From 8ecd06277a7664f4ef018abae3abd3451d64e7a6 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 17 Jun 2024 11:18:15 +0200 Subject: [PATCH 1/5] netfilter: ipset: Fix suspicious rcu_dereference_protected() When destroying all sets, we are either in pernet exit phase or are executing a "destroy all sets command" from userspace. The latter was taken into account in ip_set_dereference() (nfnetlink mutex is held), but the former was not. The patch adds the required check to rcu_dereference_protected() in ip_set_dereference(). Fixes: 4e7aaa6b82d6 ("netfilter: ipset: Fix race between namespace cleanup and gc in the list:set type") Reported-by: syzbot+b62c37cdd58103293a5a@syzkaller.appspotmail.com Reported-by: syzbot+cfbe1da5fdfc39efc293@syzkaller.appspotmail.com Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202406141556.e0b6f17e-lkp@intel.com Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_core.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index c7ae4d9bf3d2..61431690cbd5 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -53,12 +53,13 @@ MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); /* When the nfnl mutex or ip_set_ref_lock is held: */ -#define ip_set_dereference(p) \ - rcu_dereference_protected(p, \ +#define ip_set_dereference(inst) \ + rcu_dereference_protected((inst)->ip_set_list, \ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ - lockdep_is_held(&ip_set_ref_lock)) + lockdep_is_held(&ip_set_ref_lock) || \ + (inst)->is_deleted) #define ip_set(inst, id) \ - ip_set_dereference((inst)->ip_set_list)[id] + ip_set_dereference(inst)[id] #define ip_set_ref_netlink(inst,id) \ rcu_dereference_raw((inst)->ip_set_list)[id] #define ip_set_dereference_nfnl(p) \ @@ -1133,7 +1134,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info, if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ - tmp = ip_set_dereference(inst->ip_set_list); + tmp = ip_set_dereference(inst); memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max); rcu_assign_pointer(inst->ip_set_list, list); /* Make sure all current packets have passed through */ From 9a3bc8d16e0aacd65c31aaf23a2bced3288a7779 Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Thu, 13 Jun 2024 17:42:46 +0800 Subject: [PATCH 2/5] seg6: fix parameter passing when calling NF_HOOK() in End.DX4 and End.DX6 behaviors input_action_end_dx4() and input_action_end_dx6() are called NF_HOOK() for PREROUTING hook, in PREROUTING hook, we should passing a valid indev, and a NULL outdev to NF_HOOK(), otherwise may trigger a NULL pointer dereference, as below: [74830.647293] BUG: kernel NULL pointer dereference, address: 0000000000000090 [74830.655633] #PF: supervisor read access in kernel mode [74830.657888] #PF: error_code(0x0000) - not-present page [74830.659500] PGD 0 P4D 0 [74830.660450] Oops: 0000 [#1] PREEMPT SMP PTI ... [74830.664953] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [74830.666569] RIP: 0010:rpfilter_mt+0x44/0x15e [ipt_rpfilter] ... [74830.689725] Call Trace: [74830.690402] [74830.690953] ? show_trace_log_lvl+0x1c4/0x2df [74830.692020] ? show_trace_log_lvl+0x1c4/0x2df [74830.693095] ? ipt_do_table+0x286/0x710 [ip_tables] [74830.694275] ? __die_body.cold+0x8/0xd [74830.695205] ? page_fault_oops+0xac/0x140 [74830.696244] ? exc_page_fault+0x62/0x150 [74830.697225] ? asm_exc_page_fault+0x22/0x30 [74830.698344] ? rpfilter_mt+0x44/0x15e [ipt_rpfilter] [74830.699540] ipt_do_table+0x286/0x710 [ip_tables] [74830.700758] ? ip6_route_input+0x19d/0x240 [74830.701752] nf_hook_slow+0x3f/0xb0 [74830.702678] input_action_end_dx4+0x19b/0x1e0 [74830.703735] ? input_action_end_t+0xe0/0xe0 [74830.704734] seg6_local_input_core+0x2d/0x60 [74830.705782] lwtunnel_input+0x5b/0xb0 [74830.706690] __netif_receive_skb_one_core+0x63/0xa0 [74830.707825] process_backlog+0x99/0x140 [74830.709538] __napi_poll+0x2c/0x160 [74830.710673] net_rx_action+0x296/0x350 [74830.711860] __do_softirq+0xcb/0x2ac [74830.713049] do_softirq+0x63/0x90 input_action_end_dx4() passing a NULL indev to NF_HOOK(), and finally trigger a NULL dereference in rpfilter_mt()->rpfilter_is_loopback(): static bool rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in) { // in is NULL return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; } Fixes: 7a3f5b0de364 ("netfilter: add netfilter hooks to SRv6 data plane") Signed-off-by: Jianguo Wu Reviewed-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/ipv6/seg6_local.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 24e2b4b494cb..c434940131b1 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -941,8 +941,8 @@ static int input_action_end_dx6(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx6_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx6_finish); return input_action_end_dx6_finish(dev_net(skb->dev), NULL, skb); drop: @@ -991,8 +991,8 @@ static int input_action_end_dx4(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx4_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx4_finish); return input_action_end_dx4_finish(dev_net(skb->dev), NULL, skb); drop: From a2225e0250c5fa397dcebf6ce65a9f05a114e0cf Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Thu, 13 Jun 2024 17:42:47 +0800 Subject: [PATCH 3/5] netfilter: move the sysctl nf_hooks_lwtunnel into the netfilter core Currently, the sysctl net.netfilter.nf_hooks_lwtunnel depends on the nf_conntrack module, but the nf_conntrack module is not always loaded. Therefore, accessing net.netfilter.nf_hooks_lwtunnel may have an error. Move sysctl nf_hooks_lwtunnel into the netfilter core. Fixes: 7a3f5b0de364 ("netfilter: add netfilter hooks to SRv6 data plane") Suggested-by: Pablo Neira Ayuso Signed-off-by: Jianguo Wu Signed-off-by: Pablo Neira Ayuso --- include/net/netns/netfilter.h | 3 ++ net/netfilter/core.c | 13 ++++- net/netfilter/nf_conntrack_standalone.c | 15 ------ net/netfilter/nf_hooks_lwtunnel.c | 67 +++++++++++++++++++++++++ net/netfilter/nf_internals.h | 6 +++ 5 files changed, 87 insertions(+), 17 deletions(-) diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 02bbdc577f8e..a6a0bf4a247e 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -15,6 +15,9 @@ struct netns_nf { const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO]; #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; +#ifdef CONFIG_LWTUNNEL + struct ctl_table_header *nf_lwtnl_dir_header; +#endif #endif struct nf_hook_entries __rcu *hooks_ipv4[NF_INET_NUMHOOKS]; struct nf_hook_entries __rcu *hooks_ipv6[NF_INET_NUMHOOKS]; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 3126911f5042..b00fc285b334 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -815,12 +815,21 @@ int __init netfilter_init(void) if (ret < 0) goto err; +#ifdef CONFIG_LWTUNNEL + ret = netfilter_lwtunnel_init(); + if (ret < 0) + goto err_lwtunnel_pernet; +#endif ret = netfilter_log_init(); if (ret < 0) - goto err_pernet; + goto err_log_pernet; return 0; -err_pernet: +err_log_pernet: +#ifdef CONFIG_LWTUNNEL + netfilter_lwtunnel_fini(); +err_lwtunnel_pernet: +#endif unregister_pernet_subsys(&netfilter_net_ops); err: return ret; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 74112e9c5dab..6c40bdf8b05a 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -22,9 +22,6 @@ #include #include #include -#ifdef CONFIG_LWTUNNEL -#include -#endif #include static bool enable_hooks __read_mostly; @@ -612,9 +609,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_GRE, NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, #endif -#ifdef CONFIG_LWTUNNEL - NF_SYSCTL_CT_LWTUNNEL, -#endif NF_SYSCTL_CT_LAST_SYSCTL, }; @@ -946,15 +940,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, #endif -#ifdef CONFIG_LWTUNNEL - [NF_SYSCTL_CT_LWTUNNEL] = { - .procname = "nf_hooks_lwtunnel", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = nf_hooks_lwtunnel_sysctl_handler, - }, -#endif }; static struct ctl_table nf_ct_netfilter_table[] = { diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c index 00e89ffd78f6..7cdb59bb4459 100644 --- a/net/netfilter/nf_hooks_lwtunnel.c +++ b/net/netfilter/nf_hooks_lwtunnel.c @@ -3,6 +3,9 @@ #include #include #include +#include + +#include "nf_internals.h" static inline int nf_hooks_lwtunnel_get(void) { @@ -50,4 +53,68 @@ int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write, return ret; } EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_sysctl_handler); + +static struct ctl_table nf_lwtunnel_sysctl_table[] = { + { + .procname = "nf_hooks_lwtunnel", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = nf_hooks_lwtunnel_sysctl_handler, + }, +}; + +static int __net_init nf_lwtunnel_net_init(struct net *net) +{ + struct ctl_table_header *hdr; + struct ctl_table *table; + + table = nf_lwtunnel_sysctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(nf_lwtunnel_sysctl_table, + sizeof(nf_lwtunnel_sysctl_table), + GFP_KERNEL); + if (!table) + goto err_alloc; + } + + hdr = register_net_sysctl_sz(net, "net/netfilter", table, + ARRAY_SIZE(nf_lwtunnel_sysctl_table)); + if (!hdr) + goto err_reg; + + net->nf.nf_lwtnl_dir_header = hdr; + + return 0; +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit nf_lwtunnel_net_exit(struct net *net) +{ + const struct ctl_table *table; + + table = net->nf.nf_lwtnl_dir_header->ctl_table_arg; + unregister_net_sysctl_table(net->nf.nf_lwtnl_dir_header); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct pernet_operations nf_lwtunnel_net_ops = { + .init = nf_lwtunnel_net_init, + .exit = nf_lwtunnel_net_exit, +}; + +int __init netfilter_lwtunnel_init(void) +{ + return register_pernet_subsys(&nf_lwtunnel_net_ops); +} + +void netfilter_lwtunnel_fini(void) +{ + unregister_pernet_subsys(&nf_lwtunnel_net_ops); +} #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 832ae64179f0..25403023060b 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -29,6 +29,12 @@ void nf_queue_nf_hook_drop(struct net *net); /* nf_log.c */ int __init netfilter_log_init(void); +#ifdef CONFIG_LWTUNNEL +/* nf_hooks_lwtunnel.c */ +int __init netfilter_lwtunnel_init(void); +void netfilter_lwtunnel_fini(void); +#endif + /* core.c */ void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg); From 72e50ef99431163203657128050d0697caf3321d Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Thu, 13 Jun 2024 17:42:48 +0800 Subject: [PATCH 4/5] selftests: add selftest for the SRv6 End.DX4 behavior with netfilter this selftest is designed for evaluating the SRv6 End.DX4 behavior used with netfilter(rpfilter), in this example, for implementing IPv4 L3 VPN use cases. Signed-off-by: Jianguo Wu Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 1 + .../net/srv6_end_dx4_netfilter_test.sh | 335 ++++++++++++++++++ 3 files changed, 337 insertions(+) create mode 100755 tools/testing/selftests/net/srv6_end_dx4_netfilter_test.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index bd01e4a0be2c..7a5f7dd320de 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -43,6 +43,7 @@ TEST_PROGS += srv6_hl2encap_red_l2vpn_test.sh TEST_PROGS += srv6_end_next_csid_l3vpn_test.sh TEST_PROGS += srv6_end_x_next_csid_l3vpn_test.sh TEST_PROGS += srv6_end_flavors_test.sh +TEST_PROGS += srv6_end_dx4_netfilter_test.sh TEST_PROGS += vrf_strict_mode_test.sh TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS += ndisc_unsolicited_na_test.sh diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 04de7a6ba6f3..c2766e558f92 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -101,3 +101,4 @@ CONFIG_NETFILTER_XT_MATCH_POLICY=m CONFIG_CRYPTO_ARIA=y CONFIG_XFRM_INTERFACE=m CONFIG_XFRM_USER=m +CONFIG_IP_NF_MATCH_RPFILTER=m diff --git a/tools/testing/selftests/net/srv6_end_dx4_netfilter_test.sh b/tools/testing/selftests/net/srv6_end_dx4_netfilter_test.sh new file mode 100755 index 000000000000..e23210aa547f --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_dx4_netfilter_test.sh @@ -0,0 +1,335 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Jianguo Wu +# +# Mostly copied from tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh. +# +# This script is designed for testing the support of netfilter hooks for +# SRv6 End.DX4 behavior. +# +# Hereafter a network diagram is shown, where one tenants (named 100) offer +# IPv4 L3 VPN services allowing hosts to communicate with each other across +# an IPv6 network. +# +# 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.DX4 behavior. +# +# 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-1 pings +# the host hs-2. +# +# First of all, L2 reachability of the host hs-2 is taken into account by +# the router rt-1 which acts as an arp proxy. +# +# When the host hs-1 sends an IPv4 packet destined to hs-2, the router rt-1 +# receives the packet on the internal veth-t100 interface, rt-1 contains the +# SRv6 Encap route for encapsulating the 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.DX4 behavior removes the outer IPv6+SRH headers and +# routs the packet to the specified nexthop. Afterwards, the packet is sent to +# the host hs-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. +# +# And when net.netfilter.nf_hooks_lwtunnel is set to 1 in rt-1 or rt-2, and a +# rpfilter iptables rule is added, SRv6 packets will go through netfilter PREROUTING +# hooks. +# +# +# +-------------------+ +-------------------+ +# | | | | +# | hs-1 netns | | hs-2 netns | +# | | | | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | 10.0.0.1/24 | | | | 10.0.0.2/24 | | +# | +-------------+ | | +-------------+ | +# | . | | . | +# +-------------------+ +-------------------+ +# . . +# . . +# . . +# +-----------------------------------+ +-----------------------------------+ +# | . | | . | +# | +---------------+ | | +---------------- | +# | | veth-t100 | | | | veth-t100 | | +# | | 10.0.0.11/24 | +----------+ | | +----------+ | 10.0.0.22/24 | | +# | +-------+-------+ | route | | | | route | +-------+-------- | +# | | table | | | | table | | +# | +----------+ | | +----------+ | +# | +--------------+ | | +--------------+ | +# | | veth0 | | | | veth0 | | +# | | 2001:11::1/64 |.|...|.| 2001:11::2/64 | | +# | +--------------+ | | +--------------+ | +# | | | | +# | rt-1 netns | | rt-2 netns | +# | | | | +# +-----------------------------------+ +-----------------------------------+ +# +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# | Network configuration | +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# +# rt-1: localsid table +# +----------------------------------------------------------------+ +# |SID |Action | +# +----------------------------------------------------------------+ +# |fc00:21:100::6004|apply SRv6 End.DX4 nh4 10.0.0.1 dev veth-t100 | +# +----------------------------------------------------------------+ +# +# rt-1: route table +# +---------------------------------------------------+ +# |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-2: localsid table +# +---------------------------------------------------------------+ +# |SID |Action | +# +---------------------------------------------------------------+ +# |fc00:12:100::6004|apply SRv6 End.DX4 nh4 10.0.0.2 dev veth-t100| +# +---------------------------------------------------------------+ +# +# rt-2: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |10.0.0.1 |apply seg6 encap segs fc00:21:100::6004| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth_t100 | +# +---------------------------------------------------+ +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +readonly IPv6_RT_NETWORK=2001:11 +readonly IPv4_HS_NETWORK=10.0.0 +readonly SID_LOCATOR=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 netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip link set veth-rt-${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 nodad + 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_rt_netfilter() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns exec ${nsname} sysctl -wq net.netfilter.nf_hooks_lwtunnel=1 + ip netns exec ${nsname} iptables -t raw -A PREROUTING -m rpfilter --invert -j DROP +} + +setup_hs() +{ + local hs=$1 + local rt=$2 + local tid=$3 + local hsname=hs-${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 + + ip -netns ${rtname} addr add ${IPv4_HS_NETWORK}.${rt}${hs}/24 dev ${rtveth} + ip -netns ${rtname} link set ${rtveth} up + + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 +} + +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-${rtdst} + local vpn_sid=${SID_LOCATOR}:${hssrc}${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 \ + encap seg6 mode encap segs ${vpn_sid} dev veth0 + ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 \ + via 2001:11::${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 \ + encap seg6local action End.DX4 nh4 ${IPv4_HS_NETWORK}.${hsdst} dev veth-t${tid} +} + +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 + setup_hs 2 2 100 + + # setup the IPv4 L3 VPN which connects the host hs-1 and host hs-2. + 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 +} + +check_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + ip netns exec hs-${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 $? 0 "Hosts connectivity: hs-${hssrc} -> hs-${hsdst} (tenant ${tid})" +} + +host_tests() +{ + log_section "SRv6 VPN connectivity test among hosts in the same tenant" + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +router_netfilter_tests() +{ + log_section "SRv6 VPN connectivity test with netfilter enabled in routers" + setup_rt_netfilter 1 + setup_rt_netfilter 2 + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +if [ "$(id -u)" -ne 0 ];then + 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 + +cleanup &>/dev/null + +setup + +host_tests +router_netfilter_tests + +print_log_test_results + +cleanup &>/dev/null + +exit ${ret} From 221200ffeb065c6bbd196760c168b42305961655 Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Thu, 13 Jun 2024 17:42:49 +0800 Subject: [PATCH 5/5] selftests: add selftest for the SRv6 End.DX6 behavior with netfilter this selftest is designed for evaluating the SRv6 End.DX6 behavior used with netfilter(rpfilter), in this example, for implementing IPv6 L3 VPN use cases. Signed-off-by: Jianguo Wu Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 1 + .../net/srv6_end_dx6_netfilter_test.sh | 340 ++++++++++++++++++ 3 files changed, 342 insertions(+) create mode 100755 tools/testing/selftests/net/srv6_end_dx6_netfilter_test.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 7a5f7dd320de..d9393569d03a 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -44,6 +44,7 @@ TEST_PROGS += srv6_end_next_csid_l3vpn_test.sh TEST_PROGS += srv6_end_x_next_csid_l3vpn_test.sh TEST_PROGS += srv6_end_flavors_test.sh TEST_PROGS += srv6_end_dx4_netfilter_test.sh +TEST_PROGS += srv6_end_dx6_netfilter_test.sh TEST_PROGS += vrf_strict_mode_test.sh TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS += ndisc_unsolicited_na_test.sh diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index c2766e558f92..d4891f7a2bfa 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -102,3 +102,4 @@ CONFIG_CRYPTO_ARIA=y CONFIG_XFRM_INTERFACE=m CONFIG_XFRM_USER=m CONFIG_IP_NF_MATCH_RPFILTER=m +CONFIG_IP6_NF_MATCH_RPFILTER=m diff --git a/tools/testing/selftests/net/srv6_end_dx6_netfilter_test.sh b/tools/testing/selftests/net/srv6_end_dx6_netfilter_test.sh new file mode 100755 index 000000000000..9e69a2ed5bc3 --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_dx6_netfilter_test.sh @@ -0,0 +1,340 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Jianguo Wu +# +# Mostly copied from tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh. +# +# This script is designed for testing the support of netfilter hooks for +# SRv6 End.DX4 behavior. +# +# Hereafter a network diagram is shown, where one tenants (named 100) offer +# IPv6 L3 VPN services allowing hosts to communicate with each other across +# an IPv6 network. +# +# Routers rt-1 and rt-2 implement IPv6 L3 VPN services leveraging the SRv6 +# architecture. The key components for such VPNs are: a) SRv6 Encap behavior, +# b) SRv6 End.DX4 behavior. +# +# To explain how an IPv6 L3 VPN based on SRv6 works, let us briefly consider an +# example where, within the same domain of tenant 100, the host hs-1 pings +# the host hs-2. +# +# First of all, L2 reachability of the host hs-2 is taken into account by +# the router rt-1 which acts as an arp proxy. +# +# When the host hs-1 sends an IPv6 packet destined to hs-2, the router rt-1 +# receives the packet on the internal veth-t100 interface, rt-1 contains the +# SRv6 Encap route for encapsulating the IPv6 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.DX4 behavior removes the outer IPv6+SRH headers and +# routs the packet to the specified nexthop. Afterwards, the packet is sent to +# the host hs-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. +# +# And when net.netfilter.nf_hooks_lwtunnel is set to 1 in rt-1 or rt-2, and a +# rpfilter iptables rule is added, SRv6 packets will go through netfilter PREROUTING +# hooks. +# +# +# +-------------------+ +-------------------+ +# | | | | +# | hs-1 netns | | hs-2 netns | +# | | | | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | cafe::1/64 | | | | cafe::2/64 | | +# | +-------------+ | | +-------------+ | +# | . | | . | +# +-------------------+ +-------------------+ +# . . +# . . +# . . +# +-----------------------------------+ +-----------------------------------+ +# | . | | . | +# | +---------------+ | | +---------------- | +# | | veth-t100 | | | | veth-t100 | | +# | | cafe::11/64 | +----------+ | | +----------+ | cafe::22/64 | | +# | +-------+-------+ | route | | | | route | +-------+-------- | +# | | table | | | | table | | +# | +----------+ | | +----------+ | +# | +--------------+ | | +--------------+ | +# | | veth0 | | | | veth0 | | +# | | 2001:11::1/64 |.|...|.| 2001:11::2/64 | | +# | +--------------+ | | +--------------+ | +# | | | | +# | rt-1 netns | | rt-2 netns | +# | | | | +# +-----------------------------------+ +-----------------------------------+ +# +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# | Network configuration | +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# +# rt-1: localsid table +# +----------------------------------------------------------------+ +# |SID |Action | +# +----------------------------------------------------------------+ +# |fc00:21:100::6004|apply SRv6 End.DX6 nh6 cafe::1 dev veth-t100 | +# +----------------------------------------------------------------+ +# +# rt-1: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |cafe::2 |apply seg6 encap segs fc00:12:100::6004| +# +---------------------------------------------------+ +# |cafe::/64 |forward to dev veth_t100 | +# +---------------------------------------------------+ +# +# +# rt-2: localsid table +# +---------------------------------------------------------------+ +# |SID |Action | +# +---------------------------------------------------------------+ +# |fc00:12:100::6004|apply SRv6 End.DX6 nh6 cafe::2 dev veth-t100 | +# +---------------------------------------------------------------+ +# +# rt-2: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |cafe::1 |apply seg6 encap segs fc00:21:100::6004| +# +---------------------------------------------------+ +# |cafe::/64 |forward to dev veth_t100 | +# +---------------------------------------------------+ +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +readonly IPv6_RT_NETWORK=2001:11 +readonly IPv6_HS_NETWORK=cafe +readonly SID_LOCATOR=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 netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip link set veth-rt-${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 nodad + ip -netns ${nsname} link set veth0 up + ip -netns ${nsname} link set lo up + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.forwarding=1 +} + +setup_rt_netfilter() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns exec ${nsname} sysctl -wq net.netfilter.nf_hooks_lwtunnel=1 + ip netns exec ${nsname} ip6tables -t raw -A PREROUTING -m rpfilter --invert -j DROP +} + +setup_hs() +{ + local hs=$1 + local rt=$2 + local tid=$3 + local hsname=hs-${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 ${IPv6_HS_NETWORK}::${hs}/64 dev veth0 nodad + ip -netns ${hsname} link set veth0 up + ip -netns ${hsname} link set lo up + + ip -netns ${rtname} addr add ${IPv6_HS_NETWORK}::${rt}${hs}/64 dev ${rtveth} + ip -netns ${rtname} link set ${rtveth} up + + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.${rtveth}.proxy_ndp=1 +} + +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-${rtdst} + local rtveth=veth-t${tid} + local vpn_sid=${SID_LOCATOR}:${hssrc}${hsdst}:${tid}::6004 + + ip -netns ${rtsrc_name} -6 neigh add proxy ${IPv6_HS_NETWORK}::${hsdst} dev ${rtveth} + + # set the encap route for encapsulating packets which arrive from the + # host hssrc and destined to the access router rtsrc. + ip -netns ${rtsrc_name} -6 route add ${IPv6_HS_NETWORK}::${hsdst}/128 \ + encap seg6 mode encap segs ${vpn_sid} dev veth0 + ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 \ + via 2001:11::${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 \ + encap seg6local action End.DX6 nh6 ${IPv6_HS_NETWORK}::${hsdst} dev veth-t${tid} +} + +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 + setup_hs 2 2 100 + + # setup the IPv4 L3 VPN which connects the host hs-1 and host hs-2. + 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 +} + +check_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + ip netns exec hs-${hssrc} ping -6 -c 1 -W ${PING_TIMEOUT_SEC} \ + ${IPv6_HS_NETWORK}::${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 $? 0 "Hosts connectivity: hs-${hssrc} -> hs-${hsdst} (tenant ${tid})" +} + +host_tests() +{ + log_section "SRv6 VPN connectivity test among hosts in the same tenant" + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +router_netfilter_tests() +{ + log_section "SRv6 VPN connectivity test with netfilter enabled in routers" + setup_rt_netfilter 1 + setup_rt_netfilter 2 + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +if [ "$(id -u)" -ne 0 ];then + 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 + +cleanup &>/dev/null + +setup + +host_tests +router_netfilter_tests + +print_log_test_results + +cleanup &>/dev/null + +exit ${ret}