct
static struct xt_table packet_mangler = {
.name = "mangle",
.valid_hooks = MANGLE_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(packet_mangler.lock),
.me = THIS_MODULE,
.af = AF_INET6,
};
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index 109fab6f831..4b792b6ca32 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -38,7 +38,6 @@ static struct
static struct xt_table packet_raw = {
.name = "raw",
.valid_hooks = RAW_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(packet_raw.lock),
.me = THIS_MODULE,
.af = AF_INET6,
};
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index 20bc52f13e4..0ea37ff15d5 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -59,7 +59,6 @@ static struct
static struct xt_table security_table = {
.name = "security",
.valid_hooks = SECURITY_VALID_HOOKS,
- .lock = __RW_LOCK_UNLOCKED(security_table.lock),
.me = THIS_MODULE,
.af = AF_INET6,
};
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 727b9530448..2a15c2d66c6 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -26,6 +26,7 @@
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
struct nf_conntrack_tuple *tuple)
@@ -341,6 +342,11 @@ static int ipv6_nlattr_to_tuple(struct nlattr *tb[],
return 0;
}
+
+static int ipv6_nlattr_tuple_size(void)
+{
+ return nla_policy_len(ipv6_nla_policy, CTA_IP_MAX + 1);
+}
#endif
struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = {
@@ -352,6 +358,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = {
.get_l4proto = ipv6_get_l4proto,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.tuple_to_nlattr = ipv6_tuple_to_nlattr,
+ .nlattr_tuple_size = ipv6_nlattr_tuple_size,
.nlattr_to_tuple = ipv6_nlattr_to_tuple,
.nla_policy = ipv6_nla_policy,
#endif
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 72dbb6d1a6b..9903227bf37 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -126,6 +126,10 @@ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
pr_debug("icmpv6: can't create new conn with type %u\n",
type + 128);
nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple);
+ if (LOG_INVALID(nf_ct_net(ct), IPPROTO_ICMPV6))
+ nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
+ "nf_ct_icmpv6: invalid new with type %d ",
+ type + 128);
return false;
}
atomic_set(&ct->proto.icmp.count, 0);
@@ -265,6 +269,11 @@ static int icmpv6_nlattr_to_tuple(struct nlattr *tb[],
return 0;
}
+
+static int icmpv6_nlattr_tuple_size(void)
+{
+ return nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1);
+}
#endif
#ifdef CONFIG_SYSCTL
@@ -296,6 +305,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly =
.error = icmpv6_error,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.tuple_to_nlattr = icmpv6_tuple_to_nlattr,
+ .nlattr_tuple_size = icmpv6_nlattr_tuple_size,
.nlattr_to_tuple = icmpv6_nlattr_to_tuple,
.nla_policy = icmpv6_nla_policy,
#endif
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index ed4d79a9e4a..058a5e4a60c 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -528,14 +528,14 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
if (!ipv6_ext_hdr(nexthdr)) {
return -1;
}
- if (len < (int)sizeof(struct ipv6_opt_hdr)) {
- pr_debug("too short\n");
- return -1;
- }
if (nexthdr == NEXTHDR_NONE) {
pr_debug("next header is none\n");
return -1;
}
+ if (len < (int)sizeof(struct ipv6_opt_hdr)) {
+ pr_debug("too short\n");
+ return -1;
+ }
if (skb_copy_bits(skb, start, &hdr, sizeof(hdr)))
BUG();
if (nexthdr == NEXTHDR_AUTH)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 3c575118fca..e9ac7a12f59 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -452,6 +452,7 @@ err:
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev)
{
+ struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
struct sk_buff *fp, *head = fq->q.fragments;
int payload_len;
unsigned int nhoff;
@@ -551,8 +552,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
head->csum);
rcu_read_lock();
- IP6_INC_STATS_BH(dev_net(dev),
- __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
+ IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.fragments = NULL;
return 1;
@@ -566,8 +566,7 @@ out_oom:
printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
out_fail:
rcu_read_lock();
- IP6_INC_STATS_BH(dev_net(dev),
- __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+ IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
return -1;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9c574235c90..1394ddb6e35 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -98,7 +98,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
static struct dst_ops ip6_dst_ops_template = {
.family = AF_INET6,
- .protocol = __constant_htons(ETH_P_IPV6),
+ .protocol = cpu_to_be16(ETH_P_IPV6),
.gc = ip6_dst_gc,
.gc_thresh = 1024,
.check = ip6_dst_check,
@@ -117,7 +117,7 @@ static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
static struct dst_ops ip6_dst_blackhole_ops = {
.family = AF_INET6,
- .protocol = __constant_htons(ETH_P_IPV6),
+ .protocol = cpu_to_be16(ETH_P_IPV6),
.destroy = ip6_dst_destroy,
.check = ip6_dst_check,
.update_pmtu = ip6_rt_blackhole_update_pmtu,
@@ -2400,8 +2400,9 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE,
- info->nlh, gfp_any());
+ rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE,
+ info->nlh, gfp_any());
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index d3467e563f0..664ab82e03b 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -188,9 +188,9 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
}
nt = netdev_priv(dev);
- ipip6_tunnel_init(dev);
nt->parms = *parms;
+ ipip6_tunnel_init(dev);
if (parms->i_flags & SIT_ISATAP)
dev->priv_flags |= IFF_ISATAP;
@@ -454,7 +454,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
goto out;
- if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
+ if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
t->err_count++;
else
t->err_count = 1;
@@ -658,7 +658,8 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
}
if (tunnel->err_count > 0) {
- if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
+ if (time_before(jiffies,
+ tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e5b85d45bee..4b5aa185426 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -533,8 +533,7 @@ static inline void syn_flood_warning(struct sk_buff *skb)
static void tcp_v6_reqsk_destructor(struct request_sock *req)
{
- if (inet6_rsk(req)->pktopts)
- kfree_skb(inet6_rsk(req)->pktopts);
+ kfree_skb(inet6_rsk(req)->pktopts);
}
#ifdef CONFIG_TCP_MD5SIG
@@ -948,7 +947,7 @@ struct sk_buff **tcp6_gro_receive(struct sk_buff **head, struct sk_buff *skb)
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
- if (!tcp_v6_check(skb->len, &iph->saddr, &iph->daddr,
+ if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr,
skb->csum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
@@ -1611,8 +1610,7 @@ ipv6_pktoptions:
}
}
- if (opt_skb)
- kfree_skb(opt_skb);
+ kfree_skb(opt_skb);
return 0;
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 84b1a296eec..6842dd2edd5 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -49,6 +49,34 @@
#include <linux/seq_file.h>
#include "udp_impl.h"
+int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
+{
+ const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
+ const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
+ int sk_ipv6only = ipv6_only_sock(sk);
+ int sk2_ipv6only = inet_v6_ipv6only(sk2);
+ int addr_type = ipv6_addr_type(sk_rcv_saddr6);
+ int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
+
+ /* if both are mapped, treat as IPv4 */
+ if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED)
+ return ipv4_rcv_saddr_equal(sk, sk2);
+
+ if (addr_type2 == IPV6_ADDR_ANY &&
+ !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
+ return 1;
+
+ if (addr_type == IPV6_ADDR_ANY &&
+ !(sk_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
+ return 1;
+
+ if (sk2_rcv_saddr6 &&
+ ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6))
+ return 1;
+
+ return 0;
+}
+
int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal);
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 97ab068e8cc..b4b16a43f27 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -272,7 +272,7 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
static struct dst_ops xfrm6_dst_ops = {
.family = AF_INET6,
- .protocol = __constant_htons(ETH_P_IPV6),
+ .protocol = cpu_to_be16(ETH_P_IPV6),
.gc = xfrm6_garbage_collect,
.update_pmtu = xfrm6_update_pmtu,
.destroy = xfrm6_dst_destroy,
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index 0e685b05496..f417b77fa0e 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -69,7 +69,7 @@ __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(void *p), int maxclass)
for (i = 0; i < n; i++) {
dst[count[class[i] - 1]++] = src[i];
- src[i] = 0;
+ src[i] = NULL;
}
return 0;
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index b6e70f92e7f..1627050e29f 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1958,13 +1958,13 @@ static const struct proto_ops SOCKOPS_WRAPPED(ipx_dgram_ops) = {
SOCKOPS_WRAP(ipx_dgram, PF_IPX);
-static struct packet_type ipx_8023_packet_type = {
- .type = __constant_htons(ETH_P_802_3),
+static struct packet_type ipx_8023_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_802_3),
.func = ipx_rcv,
};
-static struct packet_type ipx_dix_packet_type = {
- .type = __constant_htons(ETH_P_IPX),
+static struct packet_type ipx_dix_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_IPX),
.func = ipx_rcv,
};
@@ -1975,15 +1975,15 @@ static struct notifier_block ipx_dev_notifier = {
extern struct datalink_proto *make_EII_client(void);
extern void destroy_EII_client(struct datalink_proto *);
-static unsigned char ipx_8022_type = 0xE0;
-static unsigned char ipx_snap_id[5] = { 0x0, 0x0, 0x0, 0x81, 0x37 };
-static char ipx_EII_err_msg[] __initdata =
+static const unsigned char ipx_8022_type = 0xE0;
+static const unsigned char ipx_snap_id[5] = { 0x0, 0x0, 0x0, 0x81, 0x37 };
+static const char ipx_EII_err_msg[] __initconst =
KERN_CRIT "IPX: Unable to register with Ethernet II\n";
-static char ipx_8023_err_msg[] __initdata =
+static const char ipx_8023_err_msg[] __initconst =
KERN_CRIT "IPX: Unable to register with 802.3\n";
-static char ipx_llc_err_msg[] __initdata =
+static const char ipx_llc_err_msg[] __initconst =
KERN_CRIT "IPX: Unable to register with 802.2\n";
-static char ipx_snap_err_msg[] __initdata =
+static const char ipx_snap_err_msg[] __initconst =
KERN_CRIT "IPX: Unable to register with SNAP\n";
static int __init ipx_init(void)
diff --git a/net/irda/irda_device.c b/net/irda/irda_device.c
index ea319e3ddc1..bf92e147344 100644
--- a/net/irda/irda_device.c
+++ b/net/irda/irda_device.c
@@ -149,13 +149,14 @@ int irda_device_is_receiving(struct net_device *dev)
IRDA_DEBUG(2, "%s()\n", __func__);
- if (!dev->do_ioctl) {
+ if (!dev->netdev_ops->ndo_do_ioctl) {
IRDA_ERROR("%s: do_ioctl not impl. by device driver\n",
__func__);
return -1;
}
- ret = dev->do_ioctl(dev, (struct ifreq *) &req, SIOCGRECEIVING);
+ ret = (dev->netdev_ops->ndo_do_ioctl)(dev, (struct ifreq *) &req,
+ SIOCGRECEIVING);
if (ret < 0)
return ret;
diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c
index 05112be9956..724bcf951b8 100644
--- a/net/irda/irlan/irlan_eth.c
+++ b/net/irda/irlan/irlan_eth.c
@@ -45,6 +45,16 @@ static int irlan_eth_xmit(struct sk_buff *skb, struct net_device *dev);
static void irlan_eth_set_multicast_list( struct net_device *dev);
static struct net_device_stats *irlan_eth_get_stats(struct net_device *dev);
+static const struct net_device_ops irlan_eth_netdev_ops = {
+ .ndo_open = irlan_eth_open,
+ .ndo_stop = irlan_eth_close,
+ .ndo_start_xmit = irlan_eth_xmit,
+ .ndo_get_stats = irlan_eth_get_stats,
+ .ndo_set_multicast_list = irlan_eth_set_multicast_list,
+ .ndo_change_mtu = eth_change_mtu,
+ .ndo_validate_addr = eth_validate_addr,
+};
+
/*
* Function irlan_eth_setup (dev)
*
@@ -53,14 +63,11 @@ static struct net_device_stats *irlan_eth_get_stats(struct net_device *dev);
*/
static void irlan_eth_setup(struct net_device *dev)
{
- dev->open = irlan_eth_open;
- dev->stop = irlan_eth_close;
- dev->hard_start_xmit = irlan_eth_xmit;
- dev->get_stats = irlan_eth_get_stats;
- dev->set_multicast_list = irlan_eth_set_multicast_list;
+ ether_setup(dev);
+
+ dev->netdev_ops = &irlan_eth_netdev_ops;
dev->destructor = free_netdev;
- ether_setup(dev);
/*
* Lets do all queueing in IrTTP instead of this device driver.
diff --git a/net/irda/irmod.c b/net/irda/irmod.c
index 4c487a88372..303a68d9273 100644
--- a/net/irda/irmod.c
+++ b/net/irda/irmod.c
@@ -55,8 +55,8 @@ EXPORT_SYMBOL(irda_debug);
/* Packet type handler.
* Tell the kernel how IrDA packets should be handled.
*/
-static struct packet_type irda_packet_type = {
- .type = __constant_htons(ETH_P_IRDA),
+static struct packet_type irda_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_IRDA),
.func = irlap_driver_rcv, /* Packet type handler irlap_frame.c */
};
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index eb8a2a0b6eb..49e786535dc 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1171,8 +1171,7 @@ static void iucv_callback_txdone(struct iucv_path *path,
spin_unlock_irqrestore(&list->lock, flags);
- if (this)
- kfree_skb(this);
+ kfree_skb(this);
}
BUG_ON(!this);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 7dcbde3ea7d..643c1be2d02 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -313,8 +313,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
if (one_sk != NULL)
err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk);
- if (skb2)
- kfree_skb(skb2);
+ kfree_skb(skb2);
kfree_skb(skb);
return err;
}
@@ -3573,8 +3572,7 @@ static int pfkey_sendmsg(struct kiocb *kiocb,
out:
if (err && hdr && pfkey_error(hdr, err, sk) == 0)
err = 0;
- if (skb)
- kfree_skb(skb);
+ kfree_skb(skb);
return err ? : len;
}
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 56fd85ab358..febae702685 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -1118,11 +1118,11 @@ static const struct proto_ops llc_ui_ops = {
.sendpage = sock_no_sendpage,
};
-static char llc_proc_err_msg[] __initdata =
+static const char llc_proc_err_msg[] __initconst =
KERN_CRIT "LLC: Unable to register the proc_fs entries\n";
-static char llc_sysctl_err_msg[] __initdata =
+static const char llc_sysctl_err_msg[] __initconst =
KERN_CRIT "LLC: Unable to register the sysctl entries\n";
-static char llc_sock_err_msg[] __initdata =
+static const char llc_sock_err_msg[] __initconst =
KERN_CRIT "LLC: Unable to register the network family\n";
static int __init llc2_init(void)
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 5c6d89c6d51..3477624a490 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -332,8 +332,7 @@ int llc_conn_remove_acked_pdus(struct sock *sk, u8 nr, u16 *how_many_unacked)
for (i = 0; i < pdu_pos && i < q_len; i++) {
skb = skb_dequeue(&llc->pdu_unack_q);
- if (skb)
- kfree_skb(skb);
+ kfree_skb(skb);
nbr_acked++;
}
out:
diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c
index 50d5b10e23a..ff4c0ab96a6 100644
--- a/net/llc/llc_core.c
+++ b/net/llc/llc_core.c
@@ -147,13 +147,13 @@ void llc_sap_close(struct llc_sap *sap)
kfree(sap);
}
-static struct packet_type llc_packet_type = {
- .type = __constant_htons(ETH_P_802_2),
+static struct packet_type llc_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_802_2),
.func = llc_rcv,
};
-static struct packet_type llc_tr_packet_type = {
- .type = __constant_htons(ETH_P_TR_802_2),
+static struct packet_type llc_tr_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_TR_802_2),
.func = llc_rcv,
};
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index 7d4971aa443..0e3ab88bb70 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -8,13 +8,15 @@ mac80211-y := \
wep.o \
wpa.o \
scan.o \
- ht.o \
+ ht.o agg-tx.o agg-rx.o \
+ ibss.o \
mlme.o \
iface.o \
rate.o \
michael.o \
tkip.o \
aes_ccm.o \
+ aes_cmac.o \
cfg.o \
rx.o \
spectmgmt.o \
@@ -37,6 +39,8 @@ mac80211-$(CONFIG_MAC80211_MESH) += \
mesh_plink.o \
mesh_hwmp.o
+mac80211-$(CONFIG_PM) += pm.o
+
# objects for PID algorithm
rc80211_pid-y := rc80211_pid_algo.o
rc80211_pid-$(CONFIG_MAC80211_DEBUGFS) += rc80211_pid_debugfs.o
diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c
new file mode 100644
index 00000000000..3d097b3d7b6
--- /dev/null
+++ b/net/mac80211/aes_cmac.c
@@ -0,0 +1,135 @@
+/*
+ * AES-128-CMAC with TLen 16 for IEEE 802.11w BIP
+ * Copyright 2008, Jouni Malinen <j@w1.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+
+#include <net/mac80211.h>
+#include "key.h"
+#include "aes_cmac.h"
+
+#define AES_BLOCK_SIZE 16
+#define AES_CMAC_KEY_LEN 16
+#define CMAC_TLEN 8 /* CMAC TLen = 64 bits (8 octets) */
+#define AAD_LEN 20
+
+
+static void gf_mulx(u8 *pad)
+{
+ int i, carry;
+
+ carry = pad[0] & 0x80;
+ for (i = 0; i < AES_BLOCK_SIZE - 1; i++)
+ pad[i] = (pad[i] << 1) | (pad[i + 1] >> 7);
+ pad[AES_BLOCK_SIZE - 1] <<= 1;
+ if (carry)
+ pad[AES_BLOCK_SIZE - 1] ^= 0x87;
+}
+
+
+static void aes_128_cmac_vector(struct crypto_cipher *tfm, u8 *scratch,
+ size_t num_elem,
+ const u8 *addr[], const size_t *len, u8 *mac)
+{
+ u8 *cbc, *pad;
+ const u8 *pos, *end;
+ size_t i, e, left, total_len;
+
+ cbc = scratch;
+ pad = scratch + AES_BLOCK_SIZE;
+
+ memset(cbc, 0, AES_BLOCK_SIZE);
+
+ total_len = 0;
+ for (e = 0; e < num_elem; e++)
+ total_len += len[e];
+ left = total_len;
+
+ e = 0;
+ pos = addr[0];
+ end = pos + len[0];
+
+ while (left >= AES_BLOCK_SIZE) {
+ for (i = 0; i < AES_BLOCK_SIZE; i++) {
+ cbc[i] ^= *pos++;
+ if (pos >= end) {
+ e++;
+ pos = addr[e];
+ end = pos + len[e];
+ }
+ }
+ if (left > AES_BLOCK_SIZE)
+ crypto_cipher_encrypt_one(tfm, cbc, cbc);
+ left -= AES_BLOCK_SIZE;
+ }
+
+ memset(pad, 0, AES_BLOCK_SIZE);
+ crypto_cipher_encrypt_one(tfm, pad, pad);
+ gf_mulx(pad);
+
+ if (left || total_len == 0) {
+ for (i = 0; i < left; i++) {
+ cbc[i] ^= *pos++;
+ if (pos >= end) {
+ e++;
+ pos = addr[e];
+ end = pos + len[e];
+ }
+ }
+ cbc[left] ^= 0x80;
+ gf_mulx(pad);
+ }
+
+ for (i = 0; i < AES_BLOCK_SIZE; i++)
+ pad[i] ^= cbc[i];
+ crypto_cipher_encrypt_one(tfm, pad, pad);
+ memcpy(mac, pad, CMAC_TLEN);
+}
+
+
+void ieee80211_aes_cmac(struct crypto_cipher *tfm, u8 *scratch, const u8 *aad,
+ const u8 *data, size_t data_len, u8 *mic)
+{
+ const u8 *addr[3];
+ size_t len[3];
+ u8 zero[CMAC_TLEN];
+
+ memset(zero, 0, CMAC_TLEN);
+ addr[0] = aad;
+ len[0] = AAD_LEN;
+ addr[1] = data;
+ len[1] = data_len - CMAC_TLEN;
+ addr[2] = zero;
+ len[2] = CMAC_TLEN;
+
+ aes_128_cmac_vector(tfm, scratch, 3, addr, len, mic);
+}
+
+
+struct crypto_cipher * ieee80211_aes_cmac_key_setup(const u8 key[])
+{
+ struct crypto_cipher *tfm;
+
+ tfm = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(tfm))
+ return NULL;
+
+ crypto_cipher_setkey(tfm, key, AES_CMAC_KEY_LEN);
+
+ return tfm;
+}
+
+
+void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm)
+{
+ if (tfm)
+ crypto_free_cipher(tfm);
+}
diff --git a/net/mac80211/aes_cmac.h b/net/mac80211/aes_cmac.h
new file mode 100644
index 00000000000..0eb9a483150
--- /dev/null
+++ b/net/mac80211/aes_cmac.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright 2008, Jouni Malinen <j@w1.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef AES_CMAC_H
+#define AES_CMAC_H
+
+#include <linux/crypto.h>
+
+struct crypto_cipher * ieee80211_aes_cmac_key_setup(const u8 key[]);
+void ieee80211_aes_cmac(struct crypto_cipher *tfm, u8 *scratch, const u8 *aad,
+ const u8 *data, size_t data_len, u8 *mic);
+void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm);
+
+#endif /* AES_CMAC_H */
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
new file mode 100644
index 00000000000..07656d830bc
--- /dev/null
+++ b/net/mac80211/agg-rx.c
@@ -0,0 +1,310 @@
+/*
+ * HT handling
+ *
+ * Copyright 2003, Jouni Malinen <jkmaline@cc.hut.fi>
+ * Copyright 2002-2005, Instant802 Networks, Inc.
+ * Copyright 2005-2006, Devicescape Software, Inc.
+ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
+ * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
+ * Copyright 2007-2008, Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ieee80211.h>
+#include <net/mac80211.h>
+#include "ieee80211_i.h"
+
+void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
+ u16 initiator, u16 reason)
+{
+ struct ieee80211_local *local = sta->local;
+ struct ieee80211_hw *hw = &local->hw;
+ int i;
+
+ /* check if TID is in operational state */
+ spin_lock_bh(&sta->lock);
+ if (sta->ampdu_mlme.tid_state_rx[tid] != HT_AGG_STATE_OPERATIONAL) {
+ spin_unlock_bh(&sta->lock);
+ return;
+ }
+
+ sta->ampdu_mlme.tid_state_rx[tid] =
+ HT_AGG_STATE_REQ_STOP_BA_MSK |
+ (initiator << HT_AGG_STATE_INITIATOR_SHIFT);
+ spin_unlock_bh(&sta->lock);
+
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Rx BA session stop requested for %pM tid %u\n",
+ sta->sta.addr, tid);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+
+ if (local->ops->ampdu_action(hw, IEEE80211_AMPDU_RX_STOP,
+ &sta->sta, tid, NULL))
+ printk(KERN_DEBUG "HW problem - can not stop rx "
+ "aggregation for tid %d\n", tid);
+
+ /* shutdown timer has not expired */
+ if (initiator != WLAN_BACK_TIMER)
+ del_timer_sync(&sta->ampdu_mlme.tid_rx[tid]->session_timer);
+
+ /* check if this is a self generated aggregation halt */
+ if (initiator == WLAN_BACK_RECIPIENT || initiator == WLAN_BACK_TIMER)
+ ieee80211_send_delba(sta->sdata, sta->sta.addr,
+ tid, 0, reason);
+
+ /* free the reordering buffer */
+ for (i = 0; i < sta->ampdu_mlme.tid_rx[tid]->buf_size; i++) {
+ if (sta->ampdu_mlme.tid_rx[tid]->reorder_buf[i]) {
+ /* release the reordered frames */
+ dev_kfree_skb(sta->ampdu_mlme.tid_rx[tid]->reorder_buf[i]);
+ sta->ampdu_mlme.tid_rx[tid]->stored_mpdu_num--;
+ sta->ampdu_mlme.tid_rx[tid]->reorder_buf[i] = NULL;
+ }
+ }
+
+ spin_lock_bh(&sta->lock);
+ /* free resources */
+ kfree(sta->ampdu_mlme.tid_rx[tid]->reorder_buf);
+
+ if (!sta->ampdu_mlme.tid_rx[tid]->shutdown) {
+ kfree(sta->ampdu_mlme.tid_rx[tid]);
+ sta->ampdu_mlme.tid_rx[tid] = NULL;
+ }
+
+ sta->ampdu_mlme.tid_state_rx[tid] = HT_AGG_STATE_IDLE;
+ spin_unlock_bh(&sta->lock);
+}
+
+void ieee80211_sta_stop_rx_ba_session(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid,
+ u16 initiator, u16 reason)
+{
+ struct ieee80211_local *local = sdata->local;
+ struct sta_info *sta;
+
+ /* stop HW Rx aggregation. ampdu_action existence
+ * already verified in session init so we add the BUG_ON */
+ BUG_ON(!local->ops->ampdu_action);
+
+ rcu_read_lock();
+
+ sta = sta_info_get(local, ra);
+ if (!sta) {
+ rcu_read_unlock();
+ return;
+ }
+
+ __ieee80211_stop_rx_ba_session(sta, tid, initiator, reason);
+
+ rcu_read_unlock();
+}
+
+/*
+ * After accepting the AddBA Request we activated a timer,
+ * resetting it after each frame that arrives from the originator.
+ * if this timer expires ieee80211_sta_stop_rx_ba_session will be executed.
+ */
+static void sta_rx_agg_session_timer_expired(unsigned long data)
+{
+ /* not an elegant detour, but there is no choice as the timer passes
+ * only one argument, and various sta_info are needed here, so init
+ * flow in sta_info_create gives the TID as data, while the timer_to_id
+ * array gives the sta through container_of */
+ u8 *ptid = (u8 *)data;
+ u8 *timer_to_id = ptid - *ptid;
+ struct sta_info *sta = container_of(timer_to_id, struct sta_info,
+ timer_to_tid[0]);
+
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "rx session timer expired on tid %d\n", (u16)*ptid);
+#endif
+ ieee80211_sta_stop_rx_ba_session(sta->sdata, sta->sta.addr,
+ (u16)*ptid, WLAN_BACK_TIMER,
+ WLAN_REASON_QSTA_TIMEOUT);
+}
+
+static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *da, u16 tid,
+ u8 dialog_token, u16 status, u16 policy,
+ u16 buf_size, u16 timeout)
+{
+ struct ieee80211_local *local = sdata->local;
+ struct sk_buff *skb;
+ struct ieee80211_mgmt *mgmt;
+ u16 capab;
+
+ skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom);
+
+ if (!skb) {
+ printk(KERN_DEBUG "%s: failed to allocate buffer "
+ "for addba resp frame\n", sdata->dev->name);
+ return;
+ }
+
+ skb_reserve(skb, local->hw.extra_tx_headroom);
+ mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24);
+ memset(mgmt, 0, 24);
+ memcpy(mgmt->da, da, ETH_ALEN);
+ memcpy(mgmt->sa, sdata->dev->dev_addr, ETH_ALEN);
+ if (sdata->vif.type == NL80211_IFTYPE_AP ||
+ sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+ memcpy(mgmt->bssid, sdata->dev->dev_addr, ETH_ALEN);
+ else if (sdata->vif.type == NL80211_IFTYPE_STATION)
+ memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN);
+
+ mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
+ IEEE80211_STYPE_ACTION);
+
+ skb_put(skb, 1 + sizeof(mgmt->u.action.u.addba_resp));
+ mgmt->u.action.category = WLAN_CATEGORY_BACK;
+ mgmt->u.action.u.addba_resp.action_code = WLAN_ACTION_ADDBA_RESP;
+ mgmt->u.action.u.addba_resp.dialog_token = dialog_token;
+
+ capab = (u16)(policy << 1); /* bit 1 aggregation policy */
+ capab |= (u16)(tid << 2); /* bit 5:2 TID number */
+ capab |= (u16)(buf_size << 6); /* bit 15:6 max size of aggregation */
+
+ mgmt->u.action.u.addba_resp.capab = cpu_to_le16(capab);
+ mgmt->u.action.u.addba_resp.timeout = cpu_to_le16(timeout);
+ mgmt->u.action.u.addba_resp.status = cpu_to_le16(status);
+
+ ieee80211_tx_skb(sdata, skb, 1);
+}
+
+void ieee80211_process_addba_request(struct ieee80211_local *local,
+ struct sta_info *sta,
+ struct ieee80211_mgmt *mgmt,
+ size_t len)
+{
+ struct ieee80211_hw *hw = &local->hw;
+ struct ieee80211_conf *conf = &hw->conf;
+ struct tid_ampdu_rx *tid_agg_rx;
+ u16 capab, tid, timeout, ba_policy, buf_size, start_seq_num, status;
+ u8 dialog_token;
+ int ret = -EOPNOTSUPP;
+
+ /* extract session parameters from addba request frame */
+ dialog_token = mgmt->u.action.u.addba_req.dialog_token;
+ timeout = le16_to_cpu(mgmt->u.action.u.addba_req.timeout);
+ start_seq_num =
+ le16_to_cpu(mgmt->u.action.u.addba_req.start_seq_num) >> 4;
+
+ capab = le16_to_cpu(mgmt->u.action.u.addba_req.capab);
+ ba_policy = (capab & IEEE80211_ADDBA_PARAM_POLICY_MASK) >> 1;
+ tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2;
+ buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6;
+
+ status = WLAN_STATUS_REQUEST_DECLINED;
+
+ if (test_sta_flags(sta, WLAN_STA_SUSPEND)) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Suspend in progress. "
+ "Denying ADDBA request\n");
+#endif
+ goto end_no_lock;
+ }
+
+ /* sanity check for incoming parameters:
+ * check if configuration can support the BA policy
+ * and if buffer size does not exceeds max value */
+ /* XXX: check own ht delayed BA capability?? */
+ if (((ba_policy != 1)
+ && (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA)))
+ || (buf_size > IEEE80211_MAX_AMPDU_BUF)) {
+ status = WLAN_STATUS_INVALID_QOS_PARAM;
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ if (net_ratelimit())
+ printk(KERN_DEBUG "AddBA Req with bad params from "
+ "%pM on tid %u. policy %d, buffer size %d\n",
+ mgmt->sa, tid, ba_policy,
+ buf_size);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+ goto end_no_lock;
+ }
+ /* determine default buffer size */
+ if (buf_size == 0) {
+ struct ieee80211_supported_band *sband;
+
+ sband = local->hw.wiphy->bands[conf->channel->band];
+ buf_size = IEEE80211_MIN_AMPDU_BUF;
+ buf_size = buf_size << sband->ht_cap.ampdu_factor;
+ }
+
+
+ /* examine state machine */
+ spin_lock_bh(&sta->lock);
+
+ if (sta->ampdu_mlme.tid_state_rx[tid] != HT_AGG_STATE_IDLE) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ if (net_ratelimit())
+ printk(KERN_DEBUG "unexpected AddBA Req from "
+ "%pM on tid %u\n",
+ mgmt->sa, tid);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+ goto end;
+ }
+
+ /* prepare A-MPDU MLME for Rx aggregation */
+ sta->ampdu_mlme.tid_rx[tid] =
+ kmalloc(sizeof(struct tid_ampdu_rx), GFP_ATOMIC);
+ if (!sta->ampdu_mlme.tid_rx[tid]) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ if (net_ratelimit())
+ printk(KERN_ERR "allocate rx mlme to tid %d failed\n",
+ tid);
+#endif
+ goto end;
+ }
+ /* rx timer */
+ sta->ampdu_mlme.tid_rx[tid]->session_timer.function =
+ sta_rx_agg_session_timer_expired;
+ sta->ampdu_mlme.tid_rx[tid]->session_timer.data =
+ (unsigned long)&sta->timer_to_tid[tid];
+ init_timer(&sta->ampdu_mlme.tid_rx[tid]->session_timer);
+
+ tid_agg_rx = sta->ampdu_mlme.tid_rx[tid];
+
+ /* prepare reordering buffer */
+ tid_agg_rx->reorder_buf =
+ kcalloc(buf_size, sizeof(struct sk_buff *), GFP_ATOMIC);
+ if (!tid_agg_rx->reorder_buf) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ if (net_ratelimit())
+ printk(KERN_ERR "can not allocate reordering buffer "
+ "to tid %d\n", tid);
+#endif
+ kfree(sta->ampdu_mlme.tid_rx[tid]);
+ goto end;
+ }
+
+ if (local->ops->ampdu_action)
+ ret = local->ops->ampdu_action(hw, IEEE80211_AMPDU_RX_START,
+ &sta->sta, tid, &start_seq_num);
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Rx A-MPDU request on tid %d result %d\n", tid, ret);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+
+ if (ret) {
+ kfree(tid_agg_rx->reorder_buf);
+ kfree(tid_agg_rx);
+ sta->ampdu_mlme.tid_rx[tid] = NULL;
+ goto end;
+ }
+
+ /* change state and send addba resp */
+ sta->ampdu_mlme.tid_state_rx[tid] = HT_AGG_STATE_OPERATIONAL;
+ tid_agg_rx->dialog_token = dialog_token;
+ tid_agg_rx->ssn = start_seq_num;
+ tid_agg_rx->head_seq_num = start_seq_num;
+ tid_agg_rx->buf_size = buf_size;
+ tid_agg_rx->timeout = timeout;
+ tid_agg_rx->stored_mpdu_num = 0;
+ status = WLAN_STATUS_SUCCESS;
+end:
+ spin_unlock_bh(&sta->lock);
+
+end_no_lock:
+ ieee80211_send_addba_resp(sta->sdata, sta->sta.addr, tid,
+ dialog_token, status, 1, buf_size, timeout);
+}
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
new file mode 100644
index 00000000000..947aaaad35d
--- /dev/null
+++ b/net/mac80211/agg-tx.c
@@ -0,0 +1,695 @@
+/*
+ * HT handling
+ *
+ * Copyright 2003, Jouni Malinen <jkmaline@cc.hut.fi>
+ * Copyright 2002-2005, Instant802 Networks, Inc.
+ * Copyright 2005-2006, Devicescape Software, Inc.
+ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
+ * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
+ * Copyright 2007-2009, Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ieee80211.h>
+#include <net/mac80211.h>
+#include "ieee80211_i.h"
+#include "wme.h"
+
+/**
+ * DOC: TX aggregation
+ *
+ * Aggregation on the TX side requires setting the hardware flag
+ * %IEEE80211_HW_AMPDU_AGGREGATION as well as, if present, the @ampdu_queues
+ * hardware parameter to the number of hardware AMPDU queues. If there are no
+ * hardware queues then the driver will (currently) have to do all frame
+ * buffering.
+ *
+ * When TX aggregation is started by some subsystem (usually the rate control
+ * algorithm would be appropriate) by calling the
+ * ieee80211_start_tx_ba_session() function, the driver will be notified via
+ * its @ampdu_action function, with the %IEEE80211_AMPDU_TX_START action.
+ *
+ * In response to that, the driver is later required to call the
+ * ieee80211_start_tx_ba_cb() (or ieee80211_start_tx_ba_cb_irqsafe())
+ * function, which will start the aggregation session.
+ *
+ * Similarly, when the aggregation session is stopped by
+ * ieee80211_stop_tx_ba_session(), the driver's @ampdu_action function will
+ * be called with the action %IEEE80211_AMPDU_TX_STOP. In this case, the
+ * call must not fail, and the driver must later call ieee80211_stop_tx_ba_cb()
+ * (or ieee80211_stop_tx_ba_cb_irqsafe()).
+ */
+
+static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata,
+ const u8 *da, u16 tid,
+ u8 dialog_token, u16 start_seq_num,
+ u16 agg_size, u16 timeout)
+{
+ struct ieee80211_local *local = sdata->local;
+ struct sk_buff *skb;
+ struct ieee80211_mgmt *mgmt;
+ u16 capab;
+
+ skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom);
+
+ if (!skb) {
+ printk(KERN_ERR "%s: failed to allocate buffer "
+ "for addba request frame\n", sdata->dev->name);
+ return;
+ }
+ skb_reserve(skb, local->hw.extra_tx_headroom);
+ mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24);
+ memset(mgmt, 0, 24);
+ memcpy(mgmt->da, da, ETH_ALEN);
+ memcpy(mgmt->sa, sdata->dev->dev_addr, ETH_ALEN);
+ if (sdata->vif.type == NL80211_IFTYPE_AP ||
+ sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+ memcpy(mgmt->bssid, sdata->dev->dev_addr, ETH_ALEN);
+ else if (sdata->vif.type == NL80211_IFTYPE_STATION)
+ memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN);
+
+ mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
+ IEEE80211_STYPE_ACTION);
+
+ skb_put(skb, 1 + sizeof(mgmt->u.action.u.addba_req));
+
+ mgmt->u.action.category = WLAN_CATEGORY_BACK;
+ mgmt->u.action.u.addba_req.action_code = WLAN_ACTION_ADDBA_REQ;
+
+ mgmt->u.action.u.addba_req.dialog_token = dialog_token;
+ capab = (u16)(1 << 1); /* bit 1 aggregation policy */
+ capab |= (u16)(tid << 2); /* bit 5:2 TID number */
+ capab |= (u16)(agg_size << 6); /* bit 15:6 max size of aggergation */
+
+ mgmt->u.action.u.addba_req.capab = cpu_to_le16(capab);
+
+ mgmt->u.action.u.addba_req.timeout = cpu_to_le16(timeout);
+ mgmt->u.action.u.addba_req.start_seq_num =
+ cpu_to_le16(start_seq_num << 4);
+
+ ieee80211_tx_skb(sdata, skb, 1);
+}
+
+void ieee80211_send_bar(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid, u16 ssn)
+{
+ struct ieee80211_local *local = sdata->local;
+ struct sk_buff *skb;
+ struct ieee80211_bar *bar;
+ u16 bar_control = 0;
+
+ skb = dev_alloc_skb(sizeof(*bar) + local->hw.extra_tx_headroom);
+ if (!skb) {
+ printk(KERN_ERR "%s: failed to allocate buffer for "
+ "bar frame\n", sdata->dev->name);
+ return;
+ }
+ skb_reserve(skb, local->hw.extra_tx_headroom);
+ bar = (struct ieee80211_bar *)skb_put(skb, sizeof(*bar));
+ memset(bar, 0, sizeof(*bar));
+ bar->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL |
+ IEEE80211_STYPE_BACK_REQ);
+ memcpy(bar->ra, ra, ETH_ALEN);
+ memcpy(bar->ta, sdata->dev->dev_addr, ETH_ALEN);
+ bar_control |= (u16)IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL;
+ bar_control |= (u16)IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA;
+ bar_control |= (u16)(tid << 12);
+ bar->control = cpu_to_le16(bar_control);
+ bar->start_seq_num = cpu_to_le16(ssn);
+
+ ieee80211_tx_skb(sdata, skb, 0);
+}
+
+static int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
+ enum ieee80211_back_parties initiator)
+{
+ struct ieee80211_local *local = sta->local;
+ int ret;
+ u8 *state;
+
+ state = &sta->ampdu_mlme.tid_state_tx[tid];
+
+ *state = HT_AGG_STATE_REQ_STOP_BA_MSK |
+ (initiator << HT_AGG_STATE_INITIATOR_SHIFT);
+
+ ret = local->ops->ampdu_action(&local->hw, IEEE80211_AMPDU_TX_STOP,
+ &sta->sta, tid, NULL);
+
+ /* HW shall not deny going back to legacy */
+ if (WARN_ON(ret)) {
+ *state = HT_AGG_STATE_OPERATIONAL;
+ /*
+ * We may have pending packets get stuck in this case...
+ * Not bothering with a workaround for now.
+ */
+ }
+
+ return ret;
+}
+
+/*
+ * After sending add Block Ack request we activated a timer until
+ * add Block Ack response will arrive from the recipient.
+ * If this timer expires sta_addba_resp_timer_expired will be executed.
+ */
+static void sta_addba_resp_timer_expired(unsigned long data)
+{
+ /* not an elegant detour, but there is no choice as the timer passes
+ * only one argument, and both sta_info and TID are needed, so init
+ * flow in sta_info_create gives the TID as data, while the timer_to_id
+ * array gives the sta through container_of */
+ u16 tid = *(u8 *)data;
+ struct sta_info *sta = container_of((void *)data,
+ struct sta_info, timer_to_tid[tid]);
+ u8 *state;
+
+ state = &sta->ampdu_mlme.tid_state_tx[tid];
+
+ /* check if the TID waits for addBA response */
+ spin_lock_bh(&sta->lock);
+ if (!(*state & HT_ADDBA_REQUESTED_MSK)) {
+ spin_unlock_bh(&sta->lock);
+ *state = HT_AGG_STATE_IDLE;
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "timer expired on tid %d but we are not "
+ "expecting addBA response there", tid);
+#endif
+ return;
+ }
+
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "addBA response timer expired on tid %d\n", tid);
+#endif
+
+ ___ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR);
+ spin_unlock_bh(&sta->lock);
+}
+
+static inline int ieee80211_ac_from_tid(int tid)
+{
+ return ieee802_1d_to_ac[tid & 7];
+}
+
+int ieee80211_start_tx_ba_session(struct ieee80211_hw *hw, u8 *ra, u16 tid)
+{
+ struct ieee80211_local *local = hw_to_local(hw);
+ struct sta_info *sta;
+ struct ieee80211_sub_if_data *sdata;
+ u8 *state;
+ int ret = 0;
+ u16 start_seq_num;
+
+ if (WARN_ON(!local->ops->ampdu_action))
+ return -EINVAL;
+
+ if ((tid >= STA_TID_NUM) || !(hw->flags & IEEE80211_HW_AMPDU_AGGREGATION))
+ return -EINVAL;
+
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Open BA session requested for %pM tid %u\n",
+ ra, tid);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+
+ rcu_read_lock();
+
+ sta = sta_info_get(local, ra);
+ if (!sta) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Could not find the station\n");
+#endif
+ ret = -ENOENT;
+ goto unlock;
+ }
+
+ /*
+ * The aggregation code is not prepared to handle
+ * anything but STA/AP due to the BSSID handling.
+ * IBSS could work in the code but isn't supported
+ * by drivers or the standard.
+ */
+ if (sta->sdata->vif.type != NL80211_IFTYPE_STATION &&
+ sta->sdata->vif.type != NL80211_IFTYPE_AP_VLAN &&
+ sta->sdata->vif.type != NL80211_IFTYPE_AP) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+
+ if (test_sta_flags(sta, WLAN_STA_SUSPEND)) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Suspend in progress. "
+ "Denying BA session request\n");
+#endif
+ ret = -EINVAL;
+ goto unlock;
+ }
+
+ spin_lock_bh(&sta->lock);
+ spin_lock(&local->ampdu_lock);
+
+ sdata = sta->sdata;
+
+ /* we have tried too many times, receiver does not want A-MPDU */
+ if (sta->ampdu_mlme.addba_req_num[tid] > HT_AGG_MAX_RETRIES) {
+ ret = -EBUSY;
+ goto err_unlock_sta;
+ }
+
+ state = &sta->ampdu_mlme.tid_state_tx[tid];
+ /* check if the TID is not in aggregation flow already */
+ if (*state != HT_AGG_STATE_IDLE) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "BA request denied - session is not "
+ "idle on tid %u\n", tid);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+ ret = -EAGAIN;
+ goto err_unlock_sta;
+ }
+
+ /*
+ * While we're asking the driver about the aggregation,
+ * stop the AC queue so that we don't have to worry
+ * about frames that came in while we were doing that,
+ * which would require us to put them to the AC pending
+ * afterwards which just makes the code more complex.
+ */
+ ieee80211_stop_queue_by_reason(
+ &local->hw, ieee80211_ac_from_tid(tid),
+ IEEE80211_QUEUE_STOP_REASON_AGGREGATION);
+
+ /* prepare A-MPDU MLME for Tx aggregation */
+ sta->ampdu_mlme.tid_tx[tid] =
+ kmalloc(sizeof(struct tid_ampdu_tx), GFP_ATOMIC);
+ if (!sta->ampdu_mlme.tid_tx[tid]) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ if (net_ratelimit())
+ printk(KERN_ERR "allocate tx mlme to tid %d failed\n",
+ tid);
+#endif
+ ret = -ENOMEM;
+ goto err_wake_queue;
+ }
+
+ skb_queue_head_init(&sta->ampdu_mlme.tid_tx[tid]->pending);
+
+ /* Tx timer */
+ sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer.function =
+ sta_addba_resp_timer_expired;
+ sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer.data =
+ (unsigned long)&sta->timer_to_tid[tid];
+ init_timer(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer);
+
+ /* Ok, the Addba frame hasn't been sent yet, but if the driver calls the
+ * call back right away, it must see that the flow has begun */
+ *state |= HT_ADDBA_REQUESTED_MSK;
+
+ start_seq_num = sta->tid_seq[tid];
+
+ ret = local->ops->ampdu_action(hw, IEEE80211_AMPDU_TX_START,
+ &sta->sta, tid, &start_seq_num);
+
+ if (ret) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "BA request denied - HW unavailable for"
+ " tid %d\n", tid);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+ *state = HT_AGG_STATE_IDLE;
+ goto err_free;
+ }
+
+ /* Driver vetoed or OKed, but we can take packets again now */
+ ieee80211_wake_queue_by_reason(
+ &local->hw, ieee80211_ac_from_tid(tid),
+ IEEE80211_QUEUE_STOP_REASON_AGGREGATION);
+
+ spin_unlock(&local->ampdu_lock);
+ spin_unlock_bh(&sta->lock);
+
+ /* send an addBA request */
+ sta->ampdu_mlme.dialog_token_allocator++;
+ sta->ampdu_mlme.tid_tx[tid]->dialog_token =
+ sta->ampdu_mlme.dialog_token_allocator;
+ sta->ampdu_mlme.tid_tx[tid]->ssn = start_seq_num;
+
+ ieee80211_send_addba_request(sta->sdata, ra, tid,
+ sta->ampdu_mlme.tid_tx[tid]->dialog_token,
+ sta->ampdu_mlme.tid_tx[tid]->ssn,
+ 0x40, 5000);
+ /* activate the timer for the recipient's addBA response */
+ sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer.expires =
+ jiffies + ADDBA_RESP_INTERVAL;
+ add_timer(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer);
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "activated addBA response timer on tid %d\n", tid);
+#endif
+ goto unlock;
+
+ err_free:
+ kfree(sta->ampdu_mlme.tid_tx[tid]);
+ sta->ampdu_mlme.tid_tx[tid] = NULL;
+ err_wake_queue:
+ ieee80211_wake_queue_by_reason(
+ &local->hw, ieee80211_ac_from_tid(tid),
+ IEEE80211_QUEUE_STOP_REASON_AGGREGATION);
+ err_unlock_sta:
+ spin_unlock(&local->ampdu_lock);
+ spin_unlock_bh(&sta->lock);
+ unlock:
+ rcu_read_unlock();
+ return ret;
+}
+EXPORT_SYMBOL(ieee80211_start_tx_ba_session);
+
+/*
+ * splice packets from the STA's pending to the local pending,
+ * requires a call to ieee80211_agg_splice_finish and holding
+ * local->ampdu_lock across both calls.
+ */
+static void ieee80211_agg_splice_packets(struct ieee80211_local *local,
+ struct sta_info *sta, u16 tid)
+{
+ unsigned long flags;
+ u16 queue = ieee80211_ac_from_tid(tid);
+
+ ieee80211_stop_queue_by_reason(
+ &local->hw, queue,
+ IEEE80211_QUEUE_STOP_REASON_AGGREGATION);
+
+ if (!skb_queue_empty(&sta->ampdu_mlme.tid_tx[tid]->pending)) {
+ spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
+ /* mark queue as pending, it is stopped already */
+ __set_bit(IEEE80211_QUEUE_STOP_REASON_PENDING,
+ &local->queue_stop_reasons[queue]);
+ /* copy over remaining packets */
+ skb_queue_splice_tail_init(
+ &sta->ampdu_mlme.tid_tx[tid]->pending,
+ &local->pending[queue]);
+ spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
+ }
+}
+
+static void ieee80211_agg_splice_finish(struct ieee80211_local *local,
+ struct sta_info *sta, u16 tid)
+{
+ u16 queue = ieee80211_ac_from_tid(tid);
+
+ ieee80211_wake_queue_by_reason(
+ &local->hw, queue,
+ IEEE80211_QUEUE_STOP_REASON_AGGREGATION);
+}
+
+/* caller must hold sta->lock */
+static void ieee80211_agg_tx_operational(struct ieee80211_local *local,
+ struct sta_info *sta, u16 tid)
+{
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Aggregation is on for tid %d \n", tid);
+#endif
+
+ spin_lock(&local->ampdu_lock);
+ ieee80211_agg_splice_packets(local, sta, tid);
+ /*
+ * NB: we rely on sta->lock being taken in the TX
+ * processing here when adding to the pending queue,
+ * otherwise we could only change the state of the
+ * session to OPERATIONAL _here_.
+ */
+ ieee80211_agg_splice_finish(local, sta, tid);
+ spin_unlock(&local->ampdu_lock);
+
+ local->ops->ampdu_action(&local->hw, IEEE80211_AMPDU_TX_OPERATIONAL,
+ &sta->sta, tid, NULL);
+}
+
+void ieee80211_start_tx_ba_cb(struct ieee80211_hw *hw, u8 *ra, u16 tid)
+{
+ struct ieee80211_local *local = hw_to_local(hw);
+ struct sta_info *sta;
+ u8 *state;
+
+ if (tid >= STA_TID_NUM) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Bad TID value: tid = %d (>= %d)\n",
+ tid, STA_TID_NUM);
+#endif
+ return;
+ }
+
+ rcu_read_lock();
+ sta = sta_info_get(local, ra);
+ if (!sta) {
+ rcu_read_unlock();
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Could not find station: %pM\n", ra);
+#endif
+ return;
+ }
+
+ state = &sta->ampdu_mlme.tid_state_tx[tid];
+ spin_lock_bh(&sta->lock);
+
+ if (WARN_ON(!(*state & HT_ADDBA_REQUESTED_MSK))) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "addBA was not requested yet, state is %d\n",
+ *state);
+#endif
+ spin_unlock_bh(&sta->lock);
+ rcu_read_unlock();
+ return;
+ }
+
+ if (WARN_ON(*state & HT_ADDBA_DRV_READY_MSK))
+ goto out;
+
+ *state |= HT_ADDBA_DRV_READY_MSK;
+
+ if (*state == HT_AGG_STATE_OPERATIONAL)
+ ieee80211_agg_tx_operational(local, sta, tid);
+
+ out:
+ spin_unlock_bh(&sta->lock);
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL(ieee80211_start_tx_ba_cb);
+
+void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_hw *hw,
+ const u8 *ra, u16 tid)
+{
+ struct ieee80211_local *local = hw_to_local(hw);
+ struct ieee80211_ra_tid *ra_tid;
+ struct sk_buff *skb = dev_alloc_skb(0);
+
+ if (unlikely(!skb)) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ if (net_ratelimit())
+ printk(KERN_WARNING "%s: Not enough memory, "
+ "dropping start BA session", skb->dev->name);
+#endif
+ return;
+ }
+ ra_tid = (struct ieee80211_ra_tid *) &skb->cb;
+ memcpy(&ra_tid->ra, ra, ETH_ALEN);
+ ra_tid->tid = tid;
+
+ skb->pkt_type = IEEE80211_ADDBA_MSG;
+ skb_queue_tail(&local->skb_queue, skb);
+ tasklet_schedule(&local->tasklet);
+}
+EXPORT_SYMBOL(ieee80211_start_tx_ba_cb_irqsafe);
+
+int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
+ enum ieee80211_back_parties initiator)
+{
+ u8 *state;
+ int ret;
+
+ /* check if the TID is in aggregation */
+ state = &sta->ampdu_mlme.tid_state_tx[tid];
+ spin_lock_bh(&sta->lock);
+
+ if (*state != HT_AGG_STATE_OPERATIONAL) {
+ ret = -ENOENT;
+ goto unlock;
+ }
+
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Tx BA session stop requested for %pM tid %u\n",
+ sta->sta.addr, tid);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+
+ ret = ___ieee80211_stop_tx_ba_session(sta, tid, initiator);
+
+ unlock:
+ spin_unlock_bh(&sta->lock);
+ return ret;
+}
+
+int ieee80211_stop_tx_ba_session(struct ieee80211_hw *hw,
+ u8 *ra, u16 tid,
+ enum ieee80211_back_parties initiator)
+{
+ struct ieee80211_local *local = hw_to_local(hw);
+ struct sta_info *sta;
+ int ret = 0;
+
+ if (WARN_ON(!local->ops->ampdu_action))
+ return -EINVAL;
+
+ if (tid >= STA_TID_NUM)
+ return -EINVAL;
+
+ rcu_read_lock();
+ sta = sta_info_get(local, ra);
+ if (!sta) {
+ rcu_read_unlock();
+ return -ENOENT;
+ }
+
+ ret = __ieee80211_stop_tx_ba_session(sta, tid, initiator);
+ rcu_read_unlock();
+ return ret;
+}
+EXPORT_SYMBOL(ieee80211_stop_tx_ba_session);
+
+void ieee80211_stop_tx_ba_cb(struct ieee80211_hw *hw, u8 *ra, u8 tid)
+{
+ struct ieee80211_local *local = hw_to_local(hw);
+ struct sta_info *sta;
+ u8 *state;
+
+ if (tid >= STA_TID_NUM) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Bad TID value: tid = %d (>= %d)\n",
+ tid, STA_TID_NUM);
+#endif
+ return;
+ }
+
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Stopping Tx BA session for %pM tid %d\n",
+ ra, tid);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+
+ rcu_read_lock();
+ sta = sta_info_get(local, ra);
+ if (!sta) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "Could not find station: %pM\n", ra);
+#endif
+ rcu_read_unlock();
+ return;
+ }
+ state = &sta->ampdu_mlme.tid_state_tx[tid];
+
+ /* NOTE: no need to use sta->lock in this state check, as
+ * ieee80211_stop_tx_ba_session will let only one stop call to
+ * pass through per sta/tid
+ */
+ if ((*state & HT_AGG_STATE_REQ_STOP_BA_MSK) == 0) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "unexpected callback to A-MPDU stop\n");
+#endif
+ rcu_read_unlock();
+ return;
+ }
+
+ if (*state & HT_AGG_STATE_INITIATOR_MSK)
+ ieee80211_send_delba(sta->sdata, ra, tid,
+ WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE);
+
+ spin_lock_bh(&sta->lock);
+ spin_lock(&local->ampdu_lock);
+
+ ieee80211_agg_splice_packets(local, sta, tid);
+
+ *state = HT_AGG_STATE_IDLE;
+ /* from now on packets are no longer put onto sta->pending */
+ sta->ampdu_mlme.addba_req_num[tid] = 0;
+ kfree(sta->ampdu_mlme.tid_tx[tid]);
+ sta->ampdu_mlme.tid_tx[tid] = NULL;
+
+ ieee80211_agg_splice_finish(local, sta, tid);
+
+ spin_unlock(&local->ampdu_lock);
+ spin_unlock_bh(&sta->lock);
+
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL(ieee80211_stop_tx_ba_cb);
+
+void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_hw *hw,
+ const u8 *ra, u16 tid)
+{
+ struct ieee80211_local *local = hw_to_local(hw);
+ struct ieee80211_ra_tid *ra_tid;
+ struct sk_buff *skb = dev_alloc_skb(0);
+
+ if (unlikely(!skb)) {
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ if (net_ratelimit())
+ printk(KERN_WARNING "%s: Not enough memory, "
+ "dropping stop BA session", skb->dev->name);
+#endif
+ return;
+ }
+ ra_tid = (struct ieee80211_ra_tid *) &skb->cb;
+ memcpy(&ra_tid->ra, ra, ETH_ALEN);
+ ra_tid->tid = tid;
+
+ skb->pkt_type = IEEE80211_DELBA_MSG;
+ skb_queue_tail(&local->skb_queue, skb);
+ tasklet_schedule(&local->tasklet);
+}
+EXPORT_SYMBOL(ieee80211_stop_tx_ba_cb_irqsafe);
+
+
+void ieee80211_process_addba_resp(struct ieee80211_local *local,
+ struct sta_info *sta,
+ struct ieee80211_mgmt *mgmt,
+ size_t len)
+{
+ u16 capab, tid;
+ u8 *state;
+
+ capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab);
+ tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2;
+
+ state = &sta->ampdu_mlme.tid_state_tx[tid];
+
+ spin_lock_bh(&sta->lock);
+
+ if (!(*state & HT_ADDBA_REQUESTED_MSK)) {
+ spin_unlock_bh(&sta->lock);
+ return;
+ }
+
+ if (mgmt->u.action.u.addba_resp.dialog_token !=
+ sta->ampdu_mlme.tid_tx[tid]->dialog_token) {
+ spin_unlock_bh(&sta->lock);
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "wrong addBA response token, tid %d\n", tid);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+ return;
+ }
+
+ del_timer_sync(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer);
+#ifdef CONFIG_MAC80211_HT_DEBUG
+ printk(KERN_DEBUG "switched off addBA timer for tid %d \n", tid);
+#endif /* CONFIG_MAC80211_HT_DEBUG */
+ if (le16_to_cpu(mgmt->u.action.u.addba_resp.status)
+ == WLAN_STATUS_SUCCESS) {
+ u8 curstate = *state;
+
+ *state |= HT_ADDBA_RECEIVED_MSK;
+
+ if (*state != curstate && *state == HT_AGG_STATE_OPERATIONAL)
+ ieee80211_agg_tx_operational(local, sta, tid);
+
+ sta->ampdu_mlme.addba_req_num[tid] = 0;
+ } else {
+ sta->ampdu_mlme.addba_req_num[tid]++;
+ ___ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR);
+ }
+ spin_unlock_bh(&sta->lock);
+}
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 9d4e4d846ec..e677b751d46 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -133,6 +133,9 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
case WLAN_CIPHER_SUITE_CCMP:
alg = ALG_CCMP;
break;
+ case WLAN_CIPHER_SUITE_AES_CMAC:
+ alg = ALG_AES_CMAC;
+ break;
default:
return -EINVAL;
}
@@ -275,6 +278,17 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
else
params.cipher = WLAN_CIPHER_SUITE_WEP104;
break;
+ case ALG_AES_CMAC:
+ params.cipher = WLAN_CIPHER_SUITE_AES_CMAC;
+ seq[0] = key->u.aes_cmac.tx_pn[5];
+ seq[1] = key->u.aes_cmac.tx_pn[4];
+ seq[2] = key->u.aes_cmac.tx_pn[3];
+ seq[3] = key->u.aes_cmac.tx_pn[2];
+ seq[4] = key->u.aes_cmac.tx_pn[1];
+ seq[5] = key->u.aes_cmac.tx_pn[0];
+ params.seq = seq;
+ params.seq_len = 6;
+ break;
}
params.key = key->conf.key;
@@ -304,6 +318,22 @@ static int ieee80211_config_default_key(struct wiphy *wiphy,
return 0;
}
+static int ieee80211_config_default_mgmt_key(struct wiphy *wiphy,
+ struct net_device *dev,
+ u8 key_idx)
+{
+ struct ieee80211_sub_if_data *sdata;
+
+ rcu_read_lock();
+
+ sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+ ieee80211_set_default_mgmt_key(sdata, key_idx);
+
+ rcu_read_unlock();
+
+ return 0;
+}
+
static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
@@ -311,11 +341,15 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
sinfo->filled = STATION_INFO_INACTIVE_TIME |
STATION_INFO_RX_BYTES |
STATION_INFO_TX_BYTES |
+ STATION_INFO_RX_PACKETS |
+ STATION_INFO_TX_PACKETS |
STATION_INFO_TX_BITRATE;
sinfo->inactive_time = jiffies_to_msecs(jiffies - sta->last_rx);
sinfo->rx_bytes = sta->rx_bytes;
sinfo->tx_bytes = sta->tx_bytes;
+ sinfo->rx_packets = sta->rx_packets;
+ sinfo->tx_packets = sta->tx_packets;
if (sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) {
sinfo->filled |= STATION_INFO_SIGNAL;
@@ -417,7 +451,8 @@ static int ieee80211_config_beacon(struct ieee80211_sub_if_data *sdata,
* This is a kludge. beacon interval should really be part
* of the beacon information.
*/
- if (params->interval) {
+ if (params->interval && (sdata->local->hw.conf.beacon_int !=
+ params->interval)) {
sdata->local->hw.conf.beacon_int = params->interval;
err = ieee80211_hw_config(sdata->local,
IEEE80211_CONF_CHANGE_BEACON_INTERVAL);
@@ -493,7 +528,8 @@ static int ieee80211_config_beacon(struct ieee80211_sub_if_data *sdata,
kfree(old);
- return ieee80211_if_config(sdata, IEEE80211_IFCC_BEACON);
+ return ieee80211_if_config(sdata, IEEE80211_IFCC_BEACON |
+ IEEE80211_IFCC_BEACON_ENABLED);
}
static int ieee80211_add_beacon(struct wiphy *wiphy, struct net_device *dev,
@@ -504,9 +540,6 @@ static int ieee80211_add_beacon(struct wiphy *wiphy, struct net_device *dev,
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
- if (sdata->vif.type != NL80211_IFTYPE_AP)
- return -EINVAL;
-
old = sdata->u.ap.beacon;
if (old)
@@ -523,9 +556,6 @@ static int ieee80211_set_beacon(struct wiphy *wiphy, struct net_device *dev,
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
- if (sdata->vif.type != NL80211_IFTYPE_AP)
- return -EINVAL;
-
old = sdata->u.ap.beacon;
if (!old)
@@ -541,9 +571,6 @@ static int ieee80211_del_beacon(struct wiphy *wiphy, struct net_device *dev)
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
- if (sdata->vif.type != NL80211_IFTYPE_AP)
- return -EINVAL;
-
old = sdata->u.ap.beacon;
if (!old)
@@ -553,7 +580,7 @@ static int ieee80211_del_beacon(struct wiphy *wiphy, struct net_device *dev)
synchronize_rcu();
kfree(old);
- return ieee80211_if_config(sdata, IEEE80211_IFCC_BEACON);
+ return ieee80211_if_config(sdata, IEEE80211_IFCC_BEACON_ENABLED);
}
/* Layer 2 Update frame (802.2 Type 1 LLC XID Update response) */
@@ -630,6 +657,10 @@ static void sta_apply_parameters(struct ieee80211_local *local,
sta->flags &= ~WLAN_STA_WME;
if (params->station_flags & STATION_FLAG_WME)
sta->flags |= WLAN_STA_WME;
+
+ sta->flags &= ~WLAN_STA_MFP;
+ if (params->station_flags & STATION_FLAG_MFP)
+ sta->flags |= WLAN_STA_MFP;
spin_unlock_bh(&sta->lock);
}
@@ -688,10 +719,6 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
int err;
int layer2_update;
- /* Prevent a race with changing the rate control algorithm */
- if (!netif_running(dev))
- return -ENETDOWN;
-
if (params->vlan) {
sdata = IEEE80211_DEV_TO_SUB_IF(params->vlan);
@@ -820,14 +847,8 @@ static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev,
struct sta_info *sta;
int err;
- if (!netif_running(dev))
- return -ENETDOWN;
-
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
- if (sdata->vif.type != NL80211_IFTYPE_MESH_POINT)
- return -ENOTSUPP;
-
rcu_read_lock();
sta = sta_info_get(local, next_hop);
if (!sta) {
@@ -873,14 +894,8 @@ static int ieee80211_change_mpath(struct wiphy *wiphy,
struct mesh_path *mpath;
struct sta_info *sta;
- if (!netif_running(dev))
- return -ENETDOWN;
-
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
- if (sdata->vif.type != NL80211_IFTYPE_MESH_POINT)
- return -ENOTSUPP;
-
rcu_read_lock();
sta = sta_info_get(local, next_hop);
@@ -949,9 +964,6 @@ static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev,
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
- if (sdata->vif.type != NL80211_IFTYPE_MESH_POINT)
- return -ENOTSUPP;
-
rcu_read_lock();
mpath = mesh_path_lookup(dst, sdata);
if (!mpath) {
@@ -973,9 +985,6 @@ static int ieee80211_dump_mpath(struct wiphy *wiphy, struct net_device *dev,
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
- if (sdata->vif.type != NL80211_IFTYPE_MESH_POINT)
- return -ENOTSUPP;
-
rcu_read_lock();
mpath = mesh_path_lookup_by_idx(idx, sdata);
if (!mpath) {
@@ -995,8 +1004,6 @@ static int ieee80211_get_mesh_params(struct wiphy *wiphy,
struct ieee80211_sub_if_data *sdata;
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
- if (sdata->vif.type != NL80211_IFTYPE_MESH_POINT)
- return -ENOTSUPP;
memcpy(conf, &(sdata->u.mesh.mshcfg), sizeof(struct mesh_config));
return 0;
}
@@ -1014,9 +1021,6 @@ static int ieee80211_set_mesh_params(struct wiphy *wiphy,
struct ieee80211_sub_if_data *sdata;
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
- if (sdata->vif.type != NL80211_IFTYPE_MESH_POINT)
- return -ENOTSUPP;
-
/* Set the config options which we are interested in setting */
conf = &(sdata->u.mesh.mshcfg);
if (_chg_mesh_attr(NL80211_MESHCONF_RETRY_TIMEOUT, mask))
@@ -1064,9 +1068,6 @@ static int ieee80211_change_bss(struct wiphy *wiphy,
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
- if (sdata->vif.type != NL80211_IFTYPE_AP)
- return -EINVAL;
-
if (params->use_cts_prot >= 0) {
sdata->vif.bss_conf.use_cts_prot = params->use_cts_prot;
changed |= BSS_CHANGED_ERP_CTS_PROT;
@@ -1141,6 +1142,150 @@ static int ieee80211_set_channel(struct wiphy *wiphy,
return ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL);
}
+#ifdef CONFIG_PM
+static int ieee80211_suspend(struct wiphy *wiphy)
+{
+ return __ieee80211_suspend(wiphy_priv(wiphy));
+}
+
+static int ieee80211_resume(struct wiphy *wiphy)
+{
+ return __ieee80211_resume(wiphy_priv(wiphy));
+}
+#else
+#define ieee80211_suspend NULL
+#define ieee80211_resume NULL
+#endif
+
+static int ieee80211_scan(struct wiphy *wiphy,
+ struct net_device *dev,
+ struct cfg80211_scan_request *req)
+{
+ struct ieee80211_sub_if_data *sdata;
+
+ sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+
+ if (sdata->vif.type != NL80211_IFTYPE_STATION &&
+ sdata->vif.type != NL80211_IFTYPE_ADHOC &&
+ sdata->vif.type != NL80211_IFTYPE_MESH_POINT)
+ return -EOPNOTSUPP;
+
+ return ieee80211_request_scan(sdata, req);
+}
+
+static int ieee80211_auth(struct wiphy *wiphy, struct net_device *dev,
+ struct cfg80211_auth_request *req)
+{
+ struct ieee80211_sub_if_data *sdata;
+
+ sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+
+ switch (req->auth_type) {
+ case NL80211_AUTHTYPE_OPEN_SYSTEM:
+ sdata->u.mgd.auth_algs = IEEE80211_AUTH_ALG_OPEN;
+ break;
+ case NL80211_AUTHTYPE_SHARED_KEY:
+ sdata->u.mgd.auth_algs = IEEE80211_AUTH_ALG_SHARED_KEY;
+ break;
+ case NL80211_AUTHTYPE_FT:
+ sdata->u.mgd.auth_algs = IEEE80211_AUTH_ALG_FT;
+ break;
+ case NL80211_AUTHTYPE_NETWORK_EAP:
+ sdata->u.mgd.auth_algs = IEEE80211_AUTH_ALG_LEAP;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ memcpy(sdata->u.mgd.bssid, req->peer_addr, ETH_ALEN);
+ sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_BSSID_SEL;
+ sdata->u.mgd.flags |= IEEE80211_STA_BSSID_SET;
+
+ /* TODO: req->chan */
+ sdata->u.mgd.flags |= IEEE80211_STA_AUTO_CHANNEL_SEL;
+
+ if (req->ssid) {
+ sdata->u.mgd.flags |= IEEE80211_STA_SSID_SET;
+ memcpy(sdata->u.mgd.ssid, req->ssid, req->ssid_len);
+ sdata->u.mgd.ssid_len = req->ssid_len;
+ sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_SSID_SEL;
+ }
+
+ kfree(sdata->u.mgd.sme_auth_ie);
+ sdata->u.mgd.sme_auth_ie = NULL;
+ sdata->u.mgd.sme_auth_ie_len = 0;
+ if (req->ie) {
+ sdata->u.mgd.sme_auth_ie = kmalloc(req->ie_len, GFP_KERNEL);
+ if (sdata->u.mgd.sme_auth_ie == NULL)
+ return -ENOMEM;
+ memcpy(sdata->u.mgd.sme_auth_ie, req->ie, req->ie_len);
+ sdata->u.mgd.sme_auth_ie_len = req->ie_len;
+ }
+
+ sdata->u.mgd.flags |= IEEE80211_STA_EXT_SME;
+ sdata->u.mgd.state = IEEE80211_STA_MLME_DIRECT_PROBE;
+ ieee80211_sta_req_auth(sdata);
+ return 0;
+}
+
+static int ieee80211_assoc(struct wiphy *wiphy, struct net_device *dev,
+ struct cfg80211_assoc_request *req)
+{
+ struct ieee80211_sub_if_data *sdata;
+ int ret;
+
+ sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+
+ if (memcmp(sdata->u.mgd.bssid, req->peer_addr, ETH_ALEN) != 0 ||
+ !(sdata->u.mgd.flags & IEEE80211_STA_AUTHENTICATED))
+ return -ENOLINK; /* not authenticated */
+
+ sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_BSSID_SEL;
+ sdata->u.mgd.flags |= IEEE80211_STA_BSSID_SET;
+
+ /* TODO: req->chan */
+ sdata->u.mgd.flags |= IEEE80211_STA_AUTO_CHANNEL_SEL;
+
+ if (req->ssid) {
+ sdata->u.mgd.flags |= IEEE80211_STA_SSID_SET;
+ memcpy(sdata->u.mgd.ssid, req->ssid, req->ssid_len);
+ sdata->u.mgd.ssid_len = req->ssid_len;
+ sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_SSID_SEL;
+ } else
+ sdata->u.mgd.flags |= IEEE80211_STA_AUTO_SSID_SEL;
+
+ ret = ieee80211_sta_set_extra_ie(sdata, req->ie, req->ie_len);
+ if (ret)
+ return ret;
+
+ sdata->u.mgd.flags |= IEEE80211_STA_EXT_SME;
+ sdata->u.mgd.state = IEEE80211_STA_MLME_ASSOCIATE;
+ ieee80211_sta_req_auth(sdata);
+ return 0;
+}
+
+static int ieee80211_deauth(struct wiphy *wiphy, struct net_device *dev,
+ struct cfg80211_deauth_request *req)
+{
+ struct ieee80211_sub_if_data *sdata;
+
+ sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+
+ /* TODO: req->ie */
+ return ieee80211_sta_deauthenticate(sdata, req->reason_code);
+}
+
+static int ieee80211_disassoc(struct wiphy *wiphy, struct net_device *dev,
+ struct cfg80211_disassoc_request *req)
+{
+ struct ieee80211_sub_if_data *sdata;
+
+ sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+
+ /* TODO: req->ie */
+ return ieee80211_sta_disassociate(sdata, req->reason_code);
+}
+
struct cfg80211_ops mac80211_config_ops = {
.add_virtual_intf = ieee80211_add_iface,
.del_virtual_intf = ieee80211_del_iface,
@@ -1149,6 +1294,7 @@ struct cfg80211_ops mac80211_config_ops = {
.del_key = ieee80211_del_key,
.get_key = ieee80211_get_key,
.set_default_key = ieee80211_config_default_key,
+ .set_default_mgmt_key = ieee80211_config_default_mgmt_key,
.add_beacon = ieee80211_add_beacon,
.set_beacon = ieee80211_set_beacon,
.del_beacon = ieee80211_del_beacon,
@@ -1169,4 +1315,11 @@ struct cfg80211_ops mac80211_config_ops = {
.change_bss = ieee80211_change_bss,
.set_txq_params = ieee80211_set_txq_params,
.set_channel = ieee80211_set_channel,
+ .suspend = ieee80211_suspend,
+ .resume = ieee80211_resume,
+ .scan = ieee80211_scan,
+ .auth = ieee80211_auth,
+ .assoc = ieee80211_assoc,
+ .deauth = ieee80211_deauth,
+ .disassoc = ieee80211_disassoc,
};
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 2697a2fe608..210b9b6fecd 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -40,6 +40,10 @@ static const struct file_operations name## _ops = { \
local->debugfs.name = debugfs_create_file(#name, 0400, phyd, \
local, &name## _ops);
+#define DEBUGFS_ADD_MODE(name, mode) \
+ local->debugfs.name = debugfs_create_file(#name, mode, phyd, \
+ local, &name## _ops);
+
#define DEBUGFS_DEL(name) \
debugfs_remove(local->debugfs.name); \
local->debugfs.name = NULL;
@@ -57,11 +61,80 @@ DEBUGFS_READONLY_FILE(long_retry_limit, 20, "%d",
local->hw.conf.long_frame_max_tx_count);
DEBUGFS_READONLY_FILE(total_ps_buffered, 20, "%d",
local->total_ps_buffered);
-DEBUGFS_READONLY_FILE(wep_iv, 20, "%#06x",
+DEBUGFS_READONLY_FILE(wep_iv, 20, "%#08x",
local->wep_iv & 0xffffff);
DEBUGFS_READONLY_FILE(rate_ctrl_alg, 100, "%s",
local->rate_ctrl ? local->rate_ctrl->ops->name : "<unset>");
+static ssize_t tsf_read(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct ieee80211_local *local = file->private_data;
+ u64 tsf = 0;
+ char buf[100];
+
+ if (local->ops->get_tsf)
+ tsf = local->ops->get_tsf(local_to_hw(local));
+
+ snprintf(buf, sizeof(buf), "0x%016llx\n", (unsigned long long) tsf);
+
+ return simple_read_from_buffer(user_buf, count, ppos, buf, 19);
+}
+
+static ssize_t tsf_write(struct file *file,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct ieee80211_local *local = file->private_data;
+ unsigned long long tsf;
+ char buf[100];
+ size_t len;
+
+ len = min(count, sizeof(buf) - 1);
+ if (copy_from_user(buf, user_buf, len))
+ return -EFAULT;
+ buf[len] = '\0';
+
+ if (strncmp(buf, "reset", 5) == 0) {
+ if (local->ops->reset_tsf) {
+ local->ops->reset_tsf(local_to_hw(local));
+ printk(KERN_INFO "%s: debugfs reset TSF\n", wiphy_name(local->hw.wiphy));
+ }
+ } else {
+ tsf = simple_strtoul(buf, NULL, 0);
+ if (local->ops->set_tsf) {
+ local->ops->set_tsf(local_to_hw(local), tsf);
+ printk(KERN_INFO "%s: debugfs set TSF to %#018llx\n", wiphy_name(local->hw.wiphy), tsf);
+ }
+ }
+
+ return count;
+}
+
+static const struct file_operations tsf_ops = {
+ .read = tsf_read,
+ .write = tsf_write,
+ .open = mac80211_open_file_generic
+};
+
+static ssize_t reset_write(struct file *file, const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct ieee80211_local *local = file->private_data;
+
+ rtnl_lock();
+ __ieee80211_suspend(&local->hw);
+ __ieee80211_resume(&local->hw);
+ rtnl_unlock();
+
+ return count;
+}
+
+static const struct file_operations reset_ops = {
+ .write = reset_write,
+ .open = mac80211_open_file_generic,
+};
+
/* statistics stuff */
#define DEBUGFS_STATS_FILE(name, buflen, fmt, value...) \
@@ -136,8 +209,6 @@ DEBUGFS_STATS_FILE(multicast_received_frame_count, 20, "%u",
local->dot11MulticastReceivedFrameCount);
DEBUGFS_STATS_FILE(transmitted_frame_count, 20, "%u",
local->dot11TransmittedFrameCount);
-DEBUGFS_STATS_FILE(wep_undecryptable_count, 20, "%u",
- local->dot11WEPUndecryptableCount);
#ifdef CONFIG_MAC80211_DEBUG_COUNTERS
DEBUGFS_STATS_FILE(tx_handlers_drop, 20, "%u",
local->tx_handlers_drop);
@@ -204,6 +275,8 @@ void debugfs_hw_add(struct ieee80211_local *local)
DEBUGFS_ADD(long_retry_limit);
DEBUGFS_ADD(total_ps_buffered);
DEBUGFS_ADD(wep_iv);
+ DEBUGFS_ADD(tsf);
+ DEBUGFS_ADD_MODE(reset, 0200);
statsd = debugfs_create_dir("statistics", phyd);
local->debugfs.statistics = statsd;
@@ -221,7 +294,6 @@ void debugfs_hw_add(struct ieee80211_local *local)
DEBUGFS_STATS_ADD(received_fragment_count);
DEBUGFS_STATS_ADD(multicast_received_frame_count);
DEBUGFS_STATS_ADD(transmitted_frame_count);
- DEBUGFS_STATS_ADD(wep_undecryptable_count);
#ifdef CONFIG_MAC80211_DEBUG_COUNTERS
DEBUGFS_STATS_ADD(tx_handlers_drop);
DEBUGFS_STATS_ADD(tx_handlers_queued);
@@ -258,6 +330,8 @@ void debugfs_hw_del(struct ieee80211_local *local)
DEBUGFS_DEL(long_retry_limit);
DEBUGFS_DEL(total_ps_buffered);
DEBUGFS_DEL(wep_iv);
+ DEBUGFS_DEL(tsf);
+ DEBUGFS_DEL(reset);
DEBUGFS_STATS_DEL(transmitted_fragment_count);
DEBUGFS_STATS_DEL(multicast_transmitted_frame_count);
@@ -268,7 +342,6 @@ void debugfs_hw_del(struct ieee80211_local *local)
DEBUGFS_STATS_DEL(received_fragment_count);
DEBUGFS_STATS_DEL(multicast_received_frame_count);
DEBUGFS_STATS_DEL(transmitted_frame_count);
- DEBUGFS_STATS_DEL(wep_undecryptable_count);
DEBUGFS_STATS_DEL(num_scans);
#ifdef CONFIG_MAC80211_DEBUG_COUNTERS
DEBUGFS_STATS_DEL(tx_handlers_drop);
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index 6424ac565ae..99c752588b3 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -76,6 +76,9 @@ static ssize_t key_algorithm_read(struct file *file,
case ALG_CCMP:
alg = "CCMP\n";
break;
+ case ALG_AES_CMAC:
+ alg = "AES-128-CMAC\n";
+ break;
default:
return 0;
}
@@ -105,6 +108,12 @@ static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf,
len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
tpn[0], tpn[1], tpn[2], tpn[3], tpn[4], tpn[5]);
break;
+ case ALG_AES_CMAC:
+ tpn = key->u.aes_cmac.tx_pn;
+ len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
+ tpn[0], tpn[1], tpn[2], tpn[3], tpn[4],
+ tpn[5]);
+ break;
default:
return 0;
}
@@ -142,6 +151,14 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
}
len = p - buf;
break;
+ case ALG_AES_CMAC:
+ rpn = key->u.aes_cmac.rx_pn;
+ p += scnprintf(p, sizeof(buf)+buf-p,
+ "%02x%02x%02x%02x%02x%02x\n",
+ rpn[0], rpn[1], rpn[2],
+ rpn[3], rpn[4], rpn[5]);
+ len = p - buf;
+ break;
default:
return 0;
}
@@ -156,13 +173,40 @@ static ssize_t key_replays_read(struct file *file, char __user *userbuf,
char buf[20];
int len;
- if (key->conf.alg != ALG_CCMP)
+ switch (key->conf.alg) {
+ case ALG_CCMP:
+ len = scnprintf(buf, sizeof(buf), "%u\n", key->u.ccmp.replays);
+ break;
+ case ALG_AES_CMAC:
+ len = scnprintf(buf, sizeof(buf), "%u\n",
+ key->u.aes_cmac.replays);
+ break;
+ default:
return 0;
- len = scnprintf(buf, sizeof(buf), "%u\n", key->u.ccmp.replays);
+ }
return simple_read_from_buffer(userbuf, count, ppos, buf, len);
}
KEY_OPS(replays);
+static ssize_t key_icverrors_read(struct file *file, char __user *userbuf,
+ size_t count, loff_t *ppos)
+{
+ struct ieee80211_key *key = file->private_data;
+ char buf[20];
+ int len;
+
+ switch (key->conf.alg) {
+ case ALG_AES_CMAC:
+ len = scnprintf(buf, sizeof(buf), "%u\n",
+ key->u.aes_cmac.icverrors);
+ break;
+ default:
+ return 0;
+ }
+ return simple_read_from_buffer(userbuf, count, ppos, buf, len);
+}
+KEY_OPS(icverrors);
+
static ssize_t key_key_read(struct file *file, char __user *userbuf,
size_t count, loff_t *ppos)
{
@@ -222,6 +266,7 @@ void ieee80211_debugfs_key_add(struct ieee80211_key *key)
DEBUGFS_ADD(tx_spec);
DEBUGFS_ADD(rx_spec);
DEBUGFS_ADD(replays);
+ DEBUGFS_ADD(icverrors);
DEBUGFS_ADD(key);
DEBUGFS_ADD(ifindex);
};
@@ -243,6 +288,7 @@ void ieee80211_debugfs_key_remove(struct ieee80211_key *key)
DEBUGFS_DEL(tx_spec);
DEBUGFS_DEL(rx_spec);
DEBUGFS_DEL(replays);
+ DEBUGFS_DEL(icverrors);
DEBUGFS_DEL(key);
DEBUGFS_DEL(ifindex);
@@ -280,6 +326,35 @@ void ieee80211_debugfs_key_remove_default(struct ieee80211_sub_if_data *sdata)
sdata->common_debugfs.default_key = NULL;
}
+void ieee80211_debugfs_key_add_mgmt_default(struct ieee80211_sub_if_data *sdata)
+{
+ char buf[50];
+ struct ieee80211_key *key;
+
+ if (!sdata->debugfsdir)
+ return;
+
+ /* this is running under the key lock */
+
+ key = sdata->default_mgmt_key;
+ if (key) {
+ sprintf(buf, "../keys/%d", key->debugfs.cnt);
+ sdata->common_debugfs.default_mgmt_key =
+ debugfs_create_symlink("default_mgmt_key",
+ sdata->debugfsdir, buf);
+ } else
+ ieee80211_debugfs_key_remove_mgmt_default(sdata);
+}
+
+void ieee80211_debugfs_key_remove_mgmt_default(struct ieee80211_sub_if_data *sdata)
+{
+ if (!sdata)
+ return;
+
+ debugfs_remove(sdata->common_debugfs.default_mgmt_key);
+ sdata->common_debugfs.default_mgmt_key = NULL;
+}
+
void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key,
struct sta_info *sta)
{
diff --git a/net/mac80211/debugfs_key.h b/net/mac80211/debugfs_key.h
index b1a3754ee24..54717b4e137 100644
--- a/net/mac80211/debugfs_key.h
+++ b/net/mac80211/debugfs_key.h
@@ -6,6 +6,10 @@ void ieee80211_debugfs_key_add(struct ieee80211_key *key);
void ieee80211_debugfs_key_remove(struct ieee80211_key *key);
void ieee80211_debugfs_key_add_default(struct ieee80211_sub_if_data *sdata);
void ieee80211_debugfs_key_remove_default(struct ieee80211_sub_if_data *sdata);
+void ieee80211_debugfs_key_add_mgmt_default(
+ struct ieee80211_sub_if_data *sdata);
+void ieee80211_debugfs_key_remove_mgmt_default(
+ struct ieee80211_sub_if_data *sdata);
void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key,
struct sta_info *sta);
#else
@@ -19,6 +23,12 @@ static inline void ieee80211_debugfs_key_add_default(
static inline void ieee80211_debugfs_key_remove_default(
struct ieee80211_sub_if_data *sdata)
{}
+static inline void ieee80211_debugfs_key_add_mgmt_default(
+ struct ieee80211_sub_if_data *sdata)
+{}
+static inline void ieee80211_debugfs_key_remove_mgmt_default(
+ struct ieee80211_sub_if_data *sdata)
+{}
static inline void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key,
struct sta_info *sta)
{}
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index c5421930172..e3420329f4e 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -94,31 +94,31 @@ IEEE80211_IF_FILE(drop_unencrypted, drop_unencrypted, DEC);
IEEE80211_IF_FILE(force_unicast_rateidx, force_unicast_rateidx, DEC);
IEEE80211_IF_FILE(max_ratectrl_rateidx, max_ratectrl_rateidx, DEC);
-/* STA/IBSS attributes */
-IEEE80211_IF_FILE(state, u.sta.state, DEC);
-IEEE80211_IF_FILE(bssid, u.sta.bssid, MAC);
-IEEE80211_IF_FILE(prev_bssid, u.sta.prev_bssid, MAC);
-IEEE80211_IF_FILE(ssid_len, u.sta.ssid_len, SIZE);
-IEEE80211_IF_FILE(aid, u.sta.aid, DEC);
-IEEE80211_IF_FILE(ap_capab, u.sta.ap_capab, HEX);
-IEEE80211_IF_FILE(capab, u.sta.capab, HEX);
-IEEE80211_IF_FILE(extra_ie_len, u.sta.extra_ie_len, SIZE);
-IEEE80211_IF_FILE(auth_tries, u.sta.auth_tries, DEC);
-IEEE80211_IF_FILE(assoc_tries, u.sta.assoc_tries, DEC);
-IEEE80211_IF_FILE(auth_algs, u.sta.auth_algs, HEX);
-IEEE80211_IF_FILE(auth_alg, u.sta.auth_alg, DEC);
-IEEE80211_IF_FILE(auth_transaction, u.sta.auth_transaction, DEC);
+/* STA attributes */
+IEEE80211_IF_FILE(state, u.mgd.state, DEC);
+IEEE80211_IF_FILE(bssid, u.mgd.bssid, MAC);
+IEEE80211_IF_FILE(prev_bssid, u.mgd.prev_bssid, MAC);
+IEEE80211_IF_FILE(ssid_len, u.mgd.ssid_len, SIZE);
+IEEE80211_IF_FILE(aid, u.mgd.aid, DEC);
+IEEE80211_IF_FILE(ap_capab, u.mgd.ap_capab, HEX);
+IEEE80211_IF_FILE(capab, u.mgd.capab, HEX);
+IEEE80211_IF_FILE(extra_ie_len, u.mgd.extra_ie_len, SIZE);
+IEEE80211_IF_FILE(auth_tries, u.mgd.auth_tries, DEC);
+IEEE80211_IF_FILE(assoc_tries, u.mgd.assoc_tries, DEC);
+IEEE80211_IF_FILE(auth_algs, u.mgd.auth_algs, HEX);
+IEEE80211_IF_FILE(auth_alg, u.mgd.auth_alg, DEC);
+IEEE80211_IF_FILE(auth_transaction, u.mgd.auth_transaction, DEC);
static ssize_t ieee80211_if_fmt_flags(
const struct ieee80211_sub_if_data *sdata, char *buf, int buflen)
{
return scnprintf(buf, buflen, "%s%s%s%s%s%s%s\n",
- sdata->u.sta.flags & IEEE80211_STA_SSID_SET ? "SSID\n" : "",
- sdata->u.sta.flags & IEEE80211_STA_BSSID_SET ? "BSSID\n" : "",
- sdata->u.sta.flags & IEEE80211_STA_PREV_BSSID_SET ? "prev BSSID\n" : "",
- sdata->u.sta.flags & IEEE80211_STA_AUTHENTICATED ? "AUTH\n" : "",
- sdata->u.sta.flags & IEEE80211_STA_ASSOCIATED ? "ASSOC\n" : "",
- sdata->u.sta.flags & IEEE80211_STA_PROBEREQ_POLL ? "PROBEREQ POLL\n" : "",
+ sdata->u.mgd.flags & IEEE80211_STA_SSID_SET ? "SSID\n" : "",
+ sdata->u.mgd.flags & IEEE80211_STA_BSSID_SET ? "BSSID\n" : "",
+ sdata->u.mgd.flags & IEEE80211_STA_PREV_BSSID_SET ? "prev BSSID\n" : "",
+ sdata->u.mgd.flags & IEEE80211_STA_AUTHENTICATED ? "AUTH\n" : "",
+ sdata->u.mgd.flags & IEEE80211_STA_ASSOCIATED ? "ASSOC\n" : "",
+ sdata->u.mgd.flags & IEEE80211_STA_PROBEREQ_POLL ? "PROBEREQ POLL\n" : "",
sdata->vif.bss_conf.use_cts_prot ? "CTS prot\n" : "");
}
__IEEE80211_IF_FILE(flags);
@@ -283,9 +283,11 @@ static void add_files(struct ieee80211_sub_if_data *sdata)
#endif
break;
case NL80211_IFTYPE_STATION:
- case NL80211_IFTYPE_ADHOC:
add_sta_files(sdata);
break;
+ case NL80211_IFTYPE_ADHOC:
+ /* XXX */
+ break;
case NL80211_IFTYPE_AP:
add_ap_files(sdata);
break;
@@ -418,9 +420,11 @@ static void del_files(struct ieee80211_sub_if_data *sdata)
#endif
break;
case NL80211_IFTYPE_STATION:
- case NL80211_IFTYPE_ADHOC:
del_sta_files(sdata);
break;
+ case NL80211_IFTYPE_ADHOC:
+ /* XXX */
+ break;
case NL80211_IFTYPE_AP:
del_ap_files(sdata);
break;
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index a2fbe013131..90230c718b5 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -67,14 +67,15 @@ static ssize_t sta_flags_read(struct file *file, char __user *userbuf,
char buf[100];
struct sta_info *sta = file->private_data;
u32 staflags = get_sta_flags(sta);
- int res = scnprintf(buf, sizeof(buf), "%s%s%s%s%s%s%s",
+ int res = scnprintf(buf, sizeof(buf), "%s%s%s%s%s%s%s%s",
staflags & WLAN_STA_AUTH ? "AUTH\n" : "",
staflags & WLAN_STA_ASSOC ? "ASSOC\n" : "",
staflags & WLAN_STA_PS ? "PS\n" : "",
staflags & WLAN_STA_AUTHORIZED ? "AUTHORIZED\n" : "",
staflags & WLAN_STA_SHORT_PREAMBLE ? "SHORT PREAMBLE\n" : "",
staflags & WLAN_STA_WME ? "WME\n" : "",
- staflags & WLAN_STA_WDS ? "WDS\n" : "");
+ staflags & WLAN_STA_WDS ? "WDS\n" : "",
+ staflags & WLAN_STA_MFP ? "MFP\n" : "");
return simple_read_from_buffer(userbuf, count, ppos, buf, res);
}
STA_OPS(flags);
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index c5c0c527109..4e3c72f20de 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -17,8 +17,7 @@
#include <net/wireless.h>
#include <net/mac80211.h>
#include "ieee80211_i.h"
-#include "sta_info.h"
-#include "wme.h"
+#include "rate.h"
void ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_supported_band *sband,
struct ieee80211_ht_cap *ht_cap_ie,
@@ -95,7 +94,9 @@ u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata,
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_supported_band *sband;
+ struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct ieee80211_bss_ht_conf ht;
+ struct sta_info *sta;
u32 changed = 0;
bool enable_ht = true, ht_changed;
enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT;
@@ -130,14 +131,25 @@ u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata,
}
}
- ht_changed = local->hw.conf.ht.enabled != enable_ht ||
- channel_type != local->hw.conf.ht.channel_type;
+ ht_changed = conf_is_ht(&local->hw.conf) != enable_ht ||
+ channel_type != local->hw.conf.channel_type;
local->oper_channel_type = channel_type;
- local->hw.conf.ht.enabled = enable_ht;
- if (ht_changed)
- ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_HT);
+ if (ht_changed) {
+ /* channel_type change automatically detected */
+ ieee80211_hw_config(local, 0);
+
+ rcu_read_lock();
+
+ sta = sta_info_get(local, ifmgd->bssid);
+ if (sta)
+ rate_control_rate_update(local, sband, sta,
+ IEEE80211_RC_HT_CHANGED);
+
+ rcu_read_unlock();
+
+ }
/* disable HT */
if (!enable_ht)
@@ -154,108 +166,22 @@ u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata,
return changed;
}
-static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata,
- const u8 *da, u16 tid,
- u8 dialog_token, u16 start_seq_num,
- u16 agg_size, u16 timeout)
+void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta)
{
- struct ieee80211_local *local = sdata->local;
- struct ieee80211_if_sta *ifsta = &sdata->u.sta;
- struct sk_buff *skb;
- struct ieee80211_mgmt *mgmt;
- u16 capab;
-
- skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom);
-
- if (!skb) {
- printk(KERN_ERR "%s: failed to allocate buffer "
- "for addba request frame\n", sdata->dev->name);
- return;
- }
- skb_reserve(skb, local->hw.extra_tx_headroom);
- mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24);
- memset(mgmt, 0, 24);
- memcpy(mgmt->da, da, ETH_ALEN);
- memcpy(mgmt->sa, sdata->dev->dev_addr, ETH_ALEN);
- if (sdata->vif.type == NL80211_IFTYPE_AP)
- memcpy(mgmt->bssid, sdata->dev->dev_addr, ETH_ALEN);
- else
- memcpy(mgmt->bssid, ifsta->bssid, ETH_ALEN);
-
- mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
- IEEE80211_STYPE_ACTION);
-
- skb_put(skb, 1 + sizeof(mgmt->u.action.u.addba_req));
-
- mgmt->u.action.category = WLAN_CATEGORY_BACK;
- mgmt->u.action.u.addba_req.action_code = WLAN_ACTION_ADDBA_REQ;
-
- mgmt->u.action.u.addba_req.dialog_token = dialog_token;
- capab = (u16)(1 << 1); /* bit 1 aggregation policy */
- capab |= (u16)(tid << 2); /* bit 5:2 TID number */
- capab |= (u16)(agg_size << 6); /* bit 15:6 max size of aggergation */
-
- mgmt->u.action.u.addba_req.capab = cpu_to_le16(capab);
-
- mgmt->u.action.u.addba_req.timeout = cpu_to_le16(timeout);
- mgmt->u.action.u.addba_req.start_seq_num =
- cpu_to_le16(start_seq_num << 4);
-
- ieee80211_tx_skb(sdata, skb, 0);
-}
-
-static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *da, u16 tid,
- u8 dialog_token, u16 status, u16 policy,
- u16 buf_size, u16 timeout)
-{
- struct ieee80211_if_sta *ifsta = &sdata->u.sta;
- struct ieee80211_local *local = sdata->local;
- struct sk_buff *skb;
- struct ieee80211_mgmt *mgmt;
- u16 capab;
-
- skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom);
+ int i;
- if (!skb) {
- printk(KERN_DEBUG "%s: failed to allocate buffer "
- "for addba resp frame\n", sdata->dev->name);
- return;
+ for (i = 0; i < STA_TID_NUM; i++) {
+ __ieee80211_stop_tx_ba_session(sta, i, WLAN_BACK_INITIATOR);
+ __ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT,
+ WLAN_REASON_QSTA_LEAVE_QBSS);
}
-
- skb_reserve(skb, local->hw.extra_tx_headroom);
- mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24);
- memset(mgmt, 0, 24);
- memcpy(mgmt->da, da, ETH_ALEN);
- memcpy(mgmt->sa, sdata->dev->dev_addr, ETH_ALEN);
- if (sdata->vif.type == NL80211_IFTYPE_AP)
- memcpy(mgmt->bssid, sdata->dev->dev_addr, ETH_ALEN);
- else
- memcpy(mgmt->bssid, ifsta->bssid, ETH_ALEN);
- mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
- IEEE80211_STYPE_ACTION);
-
- skb_put(skb, 1 + sizeof(mgmt->u.action.u.addba_resp));
- mgmt->u.action.category = WLAN_CATEGORY_BACK;
- mgmt->u.action.u.addba_resp.action_code = WLAN_ACTION_ADDBA_RESP;
- mgmt->u.action.u.addba_resp.dialog_token = dialog_token;
-
- capab = (u16)(policy << 1); /* bit 1 aggregation policy */
- capab |= (u16)(tid << 2); /* bit 5:2 TID number */
- capab |= (u16)(buf_size << 6); /* bit 15:6 max size of aggregation */
-
- mgmt->u.action.u.addba_resp.capab = cpu_to_le16(capab);
- mgmt->u.action.u.addba_resp.timeout = cpu_to_le16(timeout);
- mgmt->u.action.u.addba_resp.status = cpu_to_le16(status);
-
- ieee80211_tx_skb(sdata, skb, 0);
}
-static void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata,
- const u8 *da, u16 tid,
- u16 initiator, u16 reason_code)
+void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata,
+ const u8 *da, u16 tid,
+ u16 initiator, u16 reason_code)
{
struct ieee80211_local *local = sdata->local;
- struct ieee80211_if_sta *ifsta = &sdata->u.sta;
struct sk_buff *skb;
struct ieee80211_mgmt *mgmt;
u16 params;
@@ -273,10 +199,12 @@ static void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata,
memset(mgmt, 0, 24);
memcpy(mgmt->da, da, ETH_ALEN);
memcpy(mgmt->sa, sdata->dev->dev_addr, ETH_ALEN);
- if (sdata->vif.type == NL80211_IFTYPE_AP)
+ if (sdata->vif.type == NL80211_IFTYPE_AP ||
+ sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
memcpy(mgmt->bssid, sdata->dev->dev_addr, ETH_ALEN);
- else
- memcpy(mgmt->bssid, ifsta->bssid, ETH_ALEN);
+ else if (sdata->vif.type == NL80211_IFTYPE_STATION)
+ memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN);
+
mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
IEEE80211_STYPE_ACTION);
@@ -290,770 +218,7 @@ static void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata,
mgmt->u.action.u.delba.params = cpu_to_le16(params);
mgmt->u.action.u.delba.reason_code = cpu_to_le16(reason_code);
- ieee80211_tx_skb(sdata, skb, 0);
-}
-
-void ieee80211_send_bar(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid, u16 ssn)
-{
- struct ieee80211_local *local = sdata->local;
- struct sk_buff *skb;
- struct ieee80211_bar *bar;
- u16 bar_control = 0;
-
- skb = dev_alloc_skb(sizeof(*bar) + local->hw.extra_tx_headroom);
- if (!skb) {
- printk(KERN_ERR "%s: failed to allocate buffer for "
- "bar frame\n", sdata->dev->name);
- return;
- }
- skb_reserve(skb, local->hw.extra_tx_headroom);
- bar = (struct ieee80211_bar *)skb_put(skb, sizeof(*bar));
- memset(bar, 0, sizeof(*bar));
- bar->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL |
- IEEE80211_STYPE_BACK_REQ);
- memcpy(bar->ra, ra, ETH_ALEN);
- memcpy(bar->ta, sdata->dev->dev_addr, ETH_ALEN);
- bar_control |= (u16)IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL;
- bar_control |= (u16)IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA;
- bar_control |= (u16)(tid << 12);
- bar->control = cpu_to_le16(bar_control);
- bar->start_seq_num = cpu_to_le16(ssn);
-
- ieee80211_tx_skb(sdata, skb, 0);
-}
-
-void ieee80211_sta_stop_rx_ba_session(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid,
- u16 initiator, u16 reason)
-{
- struct ieee80211_local *local = sdata->local;
- struct ieee80211_hw *hw = &local->hw;
- struct sta_info *sta;
- int ret, i;
-
- rcu_read_lock();
-
- sta = sta_info_get(local, ra);
- if (!sta) {
- rcu_read_unlock();
- return;
- }
-
- /* check if TID is in operational state */
- spin_lock_bh(&sta->lock);
- if (sta->ampdu_mlme.tid_state_rx[tid]