diff options
Diffstat (limited to 'tools')
33 files changed, 3901 insertions, 898 deletions
diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h index 54d9c8bf7c55..281df9139d2b 100644 --- a/tools/include/uapi/asm-generic/socket.h +++ b/tools/include/uapi/asm-generic/socket.h @@ -124,6 +124,8 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SCM_TS_OPT_ID 78 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index f0d71b2a3f1e..8516c1ccd57a 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -377,6 +377,7 @@ enum { IFLA_GSO_IPV4_MAX_SIZE, IFLA_GRO_IPV4_MAX_SIZE, IFLA_DPLL_PIN, + IFLA_MAX_PACING_OFFLOAD_HORIZON, __IFLA_MAX }; @@ -461,6 +462,286 @@ enum in6_addr_gen_mode { /* Bridge section */ +/** + * DOC: Bridge enum definition + * + * Please *note* that the timer values in the following section are expected + * in clock_t format, which is seconds multiplied by USER_HZ (generally + * defined as 100). + * + * @IFLA_BR_FORWARD_DELAY + * The bridge forwarding delay is the time spent in LISTENING state + * (before moving to LEARNING) and in LEARNING state (before moving + * to FORWARDING). Only relevant if STP is enabled. + * + * The valid values are between (2 * USER_HZ) and (30 * USER_HZ). + * The default value is (15 * USER_HZ). + * + * @IFLA_BR_HELLO_TIME + * The time between hello packets sent by the bridge, when it is a root + * bridge or a designated bridge. Only relevant if STP is enabled. + * + * The valid values are between (1 * USER_HZ) and (10 * USER_HZ). + * The default value is (2 * USER_HZ). + * + * @IFLA_BR_MAX_AGE + * The hello packet timeout is the time until another bridge in the + * spanning tree is assumed to be dead, after reception of its last hello + * message. Only relevant if STP is enabled. + * + * The valid values are between (6 * USER_HZ) and (40 * USER_HZ). + * The default value is (20 * USER_HZ). + * + * @IFLA_BR_AGEING_TIME + * Configure the bridge's FDB entries aging time. It is the time a MAC + * address will be kept in the FDB after a packet has been received from + * that address. After this time has passed, entries are cleaned up. + * Allow values outside the 802.1 standard specification for special cases: + * + * * 0 - entry never ages (all permanent) + * * 1 - entry disappears (no persistence) + * + * The default value is (300 * USER_HZ). + * + * @IFLA_BR_STP_STATE + * Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off + * (*IFLA_BR_STP_STATE* == 0) for this bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_PRIORITY + * Set this bridge's spanning tree priority, used during STP root bridge + * election. + * + * The valid values are between 0 and 65535. + * + * @IFLA_BR_VLAN_FILTERING + * Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off + * (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not + * consider the VLAN tag when handling packets. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_VLAN_PROTOCOL + * Set the protocol used for VLAN filtering. + * + * The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value + * is 0x8100(802.1Q). + * + * @IFLA_BR_GROUP_FWD_MASK + * The group forwarding mask. This is the bitmask that is applied to + * decide whether to forward incoming frames destined to link-local + * addresses (of the form 01:80:C2:00:00:0X). + * + * The default value is 0, which means the bridge does not forward any + * link-local frames coming on this port. + * + * @IFLA_BR_ROOT_ID + * The bridge root id, read only. + * + * @IFLA_BR_BRIDGE_ID + * The bridge id, read only. + * + * @IFLA_BR_ROOT_PORT + * The bridge root port, read only. + * + * @IFLA_BR_ROOT_PATH_COST + * The bridge root path cost, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE + * The bridge topology change, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED + * The bridge topology change detected, read only. + * + * @IFLA_BR_HELLO_TIMER + * The bridge hello timer, read only. + * + * @IFLA_BR_TCN_TIMER + * The bridge tcn timer, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE_TIMER + * The bridge topology change timer, read only. + * + * @IFLA_BR_GC_TIMER + * The bridge gc timer, read only. + * + * @IFLA_BR_GROUP_ADDR + * Set the MAC address of the multicast group this bridge uses for STP. + * The address must be a link-local address in standard Ethernet MAC address + * format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f]. + * + * The default value is 0. + * + * @IFLA_BR_FDB_FLUSH + * Flush bridge's fdb dynamic entries. + * + * @IFLA_BR_MCAST_ROUTER + * Set bridge's multicast router if IGMP snooping is enabled. + * The valid values are: + * + * * 0 - disabled. + * * 1 - automatic (queried). + * * 2 - permanently enabled. + * + * The default value is 1. + * + * @IFLA_BR_MCAST_SNOOPING + * Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off + * (*IFLA_BR_MCAST_SNOOPING* == 0). + * + * The default value is 1. + * + * @IFLA_BR_MCAST_QUERY_USE_IFADDR + * If enabled use the bridge's own IP address as source address for IGMP + * queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0 + * (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0). + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_QUERIER + * Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable + * (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast + * queries by the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_HASH_ELASTICITY + * Set multicast database hash elasticity, It is the maximum chain length in + * the multicast hash table. This attribute is *deprecated* and the value + * is always 16. + * + * @IFLA_BR_MCAST_HASH_MAX + * Set maximum size of the multicast hash table + * + * The default value is 4096, the value must be a power of 2. + * + * @IFLA_BR_MCAST_LAST_MEMBER_CNT + * The Last Member Query Count is the number of Group-Specific Queries + * sent before the router assumes there are no local members. The Last + * Member Query Count is also the number of Group-and-Source-Specific + * Queries sent before the router assumes there are no listeners for a + * particular source. + * + * The default value is 2. + * + * @IFLA_BR_MCAST_STARTUP_QUERY_CNT + * The Startup Query Count is the number of Queries sent out on startup, + * separated by the Startup Query Interval. + * + * The default value is 2. + * + * @IFLA_BR_MCAST_LAST_MEMBER_INTVL + * The Last Member Query Interval is the Max Response Time inserted into + * Group-Specific Queries sent in response to Leave Group messages, and + * is also the amount of time between Group-Specific Query messages. + * + * The default value is (1 * USER_HZ). + * + * @IFLA_BR_MCAST_MEMBERSHIP_INTVL + * The interval after which the bridge will leave a group, if no membership + * reports for this group are received. + * + * The default value is (260 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERIER_INTVL + * The interval between queries sent by other routers. if no queries are + * seen after this delay has passed, the bridge will start to send its own + * queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled). + * + * The default value is (255 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERY_INTVL + * The Query Interval is the interval between General Queries sent by + * the Querier. + * + * The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL + * The Max Response Time used to calculate the Max Resp Code inserted + * into the periodic General Queries. + * + * The default value is (10 * USER_HZ). + * + * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL + * The interval between queries in the startup phase. + * + * The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ). + * + * @IFLA_BR_NF_CALL_IPTABLES + * Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0) + * iptables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_NF_CALL_IP6TABLES + * Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0) + * ip6tables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_NF_CALL_ARPTABLES + * Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0) + * arptables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_VLAN_DEFAULT_PVID + * VLAN ID applied to untagged and priority-tagged incoming packets. + * + * The default value is 1. Setting to the special value 0 makes all ports of + * this bridge not have a PVID by default, which means that they will + * not accept VLAN-untagged traffic. + * + * @IFLA_BR_PAD + * Bridge attribute padding type for netlink message. + * + * @IFLA_BR_VLAN_STATS_ENABLED + * Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable + * (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_STATS_ENABLED + * Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable + * (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats + * accounting. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_IGMP_VERSION + * Set the IGMP version. + * + * The valid values are 2 and 3. The default value is 2. + * + * @IFLA_BR_MCAST_MLD_VERSION + * Set the MLD version. + * + * The valid values are 1 and 2. The default value is 1. + * + * @IFLA_BR_VLAN_STATS_PER_PORT + * Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable + * (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting. + * Can be changed only when there are no port VLANs configured. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MULTI_BOOLOPT + * The multi_boolopt is used to control new boolean options to avoid adding + * new netlink attributes. You can look at ``enum br_boolopt_id`` for those + * options. + * + * @IFLA_BR_MCAST_QUERIER_STATE + * Bridge mcast querier states, read only. + * + * @IFLA_BR_FDB_N_LEARNED + * The number of dynamically learned FDB entries for the current bridge, + * read only. + * + * @IFLA_BR_FDB_MAX_LEARNED + * Set the number of max dynamically learned FDB entries for the current + * bridge. + */ enum { IFLA_BR_UNSPEC, IFLA_BR_FORWARD_DELAY, @@ -510,6 +791,8 @@ enum { IFLA_BR_VLAN_STATS_PER_PORT, IFLA_BR_MULTI_BOOLOPT, IFLA_BR_MCAST_QUERIER_STATE, + IFLA_BR_FDB_N_LEARNED, + IFLA_BR_FDB_MAX_LEARNED, __IFLA_BR_MAX, }; @@ -520,11 +803,252 @@ struct ifla_bridge_id { __u8 addr[6]; /* ETH_ALEN */ }; +/** + * DOC: Bridge mode enum definition + * + * @BRIDGE_MODE_HAIRPIN + * Controls whether traffic may be sent back out of the port on which it + * was received. This option is also called reflective relay mode, and is + * used to support basic VEPA (Virtual Ethernet Port Aggregator) + * capabilities. By default, this flag is turned off and the bridge will + * not forward traffic back out of the receiving port. + */ enum { BRIDGE_MODE_UNSPEC, BRIDGE_MODE_HAIRPIN, }; +/** + * DOC: Bridge port enum definition + * + * @IFLA_BRPORT_STATE + * The operation state of the port. Here are the valid values. + * + * * 0 - port is in STP *DISABLED* state. Make this port completely + * inactive for STP. This is also called BPDU filter and could be used + * to disable STP on an untrusted port, like a leaf virtual device. + * The traffic forwarding is also stopped on this port. + * * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled + * on the bridge. In this state the port listens for STP BPDUs and + * drops all other traffic frames. + * * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on + * the bridge. In this state the port will accept traffic only for the + * purpose of updating MAC address tables. + * * 3 - port is in STP *FORWARDING* state. Port is fully active. + * * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on + * the bridge. This state is used during the STP election process. + * In this state, port will only process STP BPDUs. + * + * @IFLA_BRPORT_PRIORITY + * The STP port priority. The valid values are between 0 and 255. + * + * @IFLA_BRPORT_COST + * The STP path cost of the port. The valid values are between 1 and 65535. + * + * @IFLA_BRPORT_MODE + * Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details. + * + * @IFLA_BRPORT_GUARD + * Controls whether STP BPDUs will be processed by the bridge port. By + * default, the flag is turned off to allow BPDU processing. Turning this + * flag on will disable the bridge port if a STP BPDU packet is received. + * + * If the bridge has Spanning Tree enabled, hostile devices on the network + * may send BPDU on a port and cause network failure. Setting *guard on* + * will detect and stop this by disabling the port. The port will be + * restarted if the link is brought down, or removed and reattached. + * + * @IFLA_BRPORT_PROTECT + * Controls whether a given port is allowed to become a root port or not. + * Only used when STP is enabled on the bridge. By default the flag is off. + * + * This feature is also called root port guard. If BPDU is received from a + * leaf (edge) port, it should not be elected as root port. This could + * be used if using STP on a bridge and the downstream bridges are not fully + * trusted; this prevents a hostile guest from rerouting traffic. + * + * @IFLA_BRPORT_FAST_LEAVE + * This flag allows the bridge to immediately stop multicast traffic + * forwarding on a port that receives an IGMP Leave message. It is only used + * when IGMP snooping is enabled on the bridge. By default the flag is off. + * + * @IFLA_BRPORT_LEARNING + * Controls whether a given port will learn *source* MAC addresses from + * received traffic or not. Also controls whether dynamic FDB entries + * (which can also be added by software) will be refreshed by incoming + * traffic. By default this flag is on. + * + * @IFLA_BRPORT_UNICAST_FLOOD + * Controls whether unicast traffic for which there is no FDB entry will + * be flooded towards this port. By default this flag is on. + * + * @IFLA_BRPORT_PROXYARP + * Enable proxy ARP on this port. + * + * @IFLA_BRPORT_LEARNING_SYNC + * Controls whether a given port will sync MAC addresses learned on device + * port to bridge FDB. + * + * @IFLA_BRPORT_PROXYARP_WIFI + * Enable proxy ARP on this port which meets extended requirements by + * IEEE 802.11 and Hotspot 2.0 specifications. + * + * @IFLA_BRPORT_ROOT_ID + * + * @IFLA_BRPORT_BRIDGE_ID + * + * @IFLA_BRPORT_DESIGNATED_PORT + * + * @IFLA_BRPORT_DESIGNATED_COST + * + * @IFLA_BRPORT_ID + * + * @IFLA_BRPORT_NO + * + * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK + * + * @IFLA_BRPORT_CONFIG_PENDING + * + * @IFLA_BRPORT_MESSAGE_AGE_TIMER + * + * @IFLA_BRPORT_FORWARD_DELAY_TIMER + * + * @IFLA_BRPORT_HOLD_TIMER + * + * @IFLA_BRPORT_FLUSH + * Flush bridge ports' fdb dynamic entries. + * + * @IFLA_BRPORT_MULTICAST_ROUTER + * Configure the port's multicast router presence. A port with + * a multicast router will receive all multicast traffic. + * The valid values are: + * + * * 0 disable multicast routers on this port + * * 1 let the system detect the presence of routers (default) + * * 2 permanently enable multicast traffic forwarding on this port + * * 3 enable multicast routers temporarily on this port, not depending + * on incoming queries. + * + * @IFLA_BRPORT_PAD + * + * @IFLA_BRPORT_MCAST_FLOOD + * Controls whether a given port will flood multicast traffic for which + * there is no MDB entry. By default this flag is on. + * + * @IFLA_BRPORT_MCAST_TO_UCAST + * Controls whether a given port will replicate packets using unicast + * instead of multicast. By default this flag is off. + * + * This is done by copying the packet per host and changing the multicast + * destination MAC to a unicast one accordingly. + * + * *mcast_to_unicast* works on top of the multicast snooping feature of the + * bridge. Which means unicast copies are only delivered to hosts which + * are interested in unicast and signaled this via IGMP/MLD reports previously. + * + * This feature is intended for interface types which have a more reliable + * and/or efficient way to deliver unicast packets than broadcast ones + * (e.g. WiFi). + * + * However, it should only be enabled on interfaces where no IGMPv2/MLDv1 + * report suppression takes place. IGMP/MLD report suppression issue is + * usually overcome by the network daemon (supplicant) enabling AP isolation + * and by that separating all STAs. + * + * Delivery of STA-to-STA IP multicast is made possible again by enabling + * and utilizing the bridge hairpin mode, which considers the incoming port + * as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option). + * Hairpin mode is performed after multicast snooping, therefore leading + * to only deliver reports to STAs running a multicast router. + * + * @IFLA_BRPORT_VLAN_TUNNEL + * Controls whether vlan to tunnel mapping is enabled on the port. + * By default this flag is off. + * + * @IFLA_BRPORT_BCAST_FLOOD + * Controls flooding of broadcast traffic on the given port. By default + * this flag is on. + * + * @IFLA_BRPORT_GROUP_FWD_MASK + * Set the group forward mask. This is a bitmask that is applied to + * decide whether to forward incoming frames destined to link-local + * addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults + * to 0, which means the bridge does not forward any link-local frames + * coming on this port). + * + * @IFLA_BRPORT_NEIGH_SUPPRESS + * Controls whether neighbor discovery (arp and nd) proxy and suppression + * is enabled on the port. By default this flag is off. + * + * @IFLA_BRPORT_ISOLATED + * Controls whether a given port will be isolated, which means it will be + * able to communicate with non-isolated ports only. By default this + * flag is off. + * + * @IFLA_BRPORT_BACKUP_PORT + * Set a backup port. If the port loses carrier all traffic will be + * redirected to the configured backup port. Set the value to 0 to disable + * it. + * + * @IFLA_BRPORT_MRP_RING_OPEN + * + * @IFLA_BRPORT_MRP_IN_OPEN + * + * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + * The number of per-port EHT hosts limit. The default value is 512. + * Setting to 0 is not allowed. + * + * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT + * The current number of tracked hosts, read only. + * + * @IFLA_BRPORT_LOCKED + * Controls whether a port will be locked, meaning that hosts behind the + * port will not be able to communicate through the port unless an FDB + * entry with the unit's MAC address is in the FDB. The common use case is + * that hosts are allowed access through authentication with the IEEE 802.1X + * protocol or based on whitelists. By default this flag is off. + * + * Please note that secure 802.1X deployments should always use the + * *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its + * FDB based on link-local (EAPOL) traffic received on the port. + * + * @IFLA_BRPORT_MAB + * Controls whether a port will use MAC Authentication Bypass (MAB), a + * technique through which select MAC addresses may be allowed on a locked + * port, without using 802.1X authentication. Packets with an unknown source + * MAC address generates a "locked" FDB entry on the incoming bridge port. + * The common use case is for user space to react to these bridge FDB + * notifications and optionally replace the locked FDB entry with a normal + * one, allowing traffic to pass for whitelisted MAC addresses. + * + * Setting this flag also requires *IFLA_BRPORT_LOCKED* and + * *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized + * data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic + * FDB entries installed by user space (as replacements for the locked FDB + * entries) to be refreshed and/or aged out. + * + * @IFLA_BRPORT_MCAST_N_GROUPS + * + * @IFLA_BRPORT_MCAST_MAX_GROUPS + * Sets the maximum number of MDB entries that can be registered for a + * given port. Attempts to register more MDB entries at the port than this + * limit allows will be rejected, whether they are done through netlink + * (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a + * limit of 0 disables the limit. The default value is 0. + * + * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS + * Controls whether neighbor discovery (arp and nd) proxy and suppression is + * enabled for a given port. By default this flag is off. + * + * Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS* + * is enabled for a given port. + * + * @IFLA_BRPORT_BACKUP_NHID + * The FDB nexthop object ID to attach to packets being redirected to a + * backup port that has VLAN tunnel mapping enabled (via the + * *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has + * the effect of not attaching any ID. + */ enum { IFLA_BRPORT_UNSPEC, IFLA_BRPORT_STATE, /* Spanning tree state */ @@ -769,6 +1293,19 @@ enum netkit_mode { NETKIT_L3, }; +/* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to + * the BPF program if attached. This also means the latter can + * consume the two fields if they were populated earlier. + * + * NETKIT_SCRUB_DEFAULT zeroes skb->{mark,priority} fields before + * invoking the attached BPF program when the peer device resides + * in a different network namespace. This is the default behavior. + */ +enum netkit_scrub { + NETKIT_SCRUB_NONE, + NETKIT_SCRUB_DEFAULT, +}; + enum { IFLA_NETKIT_UNSPEC, IFLA_NETKIT_PEER_INFO, @@ -776,6 +1313,8 @@ enum { IFLA_NETKIT_POLICY, IFLA_NETKIT_PEER_POLICY, IFLA_NETKIT_MODE, + IFLA_NETKIT_SCRUB, + IFLA_NETKIT_PEER_SCRUB, __IFLA_NETKIT_MAX, }; #define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1) @@ -854,6 +1393,7 @@ enum { IFLA_VXLAN_DF, IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */ IFLA_VXLAN_LOCALBYPASS, + IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */ __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) @@ -871,6 +1411,13 @@ enum ifla_vxlan_df { VXLAN_DF_MAX = __VXLAN_DF_END - 1, }; +enum ifla_vxlan_label_policy { + VXLAN_LABEL_FIXED = 0, + VXLAN_LABEL_INHERIT = 1, + __VXLAN_LABEL_END, + VXLAN_LABEL_MAX = __VXLAN_LABEL_END - 1, +}; + /* GENEVE section */ enum { IFLA_GENEVE_UNSPEC, @@ -935,6 +1482,8 @@ enum { IFLA_GTP_ROLE, IFLA_GTP_CREATE_SOCKETS, IFLA_GTP_RESTART_COUNT, + IFLA_GTP_LOCAL, + IFLA_GTP_LOCAL6, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) @@ -1240,6 +1789,7 @@ enum { IFLA_HSR_PROTOCOL, /* Indicate different protocol than * HSR. For example PRP. */ + IFLA_HSR_INTERLINK, /* HSR interlink network device */ __IFLA_HSR_MAX, }; @@ -1417,7 +1967,9 @@ enum { enum { IFLA_DSA_UNSPEC, - IFLA_DSA_MASTER, + IFLA_DSA_CONDUIT, + /* Deprecated, use IFLA_DSA_CONDUIT instead */ + IFLA_DSA_MASTER = IFLA_DSA_CONDUIT, __IFLA_DSA_MAX, }; diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 7c308f04e7a0..e3ebb49f60d2 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -122,6 +122,8 @@ enum { NETDEV_A_NAPI_ID, NETDEV_A_NAPI_IRQ, NETDEV_A_NAPI_PID, + NETDEV_A_NAPI_DEFER_HARD_IRQS, + NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) @@ -199,6 +201,7 @@ enum { NETDEV_CMD_NAPI_GET, NETDEV_CMD_QSTATS_GET, NETDEV_CMD_BIND_RX, + NETDEV_CMD_NAPI_SET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 717530bc9c52..d64cb2b49c44 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -80,11 +80,21 @@ class Type(SpecAttr): value = self.checks.get(limit, default) if value is None: return value - elif value in self.family.consts: + if isinstance(value, int): + return value + if value in self.family.consts: + raise Exception("Resolving family constants not implemented, yet") + return limit_to_number(value) + + def get_limit_str(self, limit, default=None, suffix=''): + value = self.checks.get(limit, default) + if value is None: + return '' + if isinstance(value, int): + return str(value) + suffix + if value in self.family.consts: return c_upper(f"{self.family['name']}-{value}") - if not isinstance(value, int): - value = limit_to_number(value) - return value + return c_upper(value) def resolve(self): if 'name-prefix' in self.attr: @@ -358,11 +368,11 @@ class TypeScalar(Type): elif 'full-range' in self.checks: return f"NLA_POLICY_FULL_RANGE({policy}, &{c_lower(self.enum_name)}_range)" elif 'range' in self.checks: - return f"NLA_POLICY_RANGE({policy}, {self.get_limit('min')}, {self.get_limit('max')})" + return f"NLA_POLICY_RANGE({policy}, {self.get_limit_str('min')}, {self.get_limit_str('max')})" elif 'min' in self.checks: - return f"NLA_POLICY_MIN({policy}, {self.get_limit('min')})" + return f"NLA_POLICY_MIN({policy}, {self.get_limit_str('min')})" elif 'max' in self.checks: - return f"NLA_POLICY_MAX({policy}, {self.get_limit('max')})" + return f"NLA_POLICY_MAX({policy}, {self.get_limit_str('max')})" return super()._attr_policy(policy) def _attr_typol(self): @@ -413,11 +423,11 @@ class TypeString(Type): def _attr_policy(self, policy): if 'exact-len' in self.checks: - mem = 'NLA_POLICY_EXACT_LEN(' + str(self.get_limit('exact-len')) + ')' + mem = 'NLA_POLICY_EXACT_LEN(' + self.get_limit_str('exact-len') + ')' else: mem = '{ .type = ' + policy if 'max-len' in self.checks: - mem += ', .len = ' + str(self.get_limit('max-len')) + mem += ', .len = ' + self.get_limit_str('max-len') mem += ', }' return mem @@ -464,17 +474,22 @@ class TypeBinary(Type): return f'.type = YNL_PT_BINARY,' def _attr_policy(self, policy): - if 'exact-len' in self.checks: - mem = 'NLA_POLICY_EXACT_LEN(' + str(self.get_limit('exact-len')) + ')' + if len(self.checks) == 0: + pass + elif len(self.checks) == 1: + check_name = list(self.checks)[0] + if check_name not in {'exact-len', 'min-len'}: + raise Exception('Unsupported check for binary type: ' + check_name) else: - mem = '{ ' - if len(self.checks) == 1 and 'min-len' in self.checks: - mem += '.len = ' + str(self.get_limit('min-len')) - elif len(self.checks) == 0: - mem += '.type = NLA_BINARY' - else: - raise Exception('One or more of binary type checks not implemented, yet') - mem += ', }' + raise Exception('More than one check for binary type not implemented, yet') + + if len(self.checks) == 0: + mem = '{ .type = NLA_BINARY, }' + elif 'exact-len' in self.checks: + mem = 'NLA_POLICY_EXACT_LEN(' + self.get_limit_str('exact-len') + ')' + elif 'min-len' in self.checks: + mem = '{ .len = ' + self.get_limit_str('min-len') + ', }' + return mem def attr_put(self, ri, var): @@ -2161,9 +2176,9 @@ def print_kernel_policy_ranges(family, cw): cw.block_start(line=f'static const struct netlink_range_validation{sign} {c_lower(attr.enum_name)}_range =') members = [] if 'min' in attr.checks: - members.append(('min', str(attr.get_limit('min')) + suffix)) + members.append(('min', attr.get_limit_str('min', suffix=suffix))) if 'max' in attr.checks: - members.append(('max', str(attr.get_limit('max')) + suffix)) + members.append(('max', attr.get_limit_str('max', suffix=suffix))) cw.write_struct_init(members) cw.block_end(line=';') cw.nl() diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index c72c16e1aff8..5764155b6d25 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NETWORK_HELPERS_H #define __NETWORK_HELPERS_H +#include <arpa/inet.h> #include <sys/socket.h> #include <sys/types.h> #include <linux/types.h> diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c index d2ca32fa3b21..be3cad2aff77 100644 --- a/tools/testing/selftests/bpf/prog_tests/mptcp.c +++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c @@ -5,12 +5,17 @@ #include <linux/const.h> #include <netinet/in.h> #include <test_progs.h> +#include <unistd.h> #include "cgroup_helpers.h" #include "network_helpers.h" #include "mptcp_sock.skel.h" #include "mptcpify.skel.h" +#include "mptcp_subflow.skel.h" #define NS_TEST "mptcp_ns" +#define ADDR_1 "10.0.1.1" +#define ADDR_2 "10.0.1.2" +#define PORT_1 10001 #ifndef IPPROTO_MPTCP #define IPPROTO_MPTCP 262 @@ -335,10 +340,126 @@ fail: close(cgroup_fd); } +static int endpoint_init(char *flags) +{ + SYS(fail, "ip -net %s link add veth1 type veth peer name veth2", NS_TEST); + SYS(fail, "ip -net %s addr add %s/24 dev veth1", NS_TEST, ADDR_1); + SYS(fail, "ip -net %s link set dev veth1 up", NS_TEST); + SYS(fail, "ip -net %s addr add %s/24 dev veth2", NS_TEST, ADDR_2); + SYS(fail, "ip -net %s link set dev veth2 up", NS_TEST); + if (SYS_NOFAIL("ip -net %s mptcp endpoint add %s %s", NS_TEST, ADDR_2, flags)) { + printf("'ip mptcp' not supported, skip this test.\n"); + test__skip(); + goto fail; + } + + return 0; +fail: + return -1; +} + +static void wait_for_new_subflows(int fd) +{ + socklen_t len; + u8 subflows; + int err, i; + + len = sizeof(subflows); + /* Wait max 5 sec for new subflows to be created */ + for (i = 0; i < 50; i++) { + err = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &subflows, &len); + if (!err && subflows > 0) + break; + + usleep(100000); /* 0.1s */ + } +} + +static void run_subflow(void) +{ + int server_fd, client_fd, err; + char new[TCP_CA_NAME_MAX]; + char cc[TCP_CA_NAME_MAX]; + unsigned int mark; + socklen_t len; + + server_fd = start_mptcp_server(AF_INET, ADDR_1, PORT_1, 0); + if (!ASSERT_OK_FD(server_fd, "start_mptcp_server")) + return; + + client_fd = connect_to_fd(server_fd, 0); + if (!ASSERT_OK_FD(client_fd, "connect_to_fd")) + goto close_server; + + send_byte(client_fd); + wait_for_new_subflows(client_fd); + + len = sizeof(mark); + err = getsockopt(client_fd, SOL_SOCKET, SO_MARK, &mark, &len); + if (ASSERT_OK(err, "getsockopt(client_fd, SO_MARK)")) + ASSERT_EQ(mark, 0, "mark"); + + len = sizeof(new); + err = getsockopt(client_fd, SOL_TCP, TCP_CONGESTION, new, &len); + if (ASSERT_OK(err, "getsockopt(client_fd, TCP_CONGESTION)")) { + get_msk_ca_name(cc); + ASSERT_STREQ(new, cc, "cc"); + } + + close(client_fd); +close_server: + close(server_fd); +} + +static void test_subflow(void) +{ + struct mptcp_subflow *skel; + struct nstoken *nstoken; + int cgroup_fd; + + cgroup_fd = test__join_cgroup("/mptcp_subflow"); + if (!ASSERT_OK_FD(cgroup_fd, "join_cgroup: mptcp_subflow")) + return; + + skel = mptcp_subflow__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_load: mptcp_subflow")) + goto close_cgroup; + + skel->bss->pid = getpid(); + + skel->links.mptcp_subflow = + bpf_program__attach_cgroup(skel->progs.mptcp_subflow, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.mptcp_subflow, "attach mptcp_subflow")) + goto skel_destroy; + + skel->links._getsockopt_subflow = + bpf_program__attach_cgroup(skel->progs._getsockopt_subflow, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links._getsockopt_subflow, "attach _getsockopt_subflow")) + goto skel_destroy; + + nstoken = create_netns(); + if (!ASSERT_OK_PTR(nstoken, "create_netns: mptcp_subflow")) + goto skel_destroy; + + if (endpoint_init("subflow") < 0) + goto close_netns; + + run_subflow(); + +close_netns: + cleanup_netns(nstoken); +skel_destroy: + mptcp_subflow__destroy(skel); +close_cgroup: + close(cgroup_fd); +} + void test_mptcp(void) { if (test__start_subtest("base")) test_base(); if (test__start_subtest("mptcpify")) test_mptcpify(); + if (test__start_subtest("subflow")) + test_subflow(); } diff --git a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c index 71d8f3ba7d6b..ac3c3c097c0e 100644 --- a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c @@ -8,12 +8,16 @@ #define SO_NETNS_COOKIE 71 #endif +#define loopback 1 + static int duration; void test_netns_cookie(void) { + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); int server_fd = -1, client_fd = -1, cgroup_fd = -1; - int err, val, ret, map, verdict; + int err, val, ret, map, verdict, tc_fd; struct netns_cookie_prog *skel; uint64_t cookie_expected_value; socklen_t vallen = sizeof(cookie_expected_value); @@ -38,36 +42,47 @@ void test_netns_cookie(void) if (!ASSERT_OK(err, "prog_attach")) goto done; + tc_fd = bpf_program__fd(skel->progs.get_netns_cookie_tcx); + err = bpf_prog_attach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &opta); + if (!ASSERT_OK(err, "prog_attach")) + goto done; + server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); if (CHECK(server_fd < 0, "start_server", "errno %d\n", errno)) - goto done; + goto cleanup_tc; client_fd = connect_to_fd(server_fd, 0); if (CHECK(client_fd < 0, "connect_to_fd", "errno %d\n", errno)) - goto done; + goto cleanup_tc; ret = send(client_fd, send_msg, sizeof(send_msg), 0); if (CHECK(ret != sizeof(send_msg), "send(msg)", "ret:%d\n", ret)) - goto done; + goto cleanup_tc; err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sockops_netns_cookies), &client_fd, &val); if (!ASSERT_OK(err, "map_lookup(sockops_netns_cookies)")) - goto done; + goto cleanup_tc; err = getsockopt(client_fd, SOL_SOCKET, SO_NETNS_COOKIE, &cookie_expected_value, &vallen); if (!ASSERT_OK(err, "getsockopt")) - goto done; + goto cleanup_tc; ASSERT_EQ(val, cookie_expected_value, "cookie_value"); err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sk_msg_netns_cookies), &client_fd, &val); if (!ASSERT_OK(err, "map_lookup(sk_msg_netns_cookies)")) - goto done; + goto cleanup_tc; ASSERT_EQ(val, cookie_expected_value, "cookie_value"); + ASSERT_EQ(skel->bss->tcx_init_netns_cookie, cookie_expected_value, "cookie_value"); + ASSERT_EQ(skel->bss->tcx_netns_cookie, cookie_expected_value, "cookie_value"); + +cleanup_tc: + err = bpf_prog_detach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &optd); + ASSERT_OK(err, "prog_detach"); done: if (server_fd != -1) diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c index b9135720024c..151a4210028f 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c @@ -14,7 +14,9 @@ #include "netlink_helpers.h" #include "tc_helpers.h" -#define ICMP_ECHO 8 +#define MARK 42 +#define PRIO 0xeb9f +#define ICMP_ECHO 8 struct icmphdr { __u8 type; @@ -33,7 +35,7 @@ struct iplink_req { }; static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, - bool same_netns) + bool same_netns, int scrub, int peer_scrub) { struct rtnl_handle rth = { .fd = -1 }; struct iplink_req req = {}; @@ -58,6 +60,8 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA); addattr32(&req.n, sizeof(req), IFLA_NETKIT_POLICY, policy); addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_POLICY, peer_policy); + addattr32(&req.n, sizeof(req), IFLA_NETKIT_SCRUB, scrub); + addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_SCRUB, peer_scrub); addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode); addattr_nest_end(&req.n, data); addattr_nest_end(&req.n, linkinfo); @@ -118,9 +122,9 @@ static void destroy_netkit(void) static int __send_icmp(__u32 dest) { + int sock, ret, mark = MARK, prio = PRIO; struct sockaddr_in addr; struct icmphdr icmp; - int sock, ret; ret = write_sysctl("/proc/sys/net/ipv4/ping_group_range", "0 0"); if (!ASSERT_OK(ret, "write_sysctl(net.ipv4.ping_group_range)")) @@ -135,6 +139,15 @@ static int __send_icmp(__u32 dest) if (!ASSERT_OK(ret, "setsockopt(SO_BINDTODEVICE)")) goto out; + ret = setsockopt(sock, SOL_SOCKET, SO_MARK, &mark, sizeof(mark)); + if (!ASSERT_OK(ret, "setsockopt(SO_MARK)")) + goto out; + + ret = setsockopt(sock, SOL_SOCKET, SO_PRIORITY, + &prio, sizeof(prio)); + if (!ASSERT_OK(ret, "setsockopt(SO_PRIORITY)")) + goto out; + memset(&addr, 0, sizeof(addr)); addr.sin_family = AF_INET; addr.sin_addr.s_addr = htonl(dest); @@ -171,7 +184,8 @@ void serial_test_tc_netkit_basic(void) int err, ifindex; err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS, - &ifindex, false); + &ifindex, false, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT); if (err) return; @@ -285,7 +299,8 @@ static void serial_test_tc_netkit_multi_links_target(int mode, int target) int err, ifindex; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, false); + &ifindex, false, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT); if (err) return; @@ -413,7 +428,8 @@ static void serial_test_tc_netkit_multi_opts_target(int mode, int target) int err, ifindex; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, false); + &ifindex, false, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT); if (err) return; @@ -527,7 +543,8 @@ void serial_test_tc_netkit_device(void) int err, ifindex, ifindex2; err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS, - &ifindex, true); + &ifindex, true, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT); if (err) return; @@ -638,7 +655,8 @@ static void serial_test_tc_netkit_neigh_links_target(int mode, int target) int err, ifindex; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, false); + &ifindex, false, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT); if (err) return; @@ -715,7 +733,8 @@ static void serial_test_tc_netkit_pkt_type_mode(int mode) struct bpf_link *link; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, true); + &ifindex, true, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT); if (err) return; @@ -779,3 +798,60 @@ void serial_test_tc_netkit_pkt_type(void) serial_test_tc_netkit_pkt_type_mode(NETKIT_L2); serial_test_tc_netkit_pkt_type_mode(NETKIT_L3); } + +static void serial_test_tc_netkit_scrub_type(int scrub) +{ + LIBBPF_OPTS(bpf_netkit_opts, optl); + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex; + + err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS, + &ifindex, false, scrub, scrub); + if (err) + return; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc8, + BPF_NETKIT_PRIMARY), 0, "tc8_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + + ASSERT_EQ(skel->bss->seen_tc8, false, "seen_tc8"); + + link = bpf_program__attach_netkit(skel->progs.tc8, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc8 = link; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc8, true, "seen_tc8"); + ASSERT_EQ(skel->bss->mark, scrub == NETKIT_SCRUB_NONE ? MARK : 0, "mark"); + ASSERT_EQ(skel->bss->prio, scrub == NETKIT_SCRUB_NONE ? PRIO : 0, "prio"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + destroy_netkit(); +} + +void serial_test_tc_netkit_scrub(void) +{ + serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_DEFAULT); + serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_NONE); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c index 481626a875d1..c7f74f068e78 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -2,35 +2,41 @@ #include <uapi/linux/bpf.h> #include <linux/if_link.h> #include <test_progs.h> +#include <network_helpers.h> #include "test_xdp_with_cpumap_frags_helpers.skel.h" #include "test_xdp_with_cpumap_helpers.skel.h" #define IFINDEX_LO 1 +#define TEST_NS "cpu_attach_ns" static void test_xdp_with_cpumap_helpers(void) { - struct test_xdp_with_cpumap_helpers *skel; + struct test_xdp_with_cpumap_helpers *skel = NULL; struct bpf_prog_info info = {}; __u32 len = sizeof(info); struct bpf_cpumap_val val = { .qsize = 192, }; - int err, prog_fd, map_fd; + int err, prog_fd, prog_redir_fd, map_fd; + struct nstoken *nstoken = NULL; __u32 idx = 0; + SYS(out_close, "ip netns add %s", TEST_NS); + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto out_close; + SYS(out_close, "ip link set dev lo up"); + skel = test_xdp_with_cpumap_helpers__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_xdp_with_cpumap_helpers__open_and_load")) return; - prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog); - err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); + prog_redir_fd = bpf_program__fd(skel->progs.xdp_redir_prog); + err = bpf_xdp_attach(IFINDEX_LO, prog_redir_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_OK(err, "Generic attach of program with 8-byte CPUMAP")) goto out_close; - err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); - ASSERT_OK(err, "XDP program detach"); - prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm); map_fd = bpf_map__fd(skel->maps.cpu_map); err = bpf_prog_get_info_by_fd(prog_fd, &info, &len); @@ -45,6 +51,26 @@ static void test_xdp_with_cpumap_helpers(void) ASSERT_OK(err, "Read cpumap entry"); ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id"); + /* send a packet to trigger any potential bugs in there */ + char data[10] = {}; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = 10, + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = 1, + ); + err = bpf_prog_test_run_opts(prog_redir_fd, &opts); + ASSERT_OK(err, "XDP test run"); + + /* wait for the packets to be flushed, then check that redirect has been + * performed + */ + kern_sync_rcu(); + ASSERT_NEQ(skel->bss->redirect_count, 0, "redirected packets"); + + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); + ASSERT_OK(err, "XDP program detach"); + /* can not attach BPF_XDP_CPUMAP program to a device */ err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_CPUMAP program")) @@ -65,6 +91,8 @@ static void test_xdp_with_cpumap_helpers(void) ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to cpumap entry"); out_close: + close_netns(nstoken); + SYS_NOFAIL("ip netns del %s", TEST_NS); test_xdp_with_cpumap_helpers__destroy(skel); } @@ -111,7 +139,7 @@ out_close: test_xdp_with_cpumap_frags_helpers__destroy(skel); } -void serial_test_xdp_cpumap_attach(void) +void test_xdp_cpumap_attach(void) { if (test__start_subtest("CPUMAP with programs in entries")) test_xdp_with_cpumap_helpers(); diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf.h b/tools/testing/selftests/bpf/progs/mptcp_bpf.h new file mode 100644 index 000000000000..3b188ccdcc40 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/mptcp_bpf.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __MPTCP_BPF_H__ +#define __MPTCP_BPF_H__ + +#include "bpf_experimental.h" + +/* list helpers from include/linux/list.h */ +static inline int list_is_head(const struct list_head *list, + const struct list_head *head) +{ + return list == head; +} + +#define list_entry(ptr, type, member) \ + container_of(ptr, type, member) + +#define list_first_entry(ptr, type, member) \ + list_entry((ptr)->next, type, member) + +#define list_next_entry(pos, member) \ + list_entry((pos)->member.next, typeof(*(pos)), member) + +#define list_entry_is_head(pos, head, member) \ + list_is_head(&pos->member, (head)) + +/* small difference: 'can_loop' has been added in the conditions */ +#define list_for_each_entry(pos, head, member) \ + for (pos = list_first_entry(head, typeof(*pos), member); \ + !list_entry_is_head(pos, head, member) && can_loop; \ + pos = list_next_entry(pos, member)) + +/* mptcp helpers from protocol.h */ +#define mptcp_for_each_subflow(__msk, __subflow) \ + list_for_each_entry(__subflow, &((__msk)->conn_list), node) + +static __always_inline struct sock * +mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow) +{ + return subflow->tcp_sock; +} + +#endif diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c new file mode 100644 index 000000000000..70302477e326 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020, Tessares SA. */ +/* Copyright (c) 2024, Kylin Software */ + +/* vmlinux.h, bpf_helpers.h and other 'define' */ +#include "bpf_tracing_net.h" +#include "mptcp_bpf.h" + +char _license[] SEC("license") = "GPL"; + +char cc[TCP_CA_NAME_MAX] = "reno"; +int pid; + +/* Associate a subflow counter to each token */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); + __uint(max_entries, 100); +} mptcp_sf SEC(".maps"); + +SEC("sockops") +int mptcp_subflow(struct bpf_sock_ops *skops) +{ + __u32 init = 1, key, mark, *cnt; + struct mptcp_sock *msk; + struct bpf_sock *sk; + int err; + + if (skops->op != BPF_SOCK_OPS_TCP_CONNECT_CB) + return 1; + + sk = skops->sk; + if (!sk) + return 1; + + msk = bpf_skc_to_mptcp_sock(sk); + if (!msk) + return 1; + + key = msk->token; + cnt = bpf_map_lookup_elem(&mptcp_sf, &key); + if (cnt) { + /* A new subflow is added to an existing MPTCP connection */ + __sync_fetch_and_add(cnt, 1); + mark = *cnt; + } else { + /* A new MPTCP connection is just initiated and this is its primary subflow */ + bpf_map_update_elem(&mptcp_sf, &key, &init, BPF_ANY); + mark = init; + } + + /* Set the mark of the subflow's socket based on appearance order */ + err = bpf_setsockopt(skops, SOL_SOCKET, SO_MARK, &mark, sizeof(mark)); + if (err < 0) + return 1; + if (mark == 2) + err = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION, cc, TCP_CA_NAME_MAX); + + return 1; +} + +static int _check_getsockopt_subflow_mark(struct mptcp_sock *msk, struct bpf_sockopt *ctx) +{ + struct mptcp_subflow_context *subflow; + int i = 0; + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk; + + ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow, + struct mptcp_subflow_context)); + + if (ssk->sk_mark != ++i) { + ctx->retval = -2; + break; + } + } + + return 1; +} + +static int _check_getsockopt_subflow_cc(struct mptcp_sock *msk, struct bpf_sockopt *ctx) +{ + struct mptcp_subflow_context *subflow; + + mptcp_for_each_subflow(msk, subflow) { + struct inet_connection_sock *icsk; + struct sock *ssk; + + ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow, + struct mptcp_subflow_context)); + icsk = bpf_core_cast(ssk, struct inet_connection_sock); + + if (ssk->sk_mark == 2 && + __builtin_memcmp(icsk->icsk_ca_ops->name, cc, TCP_CA_NAME_MAX)) { + ctx->retval = -2; + break; + } + } + + return 1; +} + +SEC("cgroup/getsockopt") +int _getsockopt_subflow(struct bpf_sockopt *ctx) +{ + struct bpf_sock *sk = ctx->sk; + struct mptcp_sock *msk; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 1; + + if (!sk || sk->protocol != IPPROTO_MPTCP || + (!(ctx->level == SOL_SOCKET && ctx->optname == SO_MARK) && + !(ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION))) + return 1; + + msk = bpf_core_cast(sk, struct mptcp_sock); + if (msk->pm.subflows != 1) { + ctx->retval = -1; + return 1; + } + + if (ctx->optname == SO_MARK) + return _check_getsockopt_subflow_mark(msk, ctx); + return _check_getsockopt_subflow_cc(msk, ctx); +} diff --git a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c index aeff3a4f9287..c6edf8dbefeb 100644 --- a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c +++ b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c @@ -27,6 +27,8 @@ struct { __type(value, __u64); } sock_map SEC(".maps"); +int tcx_init_netns_cookie, tcx_netns_cookie; + SEC("sockops") int get_netns_cookie_sockops(struct bpf_sock_ops *ctx) { @@ -81,4 +83,12 @@ int get_netns_cookie_sk_msg(struct sk_msg_md *msg) return 1; } +SEC("tcx/ingress") +int get_netns_cookie_tcx(struct __sk_buff *skb) +{ + tcx_init_netns_cookie = bpf_get_netns_cookie(NULL); + tcx_netns_cookie = bpf_get_netns_cookie(skb); + return TCX_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c index ab3eae3d6af8..10d825928499 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_link.c +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -18,6 +18,7 @@ bool seen_tc4; bool seen_tc5; bool seen_tc6; bool seen_tc7; +bool seen_tc8; bool set_type; @@ -25,6 +26,8 @@ bool seen_eth; bool seen_host; bool seen_mcast; +int mark, prio; + SEC("tc/ingress") int tc1(struct __sk_buff *skb) { @@ -100,3 +103,12 @@ out: seen_tc7 = true; return TCX_PASS; } + +SEC("tc/egress") +int tc8(struct __sk_buff *skb) +{ + seen_tc8 = true; + mark = skb->mark; + prio = skb->priority; + return TCX_PASS; +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c index 20ec6723df18..3619239b01b7 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -12,10 +12,12 @@ struct { __uint(max_entries, 4); } cpu_map SEC(".maps"); +__u32 redirect_count = 0; + SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { - return bpf_redirect_map(&cpu_map, 1, 0); + return bpf_redirect_map(&cpu_map, 0, 0); } SEC("xdp") @@ -27,6 +29,9 @@ int xdp_dummy_prog(struct xdp_md *ctx) SEC("xdp/cpumap") int xdp_dummy_cm(struct xdp_md *ctx) { + if (bpf_get_smp_processor_id() == 0) + redirect_count++; + if (ctx->ingress_ifindex == IFINDEX_LO) return XDP_DROP; diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 39fb97a8c1df..0fec8f9801ad 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -9,6 +9,7 @@ TEST_PROGS := \ ping.py \ queues.py \ stats.py \ + shaper.py \ # end of TEST_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 9d7adb3cf33b..29995586993c 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -6,7 +6,7 @@ import random from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt from lib.py import NetDrvEpEnv from lib.py import EthtoolFamily, NetdevFamily -from lib.py import KsftSkipEx +from lib.py import KsftSkipEx, KsftFailEx from lib.py import rand_port from lib.py import ethtool, ip, defer, GenerateTraffic, CmdExitFailure @@ -606,6 +606,33 @@ def test_rss_context_overlap2(cfg): test_rss_context_overlap(cfg, True) +def test_delete_rss_context_busy(cfg): + """ + Test that deletion returns -EBUSY when an rss context is being used + by an ntuple filter. + """ + + require_ntuple(cfg) + + # create additional rss context + ctx_id = ethtool_create(cfg, "-X", "context new") + ctx_deleter = defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete") + + # utilize context from ntuple filter + port = rand_port() + flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {ctx_id}" + ntuple_id = ethtool_create(cfg, "-N", flow) + defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}") + + # attempt to delete in-use context + try: + ctx_deleter.exec_only() + ctx_deleter.cancel() + raise KsftFailEx(f"deleted context {ctx_id} used by rule {ntuple_id}") + except CmdExitFailure: + pass + + def main() -> None: with NetDrvEpEnv(__file__, nsim_test=False) as cfg: cfg.ethnl = EthtoolFamily() @@ -616,7 +643,8 @@ def main() -> None: test_rss_context, test_rss_context4, test_rss_context32, test_rss_context_dump, test_rss_context_queue_reconfigure, test_rss_context_overlap, test_rss_context_overlap2, - test_rss_context_out_of_order, test_rss_context4_create_with_cfg], + test_rss_context_out_of_order, test_rss_context4_create_with_cfg, + test_delete_rss_context_busy], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh index 893a693ad805..45a569618424 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh @@ -186,10 +186,7 @@ bridge_vlan_flags_test() # If we did not handle references correctly, then this should produce a # trace - devlink dev reload "$DEVLINK_DEV" - - # Allow netdevices to be re-created following the reload - sleep 20 + devlink_reload log_test "bridge vlan flags" } @@ -923,12 +920,9 @@ devlink_reload_test() # devlink reload can be performed without errors RET=0 - devlink dev reload "$DEVLINK_DEV" - check_err $? "devlink reload failed" + devlink_reload log_test "devlink reload - last test" - - sleep 20 } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 299e06a5808c..f4c324957dcc 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -137,7 +137,7 @@ h2_create() # Prevent this by adding a shaper which limits the traffic in $h2 to # 1Gbps. - tc qdisc replace dev $h2 root handle 10: tbf rate 1gbit \ + tc qdisc replace dev $h2 root handle 10: tbf rate 200mbit \ burst 128K limit 1G } @@ -199,7 +199,7 @@ switch_create() done for intf in $swp3 $swp4; do - tc qdisc replace dev $intf root handle 1: tbf rate 1gbit \ + tc qdisc replace dev $intf root handle 1: tbf rate 200mbit \ burst 128K limit 1G done @@ -372,6 +372,7 @@ build_backlog() local i=0 while :; do + sleep 1 local cur=$(busywait 1100 until_counter_is "> $cur" \ get_qdisc_backlog $vlan) local diff=$((size - cur)) @@ -532,10 +533,11 @@ do_red_test() check_fail $? "Traffic went into backlog instead of being early-dropped" pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + backlog=$(get_qdisc_backlog $vlan) local diff=$((limit - backlog)) pct=$((100 * diff / limit)) - ((-10 <= pct && pct <= 10)) - check_err $? "backlog $backlog / $limit expected <= 10% distance" + ((-15 <= pct && pct <= 15)) + check_err $? "backlog $backlog / $limit expected <= 15% distance" log_test "TC $((vlan - 10)): RED backlog > limit" stop_traffic @@ -600,7 +602,7 @@ do_mark_test() # Above limit, everything should be mirrored, we should see lots of # packets. build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01 >/dev/null - busywait_for_counter 1100 +10000 \ + busywait_for_counter 1100 +2500 \ $fetch_counter > /dev/null check_err_fail "$should_fail" $? "ECN-marked packets $subtest'd" @@ -651,20 +653,22 @@ do_drop_test() build_backlog $vlan $((3 * limit / 2)) udp >/dev/null base=$($fetch_counter) - send_packets $vlan udp 11 + send_packets $vlan udp 100 - now=$(busywait 1100 until_counter_is ">= $((base + 10))" $fetch_counter) - check_err $? "Dropped packets not observed: 11 expected, $((now - base)) seen" + now=$(busywait 1100 until_counter_is ">= $((base + 95))" $fetch_counter) + check_err $? "${trigger}ped packets not observed: 100 expected, $((now - base)) seen" # When no extra traffic is injected, there should be no mirroring. - busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null + busywait 1100 until_counter_is ">= $((base + 110))" \ + $fetch_counter >/dev/null check_fail $? "Spurious packets observed" # When the rule is uninstalled, there should be no mirroring. qevent_rule_uninstall_$subtest - send_packets $vlan udp 11 - busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null - check_fail $? "Spurious packets observed after uninstall" + send_packets $vlan udp 100 + now=$(busywait 1100 until_counter_is ">= $((base + 110))" \ + $fetch_counter) + check_fail $? "$((now - base)) spurious packets observed after uninstall" log_test "TC $((vlan - 10)): ${trigger}ped packets $subtest'd" diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index 8ecddafa79b3..576067b207a8 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -20,8 +20,8 @@ source sch_red_core.sh # $BACKLOG2 are far enough not to overlap, so that we can assume that if we do # see (do not see) marking, it is actually due to the configuration of that one # TC, and not due to configuration of the other TC leaking over. -BACKLOG1=200000 -BACKLOG2=500000 +BACKLOG1=400000 +BACKLOG2=1000000 install_root_qdisc() { @@ -35,7 +35,7 @@ install_qdisc_tc0() tc qdisc add dev $swp3 parent 10:8 handle 108: red \ limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \ - probability 1.0 avpkt 8000 burst 38 "${args[@]}" + probability 1.0 avpkt 8000 burst 51 "${args[@]}" } install_qdisc_tc1() @@ -44,7 +44,7 @@ install_qdisc_tc1() tc qdisc add dev $swp3 parent 10:7 handle 107: red \ limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \ - probability 1.0 avpkt 8000 burst 63 "${args[@]}" + probability 1.0 avpkt 8000 burst 126 "${args[@]}" } install_qdisc() diff --git a/tools/testing/selftests/drivers/net/shaper.py b/tools/testing/selftests/drivers/net/shaper.py new file mode 100755 index 000000000000..11310f19bfa0 --- /dev/null +++ b/tools/testing/selftests/drivers/net/shaper.py @@ -0,0 +1,461 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_true, KsftSkipEx +from lib.py import EthtoolFamily, NetshaperFamily +from lib.py import NetDrvEnv +from lib.py import NlError +from lib.py import cmd + +def get_shapers(cfg, nl_shaper) -> None: + try: + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + except NlError as e: + if e.error == 95: + raise KsftSkipEx("shapers not supported by the device") + raise + + # Default configuration: no shapers configured. + ksft_eq(len(shapers), 0) + +def get_caps(cfg, nl_shaper) -> None: + try: + caps = nl_shaper.cap_get({'ifindex': cfg.ifindex}, dump=True) + except NlError as e: + if e.error == 95: + raise KsftSkipEx("shapers not supported by the device") + raise + + # Each device implementing shaper support must support some + # features in at least a scope. + ksft_true(len(caps)> 0) + +def set_qshapers(cfg, nl_shaper) -> None: + try: + caps = nl_shaper.cap_get({'ifindex': cfg.ifindex, + 'scope':'queue'}) + except NlError as e: + if e.error == 95: + raise KsftSkipEx("shapers not supported by the device") + raise + if not 'support-bw-max' in caps or not 'support-metric-bps' in caps: + raise KsftSkipEx("device does not support queue scope shapers with bw_max and metric bps") + + cfg.queues = True; + netnl = EthtoolFamily() + channels = netnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + if channels['combined-count'] == 0: + cfg.rx_type = 'rx' + cfg.nr_queues = channels['rx-count'] + else: + cfg.rx_type = 'combined' + cfg.nr_queues = channels['combined-count'] + if cfg.nr_queues < 3: + raise KsftSkipEx(f"device does not support enough queues min 3 found {cfg.nr_queues}") + + nl_shaper.set({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 1}, + 'metric': 'bps', + 'bw-max': 10000}) + nl_shaper.set({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 2}, + 'metric': 'bps', + 'bw-max': 20000}) + + # Querying a specific shaper not yet configured must fail. + raised = False + try: + shaper_q0 = nl_shaper.get({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 0}}) + except (NlError): + raised = True + ksft_eq(raised, True) + + shaper_q1 = nl_shaper.get({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 1}}) + ksft_eq(shaper_q1, {'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 1}, + 'metric': 'bps', + 'bw-max': 10000}) + + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(shapers, [{'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 1}, + 'metric': 'bps', + 'bw-max': 10000}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 2}, + 'metric': 'bps', + 'bw-max': 20000}]) + +def del_qshapers(cfg, nl_shaper) -> None: + if not cfg.queues: + raise KsftSkipEx("queue shapers not supported by device, skipping delete") + + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 2}}) + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 1}}) + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(len(shapers), 0) + +def set_nshapers(cfg, nl_shaper) -> None: + # Check required features. + try: + caps = nl_shaper.cap_get({'ifindex': cfg.ifindex, + 'scope':'netdev'}) + except NlError as e: + if e.error == 95: + raise KsftSkipEx("shapers not supported by the device") + raise + if not 'support-bw-max' in caps or not 'support-metric-bps' in caps: + raise KsftSkipEx("device does not support nested netdev scope shapers with weight") + + cfg.netdev = True; + nl_shaper.set({'ifindex': cfg.ifindex, + 'handle': {'scope': 'netdev', 'id': 0}, + 'bw-max': 100000}) + + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(shapers, [{'ifindex': cfg.ifindex, + 'handle': {'scope': 'netdev'}, + 'metric': 'bps', + 'bw-max': 100000}]) + +def del_nshapers(cfg, nl_shaper) -> None: + if not cfg.netdev: + raise KsftSkipEx("netdev shaper not supported by device, skipping delete") + + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'netdev'}}) + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(len(shapers), 0) + +def basic_groups(cfg, nl_shaper) -> None: + if not cfg.netdev: + raise KsftSkipEx("netdev shaper not supported by the device") + if cfg.nr_queues < 3: + raise KsftSkipEx(f"netdev does not have enough queues min 3 reported {cfg.nr_queues}") + + try: + caps = nl_shaper.cap_get({'ifindex': cfg.ifindex, + 'scope':'queue'}) + except NlError as e: + if e.error == 95: + raise KsftSkipEx("shapers not supported by the device") + raise + if not 'support-weight' in caps: + raise KsftSkipEx("device does not support queue scope shapers with weight") + + node_handle = nl_shaper.group({ + 'ifindex': cfg.ifindex, + 'leaves':[{'handle': {'scope': 'queue', 'id': 1}, + 'weight': 1}, + {'handle': {'scope': 'queue', 'id': 2}, + 'weight': 2}], + 'handle': {'scope':'netdev'}, + 'metric': 'bps', + 'bw-max': 10000}) + ksft_eq(node_handle, {'ifindex': cfg.ifindex, + 'handle': {'scope': 'netdev'}}) + + shaper = nl_shaper.get({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 1}}) + ksft_eq(shaper, {'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 1}, + 'weight': 1 }) + + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 2}}) + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 1}}) + + # Deleting all the leaves shaper does not affect the node one + # when the latter has 'netdev' scope. + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(len(shapers), 1) + + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'netdev'}}) + +def qgroups(cfg, nl_shaper) -> None: + if cfg.nr_queues < 4: + raise KsftSkipEx(f"netdev does not have enough queues min 4 reported {cfg.nr_queues}") + try: + caps = nl_shaper.cap_get({'ifindex': cfg.ifindex, + 'scope':'node'}) + except NlError as e: + if e.error == 95: + raise KsftSkipEx("shapers not supported by the device") + raise + if not 'support-bw-max' in caps or not 'support-metric-bps' in caps: + raise KsftSkipEx("device does not support node scope shapers with bw_max and metric bps") + try: + caps = nl_shaper.cap_get({'ifindex': cfg.ifindex, + 'scope':'queue'}) + except NlError as e: + if e.error == 95: + raise KsftSkipEx("shapers not supported by the device") + raise + if not 'support-nesting' in caps or not 'support-weight' in caps or not 'support-metric-bps' in caps: + raise KsftSkipEx("device does not support nested queue scope shapers with weight") + + cfg.groups = True; + node_handle = nl_shaper.group({ + 'ifindex': cfg.ifindex, + 'leaves':[{'handle': {'scope': 'queue', 'id': 1}, + 'weight': 3}, + {'handle': {'scope': 'queue', 'id': 2}, + 'weight': 2}], + 'handle': {'scope':'node'}, + 'metric': 'bps', + 'bw-max': 10000}) + node_id = node_handle['handle']['id'] + + shaper = nl_shaper.get({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 1}}) + ksft_eq(shaper, {'ifindex': cfg.ifindex, + 'parent': {'scope': 'node', 'id': node_id}, + 'handle': {'scope': 'queue', 'id': 1}, + 'weight': 3}) + shaper = nl_shaper.get({'ifindex': cfg.ifindex, + 'handle': {'scope': 'node', 'id': node_id}}) + ksft_eq(shaper, {'ifindex': cfg.ifindex, + 'handle': {'scope': 'node', 'id': node_id}, + 'parent': {'scope': 'netdev'}, + 'metric': 'bps', + 'bw-max': 10000}) + + # Grouping to a specified, not existing node scope shaper must fail + raised = False + try: + nl_shaper.group({ + 'ifindex': cfg.ifindex, + 'leaves':[{'handle': {'scope': 'queue', 'id': 3}, + 'weight': 3}], + 'handle': {'scope':'node', 'id': node_id + 1}, + 'metric': 'bps', + 'bw-max': 10000}) + + except (NlError): + raised = True + ksft_eq(raised, True) + + # Add to an existing node + node_handle = nl_shaper.group({ + 'ifindex': cfg.ifindex, + 'leaves':[{'handle': {'scope': 'queue', 'id': 3}, + 'weight': 4}], + 'handle': {'scope':'node', 'id': node_id}}) + ksft_eq(node_handle, {'ifindex': cfg.ifindex, + 'handle': {'scope': 'node', 'id': node_id}}) + + shaper = nl_shaper.get({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 3}}) + ksft_eq(shaper, {'ifindex': cfg.ifindex, + 'parent': {'scope': 'node', 'id': node_id}, + 'handle': {'scope': 'queue', 'id': 3}, + 'weight': 4}) + + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 2}}) + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 1}}) + + # Deleting a non empty node will move the leaves downstream. + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'node', 'id': node_id}}) + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(shapers, [{'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 3}, + 'weight': 4}]) + + # Finish and verify the complete cleanup. + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': 3}}) + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(len(shapers), 0) + +def delegation(cfg, nl_shaper) -> None: + if not cfg.groups: + raise KsftSkipEx("device does not support node scope") + try: + caps = nl_shaper.cap_get({'ifindex': cfg.ifindex, + 'scope':'node'}) + except NlError as e: + if e.error == 95: + raise KsftSkipEx("node scope shapers not supported by the device") + raise + if not 'support-nesting' in caps: + raise KsftSkipEx("device does not support node scope shapers nesting") + + node_handle = nl_shaper.group({ + 'ifindex': cfg.ifindex, + 'leaves':[{'handle': {'scope': 'queue', 'id': 1}, + 'weight': 3}, + {'handle': {'scope': 'queue', 'id': 2}, + 'weight': 2}, + {'handle': {'scope': 'queue', 'id': 3}, + 'weight': 1}], + 'handle': {'scope':'node'}, + 'metric': 'bps', + 'bw-max': 10000}) + node_id = node_handle['handle']['id'] + + # Create the nested node and validate the hierarchy + nested_node_handle = nl_shaper.group({ + 'ifindex': cfg.ifindex, + 'leaves':[{'handle': {'scope': 'queue', 'id': 1}, + 'weight': 3}, + {'handle': {'scope': 'queue', 'id': 2}, + 'weight': 2}], + 'handle': {'scope':'node'}, + 'metric': 'bps', + 'bw-max': 5000}) + nested_node_id = nested_node_handle['handle']['id'] + ksft_true(nested_node_id != node_id) + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(shapers, [{'ifindex': cfg.ifindex, + 'parent': {'scope': 'node', 'id': nested_node_id}, + 'handle': {'scope': 'queue', 'id': 1}, + 'weight': 3}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'node', 'id': nested_node_id}, + 'handle': {'scope': 'queue', 'id': 2}, + 'weight': 2}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'node', 'id': node_id}, + 'handle': {'scope': 'queue', 'id': 3}, + 'weight': 1}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'node', 'id': node_id}, + 'metric': 'bps', + 'bw-max': 10000}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'node', 'id': node_id}, + 'handle': {'scope': 'node', 'id': nested_node_id}, + 'metric': 'bps', + 'bw-max': 5000}]) + + # Deleting a non empty node will move the leaves downstream. + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'node', 'id': nested_node_id}}) + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(shapers, [{'ifindex': cfg.ifindex, + 'parent': {'scope': 'node', 'id': node_id}, + 'handle': {'scope': 'queue', 'id': 1}, + 'weight': 3}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'node', 'id': node_id}, + 'handle': {'scope': 'queue', 'id': 2}, + 'weight': 2}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'node', 'id': node_id}, + 'handle': {'scope': 'queue', 'id': 3}, + 'weight': 1}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'node', 'id': node_id}, + 'metric': 'bps', + 'bw-max': 10000}]) + + # Final cleanup. + for i in range(1, 4): + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': i}}) + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(len(shapers), 0) + +def queue_update(cfg, nl_shaper) -> None: + if cfg.nr_queues < 4: + raise KsftSkipEx(f"netdev does not have enough queues min 4 reported {cfg.nr_queues}") + if not cfg.queues: + raise KsftSkipEx("device does not support queue scope") + + for i in range(3): + nl_shaper.set({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': i}, + 'metric': 'bps', + 'bw-max': (i + 1) * 1000}) + # Delete a channel, with no shapers configured on top of the related + # queue: no changes expected + cmd(f"ethtool -L {cfg.dev['ifname']} {cfg.rx_type} 3", timeout=10) + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(shapers, [{'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 0}, + 'metric': 'bps', + 'bw-max': 1000}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 1}, + 'metric': 'bps', + 'bw-max': 2000}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 2}, + 'metric': 'bps', + 'bw-max': 3000}]) + + # Delete a channel, with a shaper configured on top of the related + # queue: the shaper must be deleted, too + cmd(f"ethtool -L {cfg.dev['ifname']} {cfg.rx_type} 2", timeout=10) + + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(shapers, [{'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 0}, + 'metric': 'bps', + 'bw-max': 1000}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 1}, + 'metric': 'bps', + 'bw-max': 2000}]) + + # Restore the original channels number, no expected changes + cmd(f"ethtool -L {cfg.dev['ifname']} {cfg.rx_type} {cfg.nr_queues}", timeout=10) + shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True) + ksft_eq(shapers, [{'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 0}, + 'metric': 'bps', + 'bw-max': 1000}, + {'ifindex': cfg.ifindex, + 'parent': {'scope': 'netdev'}, + 'handle': {'scope': 'queue', 'id': 1}, + 'metric': 'bps', + 'bw-max': 2000}]) + + # Final cleanup. + for i in range(0, 2): + nl_shaper.delete({'ifindex': cfg.ifindex, + 'handle': {'scope': 'queue', 'id': i}}) + +def main() -> None: + with NetDrvEnv(__file__, queue_count=4) as cfg: + cfg.queues = False + cfg.netdev = False + cfg.groups = False + cfg.nr_queues = 0 + ksft_run([get_shapers, + get_caps, + set_qshapers, + del_qshapers, + set_nshapers, + del_nshapers, + basic_groups, + qgroups, + delegation, + queue_update], args=(cfg, NetshaperFamily())) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 649f1fe0dc46..26a4883a65c9 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -98,7 +98,6 @@ TEST_PROGS += vlan_hw_filter.sh TEST_PROGS += bpf_offload.py # YNL files, must be before "include ..lib.mk" -EXTRA_CLEAN += $(OUTPUT)/libynl.a YNL_GEN_FILES := ncdevmem TEST_GEN_FILES += $(YNL_GEN_FILES) diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index 12491850ae98..845c26dd01a9 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -3,119 +3,106 @@ # # Author: Justin Iurman <justin.iurman@uliege.be> # -# This script evaluates the IOAM insertion for IPv6 by checking the IOAM data -# consistency directly inside packets on the receiver side. Tests are divided -# into three categories: OUTPUT (evaluates the IOAM processing by the sender), -# INPUT (evaluates the IOAM processing by a receiver) and GLOBAL (evaluates -# wider use cases that do not fall into the other two categories). Both OUTPUT -# and INPUT tests only use a two-node topology (alpha and beta), while GLOBAL -# tests use the entire three-node topology (alpha, beta, gamma). Each test is -# documented inside its own handler in the code below. +# This script evaluates IOAM for IPv6 by checking local IOAM configurations and +# IOAM data inside packets. There are three categories of tests: LOCAL, OUTPUT, +# and INPUT. The former (LOCAL) checks all IOAM related configurations locally +# without sending packets. OUTPUT tests verify the processing of an IOAM +# encapsulating node, while INPUT tests verify the processing of an IOAM transit +# node. Both OUTPUT and INPUT tests send packets. Each test is documented inside +# its own handler. # -# An IOAM domain is configured from Alpha to Gamma but not on the reverse path. -# When either Beta or Gamma is the destination (depending on the test category), -# Alpha adds an IOAM option (Pre-allocated Trace) inside a Hop-by-hop. +# The topology used for OUTPUT and INPUT tests is made of three nodes: +# - Alpha (the IOAM encapsulating node) +# - Beta (the IOAM transit node) +# - Gamma (the receiver) ** # +# An IOAM domain is configured from Alpha to Beta, but not on the reverse path. +# Alpha adds an IOAM option (Pre-allocated Trace) inside a Hop-by-hop. # -# +-------------------+ +-------------------+ -# | | | | -# | Alpha netns | | Gamma netns | -# | | | | -# | +-------------+ | | +-------------+ | -# | | veth0 | | | | veth0 | | -# | | db01::2/64 | | | | db02::2/64 | | -# | +-------------+ | | +-------------+ | -# | . | | . | -# +-------------------+ +-------------------+ -# . . -# . . -# . . -# +----------------------------------------------------+ -# | . . | -# | +-------------+ +-------------+ | -# | | veth0 | | veth1 | | -# | | db01::1/64 | ................ | db02::1/64 | | -# | +-------------+ +-------------+ | -# | | -# | Beta netns | -# | | -# +----------------------------------------------------+ +# ** Gamma is required because ioam6_parser.c uses a packet socket and we need +# to see IOAM data inserted by the very last node (Beta), which would happen +# _after_ we get a copy of the packet on Beta. Note that using an +# IPv6 raw socket with IPV6_RECVHOPOPTS on Beta would not be enough: we also +# need to access the IPv6 header to check some fields (e.g., source and +# destination addresses), which is not possible in that case. As a +# consequence, we need Gamma as a receiver to run ioam6_parser.c which uses a +# packet socket. # # +# +-----------------------+ +-----------------------+ +# | | | | +# | Alpha netns | | Gamma netns | +# | | | | +# | +-------------------+ | | +-------------------+ | +# | | veth0 | | | | veth0 | | +# | | 2001:db8:1::2/64 | | | | 2001:db8:2::2/64 | | +# | +-------------------+ | | +-------------------+ | +# | . | | . | +# +-----------.-----------+ +-----------.-----------+ +# . . +# . . +# . . +# +-----------.----------------------------------.-----------+ +# | . . | +# | +-------------------+ +-------------------+ | +# | | veth0 | | veth1 | | +# | | 2001:db8:1::1/64 | ............ | 2001:db8:2::1/64 | | +# | +-------------------+ +-------------------+ | +# | | +# | Beta netns | +# | | +# +----------------------------------------------------------+ # -# ============================================================= -# | Alpha - IOAM configuration | -# +===========================================================+ -# | Node ID | 1 | -# +-----------------------------------------------------------+ -# | Node Wide ID | 11111111 | -# +-----------------------------------------------------------+ -# | Ingress ID | 0xffff (default value) | -# +-----------------------------------------------------------+ -# | Ingress Wide ID | 0xffffffff (default value) | -# +-----------------------------------------------------------+ -# | Egress ID | 101 | -# +-----------------------------------------------------------+ -# | Egress Wide ID | 101101 | -# +-----------------------------------------------------------+ -# | Namespace Data | 0xdeadbee0 | -# +-----------------------------------------------------------+ -# | Namespace Wide Data | 0xcafec0caf00dc0de | -# +-----------------------------------------------------------+ -# | Schema ID | 777 | -# +-----------------------------------------------------------+ -# | Schema Data | something that will be 4n-aligned | -# +-----------------------------------------------------------+ # # -# ============================================================= -# | Beta - IOAM configuration | -# +===========================================================+ -# | Node ID | 2 | -# +-----------------------------------------------------------+ -# | Node Wide ID | 22222222 | -# +-----------------------------------------------------------+ -# | Ingress ID | 201 | -# +-----------------------------------------------------------+ -# | Ingress Wide ID | 201201 | -# +-----------------------------------------------------------+ -# | Egress ID | 202 | -# +-----------------------------------------------------------+ -# | Egress Wide ID | 202202 | -# +-----------------------------------------------------------+ -# | Namespace Data | 0xdeadbee1 | -# +-----------------------------------------------------------+ -# | Namespace Wide Data | 0xcafec0caf11dc0de | -# +-----------------------------------------------------------+ -# | Schema ID | 666 | -# +-----------------------------------------------------------+ -# | Schema Data | Hello there -Obi | -# +-----------------------------------------------------------+ +# +==========================================================+ +# | Alpha - IOAM configuration | +# +=====================+====================================+ +# | Node ID | 1 | +# +---------------------+------------------------------------+ +# | Node Wide ID | 11111111 | +# +---------------------+------------------------------------+ +# | Ingress ID | 0xffff (default value) | +# +---------------------+------------------------------------+ +# | Ingress Wide ID | 0xffffffff (default value) | +# +---------------------+------------------------------------+ +# | Egress ID | 101 | +# +---------------------+------------------------------------+ +# | Egress Wide ID | 101101 | +# +---------------------+------------------------------------+ +# | Namespace Data | 0xdeadbeef | +# +---------------------+------------------------------------+ +# | Namespace Wide Data | 0xcafec0caf00dc0de | +# +---------------------+------------------------------------+ +# | Schema ID | 777 | +# +---------------------+------------------------------------+ +# | Schema Data | something that will be 4n-aligned | +# +---------------------+------------------------------------+ # # -# ============================================================= -# | Gamma - IOAM configuration | -# +===========================================================+ -# | Node ID | 3 | -# +-----------------------------------------------------------+ -# | Node Wide ID | 33333333 | -# +-----------------------------------------------------------+ -# | Ingress ID | 301 | -# +-----------------------------------------------------------+ -# | Ingress Wide ID | 301301 | -# +-----------------------------------------------------------+ -# | Egress ID | 0xffff (default value) | -# +-----------------------------------------------------------+ -# | Egress Wide ID | 0xffffffff (default value) | -# +-----------------------------------------------------------+ -# | Namespace Data | 0xdeadbee2 | -# +-----------------------------------------------------------+ -# | Namespace Wide Data | 0xcafec0caf22dc0de | -# +-----------------------------------------------------------+ -# | Schema ID | 0xffffff (= None) | -# +-----------------------------------------------------------+ -# | Schema Data | | -# +-----------------------------------------------------------+ +# +==========================================================+ +# | Beta - IOAM configuration | +# +=====================+====================================+ +# | Node ID | 2 | +# +---------------------+------------------------------------+ +# | Node Wide ID | 22222222 | +# +---------------------+------------------------------------+ +# | Ingress ID | 201 | +# +---------------------+------------------------------------+ +# | Ingress Wide ID | 201201 | +# +---------------------+------------------------------------+ +# | Egress ID | 202 | +# +---------------------+------------------------------------+ +# | Egress Wide ID | 202202 | +# +---------------------+------------------------------------+ +# | Namespace Data | 0xffffffff (default value) | +# +---------------------+------------------------------------+ +# | Namespace Wide Data | 0xffffffffffffffff (default value) | +# +---------------------+------------------------------------+ +# | Schema ID | 0xffffff (= None) | +# +---------------------+------------------------------------+ +# | Schema Data | | +# +---------------------+------------------------------------+ source lib.sh @@ -128,64 +115,69 @@ source lib.sh ################################################################################ ALPHA=( - 1 # ID - 11111111 # Wide ID - 0xffff # Ingress ID - 0xffffffff # Ingress Wide ID - 101 # Egress ID - 101101 # Egress Wide ID - 0xdeadbee0 # Namespace Data - 0xcafec0caf00dc0de # Namespace Wide Data - 777 # Schema ID (0xffffff = None) - "something that will be 4n-aligned" # Schema Data + 1 # ID + 11111111 # Wide ID + 0xffff # Ingress ID (default value) + 0xffffffff # Ingress Wide ID (default value) + 101 # Egress ID + 101101 # Egress Wide ID + 0xdeadbeef # Namespace Data + 0xcafec0caf00dc0de # Namespace Wide Data + 777 # Schema ID + "something that will be 4n-aligned" # Schema Data ) BETA=( - 2 - 22222222 - 201 - 201201 - 202 - 202202 - 0xdeadbee1 - 0xcafec0caf11dc0de - 666 - "Hello there -Obi" + 2 # ID + 22222222 # Wide ID + 201 # Ingress ID + 201201 # Ingress Wide ID + 202 # Egress ID + 202202 # Egress Wide ID + 0xffffffff # Namespace Data (empty value) + 0xffffffffffffffff # Namespace Wide Data (empty value) + 0xffffff # Schema ID (empty value) + "" # Schema Data (empty value) ) -GAMMA=( - 3 - 33333333 - 301 - 301301 - 0xffff - 0xffffffff - 0xdeadbee2 - 0xcafec0caf22dc0de - 0xffffff - "" -) +TESTS_LOCAL=" + local_sysctl_ioam_id + local_sysctl_ioam_id_wide + local_sysctl_ioam_intf_id + local_sysctl_ioam_intf_id_wide + local_sysctl_ioam_intf_enabled + local_ioam_namespace + local_ioam_schema + local_ioam_schema_namespace + local_route_ns + local_route_tunsrc + local_route_tundst + local_route_trace_type + local_route_trace_size + local_route_trace_type_bits + local_route_trace_size_values +" TESTS_OUTPUT=" - out_undef_ns - out_no_room - out_bits - out_full_supp_trace + output_undef_ns + output_no_room + output_no_room_oss + output_bits + output_sizes + output_full_supp_trace " TESTS_INPUT=" - in_undef_ns - in_no_room - in_oflag - in_bits - in_full_supp_trace + input_undef_ns + input_no_room + input_no_room_oss + input_disabled + input_oflag + input_bits + input_sizes + input_full_supp_trace " -TESTS_GLOBAL=" - fwd_full_supp_trace -" - - ################################################################################ # # # LIBRARY # @@ -194,66 +186,64 @@ TESTS_GLOBAL=" check_kernel_compatibility() { - setup_ns ioam_tmp_node - ip link add name veth0 netns $ioam_tmp_node type veth \ - peer name veth1 netns $ioam_tmp_node + setup_ns ioam_tmp_node &>/dev/null + local ret=$? - ip -netns $ioam_tmp_node link set veth0 up - ip -netns $ioam_tmp_node link set veth1 up + ip link add name veth0 netns $ioam_tmp_node type veth \ + peer name veth1 netns $ioam_tmp_node &>/dev/null + ret=$((ret + $?)) - ip -netns $ioam_tmp_node ioam namespace add 0 - ns_ad=$? + ip -netns $ioam_tmp_node link set veth0 up &>/dev/null + ret=$((ret + $?)) - ip -netns $ioam_tmp_node ioam namespace show | grep -q "namespace 0" - ns_sh=$? + ip -netns $ioam_tmp_node link set veth1 up &>/dev/null + ret=$((ret + $?)) - if [[ $ns_ad != 0 || $ns_sh != 0 ]] + if [ $ret != 0 ] then - echo "SKIP: kernel version probably too old, missing ioam support" - ip link del veth0 2>/dev/null || true - cleanup_ns $ioam_tmp_node || true + echo "SKIP: Setup failed." + cleanup_ns $ioam_tmp_node exit $ksft_skip fi - ip -netns $ioam_tmp_node route add db02::/64 encap ioam6 mode inline \ - trace prealloc type 0x800000 ns 0 size 4 dev veth0 - tr_ad=$? + ip -netns $ioam_tmp_node route add 2001:db8:2::/64 \ + encap ioam6 trace prealloc type 0x800000 ns 0 size 4 dev veth0 &>/dev/null + ret=$? - ip -netns $ioam_tmp_node -6 route | grep -q "encap ioam6" - tr_sh=$? + ip -netns $ioam_tmp_node -6 route 2>/dev/null | grep -q "encap ioam6" + ret=$((ret + $?)) - if [[ $tr_ad != 0 || $tr_sh != 0 ]] + if [ $ret != 0 ] then - echo "SKIP: cannot attach an ioam trace to a route, did you compile" \ - "without CONFIG_IPV6_IOAM6_LWTUNNEL?" - ip link del veth0 2>/dev/null || true - cleanup_ns $ioam_tmp_node || true + echo "SKIP: Cannot attach an IOAM trace to a route. Was your kernel" \ + "compiled without CONFIG_IPV6_IOAM6_LWTUNNEL? Are you running an" \ + "old kernel? Are you using an old version of iproute2?" + cleanup_ns $ioam_tmp_node exit $ksft_skip fi - ip link del veth0 2>/dev/null || true - cleanup_ns $ioam_tmp_node || true + cleanup_ns $ioam_tmp_node - lsmod | grep -q "ip6_tunnel" + lsmod 2>/dev/null | grep -q "ip6_tunnel" ip6tnl_loaded=$? - if [ $ip6tnl_loaded = 0 ] + if [ $ip6tnl_loaded == 0 ] then encap_tests=0 else modprobe ip6_tunnel &>/dev/null - lsmod | grep -q "ip6_tunnel" + lsmod 2>/dev/null | grep -q "ip6_tunnel" encap_tests=$? if [ $encap_tests != 0 ] then - ip a | grep -q "ip6tnl0" + ip a 2>/dev/null | grep -q "ip6tnl0" encap_tests=$? if [ $encap_tests != 0 ] then echo "Note: ip6_tunnel not found neither as a module nor inside the" \ - "kernel, tests that require it (encap mode) will be omitted" + "kernel. Any tests that require it will be skipped." fi fi fi @@ -261,477 +251,1400 @@ check_kernel_compatibility() cleanup() { - ip link del ioam-veth-alpha 2>/dev/null || true - ip link del ioam-veth-gamma 2>/dev/null || true - - cleanup_ns $ioam_node_alpha $ioam_node_beta $ioam_node_gamma || true + cleanup_ns $ioam_node_alpha $ioam_node_beta $ioam_node_gamma if [ $ip6tnl_loaded != 0 ] then - modprobe -r ip6_tunnel 2>/dev/null || true + modprobe -r ip6_tunnel &>/dev/null fi } setup() { - setup_ns ioam_node_alpha ioam_node_beta ioam_node_gamma + setup_ns ioam_node_alpha ioam_node_beta ioam_node_gamma &>/dev/null ip link add name ioam-veth-alpha netns $ioam_node_alpha type veth \ - peer name ioam-veth-betaL netns $ioam_node_beta + peer name ioam-veth-betaL netns $ioam_node_beta &>/dev/null ip link add name ioam-veth-betaR netns $ioam_node_beta type veth \ - peer name ioam-veth-gamma netns $ioam_node_gamma - - ip -netns $ioam_node_alpha link set ioam-veth-alpha name veth0 - ip -netns $ioam_node_beta link set ioam-veth-betaL name veth0 - ip -netns $ioam_node_beta link set ioam-veth-betaR name veth1 - ip -netns $ioam_node_gamma link set ioam-veth-gamma name veth0 - - ip -netns $ioam_node_alpha addr add db01::2/64 dev veth0 - ip -netns $ioam_node_alpha link set veth0 up - ip -netns $ioam_node_alpha link set lo up - ip -netns $ioam_node_alpha route add db02::/64 via db01::1 dev veth0 - ip -netns $ioam_node_alpha route del db01::/64 - ip -netns $ioam_node_alpha route add db01::/64 dev veth0 - - ip -netns $ioam_node_beta addr add db01::1/64 dev veth0 - ip -netns $ioam_node_beta addr add db02::1/64 dev veth1 - ip -netns $ioam_node_beta link set veth0 up - ip -netns $ioam_node_beta link set veth1 up - ip -netns $ioam_node_beta link set lo up - - ip -netns $ioam_node_gamma addr add db02::2/64 dev veth0 - ip -netns $ioam_node_gamma link set veth0 up - ip -netns $ioam_node_gamma link set lo up - ip -netns $ioam_node_gamma route add db01::/64 via db02::1 dev veth0 - - # - IOAM config - - ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.ioam6_id=${ALPHA[0]} - ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.ioam6_id_wide=${ALPHA[1]} - ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id=${ALPHA[4]} - ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${ALPHA[5]} - ip -netns $ioam_node_alpha ioam namespace add 123 data ${ALPHA[6]} wide ${ALPHA[7]} - ip -netns $ioam_node_alpha ioam schema add ${ALPHA[8]} "${ALPHA[9]}" - ip -netns $ioam_node_alpha ioam namespace set 123 schema ${ALPHA[8]} - - ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.all.forwarding=1 - ip netns exec $ioam_node_beta sysctl -wq net.ipv6.ioam6_id=${BETA[0]} - ip netns exec $ioam_node_beta sysctl -wq net.ipv6.ioam6_id_wide=${BETA[1]} - ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 - ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_id=${BETA[2]} - ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${BETA[3]} - ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth1.ioam6_id=${BETA[4]} - ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth1.ioam6_id_wide=${BETA[5]} - ip -netns $ioam_node_beta ioam namespace add 123 data ${BETA[6]} wide ${BETA[7]} - ip -netns $ioam_node_beta ioam schema add ${BETA[8]} "${BETA[9]}" - ip -netns $ioam_node_beta ioam namespace set 123 schema ${BETA[8]} - - ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.ioam6_id=${GAMMA[0]} - ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.ioam6_id_wide=${GAMMA[1]} - ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 - ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id=${GAMMA[2]} - ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${GAMMA[3]} - ip -netns $ioam_node_gamma ioam namespace add 123 data ${GAMMA[6]} wide ${GAMMA[7]} + peer name ioam-veth-gamma netns $ioam_node_gamma &>/dev/null + + ip -netns $ioam_node_alpha link set ioam-veth-alpha name veth0 &>/dev/null + ip -netns $ioam_node_beta link set ioam-veth-betaL name veth0 &>/dev/null + ip -netns $ioam_node_beta link set ioam-veth-betaR name veth1 &>/dev/null + ip -netns $ioam_node_gamma link set ioam-veth-gamma name veth0 &>/dev/null + + ip -netns $ioam_node_alpha addr add 2001:db8:1::50/64 dev veth0 &>/dev/null + ip -netns $ioam_node_alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null + ip -netns $ioam_node_alpha link set veth0 up &>/dev/null + ip -netns $ioam_node_alpha link set lo up &>/dev/null + ip -netns $ioam_node_alpha route add 2001:db8:2::/64 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + ip -netns $ioam_node_beta addr add 2001:db8:1::1/64 dev veth0 &>/dev/null + ip -netns $ioam_node_beta addr add 2001:db8:2::1/64 dev veth1 &>/dev/null + ip -netns $ioam_node_beta link set veth0 up &>/dev/null + ip -netns $ioam_node_beta link set veth1 up &>/dev/null + ip -netns $ioam_node_beta link set lo up &>/dev/null + + ip -netns $ioam_node_gamma addr add 2001:db8:2::2/64 dev veth0 &>/dev/null + ip -netns $ioam_node_gamma link set veth0 up &>/dev/null + ip -netns $ioam_node_gamma link set lo up &>/dev/null + ip -netns $ioam_node_gamma route add 2001:db8:1::/64 \ + via 2001:db8:2::1 dev veth0 &>/dev/null + + # - Alpha: IOAM config - + ip netns exec $ioam_node_alpha \ + sysctl -wq net.ipv6.ioam6_id=${ALPHA[0]} &>/dev/null + ip netns exec $ioam_node_alpha \ + sysctl -wq net.ipv6.ioam6_id_wide=${ALPHA[1]} &>/dev/null + ip netns exec $ioam_node_alpha \ + sysctl -wq net.ipv6.conf.veth0.ioam6_id=${ALPHA[4]} &>/dev/null + ip netns exec $ioam_node_alpha \ + sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${ALPHA[5]} &>/dev/null + ip -netns $ioam_node_alpha \ + ioam namespace add 123 data ${ALPHA[6]} wide ${ALPHA[7]} &>/dev/null + ip -netns $ioam_node_alpha \ + ioam schema add ${ALPHA[8]} "${ALPHA[9]}" &>/dev/null + ip -netns $ioam_node_alpha \ + ioam namespace set 123 schema ${ALPHA[8]} &>/dev/null + + # - Beta: IOAM config - + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.conf.all.forwarding=1 &>/dev/null + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.ioam6_id=${BETA[0]} &>/dev/null + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.ioam6_id_wide=${BETA[1]} &>/dev/null + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 &>/dev/null + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.conf.veth0.ioam6_id=${BETA[2]} &>/dev/null + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${BETA[3]} &>/dev/null + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.conf.veth1.ioam6_id=${BETA[4]} &>/dev/null + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.conf.veth1.ioam6_id_wide=${BETA[5]} &>/dev/null + ip -netns $ioam_node_beta ioam namespace add 123 &>/dev/null sleep 1 - ip netns exec $ioam_node_alpha ping6 -c 5 -W 1 db02::2 &>/dev/null + ip netns exec $ioam_node_alpha ping6 -c 5 -W 1 2001:db8:2::2 &>/dev/null if [ $? != 0 ] then - echo "Setup FAILED" - cleanup &>/dev/null - exit 0 + echo "SKIP: Setup failed." + cleanup + exit $ksft_skip fi } log_test_passed() { - local desc=$1 - printf "TEST: %-60s [ OK ]\n" "${desc}" + printf " - TEST: %-57s [ OK ]\n" "$1" + npassed=$((npassed+1)) } -log_test_failed() +log_test_skipped() { - local desc=$1 - printf "TEST: %-60s [FAIL]\n" "${desc}" + printf " - TEST: %-57s [SKIP]\n" "$1" + nskipped=$((nskipped+1)) } -log_results() +log_test_failed() { - echo "- Tests passed: ${npassed}" - echo "- Tests failed: ${nfailed}" + printf " - TEST: %-57s [FAIL]\n" "$1" + nfailed=$((nfailed+1)) } run_test() { local name=$1 local desc=$2 - local node_src=$3 - local node_dst=$4 - local ip6_dst=$5 - local trace_type=$6 - local ioam_ns=$7 - local type=$8 - - ip netns exec $node_dst ./ioam6_parser $name $trace_type $ioam_ns $type & + local ip6_src=$3 + local trace_type=$4 + local trace_size=$5 + local ioam_ns=$6 + local type=$7 + + ip netns exec $ioam_node_gamma \ + ./ioam6_parser veth0 $name $ip6_src 2001:db8:2::2 \ + $trace_type $trace_size $ioam_ns $type & local spid=$! sleep 0.1 - ip netns exec $node_src ping6 -t 64 -c 1 -W 1 $ip6_dst &>/dev/null + ip netns exec $ioam_node_alpha ping6 -t 64 -c 1 -W 1 2001:db8:2::2 &>/dev/null if [ $? != 0 ] then - nfailed=$((nfailed+1)) log_test_failed "${desc}" kill -2 $spid &>/dev/null else wait $spid - if [ $? = 0 ] - then - npassed=$((npassed+1)) - log_test_passed "${desc}" - else - nfailed=$((nfailed+1)) - log_test_failed "${desc}" - fi + [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" fi } run() { + local test + + echo + printf "+" + printf "%0.s-" {1..72} + printf "+" + echo + printf "| %-28s LOCAL tests %-29s |" echo - printf "%0.s-" {1..74} + printf "+" + printf "%0.s-" {1..72} + printf "+" echo - echo "OUTPUT tests" - printf "%0.s-" {1..74} + + echo + echo "Global config" + for test in $TESTS_LOCAL + do + $test + done + + echo + echo "Inline mode" + for test in $TESTS_LOCAL + do + $test "inline" + done + + echo + echo "Encap mode" + for test in $TESTS_LOCAL + do + $test "encap" + done + + echo + printf "+" + printf "%0.s-" {1..72} + printf "+" + echo + printf "| %-28s OUTPUT tests %-28s |" + echo + printf "+" + printf "%0.s-" {1..72} + printf "+" echo # set OUTPUT settings - ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=0 + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=0 &>/dev/null - for t in $TESTS_OUTPUT + echo + echo "Inline mode" + for test in $TESTS_OUTPUT do - $t "inline" - [ $encap_tests = 0 ] && $t "encap" + $test "inline" done - # clean OUTPUT settings - ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 - ip -netns $ioam_node_alpha route change db01::/64 dev veth0 + echo + echo "Encap mode" + for test in $TESTS_OUTPUT + do + $test "encap" + done + echo + echo "Encap mode (with tunsrc)" + for test in $TESTS_OUTPUT + do + $test "encap" "tunsrc" + done + + # clean OUTPUT settings + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 &>/dev/null echo - printf "%0.s-" {1..74} + printf "+" + printf "%0.s-" {1..72} + printf "+" echo - echo "INPUT tests" - printf "%0.s-" {1..74} + printf "| %-28s INPUT tests %-29s |" + echo + printf "+" + printf "%0.s-" {1..72} + printf "+" echo # set INPUT settings - ip -netns $ioam_node_alpha ioam namespace del 123 + ip -netns $ioam_node_alpha ioam namespace del 123 &>/dev/null - for t in $TESTS_INPUT + echo + echo "Inline mode" + for test in $TESTS_INPUT do - $t "inline" - [ $encap_tests = 0 ] && $t "encap" + $test "inline" + done + + echo + echo "Encap mode" + for test in $TESTS_INPUT + do + $test "encap" done # clean INPUT settings - ip -netns $ioam_node_alpha ioam namespace add 123 \ - data ${ALPHA[6]} wide ${ALPHA[7]} - ip -netns $ioam_node_alpha ioam namespace set 123 schema ${ALPHA[8]} - ip -netns $ioam_node_alpha route change db01::/64 dev veth0 + ip -netns $ioam_node_alpha \ + ioam namespace add 123 data ${ALPHA[6]} wide ${ALPHA[7]} &>/dev/null + ip -netns $ioam_node_alpha \ + ioam namespace set 123 schema ${ALPHA[8]} &>/dev/null echo - printf "%0.s-" {1..74} + printf "+" + printf "%0.s-" {1..72} + printf "+" echo - echo "GLOBAL tests" - printf "%0.s-" {1..74} + printf "| %-30s Results %-31s |" + echo + printf "+" + printf "%0.s-" {1..72} + printf "+" echo - for t in $TESTS_GLOBAL - do - $t "inline" - [ $encap_tests = 0 ] && $t "encap" - done - echo - log_results + echo "- Passed: ${npassed}" + echo "- Skipped: ${nskipped}" + echo "- Failed: ${nfailed}" + echo } bit2type=( 0x800000 0x400000 0x200000 0x100000 0x080000 0x040000 0x020000 0x010000 0x008000 0x004000 0x002000 0x001000 0x000800 0x000400 0x000200 0x000100 - 0x000080 0x000040 0x000020 0x000010 0x000008 0x000004 0x000002 + 0x000080 0x000040 0x000020 0x000010 0x000008 0x000004 0x000002 0x000001 ) -bit2size=( 4 4 4 4 4 4 4 4 8 8 8 4 4 4 4 4 4 4 4 4 4 4 4 ) +bit2size=( 4 4 4 4 4 4 4 4 8 8 8 4 4 4 4 4 4 4 4 4 4 4 4 0 ) ################################################################################ # # -# OUTPUT tests # +# LOCAL tests # # # -# Two nodes (sender/receiver), IOAM disabled on ingress for the receiver. # ################################################################################ -out_undef_ns() +local_sysctl_ioam_id() +{ + ############################################################################## + # Make sure the sysctl "net.ipv6.ioam6_id" works as expected. # + ############################################################################## + local desc="Sysctl net.ipv6.ioam6_id" + + [ ! -z $1 ] && return + + ip netns exec $ioam_node_alpha \ + sysctl net.ipv6.ioam6_id 2>/dev/null | grep -wq ${ALPHA[0]} + + [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" +} + +local_sysctl_ioam_id_wide() { ############################################################################## - # Make sure that the encap node won't fill the trace if the chosen IOAM # - # namespace is not configured locally. # + # Make sure the sysctl "net.ipv6.ioam6_id_wide" works as expected. # ############################################################################## - local desc="Unknown IOAM namespace" + local desc="Sysctl net.ipv6.ioam6_id_wide" - [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up + [ ! -z $1 ] && return - ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \ - trace prealloc type 0x800000 ns 0 size 4 dev veth0 + ip netns exec $ioam_node_alpha \ + sysctl net.ipv6.ioam6_id_wide 2>/dev/null | grep -wq ${ALPHA[1]} - run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::1 0x800000 0 $1 + [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" +} - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down +local_sysctl_ioam_intf_id() +{ + ############################################################################## + # Make sure the sysctl "net.ipv6.conf.XX.ioam6_id" works as expected. # + ############################################################################## + local desc="Sysctl net.ipv6.conf.XX.ioam6_id" + + [ ! -z $1 ] && return + + ip netns exec $ioam_node_alpha \ + sysctl net.ipv6.conf.veth0.ioam6_id 2>/dev/null | grep -wq ${ALPHA[4]} + + [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" } -out_no_room() +local_sysctl_ioam_intf_id_wide() { ############################################################################## - # Make sure that the encap node won't fill the trace and will set the # - # Overflow flag since there is no room enough for its data. # + # Make sure the sysctl "net.ipv6.conf.XX.ioam6_id_wide" works as expected. # ############################################################################## - local desc="Missing trace room" + local desc="Sysctl net.ipv6.conf.XX.ioam6_id_wide" + + [ ! -z $1 ] && return + + ip netns exec $ioam_node_alpha \ + sysctl net.ipv6.conf.veth0.ioam6_id_wide 2>/dev/null | grep -wq ${ALPHA[5]} + + [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" +} - [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up +local_sysctl_ioam_intf_enabled() +{ + ############################################################################## + # Make sure the sysctl "net.ipv6.conf.XX.ioam6_enabled" works as expected. # + ############################################################################## + local desc="Sysctl net.ipv6.conf.XX.ioam6_enabled" - ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \ - trace prealloc type 0xc00000 ns 123 size 4 dev veth0 + [ ! -z $1 ] && return - run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::1 0xc00000 123 $1 + ip netns exec $ioam_node_beta \ + sysctl net.ipv6.conf.veth0.ioam6_enabled 2>/dev/null | grep -wq 1 - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down + [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" } -out_bits() +local_ioam_namespace() { ############################################################################## - # Make sure that, for each trace type bit, the encap node will either: # - # (i) fill the trace with its data when it is a supported bit # - # (ii) not fill the trace with its data when it is an unsupported bit # + # Make sure the creation of an IOAM Namespace works as expected. # ############################################################################## - local desc="Trace type with bit <n> only" + local desc="Create an IOAM Namespace" - local tmp=${bit2size[22]} - bit2size[22]=$(( $tmp + ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) )) + [ ! -z $1 ] && return - [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up + ip -netns $ioam_node_alpha \ + ioam namespace show 2>/dev/null | grep -wq 123 + local ret=$? - for i in {0..22} - do - ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \ - trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ - dev veth0 &>/dev/null + ip -netns $ioam_node_alpha \ + ioam namespace show 2>/dev/null | grep -wq ${ALPHA[6]} + ret=$((ret + $?)) - local cmd_res=$? - local descr="${desc/<n>/$i}" + ip -netns $ioam_node_alpha \ + ioam namespace show 2>/dev/null | grep -wq ${ALPHA[7]} + ret=$((ret + $?)) + + [ $ret == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" +} + +local_ioam_schema() +{ + ############################################################################## + # Make sure the creation of an IOAM Schema works as expected. # + ############################################################################## + local desc="Create an IOAM Schema" + + [ ! -z $1 ] && return + + ip -netns $ioam_node_alpha \ + ioam schema show 2>/dev/null | grep -wq ${ALPHA[8]} + local ret=$? + + local sc_data=$( + for i in `seq 0 $((${#ALPHA[9]}-1))` + do + chr=${ALPHA[9]:i:1} + printf "%x " "'${chr}" + done + ) + + ip -netns $ioam_node_alpha \ + ioam schema show 2>/dev/null | grep -q "$sc_data" + ret=$((ret + $?)) + + [ $ret == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" +} + +local_ioam_schema_namespace() +{ + ############################################################################## + # Make sure the binding of a Schema to a Namespace works as expected. # + ############################################################################## + local desc="Bind an IOAM Schema to an IOAM Namespace" + + [ ! -z $1 ] && return + + ip -netns $ioam_node_alpha \ + ioam namespace show 2>/dev/null | grep -wq ${ALPHA[8]} + local ret=$? + + ip -netns $ioam_node_alpha \ + ioam schema show 2>/dev/null | grep -wq 123 + ret=$((ret + $?)) + + [ $ret == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" +} + +local_route_ns() +{ + ############################################################################## + # Make sure the Namespace-ID is always provided, whatever the mode. # + ############################################################################## + local desc="Mandatory Namespace-ID" + local mode + + [ -z $1 ] && return + + [ "$1" == "encap" ] && mode="$1 tundst 2001:db8:2::2" || mode="$1" + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type 0x800000 size 4 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + local ret1=$? + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size 4 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + local ret2=$? + + [[ $ret1 == 0 || $ret2 != 0 ]] && log_test_failed "${desc}" \ + || log_test_passed "${desc}" + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null +} + +local_route_tunsrc() +{ + ############################################################################## + # Make sure the Tunnel Source is only (and possibly) used with encap mode. # + ############################################################################## + local desc + local mode + local mode_tunsrc - if [[ $i -ge 12 && $i -le 21 ]] + [ -z $1 ] && return + + if [ "$1" == "encap" ] + then + desc="Optional Tunnel Source" + mode="$1 tundst 2001:db8:2::2" + mode_tunsrc="$1 tunsrc 2001:db8:1::50 tundst 2001:db8:2::2" + else + desc="Unneeded Tunnel Source" + mode="$1" + mode_tunsrc="$1 tunsrc 2001:db8:1::50" + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size 4 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + local ret1=$? + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode_tunsrc trace prealloc type 0x800000 ns 0 size 4 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + local ret2=$? + + if [ "$1" == "encap" ] + then + [[ $ret1 != 0 || $ret2 != 0 ]] && log_test_failed "${desc}" \ + || log_test_passed "${desc}" + else + [[ $ret1 != 0 || $ret2 == 0 ]] && log_test_failed "${desc}" \ + || log_test_passed "${desc}" + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null +} + +local_route_tundst() +{ + ############################################################################## + # Make sure the Tunnel Destination is only (and always) used with encap mode.# + ############################################################################## + local desc + + [ -z $1 ] && return + + [ "$1" == "encap" ] && desc="Mandatory Tunnel Destination" \ + || desc="Unneeded Tunnel Destination" + + local mode="$1" + local mode_tundst="$1 tundst 2001:db8:2::2" + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size 4 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + local ret1=$? + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode_tundst trace prealloc type 0x800000 ns 0 size 4 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + local ret2=$? + + if [ "$1" == "encap" ] + then + [[ $ret1 == 0 || $ret2 != 0 ]] && log_test_failed "${desc}" \ + || log_test_passed "${desc}" + else + [[ $ret1 != 0 || $ret2 == 0 ]] && log_test_failed "${desc}" \ + || log_test_passed "${desc}" + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null +} + +local_route_trace_type() +{ + ############################################################################## + # Make sure the Trace Type is always provided, whatever the mode. # + ############################################################################## + local desc="Mandatory Trace Type" + local mode + + [ -z $1 ] && return + + [ "$1" == "encap" ] && mode="$1 tundst 2001:db8:2::2" || mode="$1" + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc ns 0 size 4 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + local ret1=$? + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size 4 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + local ret2=$? + + [[ $ret1 == 0 || $ret2 != 0 ]] && log_test_failed "${desc}" \ + || log_test_passed "${desc}" + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null +} + +local_route_trace_size() +{ + ############################################################################## + # Make sure the Trace Size is always provided, whatever the mode. # + ############################################################################## + local desc="Mandatory Trace Size" + local mode + + [ -z $1 ] && return + + [ "$1" == "encap" ] && mode="$1 tundst 2001:db8:2::2" || mode="$1" + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + local ret1=$? + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size 4 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + local ret2=$? + + [[ $ret1 == 0 || $ret2 != 0 ]] && log_test_failed "${desc}" \ + || log_test_passed "${desc}" + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null +} + +local_route_trace_type_bits() +{ + ############################################################################## + # Make sure only allowed bits (0-11 and 22) are accepted. # + ############################################################################## + local desc="Trace Type bits" + local mode + + [ -z $1 ] && return + + [ "$1" == "encap" ] && mode="$1 tundst 2001:db8:2::2" || mode="$1" + + local i + for i in {0..23} + do + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type ${bit2type[$i]} ns 0 size 4 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + if [[ ($? == 0 && (($i -ge 12 && $i -le 21) || $i == 23)) || + ($? != 0 && (($i -ge 0 && $i -le 11) || $i == 22)) ]] then - if [ $cmd_res != 0 ] - then - npassed=$((npassed+1)) - log_test_passed "$descr ($1 mode)" - else - nfailed=$((nfailed+1)) - log_test_failed "$descr ($1 mode)" - fi - else - run_test "out_bit$i" "$descr ($1 mode)" $ioam_node_alpha \ - $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1 + local err=1 + break fi done - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down + [ -z $err ] && log_test_passed "${desc}" || log_test_failed "${desc}" - bit2size[22]=$tmp + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null } -out_full_supp_trace() +local_route_trace_size_values() { ############################################################################## - # Make sure that the encap node will correctly fill a full trace. Be careful,# - # "full trace" here does NOT mean all bits (only supported ones). # + # Make sure only allowed sizes (multiples of four in [4,244]) are accepted. # ############################################################################## - local desc="Full supported trace" + local desc="Trace Size values" + local mode - [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up + [ -z $1 ] && return - ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \ - trace prealloc type 0xfff002 ns 123 size 100 dev veth0 + [ "$1" == "encap" ] && mode="$1 tundst 2001:db8:2::2" || mode="$1" - run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::1 0xfff002 123 $1 + # we also try the next multiple of four after the MAX to check it's refused + local i + for i in {0..248} + do + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size $i \ + via 2001:db8:1::1 dev veth0 &>/dev/null - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down + if [[ ($? == 0 && ($i == 0 || $i == 248 || $(( $i % 4 )) != 0)) || + ($? != 0 && $i != 0 && $i != 248 && $(( $i % 4 )) == 0) ]] + then + local err=1 + break + fi + done + + [ -z $err ] && log_test_passed "${desc}" || log_test_failed "${desc}" + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null } ################################################################################ # # -# INPUT tests # +# OUTPUT tests # # # -# Two nodes (sender/receiver), the sender MUST NOT fill the trace upon # -# insertion -> the IOAM namespace configured on the sender is removed # -# and is used in the inserted trace to force the sender not to fill it. # ################################################################################ -in_undef_ns() +output_undef_ns() { ############################################################################## - # Make sure that the receiving node won't fill the trace if the related IOAM # - # namespace is not configured locally. # + # Make sure an IOAM encapsulating node does NOT fill the trace when the # + # corresponding IOAM Namespace-ID is not configured locally. # ############################################################################## - local desc="Unknown IOAM namespace" + local desc="Unknown IOAM Namespace-ID" + local ns=0 + local tr_type=0x800000 + local tr_size=4 + local mode="$1" + local saddr="2001:db8:1::2" + + if [ "$1" == "encap" ] + then + if [ $encap_tests != 0 ] + then + log_test_skipped "${desc}" + return + fi + + if [ "$2" == "tunsrc" ] + then + saddr="2001:db8:1::50" + mode+=" tunsrc 2001:db8:1::50" + fi + + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi - [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \ + via 2001:db8:1::1 dev veth0 &>/dev/null - ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \ - trace prealloc type 0x800000 ns 0 size 4 dev veth0 + if [ $? == 0 ] + then + run_test ${FUNCNAME[0]} "${desc}" $saddr $tr_type $tr_size $ns $1 + else + log_test_failed "${desc}" + fi - run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::1 0x800000 0 $1 + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null } -in_no_room() +output_no_room() { ############################################################################## - # Make sure that the receiving node won't fill the trace and will set the # - # Overflow flag if there is no room enough for its data. # + # Make sure an IOAM encapsulating node does NOT fill the trace AND sets the # + # Overflow flag when there is not enough room for its data. # ############################################################################## - local desc="Missing trace room" + local desc="Missing room for data" + local ns=123 + local tr_type=0xc00000 + local tr_size=4 + local mode="$1" + local saddr="2001:db8:1::2" + + if [ "$1" == "encap" ] + then + if [ $encap_tests != 0 ] + then + log_test_skipped "${desc}" + return + fi - [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up + if [ "$2" == "tunsrc" ] + then + saddr="2001:db8:1::50" + mode+=" tunsrc 2001:db8:1::50" + fi - ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \ - trace prealloc type 0xc00000 ns 123 size 4 dev veth0 + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi - run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::1 0xc00000 123 $1 + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \ + via 2001:db8:1::1 dev veth0 &>/dev/null - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down + if [ $? == 0 ] + then + run_test ${FUNCNAME[0]} "${desc}" $saddr $tr_type $tr_size $ns $1 + else + log_test_failed "${desc}" + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null } -in_bits() +output_no_room_oss() { ############################################################################## - # Make sure that, for each trace type bit, the receiving node will either: # - # (i) fill the trace with its data when it is a supported bit # - # (ii) not fill the trace with its data when it is an unsupported bit # + # Make sure an IOAM encapsulating node does NOT fill the trace AND sets the # + # Overflow flag when there is not enough room for the Opaque State Snapshot. # ############################################################################## - local desc="Trace type with bit <n> only" + local desc="Missing room for Opaque State Snapshot" + local ns=123 + local tr_type=0x000002 + local tr_size=4 + local mode="$1" + local saddr="2001:db8:1::2" + + if [ "$1" == "encap" ] + then + if [ $encap_tests != 0 ] + then + log_test_skipped "${desc}" + return + fi - local tmp=${bit2size[22]} - bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) )) + if [ "$2" == "tunsrc" ] + then + saddr="2001:db8:1::50" + mode+=" tunsrc 2001:db8:1::50" + fi + + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + if [ $? == 0 ] + then + run_test ${FUNCNAME[0]} "${desc}" $saddr $tr_type $tr_size $ns $1 + else + log_test_failed "${desc}" + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null +} + +output_bits() +{ + ############################################################################## + # Make sure an IOAM encapsulating node implements all supported bits by # + # checking it correctly fills the trace with its data. # + ############################################################################## + local desc="Trace Type with supported bit <n> only" + local ns=123 + local mode="$1" + local saddr="2001:db8:1::2" - [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up + if [ "$1" == "encap" ] + then + if [ "$2" == "tunsrc" ] + then + saddr="2001:db8:1::50" + mode+=" tunsrc 2001:db8:1::50" + fi + + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi + + local tmp=${bit2size[22]} + bit2size[22]=$(( $tmp + ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) )) + local i for i in {0..11} {22..22} do - ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \ - trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ - dev veth0 + local descr="${desc/<n>/$i}" + + if [[ "$1" == "encap" && $encap_tests != 0 ]] + then + log_test_skipped "${descr}" + continue + fi - run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" $ioam_node_alpha \ - $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1 + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc \ + type ${bit2type[$i]} ns $ns size ${bit2size[$i]} \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + if [ $? == 0 ] + then + run_test "output_bit$i" "${descr}" $saddr \ + ${bit2type[$i]} ${bit2size[$i]} $ns $1 + else + log_test_failed "${descr}" + fi done - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null bit2size[22]=$tmp } -in_oflag() +output_sizes() { ############################################################################## - # Make sure that the receiving node won't fill the trace since the Overflow # - # flag is set. # + # Make sure an IOAM encapsulating node allocates supported sizes correctly. # ############################################################################## - local desc="Overflow flag is set" + local desc="Trace Size of <n> bytes" + local ns=0 + local tr_type=0x800000 + local mode="$1" + local saddr="2001:db8:1::2" - # Exception: - # Here, we need the sender to set the Overflow flag. For that, we will add - # back the IOAM namespace that was previously configured on the sender. - ip -netns $ioam_node_alpha ioam namespace add 123 + if [ "$1" == "encap" ] + then + if [ "$2" == "tunsrc" ] + then + saddr="2001:db8:1::50" + mode+=" tunsrc 2001:db8:1::50" + fi - [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi - ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \ - trace prealloc type 0xc00000 ns 123 size 4 dev veth0 + local i + for i in $(seq 4 4 244) + do + local descr="${desc/<n>/$i}" - run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::1 0xc00000 123 $1 + if [[ "$1" == "encap" && $encap_tests != 0 ]] + then + log_test_skipped "${descr}" + continue + fi - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $i \ + via 2001:db8:1::1 dev veth0 &>/dev/null - # And we clean the exception for this test to get things back to normal for - # other INPUT tests - ip -netns $ioam_node_alpha ioam namespace del 123 + if [ $? == 0 ] + then + run_test "output_size$i" "${descr}" $saddr $tr_type $i $ns $1 + else + log_test_failed "${descr}" + fi + done + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null } -in_full_supp_trace() +output_full_supp_trace() { ############################################################################## - # Make sure that the receiving node will correctly fill a full trace. Be # - # careful, "full trace" here does NOT mean all bits (only supported ones). # + # Make sure an IOAM encapsulating node correctly fills a trace when all # + # supported bits are set. # ############################################################################## local desc="Full supported trace" + local ns=123 + local tr_type=0xfff002 + local tr_size + local mode="$1" + local saddr="2001:db8:1::2" - [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up + if [ "$1" == "encap" ] + then + if [ $encap_tests != 0 ] + then + log_test_skipped "${desc}" + return + fi - ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \ - trace prealloc type 0xfff002 ns 123 size 80 dev veth0 + if [ "$2" == "tunsrc" ] + then + saddr="2001:db8:1::50" + mode+=" tunsrc 2001:db8:1::50" + fi - run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::1 0xfff002 123 $1 + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi - [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down + local i + tr_size=$(( ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) )) + for i in {0..11} {22..22} + do + tr_size=$((tr_size + bit2size[$i])) + done + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + if [ $? == 0 ] + then + run_test ${FUNCNAME[0]} "${desc}" $saddr $tr_type $tr_size $ns $1 + else + log_test_failed "${desc}" + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null } ################################################################################ # # -# GLOBAL tests # +# INPUT tests # # # -# Three nodes (sender/router/receiver), IOAM fully enabled on every node. # ################################################################################ -fwd_full_supp_trace() +input_undef_ns() +{ + ############################################################################## + # Make sure an IOAM node does NOT fill the trace when the corresponding IOAM # + # Namespace-ID is not configured locally. # + ############################################################################## + local desc="Unknown IOAM Namespace-ID" + local ns=0 + local tr_type=0x800000 + local tr_size=4 + local mode="$1" + + if [ "$1" == "encap" ] + then + if [ $encap_tests != 0 ] + then + log_test_skipped "${desc}" + return + fi + + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + if [ $? == 0 ] + then + run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1 + else + log_test_failed "${desc}" + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null +} + +input_no_room() +{ + ############################################################################## + # Make sure an IOAM node does NOT fill the trace AND sets the Overflow flag # + # when there is not enough room for its data. # + ############################################################################## + local desc="Missing room for data" + local ns=123 + local tr_type=0xc00000 + local tr_size=4 + local mode="$1" + + if [ "$1" == "encap" ] + then + if [ $encap_tests != 0 ] + then + log_test_skipped "${desc}" + return + fi + + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + if [ $? == 0 ] + then + run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1 + else + log_test_failed "${desc}" + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null +} + +input_no_room_oss() +{ + ############################################################################## + # Make sure an IOAM node does NOT fill the trace AND sets the Overflow flag # + # when there is not enough room for the Opaque State Snapshot. # + ############################################################################## + local desc="Missing room for Opaque State Snapshot" + local ns=123 + local tr_type=0x000002 + local tr_size=4 + local mode="$1" + + if [ "$1" == "encap" ] + then + if [ $encap_tests != 0 ] + then + log_test_skipped "${desc}" + return + fi + + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + if [ $? == 0 ] + then + run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1 + else + log_test_failed "${desc}" + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null +} + +input_disabled() +{ + ############################################################################## + # Make sure an IOAM node does NOT fill the trace when IOAM is not enabled on # + # the corresponding (ingress) interface. # + ############################################################################## + local desc="IOAM disabled on ingress interface" + local ns=123 + local tr_type=0x800000 + local tr_size=4 + local mode="$1" + + if [ "$1" == "encap" ] + then + if [ $encap_tests != 0 ] + then + log_test_skipped "${desc}" + return + fi + + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi + + # Exception: disable IOAM on ingress interface + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=0 &>/dev/null + local ret=$? + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \ + via 2001:db8:1::1 dev veth0 &>/dev/null + ret=$((ret + $?)) + + if [ $ret == 0 ] + then + run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1 + else + log_test_failed "${desc}" + fi + + # Clean Exception + ip netns exec $ioam_node_beta \ + sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 &>/dev/null + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null +} + +input_oflag() +{ + ############################################################################## + # Make sure an IOAM node does NOT fill the trace when the Overflow flag is # + # set. # + ############################################################################## + local desc="Overflow flag is set" + local ns=123 + local tr_type=0xc00000 + local tr_size=4 + local mode="$1" + + if [ "$1" == "encap" ] + then + if [ $encap_tests != 0 ] + then + log_test_skipped "${desc}" + return + fi + + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi + + # Exception: + # Here, we need the sender to set the Overflow flag. For that, we will add + # back the IOAM namespace that was previously configured on the sender. + ip -netns $ioam_node_alpha ioam namespace add 123 &>/dev/null + local ret=$? + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \ + via 2001:db8:1::1 dev veth0 &>/dev/null + ret=$((ret + $?)) + + if [ $ret == 0 ] + then + run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1 + else + log_test_failed "${desc}" + fi + + # Clean Exception + ip -netns $ioam_node_alpha ioam namespace del 123 &>/dev/null + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null +} + +input_bits() +{ + ############################################################################## + # Make sure an IOAM node implements all supported bits by checking it # + # correctly fills the trace with its data. # + ############################################################################## + local desc="Trace Type with supported bit <n> only" + local ns=123 + local mode="$1" + + if [ "$1" == "encap" ] + then + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi + + local tmp=${bit2size[22]} + bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) )) + + local i + for i in {0..11} {22..22} + do + local descr="${desc/<n>/$i}" + + if [[ "$1" == "encap" && $encap_tests != 0 ]] + then + log_test_skipped "${descr}" + continue + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc \ + type ${bit2type[$i]} ns $ns size ${bit2size[$i]} \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + if [ $? == 0 ] + then + run_test "input_bit$i" "${descr}" 2001:db8:1::2 \ + ${bit2type[$i]} ${bit2size[$i]} $ns $1 + else + log_test_failed "${descr}" + fi + done + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null + + bit2size[22]=$tmp +} + +input_sizes() { ############################################################################## - # Make sure that all three nodes correctly filled the full supported trace # - # by checking that the trace data is consistent with the predefined config. # + # Make sure an IOAM node handles all supported sizes correctly. # ############################################################################## - local desc="Forward - Full supported trace" + local desc="Trace Size of <n> bytes" + local ns=123 + local tr_type=0x800000 + local mode="$1" + + if [ "$1" == "encap" ] + then + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi - [ "$1" = "encap" ] && mode="$1 tundst db02::2" || mode="$1" - [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 up + local i + for i in $(seq 4 4 244) + do + local descr="${desc/<n>/$i}" - ip -netns $ioam_node_alpha route change db02::/64 encap ioam6 mode $mode \ - trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0 + if [[ "$1" == "encap" && $encap_tests != 0 ]] + then + log_test_skipped "${descr}" + continue + fi - run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_gamma \ - db02::2 0xfff002 123 $1 + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $i \ + via 2001:db8:1::1 dev veth0 &>/dev/null - [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 down + if [ $? == 0 ] + then + run_test "input_size$i" "${descr}" 2001:db8:1::2 $tr_type $i $ns $1 + else + log_test_failed "${descr}" + fi + done + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null +} + +input_full_supp_trace() +{ + ############################################################################## + # Make sure an IOAM node correctly fills a trace when all supported bits are # + # set. # + ############################################################################## + local desc="Full supported trace" + local ns=123 + local tr_type=0xfff002 + local tr_size + local mode="$1" + + if [ "$1" == "encap" ] + then + if [ $encap_tests != 0 ] + then + log_test_skipped "${desc}" + return + fi + + mode+=" tundst 2001:db8:2::2" + ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null + fi + + local i + tr_size=$(( ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) )) + for i in {0..11} {22..22} + do + tr_size=$((tr_size + bit2size[$i])) + done + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 \ + encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + if [ $? == 0 ] + then + run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1 + else + log_test_failed "${desc}" + fi + + ip -netns $ioam_node_alpha \ + route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null + + [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \ + link set ip6tnl0 down &>/dev/null } @@ -742,30 +1655,29 @@ fwd_full_supp_trace() ################################################################################ npassed=0 +nskipped=0 nfailed=0 if [ "$(id -u)" -ne 0 ] then - echo "SKIP: Need root privileges" + echo "SKIP: Need root privileges." exit $ksft_skip fi if [ ! -x "$(command -v ip)" ] then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi - -ip ioam &>/dev/null -if [ $? = 1 ] -then - echo "SKIP: iproute2 too old, missing ioam command" + echo "SKIP: Could not run test without ip tool." exit $ksft_skip fi check_kernel_compatibility - -cleanup &>/dev/null setup run -cleanup &>/dev/null +cleanup + +if [ $nfailed != 0 ] +then + exit $ksft_fail +fi + +exit $ksft_pass diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c index 895e5bb5044b..de4b5c9e8a74 100644 --- a/tools/testing/selftests/net/ioam6_parser.c +++ b/tools/testing/selftests/net/ioam6_parser.c @@ -8,8 +8,10 @@ #include <errno.h> #include <limits.h> #include <linux/const.h> +#include <linux/if_ether.h> #include <linux/ioam6.h> #include <linux/ipv6.h> +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <unistd.h> @@ -40,7 +42,7 @@ static struct ioam_config node1 = { .egr_id = 101, .ingr_wide = 0xffffffff, /* default value */ .egr_wide = 101101, - .ns_data = 0xdeadbee0, + .ns_data = 0xdeadbeef, .ns_wide = 0xcafec0caf00dc0de, .sc_id = 777, .sc_data = "something that will be 4n-aligned", @@ -54,33 +56,22 @@ static struct ioam_config node2 = { .egr_id = 202, .ingr_wide = 201201, .egr_wide = 202202, - .ns_data = 0xdeadbee1, - .ns_wide = 0xcafec0caf11dc0de, - .sc_id = 666, - .sc_data = "Hello there -Obi", - .hlim = 63, -}; - -static struct ioam_config node3 = { - .id = 3, - .wide = 33333333, - .ingr_id = 301, - .egr_id = 0xffff, /* default value */ - .ingr_wide = 301301, - .egr_wide = 0xffffffff, /* default value */ - .ns_data = 0xdeadbee2, - .ns_wide = 0xcafec0caf22dc0de, + .ns_data = 0xffffffff, /* default value */ + .ns_wide = 0xffffffffffffffff, /* default value */ .sc_id = 0xffffff, /* default value */ .sc_data = NULL, - .hlim = 62, + .hlim = 63, }; enum { /********** * OUTPUT * **********/ + __TEST_OUT_MIN, + TEST_OUT_UNDEF_NS, TEST_OUT_NO_ROOM, + TEST_OUT_NO_ROOM_OSS, TEST_OUT_BIT0, TEST_OUT_BIT1, TEST_OUT_BIT2, @@ -94,13 +85,80 @@ enum { TEST_OUT_BIT10, TEST_OUT_BIT11, TEST_OUT_BIT22, + TEST_OUT_SIZE4, + TEST_OUT_SIZE8, + TEST_OUT_SIZE12, + TEST_OUT_SIZE16, + TEST_OUT_SIZE20, + TEST_OUT_SIZE24, + TEST_OUT_SIZE28, + TEST_OUT_SIZE32, + TEST_OUT_SIZE36, + TEST_OUT_SIZE40, + TEST_OUT_SIZE44, + TEST_OUT_SIZE48, + TEST_OUT_SIZE52, + TEST_OUT_SIZE56, + TEST_OUT_SIZE60, + TEST_OUT_SIZE64, + TEST_OUT_SIZE68, + TEST_OUT_SIZE72, + TEST_OUT_SIZE76, + TEST_OUT_SIZE80, + TEST_OUT_SIZE84, + TEST_OUT_SIZE88, + TEST_OUT_SIZE92, + TEST_OUT_SIZE96, + TEST_OUT_SIZE100, + TEST_OUT_SIZE104, + TEST_OUT_SIZE108, + TEST_OUT_SIZE112, + TEST_OUT_SIZE116, + TEST_OUT_SIZE120, + TEST_OUT_SIZE124, + TEST_OUT_SIZE128, + TEST_OUT_SIZE132, + TEST_OUT_SIZE136, + TEST_OUT_SIZE140, + TEST_OUT_SIZE144, + TEST_OUT_SIZE148, + TEST_OUT_SIZE152, + TEST_OUT_SIZE156, + TEST_OUT_SIZE160, + TEST_OUT_SIZE164, + TEST_OUT_SIZE168, + TEST_OUT_SIZE172, + TEST_OUT_SIZE176, + TEST_OUT_SIZE180, + TEST_OUT_SIZE184, + TEST_OUT_SIZE188, + TEST_OUT_SIZE192, + TEST_OUT_SIZE196, + TEST_OUT_SIZE200, + TEST_OUT_SIZE204, + TEST_OUT_SIZE208, + TEST_OUT_SIZE212, + TEST_OUT_SIZE216, + TEST_OUT_SIZE220, + TEST_OUT_SIZE224, + TEST_OUT_SIZE228, + TEST_OUT_SIZE232, + TEST_OUT_SIZE236, + TEST_OUT_SIZE240, + TEST_OUT_SIZE244, TEST_OUT_FULL_SUPP_TRACE, + __TEST_OUT_MAX, + /********* * INPUT * *********/ + __TEST_IN_MIN, + TEST_IN_UNDEF_NS, TEST_IN_NO_ROOM, + TEST_IN_NO_ROOM_OSS, + TEST_IN_DISABLED, TEST_IN_OFLAG, TEST_IN_BIT0, TEST_IN_BIT1, @@ -115,36 +173,107 @@ enum { TEST_IN_BIT10, TEST_IN_BIT11, TEST_IN_BIT22, + TEST_IN_SIZE4, + TEST_IN_SIZE8, + TEST_IN_SIZE12, + TEST_IN_SIZE16, + TEST_IN_SIZE20, + TEST_IN_SIZE24, + TEST_IN_SIZE28, + TEST_IN_SIZE32, + TEST_IN_SIZE36, + TEST_IN_SIZE40, + TEST_IN_SIZE44, + TEST_IN_SIZE48, + TEST_IN_SIZE52, + TEST_IN_SIZE56, + TEST_IN_SIZE60, + TEST_IN_SIZE64, + TEST_IN_SIZE68, + TEST_IN_SIZE72, + TEST_IN_SIZE76, + TEST_IN_SIZE80, + TEST_IN_SIZE84, + TEST_IN_SIZE88, + TEST_IN_SIZE92, + TEST_IN_SIZE96, + TEST_IN_SIZE100, + TEST_IN_SIZE104, + TEST_IN_SIZE108, + TEST_IN_SIZE112, + TEST_IN_SIZE116, + TEST_IN_SIZE120, + TEST_IN_SIZE124, + TEST_IN_SIZE128, + TEST_IN_SIZE132, + TEST_IN_SIZE136, + TEST_IN_SIZE140, + TEST_IN_SIZE144, + TEST_IN_SIZE148, + TEST_IN_SIZE152, + TEST_IN_SIZE156, + TEST_IN_SIZE160, + TEST_IN_SIZE164, + TEST_IN_SIZE168, + TEST_IN_SIZE172, + TEST_IN_SIZE176, + TEST_IN_SIZE180, + TEST_IN_SIZE184, + TEST_IN_SIZE188, + TEST_IN_SIZE192, + TEST_IN_SIZE196, + TEST_IN_SIZE200, + TEST_IN_SIZE204, + TEST_IN_SIZE208, + TEST_IN_SIZE212, + TEST_IN_SIZE216, + TEST_IN_SIZE220, + TEST_IN_SIZE224, + TEST_IN_SIZE228, + TEST_IN_SIZE232, + TEST_IN_SIZE236, + TEST_IN_SIZE240, + TEST_IN_SIZE244, TEST_IN_FULL_SUPP_TRACE, - /********** - * GLOBAL * - **********/ - TEST_FWD_FULL_SUPP_TRACE, + __TEST_IN_MAX, __TEST_MAX, }; -static int check_ioam_header(int tid, struct ioam6_trace_hdr *ioam6h, - __u32 trace_type, __u16 ioam_ns) +static int check_header(int tid, struct ioam6_trace_hdr *trace, + __u32 trace_type, __u8 trace_size, __u16 ioam_ns) { - if (__be16_to_cpu(ioam6h->namespace_id) != ioam_ns || - __be32_to_cpu(ioam6h->type_be32) != (trace_type << 8)) + if (__be16_to_cpu(trace->namespace_id) != ioam_ns || + __be32_to_cpu(trace->type_be32) != (trace_type << 8)) return 1; switch (tid) { case TEST_OUT_UNDEF_NS: case TEST_IN_UNDEF_NS: - return ioam6h->overflow || - ioam6h->nodelen != 1 || - ioam6h->remlen != 1; + case TEST_IN_DISABLED: + return trace->overflow == 1 || + trace->nodelen != 1 || + trace->remlen != 1; case TEST_OUT_NO_ROOM: case TEST_IN_NO_ROOM: case TEST_IN_OFLAG: - return !ioam6h->overflow || - ioam6h->nodelen != 2 || - ioam6h->remlen != 1; + return trace->overflow == 0 || + trace->nodelen != 2 || + trace->remlen != 1; + + case TEST_OUT_NO_ROOM_OSS: + return trace->overflow == 0 || + trace->nodelen != 0 || + trace->remlen != 1; + + case TEST_IN_NO_ROOM_OSS: + case TEST_OUT_BIT22: + case TEST_IN_BIT22: + return trace->overflow == 1 || + trace->nodelen != 0 || + trace->remlen != 0; case TEST_OUT_BIT0: case TEST_IN_BIT0: @@ -164,9 +293,9 @@ static int check_ioam_header(int tid, struct ioam6_trace_hdr *ioam6h, case TEST_IN_BIT7: case TEST_OUT_BIT11: case TEST_IN_BIT11: - return ioam6h->overflow || - ioam6h->nodelen != 1 || - ioam6h->remlen; + return trace->overflow == 1 || + trace->nodelen != 1 || + trace->remlen != 0; case TEST_OUT_BIT8: case TEST_IN_BIT8: @@ -174,22 +303,145 @@ static int check_ioam_header(int tid, struct ioam6_trace_hdr *ioam6h, case TEST_IN_BIT9: case TEST_OUT_BIT10: case TEST_IN_BIT10: - return ioam6h->overflow || - ioam6h->nodelen != 2 || - ioam6h->remlen; - - case TEST_OUT_BIT22: - case TEST_IN_BIT22: - return ioam6h->overflow || - ioam6h->nodelen || - ioam6h->remlen; + return trace->overflow == 1 || + trace->nodelen != 2 || + trace->remlen != 0; + + case TEST_OUT_SIZE4: + case TEST_OUT_SIZE8: + case TEST_OUT_SIZE12: + case TEST_OUT_SIZE16: + case TEST_OUT_SIZE20: + case TEST_OUT_SIZE24: + case TEST_OUT_SIZE28: + case TEST_OUT_SIZE32: + case TEST_OUT_SIZE36: + case TEST_OUT_SIZE40: + case TEST_OUT_SIZE44: + case TEST_OUT_SIZE48: + case TEST_OUT_SIZE52: + case TEST_OUT_SIZE56: + case TEST_OUT_SIZE60: + case TEST_OUT_SIZE64: + case TEST_OUT_SIZE68: + case TEST_OUT_SIZE72: + case TEST_OUT_SIZE76: + case TEST_OUT_SIZE80: + case TEST_OUT_SIZE84: + case TEST_OUT_SIZE88: + case TEST_OUT_SIZE92: + case TEST_OUT_SIZE96: + case TEST_OUT_SIZE100: + case TEST_OUT_SIZE104: + case TEST_OUT_SIZE108: + case TEST_OUT_SIZE112: + case TEST_OUT_SIZE116: + case TEST_OUT_SIZE120: + case TEST_OUT_SIZE124: + case TEST_OUT_SIZE128: + case TEST_OUT_SIZE132: + case TEST_OUT_SIZE136: + case TEST_OUT_SIZE140: + case TEST_OUT_SIZE144: + case TEST_OUT_SIZE148: + case TEST_OUT_SIZE152: + case TEST_OUT_SIZE156: + case TEST_OUT_SIZE160: + case TEST_OUT_SIZE164: + case TEST_OUT_SIZE168: + case TEST_OUT_SIZE172: + case TEST_OUT_SIZE176: + case TEST_OUT_SIZE180: + case TEST_OUT_SIZE184: + case TEST_OUT_SIZE188: + case TEST_OUT_SIZE192: + case TEST_OUT_SIZE196: + case TEST_OUT_SIZE200: + case TEST_OUT_SIZE204: + case TEST_OUT_SIZE208: + case TEST_OUT_SIZE212: + case TEST_OUT_SIZE216: + case TEST_OUT_SIZE220: + case TEST_OUT_SIZE224: + case TEST_OUT_SIZE228: + case TEST_OUT_SIZE232: + case TEST_OUT_SIZE236: + case TEST_OUT_SIZE240: + case TEST_OUT_SIZE244: + return trace->overflow == 1 || + trace->nodelen != 1 || + trace->remlen != trace_size / 4; + + case TEST_IN_SIZE4: + case TEST_IN_SIZE8: + case TEST_IN_SIZE12: + case TEST_IN_SIZE16: + case TEST_IN_SIZE20: + case TEST_IN_SIZE24: + case TEST_IN_SIZE28: + case TEST_IN_SIZE32: + case TEST_IN_SIZE36: + case TEST_IN_SIZE40: + case TEST_IN_SIZE44: + case TEST_IN_SIZE48: + case TEST_IN_SIZE52: + case TEST_IN_SIZE56: + case TEST_IN_SIZE60: + case TEST_IN_SIZE64: + case TEST_IN_SIZE68: + case TEST_IN_SIZE72: + case TEST_IN_SIZE76: + case TEST_IN_SIZE80: + case TEST_IN_SIZE84: + case TEST_IN_SIZE88: + case TEST_IN_SIZE92: + case TEST_IN_SIZE96: + case TEST_IN_SIZE100: + case TEST_IN_SIZE104: + case TEST_IN_SIZE108: + case TEST_IN_SIZE112: + case TEST_IN_SIZE116: + case TEST_IN_SIZE120: + case TEST_IN_SIZE124: + case TEST_IN_SIZE128: + case TEST_IN_SIZE132: + case TEST_IN_SIZE136: + case TEST_IN_SIZE140: + case TEST_IN_SIZE144: + case TEST_IN_SIZE148: + case TEST_IN_SIZE152: + case TEST_IN_SIZE156: + case TEST_IN_SIZE160: + case TEST_IN_SIZE164: + case TEST_IN_SIZE168: + case TEST_IN_SIZE172: + case TEST_IN_SIZE176: + case TEST_IN_SIZE180: + case TEST_IN_SIZE184: + case TEST_IN_SIZE188: + case TEST_IN_SIZE192: + case TEST_IN_SIZE196: + case TEST_IN_SIZE200: + case TEST_IN_SIZE204: + case TEST_IN_SIZE208: + case TEST_IN_SIZE212: + case TEST_IN_SIZE216: + case TEST_IN_SIZE220: + case TEST_IN_SIZE224: + case TEST_IN_SIZE228: + case TEST_IN_SIZE232: + case TEST_IN_SIZE236: + case TEST_IN_SIZE240: + case TEST_IN_SIZE244: + return trace->overflow == 1 || + trace->nodelen != 1 || + trace->remlen != (trace_size / 4) - trace->nodelen; case TEST_OUT_FULL_SUPP_TRACE: case TEST_IN_FULL_SUPP_TRACE: - case TEST_FWD_FULL_SUPP_TRACE: - return ioam6h->overflow || - ioam6h->nodelen != 15 || - ioam6h->remlen; + return trace->overflow == 1 || + trace->nodelen != 15 || + trace->remlen != 0; default: break; @@ -198,167 +450,137 @@ static int check_ioam_header(int tid, struct ioam6_trace_hdr *ioam6h, return 1; } -static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h, - const struct ioam_config cnf) +static int check_data(struct ioam6_trace_hdr *trace, __u8 trace_size, + const struct ioam_config cnf, bool is_output) { - unsigned int len; + unsigned int len, i; __u8 aligned; __u64 raw64; __u32 raw32; + __u8 *p; - if (ioam6h->type.bit0) { - raw32 = __be32_to_cpu(*((__u32 *)*p)); - if (cnf.hlim != (raw32 >> 24) || cnf.id != (raw32 & 0xffffff)) - return 1; - *p += sizeof(__u32); - } - - if (ioam6h->type.bit1) { - raw32 = __be32_to_cpu(*((__u32 *)*p)); - if (cnf.ingr_id != (raw32 >> 16) || - cnf.egr_id != (raw32 & 0xffff)) - return 1; - *p += sizeof(__u32); - } - - if (ioam6h->type.bit2) - *p += sizeof(__u32); - - if (ioam6h->type.bit3) - *p += sizeof(__u32); - - if (ioam6h->type.bit4) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) - return 1; - *p += sizeof(__u32); - } - - if (ioam6h->type.bit5) { - if (__be32_to_cpu(*((__u32 *)*p)) != cnf.ns_data) - return 1; - *p += sizeof(__u32); - } - - if (ioam6h->type.bit6) - *p += sizeof(__u32); + if (trace->type.bit12 | trace->type.bit13 | trace->type.bit14 | + trace->type.bit15 | trace->type.bit16 | trace->type.bit17 | + trace->type.bit18 | trace->type.bit19 | trace->type.bit20 | + trace->type.bit21 | trace->type.bit23) + return 1; - if (ioam6h->type.bit7) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + for (i = 0; i < trace->remlen * 4; i++) { + if (trace->data[i] != 0) return 1; - *p += sizeof(__u32); } - if (ioam6h->type.bit8) { - raw64 = __be64_to_cpu(*((__u64 *)*p)); - if (cnf.hlim != (raw64 >> 56) || - cnf.wide != (raw64 & 0xffffffffffffff)) - return 1; - *p += sizeof(__u64); - } + if (trace->remlen * 4 == trace_size) + return 0; - if (ioam6h->type.bit9) { - if (__be32_to_cpu(*((__u32 *)*p)) != cnf.ingr_wide) - return 1; - *p += sizeof(__u32); + p = trace->data + trace->remlen * 4; - if (__be32_to_cpu(*((__u32 *)*p)) != cnf.egr_wide) + if (trace->type.bit0) { + raw32 = __be32_to_cpu(*((__u32 *)p)); + if (cnf.hlim != (raw32 >> 24) || cnf.id != (raw32 & 0xffffff)) return 1; - *p += sizeof(__u32); + p += sizeof(__u32); } - if (ioam6h->type.bit10) { - if (__be64_to_cpu(*((__u64 *)*p)) != cnf.ns_wide) + if (trace->type.bit1) { + raw32 = __be32_to_cpu(*((__u32 *)p)); + if (cnf.ingr_id != (raw32 >> 16) || + cnf.egr_id != (raw32 & 0xffff)) return 1; - *p += sizeof(__u64); + p += sizeof(__u32); } - if (ioam6h->type.bit11) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (trace->type.bit2) { + raw32 = __be32_to_cpu(*((__u32 *)p)); + if ((is_output && raw32 != 0xffffffff) || + (!is_output && (raw32 == 0 || raw32 == 0xffffffff))) return 1; - *p += sizeof(__u32); + p += sizeof(__u32); } - if (ioam6h->type.bit12) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (trace->type.bit3) { + raw32 = __be32_to_cpu(*((__u32 *)p)); + if ((is_output && raw32 != 0xffffffff) || + (!is_output && (raw32 == 0 || raw32 == 0xffffffff))) return 1; - *p += sizeof(__u32); + p += sizeof(__u32); } - if (ioam6h->type.bit13) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (trace->type.bit4) { + if (__be32_to_cpu(*((__u32 *)p)) != 0xffffffff) return 1; - *p += sizeof(__u32); + p += sizeof(__u32); } - if (ioam6h->type.bit14) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (trace->type.bit5) { + if (__be32_to_cpu(*((__u32 *)p)) != cnf.ns_data) return 1; - *p += sizeof(__u32); + p += sizeof(__u32); } - if (ioam6h->type.bit15) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (trace->type.bit6) { + if (__be32_to_cpu(*((__u32 *)p)) == 0xffffffff) return 1; - *p += sizeof(__u32); + p += sizeof(__u32); } - if (ioam6h->type.bit16) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (trace->type.bit7) { + if (__be32_to_cpu(*((__u32 *)p)) != 0xffffffff) return 1; - *p += sizeof(__u32); + p += sizeof(__u32); } - if (ioam6h->type.bit17) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (trace->type.bit8) { + raw64 = __be64_to_cpu(*((__u64 *)p)); + if (cnf.hlim != (raw64 >> 56) || + cnf.wide != (raw64 & 0xffffffffffffff)) return 1; - *p += sizeof(__u32); + p += sizeof(__u64); } - if (ioam6h->type.bit18) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (trace->type.bit9) { + if (__be32_to_cpu(*((__u32 *)p)) != cnf.ingr_wide) return 1; - *p += sizeof(__u32); - } + p += sizeof(__u32); - if (ioam6h->type.bit19) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (__be32_to_cpu(*((__u32 *)p)) != cnf.egr_wide) return 1; - *p += sizeof(__u32); + p += sizeof(__u32); } - if (ioam6h->type.bit20) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (trace->type.bit10) { + if (__be64_to_cpu(*((__u64 *)p)) != cnf.ns_wide) return 1; - *p += sizeof(__u32); + p += sizeof(__u64); } - if (ioam6h->type.bit21) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + if (trace->type.bit11) { + if (__be32_to_cpu(*((__u32 *)p)) != 0xffffffff) return 1; - *p += sizeof(__u32); + p += sizeof(__u32); } - if (ioam6h->type.bit22) { + if (trace->type.bit22) { len = cnf.sc_data ? strlen(cnf.sc_data) : 0; aligned = cnf.sc_data ? __ALIGN_KERNEL(len, 4) : 0; - raw32 = __be32_to_cpu(*((__u32 *)*p)); + raw32 = __be32_to_cpu(*((__u32 *)p)); if (aligned != (raw32 >> 24) * 4 || cnf.sc_id != (raw32 & 0xffffff)) return 1; - *p += sizeof(__u32); + p += sizeof(__u32); if (cnf.sc_data) { - if (strncmp((char *)*p, cnf.sc_data, len)) + if (strncmp((char *)p, cnf.sc_data, len)) return 1; - *p += len; + p += len; aligned -= len; while (aligned--) { - if (**p != '\0') + if (*p != '\0') return 1; - *p += sizeof(__u8); + p += sizeof(__u8); } } } @@ -366,151 +588,351 @@ static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h, return 0; } -static int check_ioam_header_and_data(int tid, struct ioam6_trace_hdr *ioam6h, - __u32 trace_type, __u16 ioam_ns) +static int check_ioam_trace(int tid, struct ioam6_trace_hdr *trace, + __u32 trace_type, __u8 trace_size, __u16 ioam_ns) { - __u8 *p; - - if (check_ioam_header(tid, ioam6h, trace_type, ioam_ns)) + if (check_header(tid, trace, trace_type, trace_size, ioam_ns)) return 1; - p = ioam6h->data + ioam6h->remlen * 4; - - switch (tid) { - case TEST_OUT_BIT0: - case TEST_OUT_BIT1: - case TEST_OUT_BIT2: - case TEST_OUT_BIT3: - case TEST_OUT_BIT4: - case TEST_OUT_BIT5: - case TEST_OUT_BIT6: - case TEST_OUT_BIT7: - case TEST_OUT_BIT8: - case TEST_OUT_BIT9: - case TEST_OUT_BIT10: - case TEST_OUT_BIT11: - case TEST_OUT_BIT22: - case TEST_OUT_FULL_SUPP_TRACE: - return check_ioam6_data(&p, ioam6h, node1); - - case TEST_IN_BIT0: - case TEST_IN_BIT1: - case TEST_IN_BIT2: - case TEST_IN_BIT3: - case TEST_IN_BIT4: - case TEST_IN_BIT5: - case TEST_IN_BIT6: - case TEST_IN_BIT7: - case TEST_IN_BIT8: - case TEST_IN_BIT9: - case TEST_IN_BIT10: - case TEST_IN_BIT11: - case TEST_IN_BIT22: - case TEST_IN_FULL_SUPP_TRACE: - { - __u32 tmp32 = node2.egr_wide; - __u16 tmp16 = node2.egr_id; - int res; - - node2.egr_id = 0xffff; - node2.egr_wide = 0xffffffff; + if (tid > __TEST_OUT_MIN && tid < __TEST_OUT_MAX) + return check_data(trace, trace_size, node1, true); - res = check_ioam6_data(&p, ioam6h, node2); - - node2.egr_id = tmp16; - node2.egr_wide = tmp32; - - return res; - } - - case TEST_FWD_FULL_SUPP_TRACE: - if (check_ioam6_data(&p, ioam6h, node3)) - return 1; - if (check_ioam6_data(&p, ioam6h, node2)) - return 1; - return check_ioam6_data(&p, ioam6h, node1); - - default: - break; - } + if (tid > __TEST_IN_MIN && tid < __TEST_IN_MAX) + return check_data(trace, trace_size, node2, false); return 1; } static int str2id(const char *tname) { - if (!strcmp("out_undef_ns", tname)) + if (!strcmp("output_undef_ns", tname)) return TEST_OUT_UNDEF_NS; - if (!strcmp("out_no_room", tname)) + if (!strcmp("output_no_room", tname)) return TEST_OUT_NO_ROOM; - if (!strcmp("out_bit0", tname)) + if (!strcmp("output_no_room_oss", tname)) + return TEST_OUT_NO_ROOM_OSS; + if (!strcmp("output_bit0", tname)) return TEST_OUT_BIT0; - if (!strcmp("out_bit1", tname)) + if (!strcmp("output_bit1", tname)) return TEST_OUT_BIT1; - if (!strcmp("out_bit2", tname)) + if (!strcmp("output_bit2", tname)) return TEST_OUT_BIT2; - if (!strcmp("out_bit3", tname)) + if (!strcmp("output_bit3", tname)) return TEST_OUT_BIT3; - if (!strcmp("out_bit4", tname)) + if (!strcmp("output_bit4", tname)) return TEST_OUT_BIT4; - if (!strcmp("out_bit5", tname)) + if (!strcmp("output_bit5", tname)) return TEST_OUT_BIT5; - if (!strcmp("out_bit6", tname)) + if (!strcmp("output_bit6", tname)) return TEST_OUT_BIT6; - if (!strcmp("out_bit7", tname)) + if (!strcmp("output_bit7", tname)) return TEST_OUT_BIT7; - if (!strcmp("out_bit8", tname)) + if (!strcmp("output_bit8", tname)) return TEST_OUT_BIT8; - if (!strcmp("out_bit9", tname)) + if (!strcmp("output_bit9", tname)) return TEST_OUT_BIT9; - if (!strcmp("out_bit10", tname)) + if (!strcmp("output_bit10", tname)) return TEST_OUT_BIT10; - if (!strcmp("out_bit11", tname)) + if (!strcmp("output_bit11", tname)) return TEST_OUT_BIT11; - if (!strcmp("out_bit22", tname)) + if (!strcmp("output_bit22", tname)) return TEST_OUT_BIT22; - if (!strcmp("out_full_supp_trace", tname)) + if (!strcmp("output_size4", tname)) + return TEST_OUT_SIZE4; + if (!strcmp("output_size8", tname)) + return TEST_OUT_SIZE8; + if (!strcmp("output_size12", tname)) + return TEST_OUT_SIZE12; + if (!strcmp("output_size16", tname)) + return TEST_OUT_SIZE16; + if (!strcmp("output_size20", tname)) + return TEST_OUT_SIZE20; + if (!strcmp("output_size24", tname)) + return TEST_OUT_SIZE24; + if (!strcmp("output_size28", tname)) + return TEST_OUT_SIZE28; + if (!strcmp("output_size32", tname)) + return TEST_OUT_SIZE32; + if (!strcmp("output_size36", tname)) + return TEST_OUT_SIZE36; + if (!strcmp("output_size40", tname)) + return TEST_OUT_SIZE40; + if (!strcmp("output_size44", tname)) + return TEST_OUT_SIZE44; + if (!strcmp("output_size48", tname)) + return TEST_OUT_SIZE48; + if (!strcmp("output_size52", tname)) + return TEST_OUT_SIZE52; + if (!strcmp("output_size56", tname)) + return TEST_OUT_SIZE56; + if (!strcmp("output_size60", tname)) + return TEST_OUT_SIZE60; + if (!strcmp("output_size64", tname)) + return TEST_OUT_SIZE64; + if (!strcmp("output_size68", tname)) + return TEST_OUT_SIZE68; + if (!strcmp("output_size72", tname)) + return TEST_OUT_SIZE72; + if (!strcmp("output_size76", tname)) + return TEST_OUT_SIZE76; + if (!strcmp("output_size80", tname)) + return TEST_OUT_SIZE80; + if (!strcmp("output_size84", tname)) + return TEST_OUT_SIZE84; + if (!strcmp("output_size88", tname)) + return TEST_OUT_SIZE88; + if (!strcmp("output_size92", tname)) + return TEST_OUT_SIZE92; + if (!strcmp("output_size96", tname)) + return TEST_OUT_SIZE96; + if (!strcmp("output_size100", tname)) + return TEST_OUT_SIZE100; + if (!strcmp("output_size104", tname)) + return TEST_OUT_SIZE104; + if (!strcmp("output_size108", tname)) + return TEST_OUT_SIZE108; + if (!strcmp("output_size112", tname)) + return TEST_OUT_SIZE112; + if (!strcmp("output_size116", tname)) + return TEST_OUT_SIZE116; + if (!strcmp("output_size120", tname)) + return TEST_OUT_SIZE120; + if (!strcmp("output_size124", tname)) + return TEST_OUT_SIZE124; + if (!strcmp("output_size128", tname)) + return TEST_OUT_SIZE128; + if (!strcmp("output_size132", tname)) + return TEST_OUT_SIZE132; + if (!strcmp("output_size136", tname)) + return TEST_OUT_SIZE136; + if (!strcmp("output_size140", tname)) + return TEST_OUT_SIZE140; + if (!strcmp("output_size144", tname)) + return TEST_OUT_SIZE144; + if (!strcmp("output_size148", tname)) + return TEST_OUT_SIZE148; + if (!strcmp("output_size152", tname)) + return TEST_OUT_SIZE152; + if (!strcmp("output_size156", tname)) + return TEST_OUT_SIZE156; + if (!strcmp("output_size160", tname)) + return TEST_OUT_SIZE160; + if (!strcmp("output_size164", tname)) + return TEST_OUT_SIZE164; + if (!strcmp("output_size168", tname)) + return TEST_OUT_SIZE168; + if (!strcmp("output_size172", tname)) + return TEST_OUT_SIZE172; + if (!strcmp("output_size176", tname)) + return TEST_OUT_SIZE176; + if (!strcmp("output_size180", tname)) + return TEST_OUT_SIZE180; + if (!strcmp("output_size184", tname)) + return TEST_OUT_SIZE184; + if (!strcmp("output_size188", tname)) + return TEST_OUT_SIZE188; + if (!strcmp("output_size192", tname)) + return TEST_OUT_SIZE192; + if (!strcmp("output_size196", tname)) + return TEST_OUT_SIZE196; + if (!strcmp("output_size200", tname)) + return TEST_OUT_SIZE200; + if (!strcmp("output_size204", tname)) + return TEST_OUT_SIZE204; + if (!strcmp("output_size208", tname)) + return TEST_OUT_SIZE208; + if (!strcmp("output_size212", tname)) + return TEST_OUT_SIZE212; + if (!strcmp("output_size216", tname)) + return TEST_OUT_SIZE216; + if (!strcmp("output_size220", tname)) + return TEST_OUT_SIZE220; + if (!strcmp("output_size224", tname)) + return TEST_OUT_SIZE224; + if (!strcmp("output_size228", tname)) + return TEST_OUT_SIZE228; + if (!strcmp("output_size232", tname)) + return TEST_OUT_SIZE232; + if (!strcmp("output_size236", tname)) + return TEST_OUT_SIZE236; + if (!strcmp("output_size240", tname)) + return TEST_OUT_SIZE240; + if (!strcmp("output_size244", tname)) + return TEST_OUT_SIZE244; + if (!strcmp("output_full_supp_trace", tname)) return TEST_OUT_FULL_SUPP_TRACE; - if (!strcmp("in_undef_ns", tname)) + if (!strcmp("input_undef_ns", tname)) return TEST_IN_UNDEF_NS; - if (!strcmp("in_no_room", tname)) + if (!strcmp("input_no_room", tname)) return TEST_IN_NO_ROOM; - if (!strcmp("in_oflag", tname)) + if (!strcmp("input_no_room_oss", tname)) + return TEST_IN_NO_ROOM_OSS; + if (!strcmp("input_disabled", tname)) + return TEST_IN_DISABLED; + if (!strcmp("input_oflag", tname)) return TEST_IN_OFLAG; - if (!strcmp("in_bit0", tname)) + if (!strcmp("input_bit0", tname)) return TEST_IN_BIT0; - if (!strcmp("in_bit1", tname)) + if (!strcmp("input_bit1", tname)) return TEST_IN_BIT1; - if (!strcmp("in_bit2", tname)) + if (!strcmp("input_bit2", tname)) return TEST_IN_BIT2; - if (!strcmp("in_bit3", tname)) + if (!strcmp("input_bit3", tname)) return TEST_IN_BIT3; - if (!strcmp("in_bit4", tname)) + if (!strcmp("input_bit4", tname)) return TEST_IN_BIT4; - if (!strcmp("in_bit5", tname)) + if (!strcmp("input_bit5", tname)) return TEST_IN_BIT5; - if (!strcmp("in_bit6", tname)) + if (!strcmp("input_bit6", tname)) return TEST_IN_BIT6; - if (!strcmp("in_bit7", tname)) + if (!strcmp("input_bit7", tname)) return TEST_IN_BIT7; - if (!strcmp("in_bit8", tname)) + if (!strcmp("input_bit8", tname)) return TEST_IN_BIT8; - if (!strcmp("in_bit9", tname)) + if (!strcmp("input_bit9", tname)) return TEST_IN_BIT9; - if (!strcmp("in_bit10", tname)) + if (!strcmp("input_bit10", tname)) return TEST_IN_BIT10; - if (!strcmp("in_bit11", tname)) + if (!strcmp("input_bit11", tname)) return TEST_IN_BIT11; - if (!strcmp("in_bit22", tname)) + if (!strcmp("input_bit22", tname)) return TEST_IN_BIT22; - if (!strcmp("in_full_supp_trace", tname)) + if (!strcmp("input_size4", tname)) + return TEST_IN_SIZE4; + if (!strcmp("input_size8", tname)) + return TEST_IN_SIZE8; + if (!strcmp("input_size12", tname)) + return TEST_IN_SIZE12; + if (!strcmp("input_size16", tname)) + return TEST_IN_SIZE16; + if (!strcmp("input_size20", tname)) + return TEST_IN_SIZE20; + if (!strcmp("input_size24", tname)) + return TEST_IN_SIZE24; + if (!strcmp("input_size28", tname)) + return TEST_IN_SIZE28; + if (!strcmp("input_size32", tname)) + return TEST_IN_SIZE32; + if (!strcmp("input_size36", tname)) + return TEST_IN_SIZE36; + if (!strcmp("input_size40", tname)) + return TEST_IN_SIZE40; + if (!strcmp("input_size44", tname)) + return TEST_IN_SIZE44; + if (!strcmp("input_size48", tname)) + return TEST_IN_SIZE48; + if (!strcmp("input_size52", tname)) + return TEST_IN_SIZE52; + if (!strcmp("input_size56", tname)) + return TEST_IN_SIZE56; + if (!strcmp("input_size60", tname)) + return TEST_IN_SIZE60; + if (!strcmp("input_size64", tname)) + return TEST_IN_SIZE64; + if (!strcmp("input_size68", tname)) + return TEST_IN_SIZE68; + if (!strcmp("input_size72", tname)) + return TEST_IN_SIZE72; + if (!strcmp("input_size76", tname)) + return TEST_IN_SIZE76; + if (!strcmp("input_size80", tname)) + return TEST_IN_SIZE80; + if (!strcmp("input_size84", tname)) + return TEST_IN_SIZE84; + if (!strcmp("input_size88", tname)) + return TEST_IN_SIZE88; + if (!strcmp("input_size92", tname)) + return TEST_IN_SIZE92; + if (!strcmp("input_size96", tname)) + return TEST_IN_SIZE96; + if (!strcmp("input_size100", tname)) + return TEST_IN_SIZE100; + if (!strcmp("input_size104", tname)) + return TEST_IN_SIZE104; + if (!strcmp("input_size108", tname)) + return TEST_IN_SIZE108; + if (!strcmp("input_size112", tname)) + return TEST_IN_SIZE112; + if (!strcmp("input_size116", tname)) + return TEST_IN_SIZE116; + if (!strcmp("input_size120", tname)) + return TEST_IN_SIZE120; + if (!strcmp("input_size124", tname)) + return TEST_IN_SIZE124; + if (!strcmp("input_size128", tname)) + return TEST_IN_SIZE128; + if (!strcmp("input_size132", tname)) + return TEST_IN_SIZE132; + if (!strcmp("input_size136", tname)) + return TEST_IN_SIZE136; + if (!strcmp("input_size140", tname)) + return TEST_IN_SIZE140; + if (!strcmp("input_size144", tname)) + return TEST_IN_SIZE144; + if (!strcmp("input_size148", tname)) + return TEST_IN_SIZE148; + if (!strcmp("input_size152", tname)) + return TEST_IN_SIZE152; + if (!strcmp("input_size156", tname)) + return TEST_IN_SIZE156; + if (!strcmp("input_size160", tname)) + return TEST_IN_SIZE160; + if (!strcmp("input_size164", tname)) + return TEST_IN_SIZE164; + if (!strcmp("input_size168", tname)) + return TEST_IN_SIZE168; + if (!strcmp("input_size172", tname)) + return TEST_IN_SIZE172; + if (!strcmp("input_size176", tname)) + return TEST_IN_SIZE176; + if (!strcmp("input_size180", tname)) + return TEST_IN_SIZE180; + if (!strcmp("input_size184", tname)) + return TEST_IN_SIZE184; + if (!strcmp("input_size188", tname)) + return TEST_IN_SIZE188; + if (!strcmp("input_size192", tname)) + return TEST_IN_SIZE192; + if (!strcmp("input_size196", tname)) + return TEST_IN_SIZE196; + if (!strcmp("input_size200", tname)) + return TEST_IN_SIZE200; + if (!strcmp("input_size204", tname)) + return TEST_IN_SIZE204; + if (!strcmp("input_size208", tname)) + return TEST_IN_SIZE208; + if (!strcmp("input_size212", tname)) + return TEST_IN_SIZE212; + if (!strcmp("input_size216", tname)) + return TEST_IN_SIZE216; + if (!strcmp("input_size220", tname)) + return TEST_IN_SIZE220; + if (!strcmp("input_size224", tname)) + return TEST_IN_SIZE224; + if (!strcmp("input_size228", tname)) + return TEST_IN_SIZE228; + if (!strcmp("input_size232", tname)) + return TEST_IN_SIZE232; + if (!strcmp("input_size236", tname)) + return TEST_IN_SIZE236; + if (!strcmp("input_size240", tname)) + return TEST_IN_SIZE240; + if (!strcmp("input_size244", tname)) + return TEST_IN_SIZE244; + if (!strcmp("input_full_supp_trace", tname)) return TEST_IN_FULL_SUPP_TRACE; - if (!strcmp("fwd_full_supp_trace", tname)) - return TEST_FWD_FULL_SUPP_TRACE; return -1; } +static int ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2) +{ + return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) | + (a1->s6_addr32[1] ^ a2->s6_addr32[1]) | + (a1->s6_addr32[2] ^ a2->s6_addr32[2]) | + (a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0; +} + static int get_u32(__u32 *val, const char *arg, int base) { unsigned long res; @@ -555,119 +977,124 @@ static int get_u16(__u16 *val, const char *arg, int base) return 0; } -static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { - [TEST_OUT_UNDEF_NS] = check_ioam_header, - [TEST_OUT_NO_ROOM] = check_ioam_header, - [TEST_OUT_BIT0] = check_ioam_header_and_data, - [TEST_OUT_BIT1] = check_ioam_header_and_data, - [TEST_OUT_BIT2] = check_ioam_header_and_data, - [TEST_OUT_BIT3] = check_ioam_header_and_data, - [TEST_OUT_BIT4] = check_ioam_header_and_data, - [TEST_OUT_BIT5] = check_ioam_header_and_data, - [TEST_OUT_BIT6] = check_ioam_header_and_data, - [TEST_OUT_BIT7] = check_ioam_header_and_data, - [TEST_OUT_BIT8] = check_ioam_header_and_data, - [TEST_OUT_BIT9] = check_ioam_header_and_data, - [TEST_OUT_BIT10] = check_ioam_header_and_data, - [TEST_OUT_BIT11] = check_ioam_header_and_data, - [TEST_OUT_BIT22] = check_ioam_header_and_data, - [TEST_OUT_FULL_SUPP_TRACE] = check_ioam_header_and_data, - [TEST_IN_UNDEF_NS] = check_ioam_header, - [TEST_IN_NO_ROOM] = check_ioam_header, - [TEST_IN_OFLAG] = check_ioam_header, - [TEST_IN_BIT0] = check_ioam_header_and_data, - [TEST_IN_BIT1] = check_ioam_header_and_data, - [TEST_IN_BIT2] = check_ioam_header_and_data, - [TEST_IN_BIT3] = check_ioam_header_and_data, - [TEST_IN_BIT4] = check_ioam_header_and_data, - [TEST_IN_BIT5] = check_ioam_header_and_data, - [TEST_IN_BIT6] = check_ioam_header_and_data, - [TEST_IN_BIT7] = check_ioam_header_and_data, - [TEST_IN_BIT8] = check_ioam_header_and_data, - [TEST_IN_BIT9] = check_ioam_header_and_data, - [TEST_IN_BIT10] = check_ioam_header_and_data, - [TEST_IN_BIT11] = check_ioam_header_and_data, - [TEST_IN_BIT22] = check_ioam_header_and_data, - [TEST_IN_FULL_SUPP_TRACE] = check_ioam_header_and_data, - [TEST_FWD_FULL_SUPP_TRACE] = check_ioam_header_and_data, -}; +static int get_u8(__u8 *val, const char *arg, int base) +{ + unsigned long res; + char *ptr; + + if (!arg || !*arg) + return -1; + res = strtoul(arg, &ptr, base); + + if (!ptr || ptr == arg || *ptr) + return -1; + + if (res == ULONG_MAX && errno == ERANGE) + return -1; + + if (res > 0xFFUL) + return -1; + + *val = res; + return 0; +} int main(int argc, char **argv) { - int fd, size, hoplen, tid, ret = 1, on = 1; - struct ioam6_hdr *opt; - struct cmsghdr *cmsg; - struct msghdr msg; - struct iovec iov; - __u8 buffer[512]; + __u8 buffer[512], *ptr, nexthdr, tr_size; + struct ioam6_trace_hdr *trace; + unsigned int hoplen, ret = 1; + struct ipv6_hopopt_hdr *hbh; + int fd, size, testname_id; + struct in6_addr src, dst; + struct ioam6_hdr *ioam6; + struct timeval timeout; + struct ipv6hdr *ipv6; __u32 tr_type; __u16 ioam_ns; - __u8 *ptr; - if (argc != 5) + if (argc != 9) goto out; - tid = str2id(argv[1]); - if (tid < 0 || !func[tid]) - goto out; + testname_id = str2id(argv[2]); - if (get_u32(&tr_type, argv[2], 16) || - get_u16(&ioam_ns, argv[3], 0)) + if (testname_id < 0 || + inet_pton(AF_INET6, argv[3], &src) != 1 || + inet_pton(AF_INET6, argv[4], &dst) != 1 || + get_u32(&tr_type, argv[5], 16) || + get_u8(&tr_size, argv[6], 0) || + get_u16(&ioam_ns, argv[7], 0)) goto out; - fd = socket(PF_INET6, SOCK_RAW, - !strcmp(argv[4], "encap") ? IPPROTO_IPV6 : IPPROTO_ICMPV6); + nexthdr = (!strcmp(argv[8], "encap") ? IPPROTO_IPV6 : IPPROTO_ICMPV6); + + hoplen = sizeof(*hbh); + hoplen += 2; // 2-byte padding for alignment + hoplen += sizeof(*ioam6); // IOAM option header + hoplen += sizeof(*trace); // IOAM trace header + hoplen += tr_size; // IOAM trace size + hoplen += (tr_size % 8); // optional padding + + fd = socket(AF_PACKET, SOCK_DGRAM, __cpu_to_be16(ETH_P_IPV6)); if (fd < 0) goto out; - setsockopt(fd, IPPROTO_IPV6, IPV6_RECVHOPOPTS, &on, sizeof(on)); + if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE, + argv[1], strlen(argv[1]))) + goto close; - iov.iov_len = 1; - iov.iov_base = malloc(CMSG_SPACE(sizeof(buffer))); - if (!iov.iov_base) + timeout.tv_sec = 1; + timeout.tv_usec = 0; + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, + (const char *)&timeout, sizeof(timeout))) goto close; recv: - memset(&msg, 0, sizeof(msg)); - msg.msg_iov = &iov; - msg.msg_iovlen = 1; - msg.msg_control = buffer; - msg.msg_controllen = CMSG_SPACE(sizeof(buffer)); - - size = recvmsg(fd, &msg, 0); + size = recv(fd, buffer, sizeof(buffer), 0); if (size <= 0) goto close; - for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) { - if (cmsg->cmsg_level != IPPROTO_IPV6 || - cmsg->cmsg_type != IPV6_HOPOPTS || - cmsg->cmsg_len < sizeof(struct ipv6_hopopt_hdr)) - continue; + ipv6 = (struct ipv6hdr *)buffer; + + /* Skip packets that do not have the expected src/dst address or that + * do not have a Hop-by-hop. + */ + if (!ipv6_addr_equal(&ipv6->saddr, &src) || + !ipv6_addr_equal(&ipv6->daddr, &dst) || + ipv6->nexthdr != IPPROTO_HOPOPTS) + goto recv; + + /* Check Hbh's Next Header and Size. */ + hbh = (struct ipv6_hopopt_hdr *)(buffer + sizeof(*ipv6)); + if (hbh->nexthdr != nexthdr || hbh->hdrlen != (hoplen >> 3) - 1) + goto close; - ptr = (__u8 *)CMSG_DATA(cmsg); + /* Check we have a 2-byte padding for alignment. */ + ptr = (__u8 *)hbh + sizeof(*hbh); + if (ptr[0] != IPV6_TLV_PADN && ptr[1] != 0) + goto close; - hoplen = (ptr[1] + 1) << 3; - ptr += sizeof(struct ipv6_hopopt_hdr); + /* Check we now have the IOAM option. */ + ptr += 2; + if (ptr[0] != IPV6_TLV_IOAM) + goto close; - while (hoplen > 0) { - opt = (struct ioam6_hdr *)ptr; + /* Check its size and the IOAM option type. */ + ioam6 = (struct ioam6_hdr *)ptr; + if (ioam6->opt_len != sizeof(*ioam6) - 2 + sizeof(*trace) + tr_size || + ioam6->type != IOAM6_TYPE_PREALLOC) + goto close; - if (opt->opt_type == IPV6_TLV_IOAM && - opt->type == IOAM6_TYPE_PREALLOC) { - ptr += sizeof(*opt); - ret = func[tid](tid, - (struct ioam6_trace_hdr *)ptr, - tr_type, ioam_ns); - goto close; - } + trace = (struct ioam6_trace_hdr *)(ptr + sizeof(*ioam6)); - ptr += opt->opt_len + 2; - hoplen -= opt->opt_len + 2; - } - } + /* Check the trailing 4-byte padding (potentially). */ + ptr = (__u8 *)trace + sizeof(*trace) + tr_size; + if (tr_size % 8 && ptr[0] != IPV6_TLV_PADN && ptr[1] != 2 && + ptr[2] != 0 && ptr[3] != 0) + goto close; - goto recv; + /* Check the IOAM header and data. */ + ret = check_ioam_trace(testname_id, trace, tr_type, tr_size, ioam_ns); close: - free(iov.iov_base); close(fd); out: return ret; diff --git a/tools/testing/selftests/net/lib/csum.c b/tools/testing/selftests/net/lib/csum.c index e0a34e5e8dd5..27437590eeb5 100644 --- a/tools/testing/selftests/net/lib/csum.c +++ b/tools/testing/selftests/net/lib/csum.c @@ -675,22 +675,20 @@ static int recv_verify_packet_ipv6(void *nh, int len) { struct ipv6hdr *ip6h = nh; uint16_t proto = cfg_encap ? IPPROTO_UDP : cfg_proto; - uint16_t ip_len; + uint16_t payload_len; if (len < sizeof(*ip6h) || ip6h->nexthdr != proto) return -1; - ip_len = ntohs(ip6h->payload_len); - if (ip_len > len - sizeof(*ip6h)) + payload_len = ntohs(ip6h->payload_len); + if (payload_len > len - sizeof(*ip6h)) return -1; - len = ip_len; iph_addr_p = &ip6h->saddr; - if (proto == IPPROTO_TCP) - return recv_verify_packet_tcp(ip6h + 1, len); + return recv_verify_packet_tcp(ip6h + 1, payload_len); else - return recv_verify_packet_udp(ip6h + 1, len); + return recv_verify_packet_udp(ip6h + 1, payload_len); } /* return whether auxdata includes TP_STATUS_CSUM_VALID */ diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index b6d498d125fe..54d8f5eba810 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -6,3 +6,4 @@ from .netns import NetNS from .nsim import * from .utils import * from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily +from .ynl import NetshaperFamily diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index 1ace58370c06..a0d689d58c57 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -47,3 +47,8 @@ class NetdevFamily(YnlFamily): def __init__(self): super().__init__((SPEC_PATH / Path('netdev.yaml')).as_posix(), schema='') + +class NetshaperFamily(YnlFamily): + def __init__(self): + super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), + schema='') diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 4f31e92ebd96..84c524357075 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -48,6 +48,7 @@ #include <string.h> #include <sys/mman.h> #include <sys/socket.h> +#include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> @@ -59,6 +60,33 @@ static uint32_t cfg_max_num_members; +static void loopback_set_up_down(int state_up) +{ + struct ifreq ifreq = {}; + int fd, err; + + fd = socket(AF_PACKET, SOCK_RAW, 0); + if (fd < 0) { + perror("socket loopback"); + exit(1); + } + strcpy(ifreq.ifr_name, "lo"); + err = ioctl(fd, SIOCGIFFLAGS, &ifreq); + if (err) { + perror("SIOCGIFFLAGS"); + exit(1); + } + if (state_up != !!(ifreq.ifr_flags & IFF_UP)) { + ifreq.ifr_flags ^= IFF_UP; + err = ioctl(fd, SIOCSIFFLAGS, &ifreq); + if (err) { + perror("SIOCSIFFLAGS"); + exit(1); + } + } + close(fd); +} + /* Open a socket in a given fanout mode. * @return -1 if mode is bad, a valid socket otherwise */ static int sock_fanout_open(uint16_t typeflags, uint16_t group_id) @@ -251,6 +279,41 @@ static int sock_fanout_read(int fds[], char *rings[], const int expect[]) return 0; } +/* Test that creating/joining a fanout group fails for unbound socket without + * a specified protocol + */ +static void test_unbound_fanout(void) +{ + int val, fd0, fd1, err; + + fprintf(stderr, "test: unbound fanout\n"); + fd0 = socket(PF_PACKET, SOCK_RAW, 0); + if (fd0 < 0) { + perror("socket packet"); + exit(1); + } + /* Try to create a new fanout group. Should fail. */ + val = (PACKET_FANOUT_HASH << 16) | 1; + err = setsockopt(fd0, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val)); + if (!err) { + fprintf(stderr, "ERROR: unbound socket fanout create\n"); + exit(1); + } + fd1 = sock_fanout_open(PACKET_FANOUT_HASH, 1); + if (fd1 == -1) { + fprintf(stderr, "ERROR: failed to open HASH socket\n"); + exit(1); + } + /* Try to join an existing fanout group. Should fail. */ + err = setsockopt(fd0, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val)); + if (!err) { + fprintf(stderr, "ERROR: unbound socket fanout join\n"); + exit(1); + } + close(fd0); + close(fd1); +} + /* Test illegal mode + flag combination */ static void test_control_single(void) { @@ -264,17 +327,22 @@ static void test_control_single(void) } /* Test illegal group with different modes or flags */ -static void test_control_group(void) +static void test_control_group(int toggle) { int fds[2]; - fprintf(stderr, "test: control multiple sockets\n"); + if (toggle) + fprintf(stderr, "test: control multiple sockets with link down toggle\n"); + else + fprintf(stderr, "test: control multiple sockets\n"); fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 0); if (fds[0] == -1) { fprintf(stderr, "ERROR: failed to open HASH socket\n"); exit(1); } + if (toggle) + loopback_set_up_down(0); if (sock_fanout_open(PACKET_FANOUT_HASH | PACKET_FANOUT_FLAG_DEFRAG, 0) != -1) { fprintf(stderr, "ERROR: joined group with wrong flag defrag\n"); @@ -294,6 +362,8 @@ static void test_control_group(void) fprintf(stderr, "ERROR: failed to join group\n"); exit(1); } + if (toggle) + loopback_set_up_down(1); if (close(fds[1]) || close(fds[0])) { fprintf(stderr, "ERROR: closing sockets\n"); exit(1); @@ -488,8 +558,10 @@ int main(int argc, char **argv) const int expect_uniqueid[2][2] = { { 20, 20}, { 20, 20 } }; int port_off = 2, tries = 20, ret; + test_unbound_fanout(); test_control_single(); - test_control_group(); + test_control_group(0); + test_control_group(1); test_control_group_max_num_members(); test_unique_fanout_group_ids(); diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index bdf6f10d0558..87dce3efe31e 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -809,10 +809,10 @@ kci_test_ipsec_offload() # does driver have correct offload info run_cmd diff $sysfsf - << EOF SA count=2 tx=3 -sa[0] tx ipaddr=0x00000000 00000000 00000000 00000000 +sa[0] tx ipaddr=$dstip sa[0] spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1 sa[0] key=0x34333231 38373635 32313039 36353433 -sa[1] rx ipaddr=0x00000000 00000000 00000000 037ba8c0 +sa[1] rx ipaddr=$srcip sa[1] spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1 sa[1] key=0x34333231 38373635 32313039 36353433 EOF diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h index db44e77428dd..5db2f65cddc4 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h +++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h @@ -46,6 +46,7 @@ static inline char *test_snprintf(const char *fmt, va_list vargs) va_copy(tmp, vargs); n = vsnprintf(ret, size, fmt, tmp); + va_end(tmp); if (n < 0) return NULL; diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index d626f22f9550..dae91eb97d69 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -77,6 +77,8 @@ static bool cfg_epollet; static bool cfg_do_listen; static uint16_t dest_port = 9000; static bool cfg_print_nsec; +static uint32_t ts_opt_id; +static bool cfg_use_cmsg_opt_id; static struct sockaddr_in daddr; static struct sockaddr_in6 daddr6; @@ -136,12 +138,13 @@ static void validate_key(int tskey, int tstype) /* compare key for each subsequent request * must only test for one type, the first one requested */ - if (saved_tskey == -1) + if (saved_tskey == -1 || cfg_use_cmsg_opt_id) saved_tskey_type = tstype; else if (saved_tskey_type != tstype) return; stepsize = cfg_proto == SOCK_STREAM ? cfg_payload_len : 1; + stepsize = cfg_use_cmsg_opt_id ? 0 : stepsize; if (tskey != saved_tskey + stepsize) { fprintf(stderr, "ERROR: key %d, expected %d\n", tskey, saved_tskey + stepsize); @@ -484,7 +487,7 @@ static void fill_header_udp(void *p, bool is_ipv4) static void do_test(int family, unsigned int report_opt) { - char control[CMSG_SPACE(sizeof(uint32_t))]; + char control[2 * CMSG_SPACE(sizeof(uint32_t))]; struct sockaddr_ll laddr; unsigned int sock_opt; struct cmsghdr *cmsg; @@ -624,18 +627,32 @@ static void do_test(int family, unsigned int report_opt) msg.msg_iov = &iov; msg.msg_iovlen = 1; - if (cfg_use_cmsg) { + if (cfg_use_cmsg || cfg_use_cmsg_opt_id) { memset(control, 0, sizeof(control)); msg.msg_control = control; - msg.msg_controllen = sizeof(control); + msg.msg_controllen = cfg_use_cmsg * CMSG_SPACE(sizeof(uint32_t)); + msg.msg_controllen += cfg_use_cmsg_opt_id * CMSG_SPACE(sizeof(uint32_t)); - cmsg = CMSG_FIRSTHDR(&msg); - cmsg->cmsg_level = SOL_SOCKET; - cmsg->cmsg_type = SO_TIMESTAMPING; - cmsg->cmsg_len = CMSG_LEN(sizeof(uint32_t)); + cmsg = NULL; + if (cfg_use_cmsg) { + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SO_TIMESTAMPING; + cmsg->cmsg_len = CMSG_LEN(sizeof(uint32_t)); + + *((uint32_t *)CMSG_DATA(cmsg)) = report_opt; + } + if (cfg_use_cmsg_opt_id) { + cmsg = cmsg ? CMSG_NXTHDR(&msg, cmsg) : CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_TS_OPT_ID; + cmsg->cmsg_len = CMSG_LEN(sizeof(uint32_t)); + + *((uint32_t *)CMSG_DATA(cmsg)) = ts_opt_id; + saved_tskey = ts_opt_id; + } - *((uint32_t *) CMSG_DATA(cmsg)) = report_opt; } val = sendmsg(fd, &msg, 0); @@ -685,6 +702,7 @@ static void __attribute__((noreturn)) usage(const char *filepath) " -L listen on hostname and port\n" " -n: set no-payload option\n" " -N: print timestamps and durations in nsec (instead of usec)\n" + " -o N: use SCM_TS_OPT_ID control message to provide N as tskey\n" " -p N: connect to port N\n" " -P: use PF_PACKET\n" " -r: use raw\n" @@ -705,7 +723,7 @@ static void parse_opt(int argc, char **argv) int c; while ((c = getopt(argc, argv, - "46bc:CeEFhIl:LnNp:PrRS:t:uv:V:x")) != -1) { + "46bc:CeEFhIl:LnNo:p:PrRS:t:uv:V:x")) != -1) { switch (c) { case '4': do_ipv6 = 0; @@ -746,6 +764,10 @@ static void parse_opt(int argc, char **argv) case 'N': cfg_print_nsec = true; break; + case 'o': + ts_opt_id = strtoul(optarg, NULL, 10); + cfg_use_cmsg_opt_id = true; + break; case 'p': dest_port = strtoul(optarg, NULL, 10); break; @@ -803,6 +825,8 @@ static void parse_opt(int argc, char **argv) error(1, 0, "cannot ask for pktinfo over pf_packet"); if (cfg_busy_poll && cfg_use_epoll) error(1, 0, "pass epoll or busy_poll, not both"); + if (cfg_proto == SOCK_STREAM && cfg_use_cmsg_opt_id) + error(1, 0, "TCP sockets don't support SCM_TS_OPT_ID"); if (optind != argc - 1) error(1, 0, "missing required hostname argument"); diff --git a/tools/testing/selftests/net/txtimestamp.sh b/tools/testing/selftests/net/txtimestamp.sh index 25baca4b148e..fe4649bb8786 100755 --- a/tools/testing/selftests/net/txtimestamp.sh +++ b/tools/testing/selftests/net/txtimestamp.sh @@ -37,11 +37,13 @@ run_test_v4v6() { run_test_tcpudpraw() { local -r args=$@ - run_test_v4v6 ${args} # tcp - run_test_v4v6 ${args} -u # udp - run_test_v4v6 ${args} -r # raw - run_test_v4v6 ${args} -R # raw (IPPROTO_RAW) - run_test_v4v6 ${args} -P # pf_packet + run_test_v4v6 ${args} # tcp + run_test_v4v6 ${args} -u # udp + run_test_v4v6 ${args} -u -o 42 # udp with fixed tskey + run_test_v4v6 ${args} -r # raw + run_test_v4v6 ${args} -r -o 42 # raw + run_test_v4v6 ${args} -R # raw (IPPROTO_RAW) + run_test_v4v6 ${args} -P # pf_packet } run_test_all() { diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk index 1ef24119def0..d43afe243779 100644 --- a/tools/testing/selftests/net/ynl.mk +++ b/tools/testing/selftests/net/ynl.mk @@ -9,6 +9,8 @@ # YNL_GEN_FILES: TEST_GEN_FILES which need YNL YNL_OUTPUTS := $(patsubst %,$(OUTPUT)/%,$(YNL_GEN_FILES)) +YNL_SPECS := \ + $(patsubst %,$(top_srcdir)/Documentation/netlink/specs/%.yaml,$(YNL_GENS)) $(YNL_OUTPUTS): $(OUTPUT)/libynl.a $(YNL_OUTPUTS): CFLAGS += \ @@ -16,10 +18,20 @@ $(YNL_OUTPUTS): CFLAGS += \ -I$(top_srcdir)/tools/net/ynl/lib/ \ -I$(top_srcdir)/tools/net/ynl/generated/ -$(OUTPUT)/libynl.a: +# Make sure we rebuild libynl if user added a new family. We can't easily +# depend on the contents of a variable so create a fake file with a hash. +YNL_GENS_HASH := $(shell echo $(YNL_GENS) | sha1sum | cut -c1-8) +$(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig: + $(Q)rm -f $(OUTPUT)/.libynl-*.sig + $(Q)touch $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig + +$(OUTPUT)/libynl.a: $(YNL_SPECS) $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig + $(Q)rm -f $(top_srcdir)/tools/net/ynl/libynl.a $(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl GENS="$(YNL_GENS)" libynl.a $(Q)cp $(top_srcdir)/tools/net/ynl/libynl.a $(OUTPUT)/libynl.a EXTRA_CLEAN += \ $(top_srcdir)/tools/net/ynl/lib/__pycache__ \ - $(top_srcdir)/tools/net/ynl/lib/*.[ado] + $(top_srcdir)/tools/net/ynl/lib/*.[ado] \ + $(OUTPUT)/.libynl-*.sig \ + $(OUTPUT)/libynl.a diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index 011252fe238c..58064151f2c8 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -146,6 +146,7 @@ static void usage(char *progname) " -T val set the ptp clock time to 'val' seconds\n" " -x val get an extended ptp clock time with the desired number of samples (up to %d)\n" " -X get a ptp clock cross timestamp\n" + " -y val pre/post tstamp timebase to use {realtime|monotonic|monotonic-raw}\n" " -z test combinations of rising/falling external time stamp flags\n", progname, PTP_MAX_SAMPLES); } @@ -189,6 +190,7 @@ int main(int argc, char *argv[]) int seconds = 0; int settime = 0; int channel = -1; + clockid_t ext_clockid = CLOCK_REALTIME; int64_t t1, t2, tp; int64_t interval, offset; @@ -198,7 +200,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:Xz"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:Xy:z"))) { switch (c) { case 'c': capabilities = 1; @@ -278,6 +280,21 @@ int main(int argc, char *argv[]) case 'X': getcross = 1; break; + case 'y': + if (!strcasecmp(optarg, "realtime")) + ext_clockid = CLOCK_REALTIME; + else if (!strcasecmp(optarg, "monotonic")) + ext_clockid = CLOCK_MONOTONIC; + else if (!strcasecmp(optarg, "monotonic-raw")) + ext_clockid = CLOCK_MONOTONIC_RAW; + else { + fprintf(stderr, + "type needs to be realtime, monotonic or monotonic-raw; was given %s\n", + optarg); + return -1; + } + break; + case 'z': flagtest = 1; break; @@ -566,6 +583,7 @@ int main(int argc, char *argv[]) } soe->n_samples = getextended; + soe->clockid = ext_clockid; if (ioctl(fd, PTP_SYS_OFFSET_EXTENDED, soe)) { perror("PTP_SYS_OFFSET_EXTENDED"); @@ -574,12 +592,46 @@ int main(int argc, char *argv[]) getextended); for (i = 0; i < getextended; i++) { - printf("sample #%2d: system time before: %lld.%09u\n", - i, soe->ts[i][0].sec, soe->ts[i][0].nsec); + switch (ext_clockid) { + case CLOCK_REALTIME: + printf("sample #%2d: real time before: %lld.%09u\n", + i, soe->ts[i][0].sec, + soe->ts[i][0].nsec); + break; + case CLOCK_MONOTONIC: + printf("sample #%2d: monotonic time before: %lld.%09u\n", + i, soe->ts[i][0].sec, + soe->ts[i][0].nsec); + break; + case CLOCK_MONOTONIC_RAW: + printf("sample #%2d: monotonic-raw time before: %lld.%09u\n", + i, soe->ts[i][0].sec, + soe->ts[i][0].nsec); + break; + default: + break; + } printf(" phc time: %lld.%09u\n", soe->ts[i][1].sec, soe->ts[i][1].nsec); - printf(" system time after: %lld.%09u\n", - soe->ts[i][2].sec, soe->ts[i][2].nsec); + switch (ext_clockid) { + case CLOCK_REALTIME: + printf(" real time after: %lld.%09u\n", + soe->ts[i][2].sec, + soe->ts[i][2].nsec); + break; + case CLOCK_MONOTONIC: + printf(" monotonic time after: %lld.%09u\n", + soe->ts[i][2].sec, + soe->ts[i][2].nsec); + break; + case CLOCK_MONOTONIC_RAW: + printf(" monotonic-raw time after: %lld.%09u\n", + soe->ts[i][2].sec, + soe->ts[i][2].nsec); + break; + default: + break; + } } } |