#ifndef _LAPB_H #define _LAPB_H #include #define LAPB_HEADER_LEN 20 /* LAPB over Ethernet + a bit more */ #define LAPB_ACK_PENDING_CONDITION 0x01 #define LAPB_REJECT_CONDITION 0x02 #define LAPB_PEER_RX_BUSY_CONDITION 0x04 /* Control field templates */ #define LAPB_I 0x00 /* Information frames */ #define LAPB_S 0x01 /* Supervisory frames */ #define LAPB_U 0x03 /* Unnumbered frames */ #define LAPB_RR 0x01 /* Receiver ready */ #define LAPB_RNR 0x05 /* Receiver not ready */ #define LAPB_REJ 0x09 /* Reject */ #define LAPB_SABM 0x2F /* Set Asynchronous Balanced Mode */ #define LAPB_SABME 0x6F /* Set Asynchronous Balanced Mode Extended */ #define LAPB_DISC 0x43 /* Disconnect */ #define LAPB_DM 0x0F /* Disconnected mode */ #define LAPB_UA 0x63 /* Unnumbered acknowledge */ #define LAPB_FRMR 0x87 /* Frame reject */ #define LAPB_ILLEGAL 0x100 /* Impossible to be a real frame type */ #define LAPB_SPF 0x10 /* Poll/final bit for standard LAPB */ #define LAPB_EPF 0x01 /* Poll/final bit for extended LAPB */ #define LAPB_FRMR_W 0x01 /* Control field invalid */ #define LAPB_FRMR_X 0x02 /* I field invalid */ #define LAPB_FRMR_Y 0x04 /* I field too long */ #define LAPB_FRMR_Z 0x08 /* Invalid N(R) */ #define LAPB_POLLOFF 0 #define LAPB_POLLON 1 /* LAPB C-bit */ #define LAPB_COMMAND 1 #define LAPB_RESPONSE 2 #define LAPB_ADDR_A 0x03 #define LAPB_ADDR_B 0x01 #define LAPB_ADDR_C 0x0F #define LAPB_ADDR_D 0x07 /* Define Link State constants. */ enum { LAPB_STATE_0, /* Disconnected State */ LAPB_STATE_1, /* Awaiting Connection State */ LAPB_STATE_2, /* Awaiting Disconnection State */ LAPB_STATE_3, /* Data Transfer State */ LAPB_STATE_4 /* Frame Reject State */ }; #define LAPB_DEFAULT_MODE (LAPB_STANDARD | LAPB_SLP | LAPB_DTE) #define LAPB_DEFAULT_WINDOW 7 /* Window=7 */ #define LAPB_DEFAULT_T1 (5 * HZ) /* T1=5s */ #define LAPB_DEFAULT_T2 (1 * HZ) /* T2=1s */ #define LAPB_DEFAULT_N2 20 /* N2=20 */ #define LAPB_SMODULUS 8 #define LAPB_EMODULUS 128 /* * Information about the current frame. */ struct lapb_frame { unsigned short type; /* Parsed type */ unsigned short nr, ns; /* N(R), N(S) */ unsigned char cr; /* Command/Response */ unsigned char pf; /* Poll/Final */ unsigned char control[2]; /* Original control data*/ }; /* * The per LAPB connection control structure. */ struct lapb_cb { struct list_head node; struct net_device *dev; /* Link status fields */ unsigned int mode; unsigned char state; unsigned short vs, vr, va; unsigned char condition; unsigned short n2, n2count; unsigned short t1, t2; struct timer_list t1timer, t2timer; /* Internal control information */ struct sk_buff_head write_queue; struct sk_buff_head ack_queue; unsigned char window; const struct lapb_register_struct *callbacks; /* FRMR control information */ struct lapb_frame frmr_data; unsigned char frmr_type; atomic_t refcnt; }; /* lapb_iface.c */ void lapb_connect_confirmation(struct lapb_cb *lapb, int); void lapb_connect_indication(struct lapb_cb *lapb, int); void lapb_disconnect_confirmation(struct lapb_cb *lapb, int); void lapb_disconnect_indication(struct lapb_cb *lapb, int); int lapb_data_indication(struct lapb_cb *lapb, struct sk_buff *); int lapb_data_transmit(struct lapb_cb *lapb, struct sk_buff *); /* lapb_in.c */ void lapb_data_input(struct lapb_cb *lapb, struct sk_buff *); /* lapb_out.c */ void lapb_kick(struct lapb_cb *lapb); void lapb_transmit_buffer(struct lapb_cb *lapb, struct sk_buff *, int); void lapb_establish_data_link(struct lapb_cb *lapb); void lapb_enquiry_response(struct lapb_cb *lapb); void lapb_timeout_response(struct lapb_cb *lapb); void lapb_check_iframes_acked(struct lapb_cb *lapb, unsigned short); void lapb_check_need_response(struct lapb_cb *lapb, int, int); /* lapb_subr.c */ void lapb_clear_queues(struct lapb_cb *lapb); void lapb_frames_acked(struct lapb_cb *lapb, unsigned short); void lapb_requeue_frames(struct lapb_cb *lapb); int lapb_validate_nr(struct lapb_cb *lapb, unsigned short); int lapb_decode(struct lapb_cb *lapb, struct sk_buff *, struct lapb_frame *); void lapb_send_control(struct lapb_cb *lapb, int, int, int); void lapb_transmit_frmr(struct lapb_cb *lapb); /* lapb_timer.c */ void lapb_start_t1timer(struct lapb_cb *lapb); void lapb_start_t2timer(struct lapb_cb *lapb); void lapb_stop_t1timer(struct lapb_cb *lapb); void lapb_stop_t2timer(struct lapb_cb *lapb); int lapb_t1timer_running(struct lapb_cb *lapb); /* * Debug levels. * 0 = Off * 1 = State Changes * 2 = Packets I/O and State Changes * 3 = Hex dumps, Packets I/O and State Changes. */ #define LAPB_DEBUG 0 #define lapb_dbg(level, fmt, ...) \ do { \ if (level < LAPB_DEBUG) \ pr_debug(fmt, ##__VA_ARGS__); \ } while (0) #endif 6d38526a879deb'>bridge: mcast: Merge the mc router ports deletions to one functionNogah Frankel1-15/+9 There are three places where a port gets deleted from the mc router port list. This patch join the actual deletion to one function. It will be helpful for later patch that will offload changes in the mc router ports list. Signed-off-by: Nogah Frankel <nogahf@mellanox.com> Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Ivan Vecera <ivecera@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-10switchdev: bridge: Offload multicast disabledNogah Frankel1-0/+16 Offload multicast disabled flag, for more accurate mc flood behavior: When it is on, the mdb should be ignored. When it is off, unregistered mc packets should be flooded to mc router ports. Signed-off-by: Nogah Frankel <nogahf@mellanox.com> Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Ivan Vecera <ivecera@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-08bridge: vlan tunnel id info range fill size calc cleanupsRoopa Prabhu1-18/+16 This fixes a bug and cleans up tunnelid range size calculation code by using consistent variable names and checks in size calculation and fill functions. tested for a few cases of vlan-vni range mappings: (output from patched iproute2): $bridge vlan showtunnel port vid tunid vxlan0 100-105 1000-1005 200 2000 210 2100 211-213 2100-2102 214 2104 216-217 2108-2109 219 2119 Fixes: efa5356b0d97 ("bridge: per vlan dst_metadata netlink support") Reported-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-07bridge: avoid unnecessary read of jiffiesstephen hemminger2-4/+8 Jiffies is volatile so read it once. Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com> Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-07bridge: remove unnecessary check for vtbegin in br_fill_vlan_tinfo_rangeRoopa Prabhu1-1/+1 vtbegin should not be NULL in this function, Its already checked by the caller. this should silence the below smatch complaint: net/bridge/br_netlink_tunnel.c:144 br_fill_vlan_tinfo_range() error: we previously assumed 'vtbegin' could be null (see line 130) net/bridge/br_netlink_tunnel.c 129 130 if (vtbegin && vtend && (vtend->vid - vtbegin->vid) > 0) { ^^^^^^^ Check for NULL. Fixes: efa5356b0d97 ("bridge: per vlan dst_metadata netlink support") Reported-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-07bridge: tunnel: fix attribute checks in br_parse_vlan_tunnel_infoNikolay Aleksandrov1-4/+4 These checks should go after the attributes have been parsed otherwise we're using tb uninitialized. Fixes: efa5356b0d97 ("bridge: per vlan dst_metadata netlink support") Reported-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-07net: bridge: remove redundant check to see if err is setColin Ian King1-3/+0 The error check on err is redundant as it is being checked previously each time it has been updated. Remove this redundant check. Detected with CoverityScan, CID#140030("Logically dead code") Signed-off-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-06bridge: fdb: write to used and updated at most once per jiffyNikolay Aleksandrov2-2/+4 Writing once per jiffy is enough to limit the bridge's false sharing. After this change the bridge doesn't show up in the local load HitM stats. Suggested-by: David S. Miller <davem@davemloft.net> Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-06bridge: move write-heavy fdb members in their own cache lineNikolay Aleksandrov1-4/+6 Fdb's used and updated fields are written to on every packet forward and packet receive respectively. Thus if we are receiving packets from a particular fdb, they'll cause false-sharing with everyone who has looked it up (even if it didn't match, since mac/vid share cache line!). The "used" field is even worse since it is updated on every packet forward to that fdb, thus the standard config where X ports use a single gateway results in 100% fdb false-sharing. Note that this patch does not prevent the last scenario, but it makes it better for other bridge participants which are not using that fdb (and are only doing lookups over it). The point is with this move we make sure that only communicating parties get the false-sharing, in a later patch we'll show how to avoid that too. Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-06bridge: move to workqueue gcNikolay Aleksandrov10-23/+29 Move the fdb garbage collector to a workqueue which fires at least 10 milliseconds apart and cleans chain by chain allowing for other tasks to run in the meantime. When having thousands of fdbs the system is much more responsive. Most importantly remove the need to check if the matched entry has expired in __br_fdb_get that causes false-sharing and is completely unnecessary if we cleanup entries, at worst we'll get 10ms of traffic for that entry before it gets deleted. Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-06bridge: modify bridge and port to have often accessed fields in one cache lineNikolay Aleksandrov1-23/+20 Move around net_bridge so the vlan fields are in the beginning since they're checked on every packet even if vlan filtering is disabled. For the port move flags & vlan group to the beginning, so they're in the same cache line with the port's state (both flags and state are checked on each packet). Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-06net: remove ndo_neigh_{construct, destroy} from stacked devicesIdo Schimmel1-2/+0 In commit 18bfb924f000 ("net: introduce default neigh_construct/destroy ndo calls for L2 upper devices") we added these ndos to stacked devices such as team and bond, so that calls will be propagated to mlxsw. However, previous commit removed the reliance on these ndos and no new users of these ndos have appeared since above mentioned commit. We can therefore safely remove this dead code. Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-nextDavid S. Miller3-32/+49 Pablo Neira Ayuso says: ==================== Netfilter updates for net-next The following patchset contains Netfilter updates for your net-next tree, they are: 1) Stash ctinfo 3-bit field into pointer to nf_conntrack object from sk_buff so we only access one single cacheline in the conntrack hotpath. Patchset from Florian Westphal. 2) Don't leak pointer to internal structures when exporting x_tables ruleset back to userspace, from Willem DeBruijn. This includes new helper functions to copy data to userspace such as xt_data_to_user() as well as conversions of our ip_tables, ip6_tables and arp_tables clients to use it. Not surprinsingly, ebtables requires an ad-hoc update. There is also a new field in x_tables extensions to indicate the amount of bytes that we copy to userspace. 3) Add nf_log_all_netns sysctl: This new knob allows you to enable logging via nf_log infrastructure for all existing netnamespaces. Given the effort to provide pernet syslog has been discontinued, let's provide a way to restore logging using netfilter kernel logging facilities in trusted environments. Patch from Michal Kubecek. 4) Validate SCTP checksum from conntrack helper, from Davide Caratti. 5) Merge UDPlite conntrack and NAT helpers into UDP, this was mostly a copy&paste from the original helper, from Florian Westphal. 6) Reset netfilter state when duplicating packets, also from Florian. 7) Remove unnecessary check for broadcast in IPv6 in pkttype match and nft_meta, from Liping Zhang. 8) Add missing code to deal with loopback packets from nft_meta when used by the netdev family, also from Liping. 9) Several cleanups on nf_tables, one to remove unnecessary check from the netlink control plane path to add table, set and stateful objects and code consolidation when unregister chain hooks, from Gao Feng. 10) Fix harmless reference counter underflow in IPVS that, however, results in problems with the introduction of the new refcount_t type, from David Windsor. 11) Enable LIBCRC32C from nf_ct_sctp instead of nf_nat_sctp, from Davide Caratti. 12) Missing documentation on nf_tables uapi header, from Liping Zhang. 13) Use rb_entry() helper in xt_connlimit, from Geliang Tang. ==================== Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03bridge: vlan dst_metadata hooks in ingress and egress pathsRoopa Prabhu6-2/+82 - ingress hook: - if port is a tunnel port, use tunnel info in attached dst_metadata to map it to a local vlan - egress hook: - if port is a tunnel port, use tunnel info attached to vlan to set dst_metadata on the skb CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03bridge: per vlan dst_metadata netlink supportRoopa Prabhu7-48/+641 This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-02netfilter: allow logging from non-init namespacesMichal Kubeček1-1/+1 Commit 69b34fb996b2 ("netfilter: xt_LOG: add net namespace support for xt_LOG") disabled logging packets using the LOG target from non-init namespaces. The motivation was to prevent containers from flooding kernel log of the host. The plan was to keep it that way until syslog namespace implementation allows containers to log in a safe way. However, the work on syslog namespace seems to have hit a dead end somewhere in 2013 and there are users who want to use xt_LOG in all network namespaces. This patch allows to do so by setting /proc/sys/net/netfilter/nf_log_all_netns to a nonzero value. This sysctl is only accessible from init_net so that one cannot switch the behaviour from inside a container. Signed-off-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>