Depending on the attribute (i.e.: SEG6_LOCAL_SRH, SEG6_LOCAL_TABLE, etc), the parse() callback performs some validity checks on the provided input and updates the tunnel state (slwt) with the result of the parsing operation. However, an attribute may also need to reserve some additional resources (i.e.: memory or setting up an eBPF program) in the parse() callback to complete the parsing operation.

The parse() callbacks are invoked by the parse_nla_action() for each attribute belonging to a specific behavior. Given a behavior with N attributes, if the parsing of the i-th attribute fails, the parse_nla_action() returns immediately with an error. Nonetheless, the resources acquired during the parsing of the i-1 attributes are not freed by the parse_nla_action().

Attributes which acquire resources must release them *in an explicit way* in both the seg6_local_{build/destroy}_state(). However, adding a new attribute of this type requires changes to seg6_local_{build/destroy}_state() to release the resources correctly.

The seg6local infrastructure still lacks a simple and structured way to release the resources acquired in the parse() operations.

We introduced a new callback in the struct seg6_action_param named destroy(). This callback releases any resource which may have been acquired in the parse() counterpart. Each attribute may or may not implement the destroy() callback depending on whether it needs to free some acquired resources.

The destroy() callback comes with several of advantages:

1) we can have many attributes as we want for a given behavior with no need to explicitly free the taken resources;

2) As in case of the seg6_local_build_state(), the seg6_local_destroy_state() does not need to handle the release of resources directly. Indeed, it calls the destroy_attrs() function which is in charge of calling the destroy() callback for every set attribute. We do not need to patch seg6_local_{build/destroy}_state() anymore as we add new attributes;

3) the code is more readable and better structured. Indeed, all the information needed to handle a given attribute are contained in only one place;

4) it facilitates the integration with new features introduced in further patches.

Signed-off-by: Andrea Mayer andrea.mayer@uniroma2.it --- net/ipv6/seg6_local.c | 103 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 93 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index eba23279912d..63a82e2fdea9 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -710,6 +710,12 @@ static int cmp_nla_srh(struct seg6_local_lwt *a, struct seg6_local_lwt *b) return memcmp(a->srh, b->srh, len); }

+static void destroy_attr_srh(struct seg6_local_lwt *slwt) +{ + kfree(slwt->srh); + slwt->srh = NULL; +} + static int parse_nla_table(struct nlattr **attrs, struct seg6_local_lwt *slwt) { slwt->table = nla_get_u32(attrs[SEG6_LOCAL_TABLE]); @@ -901,16 +907,33 @@ static int cmp_nla_bpf(struct seg6_local_lwt *a, struct seg6_local_lwt *b) return strcmp(a->bpf.name, b->bpf.name); }

+static void destroy_attr_bpf(struct seg6_local_lwt *slwt) +{ + kfree(slwt->bpf.name); + if (slwt->bpf.prog) + bpf_prog_put(slwt->bpf.prog); + + slwt->bpf.name = NULL; + slwt->bpf.prog = NULL; +} + struct seg6_action_param { int (*parse)(struct nlattr **attrs, struct seg6_local_lwt *slwt); int (*put)(struct sk_buff *skb, struct seg6_local_lwt *slwt); int (*cmp)(struct seg6_local_lwt *a, struct seg6_local_lwt *b); + + /* optional destroy() callback useful for releasing resources which + * have been previously acquired in the corresponding parse() + * function. + */ + void (*destroy)(struct seg6_local_lwt *slwt); };

static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = { [SEG6_LOCAL_SRH] = { .parse = parse_nla_srh, .put = put_nla_srh, - .cmp = cmp_nla_srh }, + .cmp = cmp_nla_srh, + .destroy = destroy_attr_srh },

[SEG6_LOCAL_TABLE] = { .parse = parse_nla_table, .put = put_nla_table, @@ -934,13 +957,68 @@ static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = {

[SEG6_LOCAL_BPF] = { .parse = parse_nla_bpf, .put = put_nla_bpf, - .cmp = cmp_nla_bpf }, + .cmp = cmp_nla_bpf, + .destroy = destroy_attr_bpf },

};

+/* call the destroy() callback (if available) for each set attribute in + * @parsed_attrs, starting from attribute index @start up to @end excluded. + */ +static void __destroy_attrs(unsigned long parsed_attrs, int start, int end, + struct seg6_local_lwt *slwt) +{ + struct seg6_action_param *param; + int i; + + /* Every seg6local attribute is identified by an ID which is encoded as + * a flag (i.e: 1 << ID) in the @parsed_attrs bitmask; such bitmask + * keeps track of the attributes parsed so far. + + * We scan the @parsed_attrs bitmask, starting from the attribute + * identified by @start up to the attribute identified by @end + * excluded. For each set attribute, we retrieve the corresponding + * destroy() callback. + * If the callback is not available, then we skip to the next + * attribute; otherwise, we call the destroy() callback. + */ + for (i = start; i < end; ++i) { + if (!(parsed_attrs & (1 << i))) + continue; + + param = &seg6_action_params[i]; + + if (param->destroy) + param->destroy(slwt); + } +} + +/* release all the resources that may have been acquired during parsing + * operations. + */ +static void destroy_attrs(struct seg6_local_lwt *slwt) +{ + struct seg6_action_desc *desc; + unsigned long attrs; + + desc = slwt->desc; + if (!desc) { + WARN_ONCE(1, + "seg6local: seg6_action_desc* for action %d is NULL", + slwt->action); + return; + } + + /* get the attributes for the current behavior instance */ + attrs = desc->attrs; + + __destroy_attrs(attrs, 0, SEG6_LOCAL_MAX + 1, slwt); +} + static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt) { struct seg6_action_param *param; + unsigned long parsed_attrs = 0; struct seg6_action_desc *desc; int i, err;

@@ -963,11 +1041,22 @@ static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt)

err = param->parse(attrs, slwt); if (err < 0) - return err; + goto parse_err; + + /* current attribute has been parsed correctly */ + parsed_attrs |= (1 << i); } }

return 0; + +parse_err: + /* release any resource that may have been acquired during the i-1 + * parse() operations. + */ + __destroy_attrs(parsed_attrs, 0, i, slwt); + + return err; }

static int seg6_local_build_state(struct net *net, struct nlattr *nla, @@ -1012,7 +1101,6 @@ static int seg6_local_build_state(struct net *net, struct nlattr *nla, return 0;

out_free: - kfree(slwt->srh); kfree(newts); return err; } @@ -1021,12 +1109,7 @@ static void seg6_local_destroy_state(struct lwtunnel_state *lwt) { struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);

- kfree(slwt->srh); - - if (slwt->desc->attrs & (1 << SEG6_LOCAL_BPF)) { - kfree(slwt->bpf.name); - bpf_prog_put(slwt->bpf.prog); - } + destroy_attrs(slwt);

return; }

SRv6 End.DT4 is defined in the SRv6 Network Programming [1].

The SRv6 End.DT4 is used to implement IPv4 L3VPN use-cases in multi-tenants environments. It decapsulates the received packets and it performs IPv4 routing lookup in the routing table of the tenant.

The SRv6 End.DT4 Linux implementation leverages a VRF device in order to force the routing lookup into the associated routing table.

To make the End.DT4 work properly, it must be guaranteed that the routing table used for routing lookup operations is bound to one and only one VRF during the tunnel creation. Such constraint has to be enforced by enabling the VRF strict_mode sysctl parameter, i.e: $ sysctl -wq net.vrf.strict_mode=1.

At JANOG44, LINE corporation presented their multi-tenant DC architecture using SRv6 [2]. In the slides, they reported that the Linux kernel is missing the support of SRv6 End.DT4 behavior.

The iproute2 counterpart required for configuring the SRv6 End.DT4 behavior is already implemented along with the other supported SRv6 behaviors [3].

[1] https://tools.ietf.org/html/draft-ietf-spring-srv6-network-programming [2] https://speakerdeck.com/line_developers/line-data-center-networking-with-srv... [3] https://patchwork.ozlabs.org/patch/799837/

Signed-off-by: Andrea Mayer andrea.mayer@uniroma2.it --- net/ipv6/seg6_local.c | 205 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 205 insertions(+)

diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 4b0f155d641d..a41074acd43e 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -57,6 +57,14 @@ struct bpf_lwt_prog { char *name; };

+struct seg6_end_dt4_info { + struct net *net; + /* VRF device associated to the routing table used by the SRv6 End.DT4 + * behavior for routing IPv4 packets. + */ + int vrf_ifindex; +}; + struct seg6_local_lwt { int action; struct ipv6_sr_hdr *srh; @@ -66,6 +74,7 @@ struct seg6_local_lwt { int iif; int oif; struct bpf_lwt_prog bpf; + struct seg6_end_dt4_info dt4_info;

int headroom; struct seg6_action_desc *desc; @@ -413,6 +422,194 @@ static int input_action_end_dx4(struct sk_buff *skb, return -EINVAL; }

+#ifdef CONFIG_NET_L3_MASTER_DEV + +static struct net *fib6_config_get_net(const struct fib6_config *fib6_cfg) +{ + const struct nl_info *nli = &fib6_cfg->fc_nlinfo; + + return nli->nl_net; +} + +static int seg6_end_dt4_build(struct seg6_local_lwt *slwt, const void *cfg, + struct netlink_ext_ack *extack) +{ + struct seg6_end_dt4_info *info = &slwt->dt4_info; + int vrf_ifindex; + struct net *net; + + net = fib6_config_get_net(cfg); + + vrf_ifindex = l3mdev_ifindex_lookup_by_table_id(L3MDEV_TYPE_VRF, net, + slwt->table); + if (vrf_ifindex < 0) { + if (vrf_ifindex == -EPERM) { + NL_SET_ERR_MSG(extack, + "Strict mode for VRF is disabled"); + } else if (vrf_ifindex == -ENODEV) { + NL_SET_ERR_MSG(extack, "No such device"); + } else { + NL_SET_ERR_MSG(extack, "Unknown error"); + + pr_debug("seg6local: SRv6 End.DT4 creation error=%d\n", + vrf_ifindex); + } + + return vrf_ifindex; + } + + info->net = net; + info->vrf_ifindex = vrf_ifindex; + + return 0; +} + +/* The SRv6 End.DT4 behavior extracts the inner (IPv4) packet and routes the + * IPv4 packet by looking at the configured routing table. + * + * In the SRv6 End.DT4 use case, we can receive traffic (IPv6+Segment Routing + * Header packets) from several interfaces and the IPv6 destination address (DA) + * is used for retrieving the specific instance of the End.DT4 behavior that + * should process the packets. + * + * However, the inner IPv4 packet is not really bound to any receiving + * interface and thus the End.DT4 sets the VRF (associated with the + * corresponding routing table) as the *receiving* interface. + * In other words, the End.DT4 processes a packet as if it has been received + * directly by the VRF (and not by one of its slave devices, if any). + * In this way, the VRF interface is used for routing the IPv4 packet in + * according to the routing table configured by the End.DT4 instance. + * + * This design allows you to get some interesting features like: + * 1) the statistics on rx packets; + * 2) the possibility to install a packet sniffer on the receiving interface + * (the VRF one) for looking at the incoming packets; + * 3) the possibility to leverage the netfilter prerouting hook for the inner + * IPv4 packet. + * + * This function returns: + * - the sk_buff* when the VRF rcv handler has processed the packet correctly; + * - NULL when the skb is consumed by the VRF rcv handler; + * - a pointer which encodes a negative error number in case of error. + * Note that in this case, the function takes care of freeing the skb. + */ +static struct sk_buff *end_dt4_vrf_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + /* based on l3mdev_ip_rcv; we are only interested in the master */ + if (unlikely(!netif_is_l3_master(dev) && !netif_has_l3_rx_handler(dev))) + goto drop; + + if (unlikely(!dev->l3mdev_ops->l3mdev_l3_rcv)) + goto drop; + + /* the decap packet (IPv4) does not come with any mac header info. + * We must unset the mac header to allow the VRF device to rebuild it, + * just in case there is a sniffer attached on the device. + */ + skb_unset_mac_header(skb); + + skb = dev->l3mdev_ops->l3mdev_l3_rcv(dev, skb, AF_INET); + if (!skb) + /* the skb buffer was consumed by the handler */ + return NULL; + + /* when a packet is received by a VRF or by one of its slaves, the + * master device reference is set into the skb. + */ + if (unlikely(skb->dev != dev || skb->skb_iif != dev->ifindex)) + goto drop; + + return skb; + +drop: + kfree_skb(skb); + return ERR_PTR(-EINVAL); +} + +static struct net_device *end_dt4_get_vrf_rcu(struct sk_buff *skb, + struct seg6_end_dt4_info *info) +{ + int vrf_ifindex = info->vrf_ifindex; + struct net *net = info->net; + + if (unlikely(vrf_ifindex < 0)) + goto error; + + if (unlikely(!net_eq(dev_net(skb->dev), net))) + goto error; + + return dev_get_by_index_rcu(net, vrf_ifindex); + +error: + return NULL; +} + +static int input_action_end_dt4(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + struct net_device *vrf; + struct iphdr *iph; + int err; + + if (!decap_and_validate(skb, IPPROTO_IPIP)) + goto drop; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto drop; + + vrf = end_dt4_get_vrf_rcu(skb, &slwt->dt4_info); + if (unlikely(!vrf)) + goto drop; + + skb->protocol = htons(ETH_P_IP); + + skb_dst_drop(skb); + + skb_set_transport_header(skb, sizeof(struct iphdr)); + + skb = end_dt4_vrf_rcv(skb, vrf); + if (!skb) + /* packet has been processed and consumed by the VRF */ + return 0; + + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + return err; + } + + iph = ip_hdr(skb); + + err = ip_route_input(skb, iph->daddr, iph->saddr, 0, skb->dev); + if (err) + goto drop; + + return dst_input(skb); + +drop: + kfree_skb(skb); + return -EINVAL; +} + +#else + +static int seg6_end_dt4_build(struct seg6_local_lwt *slwt, const void *cfg, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, "Operation is not supported"); + + return -EOPNOTSUPP; +} + +static int input_action_end_dt4(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + kfree_skb(skb); + return -EOPNOTSUPP; +} + +#endif + static int input_action_end_dt6(struct sk_buff *skb, struct seg6_local_lwt *slwt) { @@ -601,6 +798,14 @@ static struct seg6_action_desc seg6_action_table[] = { .attrs = (1 << SEG6_LOCAL_NH4), .input = input_action_end_dx4, }, + { + .action = SEG6_LOCAL_ACTION_END_DT4, + .attrs = (1 << SEG6_LOCAL_TABLE), + .input = input_action_end_dt4, + .slwt_ops = { + .build_state = seg6_end_dt4_build, + }, + }, { .action = SEG6_LOCAL_ACTION_END_DT6, .attrs = (1 << SEG6_LOCAL_TABLE),

this selftest is designed for evaluating the new SRv6 End.DT4 behavior used, in this example, for implementing IPv4 L3 VPN use cases.

Signed-off-by: Andrea Mayer andrea.mayer@uniroma2.it --- .../selftests/net/srv6_end_dt4_l3vpn_test.sh | 494 ++++++++++++++++++ 1 file changed, 494 insertions(+) create mode 100755 tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh

diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh new file mode 100755 index 000000000000..a5547fed5048 --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -0,0 +1,494 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Andrea Mayer andrea.mayer@uniroma2.it + +# This test is designed for evaluating the new SRv6 End.DT4 behavior used for +# implementing IPv4 L3 VPN use cases. +# +# Hereafter a network diagram is shown, where two different tenants (named 100 +# and 200) offer IPv4 L3 VPN services allowing hosts to communicate with each +# other across an IPv6 network. +# +# Only hosts belonging to the same tenant (and to the same VPN) can communicate +# with each other. Instead, the communication among hosts of different tenants +# is forbidden. +# In other words, hosts hs-t100-1 and hs-t100-2 are connected through the IPv4 +# L3 VPN of tenant 100 while hs-t200-3 and hs-t200-4 are connected using the +# IPv4 L3 VPN of tenant 200. Cross connection between tenant 100 and tenant 200 +# is forbidden and thus, for example, hs-t100-1 cannot reach hs-t200-3 and vice +# versa. +# +# Routers rt-1 and rt-2 implement IPv4 L3 VPN services leveraging the SRv6 +# architecture. The key components for such VPNs are: a) SRv6 Encap behavior, +# b) SRv6 End.DT4 behavior and c) VRF. +# +# To explain how an IPv4 L3 VPN based on SRv6 works, let us briefly consider an +# example where, within the same domain of tenant 100, the host hs-t100-1 pings +# the host hs-t100-2. +# +# First of all, L2 reachability of the host hs-t100-2 is taken into account by +# the router rt-1 which acts as an arp proxy. +# +# When the host hs-t100-1 sends an IPv4 packet destined to hs-t100-2, the +# router rt-1 receives the packet on the internal veth-t100 interface. Such +# interface is enslaved to the VRF vrf-100 whose associated table contains the +# SRv6 Encap route for encapsulating any IPv4 packet in a IPv6 plus the Segment +# Routing Header (SRH) packet. This packet is sent through the (IPv6) core +# network up to the router rt-2 that receives it on veth0 interface. +# +# The rt-2 router uses the 'localsid' routing table to process incoming +# IPv6+SRH packets which belong to the VPN of the tenant 100. For each of these +# packets, the SRv6 End.DT4 behavior removes the outer IPv6+SRH headers and +# performs the lookup on the vrf-100 table using the destination address of +# the decapsulated IPv4 packet. Afterwards, the packet is sent to the host +# hs-t100-2 through the veth-t100 interface. +# +# The ping response follows the same processing but this time the role of rt-1 +# and rt-2 are swapped. +# +# Of course, the IPv4 L3 VPN for tenant 200 works exactly as the IPv4 L3 VPN +# for tenant 100. In this case, only hosts hs-t200-3 and hs-t200-4 are able to +# connect with each other. +# +# +# +-------------------+ +-------------------+ +# | | | | +# | hs-t100-1 netns | | hs-t100-2 netns | +# | | | | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | 10.0.0.1/24 | | | | 10.0.0.2/24 | | +# | +-------------+ | | +-------------+ | +# | . | | . | +# +-------------------+ +-------------------+ +# . . +# . . +# . . +# +-----------------------------------+ +-----------------------------------+ +# | . | | . | +# | +---------------+ | | +---------------- | +# | | veth-t100 | | | | veth-t100 | | +# | | 10.0.0.254/24 | +----------+ | | +----------+ | 10.0.0.254/24 | | +# | +-------+-------+ | localsid | | | | localsid | +-------+-------- | +# | | | table | | | | table | | | +# | +----+----+ +----------+ | | +----------+ +----+----+ | +# | | vrf-100 | | | | vrf-100 | | +# | +---------+ +------------+ | | +------------+ +---------+ | +# | | veth0 | | | | veth0 | | +# | | fd00::1/64 |.|...|.| fd00::2/64 | | +# | +---------+ +------------+ | | +------------+ +---------+ | +# | | vrf-200 | | | | vrf-200 | | +# | +----+----+ | | +----+----+ | +# | | | | | | +# | +---------------+ | | +---------------- | +# | | veth-t200 | | | | veth-t200 | | +# | | 10.0.0.254/24 | | | | 10.0.0.254/24 | | +# | +---------------+ rt-1 netns | | rt-2 netns +---------------- | +# | . | | . | +# +-----------------------------------+ +-----------------------------------+ +# . . +# . . +# . . +# . . +# +-------------------+ +-------------------+ +# | . | | . | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | 10.0.0.3/24 | | | | 10.0.0.4/24 | | +# | +-------------+ | | +-------------+ | +# | | | | +# | hs-t200-3 netns | | hs-t200-4 netns | +# | | | | +# +-------------------+ +-------------------+ +# +# +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# | Network configuration | +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# +# rt-1: localsid table (table 90) +# +----------------------------------------------+ +# |SID |Action | +# +----------------------------------------------+ +# |fc00:21:100::6004|apply SRv6 End.DT4 table 100| +# +----------------------------------------------+ +# |fc00:21:200::6004|apply SRv6 End.DT4 table 200| +# +----------------------------------------------+ +# +# rt-1: VRF tenant 100 (table 100) +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |10.0.0.2 |apply seg6 encap segs fc00:12:100::6004| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth_t100 | +# +---------------------------------------------------+ +# +# rt-1: VRF tenant 200 (table 200) +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |10.0.0.4 |apply seg6 encap segs fc00:12:200::6004| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth_t200 | +# +---------------------------------------------------+ +# +# +# rt-2: localsid table (table 90) +# +----------------------------------------------+ +# |SID |Action | +# +----------------------------------------------+ +# |fc00:12:100::6004|apply SRv6 End.DT4 table 100| +# +----------------------------------------------+ +# |fc00:12:200::6004|apply SRv6 End.DT4 table 200| +# +----------------------------------------------+ +# +# rt-2: VRF tenant 100 (table 100) +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |10.0.0.1 |apply seg6 encap segs fc00:21:100::6004| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth_t100 | +# +---------------------------------------------------+ +# +# rt-2: VRF tenant 200 (table 200) +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |10.0.0.3 |apply seg6 encap segs fc00:21:200::6004| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth_t200 | +# +---------------------------------------------------+ +# + +readonly LOCALSID_TABLE_ID=90 +readonly IPv6_RT_NETWORK=fd00 +readonly IPv4_HS_NETWORK=10.0.0 +readonly VPN_LOCATOR_SERVICE=fc00 +PING_TIMEOUT_SEC=4 + +ret=0 + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +cleanup() +{ + ip link del veth-rt-1 2>/dev/null || true + ip link del veth-rt-2 2>/dev/null || true + + # destroy routers rt-* and hosts hs-* + for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do + ip netns del ${ns} || true + done +} + +# Setup the basic networking for the routers +setup_rt_networking() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns add ${nsname} + ip link set veth-rt-${rt} netns ${nsname} + ip -netns ${nsname} link set veth-rt-${rt} name veth0 + + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 + ip -netns ${nsname} link set veth0 up + ip -netns ${nsname} link set lo up + + ip netns exec ${nsname} sysctl -wq net.ipv4.ip_forward=1 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.forwarding=1 +} + +setup_hs() +{ + local hs=$1 + local rt=$2 + local tid=$3 + local hsname=hs-t${tid}-${hs} + local rtname=rt-${rt} + local rtveth=veth-t${tid} + + # set the networking for the host + ip netns add ${hsname} + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} + ip -netns ${hsname} link set ${rtveth} netns ${rtname} + ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 + ip -netns ${hsname} link set veth0 up + ip -netns ${hsname} link set lo up + + # configure the VRF for the tenant X on the router which is directly + # connected to the source host. + ip -netns ${rtname} link add vrf-${tid} type vrf table ${tid} + ip -netns ${rtname} link set vrf-${tid} up + + # enslave the veth-tX interface to the vrf-X in the access router + ip -netns ${rtname} link set ${rtveth} master vrf-${tid} + ip -netns ${rtname} addr add ${IPv4_HS_NETWORK}.254/24 dev ${rtveth} + ip -netns ${rtname} link set ${rtveth} up + + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 + + ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" +} + +setup_vpn_config() +{ + local hssrc=$1 + local rtsrc=$2 + local hsdst=$3 + local rtdst=$4 + local tid=$5 + + local hssrc_name=hs-t${tid}-${hssrc} + local hsdst_name=hs-t${tid}-${hsdst} + local rtsrc_name=rt-${rtsrc} + local rtdst_name=rt-${rtdst} + local vpn_sid=${VPN_LOCATOR_SERVICE}:${hssrc}${hsdst}:${tid}::6004 + + # set the encap route for encapsulating packets which arrive from the + # host hssrc and destined to the access router rtsrc. + ip -netns ${rtsrc_name} -4 route add ${IPv4_HS_NETWORK}.${hsdst}/32 vrf vrf-${tid} \ + encap seg6 mode encap segs ${vpn_sid} dev veth0 + ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 vrf vrf-${tid} \ + via fd00::${rtdst} dev veth0 + + # set the decap route for decapsulating packets which arrive from + # the rtdst router and destined to the hsdst host. + ip -netns ${rtdst_name} -6 route add ${vpn_sid}/128 table ${LOCALSID_TABLE_ID} \ + encap seg6local action End.DT4 table ${tid} dev vrf-${tid} + + # all sids for VPNs start with a common locator which is fc00::/16. + # Routes for handling the SRv6 End.DT4 behavior instances are grouped + # together in the 'localsid' table. + # + # NOTE: added only once + if [ -z "$(ip -netns ${rtdst_name} -6 rule show | \ + grep "to ${VPN_LOCATOR_SERVICE}::/16 lookup ${LOCALSID_TABLE_ID}")" ]; then + ip -netns ${rtdst_name} -6 rule add \ + to ${VPN_LOCATOR_SERVICE}::/16 \ + lookup ${LOCALSID_TABLE_ID} prio 999 + fi +} + +setup() +{ + ip link add veth-rt-1 type veth peer name veth-rt-2 + # setup the networking for router rt-1 and router rt-2 + setup_rt_networking 1 + setup_rt_networking 2 + + # setup two hosts for the tenant 100. + # - host hs-1 is directly connected to the router rt-1; + # - host hs-2 is directly connected to the router rt-2. + setup_hs 1 1 100 #args: host router tenant + setup_hs 2 2 100 + + # setup two hosts for the tenant 200 + # - host hs-3 is directly connected to the router rt-1; + # - host hs-4 is directly connected to the router rt-2. + setup_hs 3 1 200 + setup_hs 4 2 200 + + # setup the IPv4 L3 VPN which connects the host hs-t100-1 and host + # hs-t100-2 within the same tenant 100. + setup_vpn_config 1 1 2 2 100 #args: src_host src_router dst_host dst_router tenant + setup_vpn_config 2 2 1 1 100 + + # setup the IPv4 L3 VPN which connects the host hs-t200-3 and host + # hs-t200-4 within the same tenant 200. + setup_vpn_config 3 1 4 2 200 + setup_vpn_config 4 2 3 1 200 +} + +check_rt_connectivity() +{ + local rtsrc=$1 + local rtdst=$2 + + ip netns exec rt-${rtsrc} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \ + >/dev/null 2>&1 +} + +check_and_log_rt_connectivity() +{ + local rtsrc=$1 + local rtdst=$2 + + check_rt_connectivity ${rtsrc} ${rtdst} + log_test $? 0 "Routers connectivity: rt-${rtsrc} -> rt-${rtdst}" +} + +check_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \ + ${IPv4_HS_NETWORK}.${hsdst} >/dev/null 2>&1 +} + +check_and_log_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + check_hs_connectivity ${hssrc} ${hsdst} ${tid} + log_test $? 0 "Hosts connectivity: hs-t${tid}-${hssrc} -> hs-t${tid}-${hsdst} (tenant ${tid})" +} + +check_and_log_hs_isolation() +{ + local hssrc=$1 + local tidsrc=$2 + local hsdst=$3 + local tiddst=$4 + + check_hs_connectivity ${hssrc} ${hsdst} ${tidsrc} + # NOTE: ping should fail + log_test $? 1 "Hosts isolation: hs-t${tidsrc}-${hssrc} -X-> hs-t${tiddst}-${hsdst}" +} + + +check_and_log_hs2gw_connectivity() +{ + local hssrc=$1 + local tid=$2 + + check_hs_connectivity ${hssrc} 254 ${tid} + log_test $? 0 "Hosts connectivity: hs-t${tid}-${hssrc} -> gw (tenant ${tid})" +} + +router_tests() +{ + log_section "IPv6 routers connectivity test" + + check_and_log_rt_connectivity 1 2 + check_and_log_rt_connectivity 2 1 +} + +host2gateway_tests() +{ + log_section "IPv4 connectivity test among hosts and gateway" + + check_and_log_hs2gw_connectivity 1 100 + check_and_log_hs2gw_connectivity 2 100 + + check_and_log_hs2gw_connectivity 3 200 + check_and_log_hs2gw_connectivity 4 200 +} + +host_vpn_tests() +{ + log_section "SRv6 VPN connectivity test among hosts in the same tenant" + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 + + check_and_log_hs_connectivity 3 4 200 + check_and_log_hs_connectivity 4 3 200 +} + +host_vpn_isolation_tests() +{ + local i + local j + local k + local tmp + local l1="1 2" + local l2="3 4" + local t1=100 + local t2=200 + + log_section "SRv6 VPN isolation test among hosts in different tentants" + + for k in 0 1; do + for i in ${l1}; do + for j in ${l2}; do + check_and_log_hs_isolation ${i} ${t1} ${j} ${t2} + done + done + + # let us test the reverse path + tmp="${l1}"; l1="${l2}"; l2="${tmp}" + tmp=${t1}; t1=${t2}; t2=${tmp} + done +} + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit 0 +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit 0 +fi + +modprobe vrf &>/dev/null +if [ ! -e /proc/sys/net/vrf/strict_mode ]; then + echo "SKIP: vrf sysctl does not exist" + exit 0 +fi + +cleanup &>/dev/null + +setup + +router_tests +host2gateway_tests +host_vpn_tests +host_vpn_isolation_tests + +print_log_test_results + +cleanup &>/dev/null + +exit ${ret}