diff options
| -rw-r--r-- | Documentation/netlink/specs/ovs_flow.yaml | 17 | ||||
| -rw-r--r-- | include/net/psample.h | 5 | ||||
| -rw-r--r-- | include/uapi/linux/openvswitch.h | 31 | ||||
| -rw-r--r-- | include/uapi/linux/psample.h | 11 | ||||
| -rw-r--r-- | net/openvswitch/Kconfig | 1 | ||||
| -rw-r--r-- | net/openvswitch/actions.c | 66 | ||||
| -rw-r--r-- | net/openvswitch/datapath.h | 3 | ||||
| -rw-r--r-- | net/openvswitch/flow_netlink.c | 32 | ||||
| -rw-r--r-- | net/openvswitch/vport.c | 1 | ||||
| -rw-r--r-- | net/psample/psample.c | 16 | ||||
| -rw-r--r-- | net/sched/act_sample.c | 12 | ||||
| -rwxr-xr-x | tools/testing/selftests/net/openvswitch/openvswitch.sh | 115 | ||||
| -rw-r--r-- | tools/testing/selftests/net/openvswitch/ovs-dpctl.py | 272 |
13 files changed, 566 insertions, 16 deletions
diff --git a/Documentation/netlink/specs/ovs_flow.yaml b/Documentation/netlink/specs/ovs_flow.yaml index 4fdfc6b5cae9..46f5d1cd8a5f 100644 --- a/Documentation/netlink/specs/ovs_flow.yaml +++ b/Documentation/netlink/specs/ovs_flow.yaml @@ -727,6 +727,12 @@ attribute-sets: name: dec-ttl type: nest nested-attributes: dec-ttl-attrs + - + name: psample + type: nest + nested-attributes: psample-attrs + doc: | + Sends a packet sample to psample for external observation. - name: tunnel-key-attrs enum-name: ovs-tunnel-key-attr @@ -938,6 +944,17 @@ attribute-sets: - name: gbp type: u32 + - + name: psample-attrs + enum-name: ovs-psample-attr + name-prefix: ovs-psample-attr- + attributes: + - + name: group + type: u32 + - + name: cookie + type: binary operations: name-prefix: ovs-flow-cmd- diff --git a/include/net/psample.h b/include/net/psample.h index 0509d2d6be67..c52e9ebd88dd 100644 --- a/include/net/psample.h +++ b/include/net/psample.h @@ -24,7 +24,10 @@ struct psample_metadata { u8 out_tc_valid:1, out_tc_occ_valid:1, latency_valid:1, - unused:5; + rate_as_probability:1, + unused:4; + const u8 *user_cookie; + u32 user_cookie_len; }; struct psample_group *psample_group_get(struct net *net, u32 group_num); diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index efc82c318fa2..3a701bd1f31b 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -649,7 +649,8 @@ enum ovs_flow_attr { * Actions are passed as nested attributes. * * Executes the specified actions with the given probability on a per-packet - * basis. + * basis. Nested actions will be able to access the probability value of the + * parent @OVS_ACTION_ATTR_SAMPLE. */ enum ovs_sample_attr { OVS_SAMPLE_ATTR_UNSPEC, @@ -914,6 +915,31 @@ struct check_pkt_len_arg { }; #endif +#define OVS_PSAMPLE_COOKIE_MAX_SIZE 16 +/** + * enum ovs_psample_attr - Attributes for %OVS_ACTION_ATTR_PSAMPLE + * action. + * + * @OVS_PSAMPLE_ATTR_GROUP: 32-bit number to identify the source of the + * sample. + * @OVS_PSAMPLE_ATTR_COOKIE: An optional variable-length binary cookie that + * contains user-defined metadata. The maximum length is + * OVS_PSAMPLE_COOKIE_MAX_SIZE bytes. + * + * Sends the packet to the psample multicast group with the specified group and + * cookie. It is possible to combine this action with the + * %OVS_ACTION_ATTR_TRUNC action to limit the size of the sample. + */ +enum ovs_psample_attr { + OVS_PSAMPLE_ATTR_GROUP = 1, /* u32 number. */ + OVS_PSAMPLE_ATTR_COOKIE, /* Optional, user specified cookie. */ + + /* private: */ + __OVS_PSAMPLE_ATTR_MAX +}; + +#define OVS_PSAMPLE_ATTR_MAX (__OVS_PSAMPLE_ATTR_MAX - 1) + /** * enum ovs_action_attr - Action types. * @@ -966,6 +992,8 @@ struct check_pkt_len_arg { * of l3 tunnel flag in the tun_flags field of OVS_ACTION_ATTR_ADD_MPLS * argument. * @OVS_ACTION_ATTR_DROP: Explicit drop action. + * @OVS_ACTION_ATTR_PSAMPLE: Send a sample of the packet to external observers + * via psample. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -1004,6 +1032,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_ADD_MPLS, /* struct ovs_action_add_mpls. */ OVS_ACTION_ATTR_DEC_TTL, /* Nested OVS_DEC_TTL_ATTR_*. */ OVS_ACTION_ATTR_DROP, /* u32 error code. */ + OVS_ACTION_ATTR_PSAMPLE, /* Nested OVS_PSAMPLE_ATTR_*. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h index e585db5bf2d2..b765f0e81f20 100644 --- a/include/uapi/linux/psample.h +++ b/include/uapi/linux/psample.h @@ -8,7 +8,11 @@ enum { PSAMPLE_ATTR_ORIGSIZE, PSAMPLE_ATTR_SAMPLE_GROUP, PSAMPLE_ATTR_GROUP_SEQ, - PSAMPLE_ATTR_SAMPLE_RATE, + PSAMPLE_ATTR_SAMPLE_RATE, /* u32, ratio between observed and + * sampled packets or scaled probability + * if PSAMPLE_ATTR_SAMPLE_PROBABILITY + * is set. + */ PSAMPLE_ATTR_DATA, PSAMPLE_ATTR_GROUP_REFCOUNT, PSAMPLE_ATTR_TUNNEL, @@ -19,6 +23,11 @@ enum { PSAMPLE_ATTR_LATENCY, /* u64, nanoseconds */ PSAMPLE_ATTR_TIMESTAMP, /* u64, nanoseconds */ PSAMPLE_ATTR_PROTO, /* u16 */ + PSAMPLE_ATTR_USER_COOKIE, /* binary, user provided data */ + PSAMPLE_ATTR_SAMPLE_PROBABILITY,/* no argument, interpret rate in + * PSAMPLE_ATTR_SAMPLE_RATE as a + * probability scaled 0 - U32_MAX. + */ __PSAMPLE_ATTR_MAX }; diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 29a7081858cd..2535f3f9f462 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -10,6 +10,7 @@ config OPENVSWITCH (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \ (!NF_NAT || NF_NAT) && \ (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT))) + depends on PSAMPLE || !PSAMPLE select LIBCRC32C select MPLS select NET_MPLS_GSO diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 964225580824..101f9a23792c 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -24,6 +24,11 @@ #include <net/checksum.h> #include <net/dsfield.h> #include <net/mpls.h> + +#if IS_ENABLED(CONFIG_PSAMPLE) +#include <net/psample.h> +#endif + #include <net/sctp/checksum.h> #include "datapath.h" @@ -1043,12 +1048,15 @@ static int sample(struct datapath *dp, struct sk_buff *skb, struct nlattr *sample_arg; int rem = nla_len(attr); const struct sample_arg *arg; + u32 init_probability; bool clone_flow_key; + int err; /* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */ sample_arg = nla_data(attr); arg = nla_data(sample_arg); actions = nla_next(sample_arg, &rem); + init_probability = OVS_CB(skb)->probability; if ((arg->probability != U32_MAX) && (!arg->probability || get_random_u32() > arg->probability)) { @@ -1057,9 +1065,16 @@ static int sample(struct datapath *dp, struct sk_buff *skb, return 0; } + OVS_CB(skb)->probability = arg->probability; + clone_flow_key = !arg->exec; - return clone_execute(dp, skb, key, 0, actions, rem, last, - clone_flow_key); + err = clone_execute(dp, skb, key, 0, actions, rem, last, + clone_flow_key); + + if (!last) + OVS_CB(skb)->probability = init_probability; + + return err; } /* When 'last' is true, clone() should always consume the 'skb'. @@ -1299,6 +1314,44 @@ static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key) return 0; } +#if IS_ENABLED(CONFIG_PSAMPLE) +static void execute_psample(struct datapath *dp, struct sk_buff *skb, + const struct nlattr *attr) +{ + struct psample_group psample_group = {}; + struct psample_metadata md = {}; + const struct nlattr *a; + u32 rate; + int rem; + + nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) { + switch (nla_type(a)) { + case OVS_PSAMPLE_ATTR_GROUP: + psample_group.group_num = nla_get_u32(a); + break; + + case OVS_PSAMPLE_ATTR_COOKIE: + md.user_cookie = nla_data(a); + md.user_cookie_len = nla_len(a); + break; + } + } + + psample_group.net = ovs_dp_get_net(dp); + md.in_ifindex = OVS_CB(skb)->input_vport->dev->ifindex; + md.trunc_size = skb->len - OVS_CB(skb)->cutlen; + md.rate_as_probability = 1; + + rate = OVS_CB(skb)->probability ? OVS_CB(skb)->probability : U32_MAX; + + psample_sample_packet(&psample_group, skb, rate, &md); +} +#else +static void execute_psample(struct datapath *dp, struct sk_buff *skb, + const struct nlattr *attr) +{} +#endif + /* Execute a list of actions against 'skb'. */ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, @@ -1502,6 +1555,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, ovs_kfree_skb_reason(skb, reason); return 0; } + + case OVS_ACTION_ATTR_PSAMPLE: + execute_psample(dp, skb, a); + OVS_CB(skb)->cutlen = 0; + if (nla_is_last(a, rem)) { + consume_skb(skb); + return 0; + } + break; } if (unlikely(err)) { diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 0cd29971a907..9ca6231ea647 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -115,12 +115,15 @@ struct datapath { * fragmented. * @acts_origlen: The netlink size of the flow actions applied to this skb. * @cutlen: The number of bytes from the packet end to be removed. + * @probability: The sampling probability that was applied to this skb; 0 means + * no sampling has occurred; U32_MAX means 100% probability. */ struct ovs_skb_cb { struct vport *input_vport; u16 mru; u16 acts_origlen; u32 cutlen; + u32 probability; }; #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb) diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index f224d9bcea5e..c92bdc4dfe19 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -64,6 +64,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_TRUNC: case OVS_ACTION_ATTR_USERSPACE: case OVS_ACTION_ATTR_DROP: + case OVS_ACTION_ATTR_PSAMPLE: break; case OVS_ACTION_ATTR_CT: @@ -2409,7 +2410,7 @@ static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) /* Whenever new actions are added, the need to update this * function should be considered. */ - BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 24); + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 25); if (!actions) return; @@ -3157,6 +3158,28 @@ static int validate_and_copy_check_pkt_len(struct net *net, return 0; } +static int validate_psample(const struct nlattr *attr) +{ + static const struct nla_policy policy[OVS_PSAMPLE_ATTR_MAX + 1] = { + [OVS_PSAMPLE_ATTR_GROUP] = { .type = NLA_U32 }, + [OVS_PSAMPLE_ATTR_COOKIE] = { + .type = NLA_BINARY, + .len = OVS_PSAMPLE_COOKIE_MAX_SIZE, + }, + }; + struct nlattr *a[OVS_PSAMPLE_ATTR_MAX + 1]; + int err; + + if (!IS_ENABLED(CONFIG_PSAMPLE)) + return -EOPNOTSUPP; + + err = nla_parse_nested(a, OVS_PSAMPLE_ATTR_MAX, attr, policy, NULL); + if (err) + return err; + + return a[OVS_PSAMPLE_ATTR_GROUP] ? 0 : -EINVAL; +} + static int copy_action(const struct nlattr *from, struct sw_flow_actions **sfa, bool log) { @@ -3212,6 +3235,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), [OVS_ACTION_ATTR_DEC_TTL] = (u32)-1, [OVS_ACTION_ATTR_DROP] = sizeof(u32), + [OVS_ACTION_ATTR_PSAMPLE] = (u32)-1, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3490,6 +3514,12 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; break; + case OVS_ACTION_ATTR_PSAMPLE: + err = validate_psample(a); + if (err) + return err; + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 972ae01a70f7..8732f6e51ae5 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -500,6 +500,7 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb, OVS_CB(skb)->input_vport = vport; OVS_CB(skb)->mru = 0; OVS_CB(skb)->cutlen = 0; + OVS_CB(skb)->probability = 0; if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) { u32 mark; diff --git a/net/psample/psample.c b/net/psample/psample.c index a5d9b8446f77..f48b5b9cd409 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -376,6 +376,10 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, void *data; int ret; + if (!genl_has_listeners(&psample_nl_family, group->net, + PSAMPLE_NL_MCGRP_SAMPLE)) + return; + meta_len = (in_ifindex ? nla_total_size(sizeof(u16)) : 0) + (out_ifindex ? nla_total_size(sizeof(u16)) : 0) + (md->out_tc_valid ? nla_total_size(sizeof(u16)) : 0) + @@ -386,7 +390,9 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, nla_total_size(sizeof(u32)) + /* group_num */ nla_total_size(sizeof(u32)) + /* seq */ nla_total_size_64bit(sizeof(u64)) + /* timestamp */ - nla_total_size(sizeof(u16)); /* protocol */ + nla_total_size(sizeof(u16)) + /* protocol */ + (md->user_cookie_len ? + nla_total_size(md->user_cookie_len) : 0); /* user cookie */ #ifdef CONFIG_INET tun_info = skb_tunnel_info(skb); @@ -486,6 +492,14 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, } #endif + if (md->user_cookie && md->user_cookie_len && + nla_put(nl_skb, PSAMPLE_ATTR_USER_COOKIE, md->user_cookie_len, + md->user_cookie)) + goto error; + + if (md->rate_as_probability) + nla_put_flag(skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY); + genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, PSAMPLE_NL_MCGRP_SAMPLE, GFP_ATOMIC); diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index a69b53d54039..2ceb4d141b71 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -167,7 +167,9 @@ TC_INDIRECT_SCOPE int tcf_sample_act(struct sk_buff *skb, { struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; + u8 cookie_data[TC_COOKIE_MAX_SIZE]; struct psample_metadata md = {}; + struct tc_cookie *user_cookie; int retval; tcf_lastuse_update(&s->tcf_tm); @@ -189,6 +191,16 @@ TC_INDIRECT_SCOPE int tcf_sample_act(struct sk_buff *skb, if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) skb_push(skb, skb->mac_len); + rcu_read_lock(); + user_cookie = rcu_dereference(a->user_cookie); + if (user_cookie) { + memcpy(cookie_data, user_cookie->data, + user_cookie->len); + md.user_cookie = cookie_data; + md.user_cookie_len = user_cookie->len; + } + rcu_read_unlock(); + md.trunc_size = s->truncate ? s->trunc_size : skb->len; psample_sample_packet(psample_group, skb, s->rate, &md); diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 531951086d9c..bc71dbc18b21 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -20,7 +20,8 @@ tests=" nat_related_v4 ip4-nat-related: ICMP related matches work with SNAT netlink_checks ovsnl: validate netlink attrs and settings upcall_interfaces ovs: test the upcall interfaces - drop_reason drop: test drop reasons are emitted" + drop_reason drop: test drop reasons are emitted + psample psample: Sampling packets with psample" info() { [ "${ovs_dir}" != "" ] && @@ -105,12 +106,21 @@ ovs_netns_spawn_daemon() { shift netns=$1 shift - info "spawning cmd: $*" - ip netns exec $netns $* >> $ovs_dir/stdout 2>> $ovs_dir/stderr & + if [ "$netns" == "_default" ]; then + $* >> $ovs_dir/stdout 2>> $ovs_dir/stderr & + else + ip netns exec $netns $* >> $ovs_dir/stdout 2>> $ovs_dir/stderr & + fi pid=$! ovs_sbx "$sbx" on_exit "kill -TERM $pid 2>/dev/null" } +ovs_spawn_daemon() { + sbx=$1 + shift + ovs_netns_spawn_daemon $sbx "_default" $* +} + ovs_add_netns_and_veths () { info "Adding netns attached: sbx:$1 dp:$2 {$3, $4, $5}" ovs_sbx "$1" ip netns add "$3" || return 1 @@ -173,6 +183,19 @@ ovs_drop_reason_count() return `echo "$perf_output" | grep "$pattern" | wc -l` } +ovs_test_flow_fails () { + ERR_MSG="Flow actions may not be safe on all matching packets" + + PRE_TEST=$(dmesg | grep -c "${ERR_MSG}") + ovs_add_flow $@ &> /dev/null $@ && return 1 + POST_TEST=$(dmesg | grep -c "${ERR_MSG}") + + if [ "$PRE_TEST" == "$POST_TEST" ]; then + return 1 + fi + return 0 +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." @@ -187,6 +210,92 @@ usage() { exit 1 } + +# psample test +# - use psample to observe packets +test_psample() { + sbx_add "test_psample" || return $? + + # Add a datapath with per-vport dispatching. + ovs_add_dp "test_psample" psample -V 2:1 || return 1 + + info "create namespaces" + ovs_add_netns_and_veths "test_psample" "psample" \ + client c0 c1 172.31.110.10/24 -u || return 1 + ovs_add_netns_and_veths "test_psample" "psample" \ + server s0 s1 172.31.110.20/24 -u || return 1 + + # Check if psample actions can be configured. + ovs_add_flow "test_psample" psample \ + 'in_port(1),eth(),eth_type(0x0806),arp()' 'psample(group=1)' &> /dev/null + if [ $? == 1 ]; then + info "no support for psample - skipping" + ovs_exit_sig + return $ksft_skip + fi + + ovs_del_flows "test_psample" psample + + # Test action verification. + OLDIFS=$IFS + IFS='*' + min_key='in_port(1),eth(),eth_type(0x0800),ipv4()' + for testcase in \ + "cookie to large"*"psample(group=1,cookie=1615141312111009080706050403020100)" \ + "no group with cookie"*"psample(cookie=abcd)" \ + "no group"*"psample()"; + do + set -- $testcase; + ovs_test_flow_fails "test_psample" psample $min_key $2 + if [ $? == 1 ]; then + info "failed - $1" + return 1 + fi + done + IFS=$OLDIFS + + ovs_del_flows "test_psample" psample + # Allow ARP + ovs_add_flow "test_psample" psample \ + 'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1 + ovs_add_flow "test_psample" psample \ + 'in_port(2),eth(),eth_type(0x0806),arp()' '1' || return 1 + + # Sample first 14 bytes of all traffic. + ovs_add_flow "test_psample" psample \ + "in_port(1),eth(),eth_type(0x0800),ipv4()" \ + "trunc(14),psample(group=1,cookie=c0ffee),2" + + # Sample all traffic. In this case, use a sample() action with both + # psample and an upcall emulating simultaneous local sampling and + # sFlow / IPFIX. + nlpid=$(grep -E "listening on upcall packet handler" \ + $ovs_dir/s0.out | cut -d ":" -f 2 | tr -d ' ') + + ovs_add_flow "test_psample" psample \ + "in_port(2),eth(),eth_type(0x0800),ipv4()" \ + "sample(sample=100%,actions(psample(group=2,cookie=eeff0c),userspace(pid=${nlpid},userdata=eeff0c))),1" + + # Record psample data. + ovs_spawn_daemon "test_psample" python3 $ovs_base/ovs-dpctl.py psample-events + + # Send a single ping. + sleep 1 + ovs_sbx "test_psample" ip netns exec client ping -I c1 172.31.110.20 -c 1 || return 1 + sleep 1 + + # We should have received one userspace action upcall and 2 psample packets. + grep -E "userspace action command" $ovs_dir/s0.out >/dev/null 2>&1 || return 1 + + # client -> server samples should only contain the first 14 bytes of the packet. + grep -E "rate:4294967295,group:1,cookie:c0ffee data:[0-9a-f]{28}$" \ + $ovs_dir/stdout >/dev/null 2>&1 || return 1 + grep -E "rate:4294967295,group:2,cookie:eeff0c" \ + $ovs_dir/stdout >/dev/null 2>&1 || return 1 + + return 0 +} + # drop_reason test # - drop packets and verify the right drop reason is reported test_drop_reason() { diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 182a09975975..1e15b0818074 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -8,6 +8,7 @@ import argparse import errno import ipaddress import logging +import math import multiprocessing import re import socket @@ -27,8 +28,10 @@ try: from pyroute2.netlink import genlmsg from pyroute2.netlink import nla from pyroute2.netlink import nlmsg_atoms + from pyroute2.netlink.event import EventSocket from pyroute2.netlink.exceptions import NetlinkError from pyroute2.netlink.generic import GenericNetlinkSocket + from pyroute2.netlink.nlsocket import Marshal import pyroute2 import pyroute2.iproute @@ -60,6 +63,7 @@ OVS_FLOW_CMD_DEL = 2 OVS_FLOW_CMD_GET = 3 OVS_FLOW_CMD_SET = 4 +UINT32_MAX = 0xFFFFFFFF def macstr(mac): outstr = ":".join(["%02X" % i for i in mac]) @@ -281,6 +285,75 @@ def parse_extract_field( return str_skipped, data +def parse_attrs(actstr, attr_desc): + """Parses the given action string and returns a list of netlink + attributes based on a list of attribute descriptions. + + Each element in the attribute description list is a tuple such as: + (name, attr_name, parse_func) + where: + name: is the string representing the attribute + attr_name: is the name of the attribute as defined in the uAPI. + parse_func: is a callable accepting a string and returning either + a single object (the parsed attribute value) or a tuple of + two values (the parsed attribute value and the remaining string) + + Returns a list of attributes and the remaining string. + """ + def parse_attr(actstr, key, func): + actstr = actstr[len(key) :] + + if not func: + return None, actstr + + delim = actstr[0] + actstr = actstr[1:] + + if delim == "=": + pos = strcspn(actstr, ",)") + ret = func(actstr[:pos]) + else: + ret = func(actstr) + + if isinstance(ret, tuple): + (datum, actstr) = ret + else: + datum = ret + actstr = actstr[strcspn(actstr, ",)"):] + + if delim == "(": + if not actstr or actstr[0] != ")": + raise ValueError("Action contains unbalanced parentheses") + + actstr = actstr[1:] + + actstr = actstr[strspn(actstr, ", ") :] + + return datum, actstr + + attrs = [] + attr_desc = list(attr_desc) + while actstr and actstr[0] != ")" and attr_desc: + found = False + for i, (key, attr, func) in enumerate(attr_desc): + if actstr.startswith(key): + datum, actstr = parse_attr(actstr, key, func) + attrs.append([attr, datum]) + found = True + del attr_desc[i] + + if not found: + raise ValueError("Unknown attribute: '%s'" % actstr) + + actstr = actstr[strspn(actstr, ", ") :] + + if actstr[0] != ")": + raise ValueError("Action string contains extra garbage or has " + "unbalanced parenthesis: '%s'" % actstr) + + return attrs, actstr[1:] + + class ovs_dp_msg(genlmsg): # include the OVS version # We need a custom header rather than just being able to rely on @@ -299,7 +372,7 @@ class ovsactions(nla): ("OVS_ACTION_ATTR_SET", "ovskey"), ("OVS_ACTION_ATTR_PUSH_VLAN", "none"), ("OVS_ACTION_ATTR_POP_VLAN", "flag"), - ("OVS_ACTION_ATTR_SAMPLE", "none"), + ("OVS_ACTION_ATTR_SAMPLE", "sample"), ("OVS_ACTION_ATTR_RECIRC", "uint32"), ("OVS_ACTION_ATTR_HASH", "none"), ("OVS_ACTION_ATTR_PUSH_MPLS", "none"), @@ -318,8 +391,85 @@ class ovsactions(nla): ("OVS_ACTION_ATTR_ADD_MPLS", "none"), ("OVS_ACTION_ATTR_DEC_TTL", "none"), ("OVS_ACTION_ATTR_DROP", "uint32"), + ("OVS_ACTION_ATTR_PSAMPLE", "psample"), ) + class psample(nla): + nla_flags = NLA_F_NESTED + + nla_map = ( + ("OVS_PSAMPLE_ATTR_UNSPEC", "none"), + ("OVS_PSAMPLE_ATTR_GROUP", "uint32"), + ("OVS_PSAMPLE_ATTR_COOKIE", "array(uint8)"), + ) + + def dpstr(self, more=False): + args = "group=%d" % self.get_attr("OVS_PSAMPLE_ATTR_GROUP") + + cookie = self.get_attr("OVS_PSAMPLE_ATTR_COOKIE") + if cookie: + args += ",cookie(%s)" % \ + "".join(format(x, "02x") for x in cookie) + + return "psample(%s)" % args + + def parse(self, actstr): + desc = ( + ("group", "OVS_PSAMPLE_ATTR_GROUP", int), + ("cookie", "OVS_PSAMPLE_ATTR_COOKIE", + lambda x: list(bytearray.fromhex(x))) + ) + + attrs, actstr = parse_attrs(actstr, desc) + + for attr in attrs: + self["attrs"].append(attr) + + return actstr + + class sample(nla): + nla_flags = NLA_F_NESTED + + nla_map = ( + ("OVS_SAMPLE_ATTR_UNSPEC", "none"), + ("OVS_SAMPLE_ATTR_PROBABILITY", "uint32"), + ("OVS_SAMPLE_ATTR_ACTIONS", "ovsactions"), + ) + + def dpstr(self, more=False): + args = [] + + args.append("sample={:.2f}%".format( + 100 * self.get_attr("OVS_SAMPLE_ATTR_PROBABILITY") / + UINT32_MAX)) + + actions = self.get_attr("OVS_SAMPLE_ATTR_ACTIONS") + if actions: + args.append("actions(%s)" % actions.dpstr(more)) + + return "sample(%s)" % ",".join(args) + + def parse(self, actstr): + def parse_nested_actions(actstr): + subacts = ovsactions() + parsed_len = subacts.parse(actstr) + return subacts, actstr[parsed_len :] + + def percent_to_rate(percent): + percent = float(percent.strip('%')) + return int(math.floor(UINT32_MAX * (percent / 100.0) + .5)) + + desc = ( + ("sample", "OVS_SAMPLE_ATTR_PROBABILITY", percent_to_rate), + ("actions", "OVS_SAMPLE_ATTR_ACTIONS", parse_nested_actions), + ) + attrs, actstr = parse_attrs(actstr, desc) + + for attr in attrs: + self["attrs"].append(attr) + + return actstr + class ctact(nla): nla_flags = NLA_F_NESTED @@ -441,13 +591,27 @@ class ovsactions(nla): print_str += "userdata=" for f in self.get_attr("OVS_USERSPACE_ATTR_USERDATA"): print_str += "%x." % f - if self.get_attr("OVS_USERSPACE_ATTR_TUN_PORT") is not None: + if self.get_attr("OVS_USERSPACE_ATTR_EGRESS_TUN_PORT") is not None: print_str += "egress_tun_port=%d" % self.get_attr( - "OVS_USERSPACE_ATTR_TUN_PORT" + "OVS_USERSPACE_ATTR_EGRESS_TUN_PORT" ) print_str += ")" return print_str + def parse(self, actstr): + attrs_desc = ( + ("pid", "OVS_USERSPACE_ATTR_PID", int), + ("userdata", "OVS_USERSPACE_ATTR_USERDATA", + lambda x: list(bytearray.fromhex(x))), + ("egress_tun_port", "OVS_USERSPACE_ATTR_EGRESS_TUN_PORT", int) + ) + + attrs, actstr = parse_attrs(actstr, attrs_desc) + for attr in attrs: + self["attrs"].append(attr) + + return actstr + def dpstr(self, more=False): print_str = "" @@ -683,6 +847,37 @@ class ovsactions(nla): self["attrs"].append(["OVS_ACTION_ATTR_CT", ctact]) parsed = True + elif parse_starts_block(actstr, "sample(", False): + sampleact = self.sample() + actstr = sampleact.parse(actstr[len("sample(") : ]) + self["attrs"].append(["OVS_ACTION_ATTR_SAMPLE", sampleact]) + parsed = True + + elif parse_starts_block(actstr, "psample(", False): + psampleact = self.psample() + actstr = psampleact.parse(actstr[len("psample(") : ]) + self["attrs"].append(["OVS_ACTION_ATTR_PSAMPLE", psampleact]) + parsed = True + + elif parse_starts_block(actstr, "userspace(", False): + uact = self.userspace() + actstr = uact.parse(actstr[len("userspace(") : ]) + self["attrs"].append(["OVS_ACTION_ATTR_USERSPACE", uact]) + parsed = True + + elif parse_starts_block(actstr, "trunc(", False): + parencount += 1 + actstr, val = parse_extract_field( + actstr, + "trunc(", + r"([0-9]+)", + int, + False, + None, + ) + self["attrs"].append(["OVS_ACTION_ATTR_TRUNC", val]) + parsed = True + actstr = actstr[strspn(actstr, ", ") :] while parencount > 0: parencount -= 1 @@ -2267,10 +2462,70 @@ class OvsFlow(GenericNetlinkSocket): print("MISS upcall[%d/%s]: %s" % (seq, pktpres, keystr), flush=True) def execute(self, packetmsg): - print("userspace execute command") + print("userspace execute command", flush=True) def action(self, packetmsg): - print("userspace action command") + print("userspace action command", flush=True) + + +class psample_sample(genlmsg): + nla_map = ( + ("PSAMPLE_ATTR_IIFINDEX", "none"), + ("PSAMPLE_ATTR_OIFINDEX", "none"), + ("PSAMPLE_ATTR_ORIGSIZE", "none"), + ("PSAMPLE_ATTR_SAMPLE_GROUP", "uint32"), + ("PSAMPLE_ATTR_GROUP_SEQ", "none"), + ("PSAMPLE_ATTR_SAMPLE_RATE", "uint32"), + ("PSAMPLE_ATTR_DATA", "array(uint8)"), + ("PSAMPLE_ATTR_GROUP_REFCOUNT", "none"), + ("PSAMPLE_ATTR_TUNNEL", "none"), + ("PSAMPLE_ATTR_PAD", "none"), + ("PSAMPLE_ATTR_OUT_TC", "none"), + ("PSAMPLE_ATTR_OUT_TC_OCC", "none"), + ("PSAMPLE_ATTR_LATENCY", "none"), + ("PSAMPLE_ATTR_TIMESTAMP", "none"), + ("PSAMPLE_ATTR_PROTO", "none"), + ("PSAMPLE_ATTR_USER_COOKIE", "array(uint8)"), + ) + + def dpstr(self): + fields = [] + data = "" + for (attr, value) in self["attrs"]: + if attr == "PSAMPLE_ATTR_SAMPLE_GROUP": + fields.append("group:%d" % value) + if attr == "PSAMPLE_ATTR_SAMPLE_RATE": + fields.append("rate:%d" % value) + if attr == "PSAMPLE_ATTR_USER_COOKIE": + value = "".join(format(x, "02x") for x in value) + fields.append("cookie:%s" % value) + if attr == "PSAMPLE_ATTR_DATA" and len(value) > 0: + data = "data:%s" % "".join(format(x, "02x") for x in value) + + return ("%s %s" % (",".join(fields), data)).strip() + + +class psample_msg(Marshal): + PSAMPLE_CMD_SAMPLE = 0 + PSAMPLE_CMD_GET_GROUP = 1 + PSAMPLE_CMD_NEW_GROUP = 2 + PSAMPLE_CMD_DEL_GROUP = 3 + PSAMPLE_CMD_SET_FILTER = 4 + msg_map = {PSAMPLE_CMD_SAMPLE: psample_sample} + + +class PsampleEvent(EventSocket): + genl_family = "psample" + mcast_groups = ["packets"] + marshal_class = psample_msg + + def read_samples(self): + while True: + try: + for msg in self.get(): + print(msg.dpstr(), flush=True) + except NetlinkError as ne: + raise ne def print_ovsdp_full(dp_lookup_rep, ifindex, ndb=NDB(), vpl=OvsVport()): @@ -2337,7 +2592,7 @@ def main(argv): help="Increment 'verbose' output counter.", default=0, ) - subparsers = parser.add_subparsers() + subparsers = parser.add_subparsers(dest="subcommand") showdpcmd = subparsers.add_parser("show") showdpcmd.add_argument( @@ -2412,6 +2667,8 @@ def main(argv): delfscmd = subparsers.add_parser("del-flows") delfscmd.add_argument("flsbr", help="Datapath name") + subparsers.add_parser("psample-events") + args = parser.parse_args() if args.verbose > 0: @@ -2426,6 +2683,9 @@ def main(argv): sys.setrecursionlimit(100000) + if args.subcommand == "psample-events": + PsampleEvent().read_samples() + if hasattr(args, "showdp"): found = False for iface in ndb.interfaces: |