[bpf-next,v2,05/13] selftests/bpf: extend bpf tunnel test with gre

Message ID	20190322151504.89983-6-willemdebruijn.kernel@gmail.com
State	Changes Requested
Headers	show Return-Path: <netdev-owner@vger.kernel.org> From: Willem de Bruijn <willemdebruijn.kernel@gmail.com> To: netdev@vger.kernel.org Cc: ast@kernel.org, daniel@iogearbox.net, alan.maguire@oracle.com, Willem de Bruijn <willemb@google.com> Subject: [PATCH bpf-next v2 05/13] selftests/bpf: extend bpf tunnel test with gre Date: Fri, 22 Mar 2019 11:14:56 -0400 Message-Id: <20190322151504.89983-6-willemdebruijn.kernel@gmail.com> In-Reply-To: <20190322151504.89983-1-willemdebruijn.kernel@gmail.com> References: <20190322151504.89983-1-willemdebruijn.kernel@gmail.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: netdev-owner@vger.kernel.org Precedence: bulk
Series	bpf tc tunneling \| expand [bpf-next,v2,00/13] bpf tc tunneling [bpf-next,v2,01/13] bpf: in bpf_skb_adjust_room avoid copy in tx fast path [bpf-next,v2,02/13] selftests/bpf: bpf tunnel encap test [bpf-next,v2,03/13] selftests/bpf: expand bpf tunnel test with decap [bpf-next,v2,04/13] selftests/bpf: expand bpf tunnel test to ipv6 [bpf-next,v2,05/13] selftests/bpf: extend bpf tunnel test with gre [bpf-next,v2,06/13] selftests/bpf: extend bpf tunnel test with tso [bpf-next,v2,07/13] bpf: add bpf_skb_adjust_room mode BPF_ADJ_ROOM_MAC [bpf-next,v2,08/13] bpf: add bpf_skb_adjust_room flag BPF_F_ADJ_ROOM_FIXED_GSO [bpf-next,v2,09/13] bpf: add bpf_skb_adjust_room encap flags [bpf-next,v2,10/13] bpf: Sync bpf.h to tools [bpf-next,v2,11/13] selftests/bpf: convert bpf tunnel test to BPF_ADJ_ROOM_MAC [bpf-next,v2,12/13] selftests/bpf: convert bpf tunnel test to BPF_F_ADJ_ROOM_FIXED_GSO [bpf-next,v2,13/13] selftests/bpf: convert bpf tunnel test to encap modes

diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c index 591f540ce513..900c5653105f 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -2,6 +2,9 @@ /* In-place tunneling */ +#include <stdbool.h> +#include <string.h> + #include <linux/stddef.h> #include <linux/bpf.h> #include <linux/if_ether.h> @@ -17,6 +20,18 @@ static const int cfg_port = 8000; +struct grev4hdr { + struct iphdr ip; + __be16 flags; + __be16 protocol; +} __attribute__((packed)); + +struct grev6hdr { + struct ipv6hdr ip; + __be16 flags; + __be16 protocol; +} __attribute__((packed)); + static __always_inline void set_ipv4_csum(struct iphdr *iph) { __u16 *iph16 = (__u16 *)iph; @@ -32,10 +47,12 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph) iph->check = ~((csum & 0xffff) + (csum >> 16)); } -static int encap_ipv4(struct __sk_buff *skb) +static __always_inline int encap_ipv4(struct __sk_buff *skb, bool with_gre) { - struct iphdr iph_outer, iph_inner; + struct grev4hdr h_outer; + struct iphdr iph_inner; struct tcphdr tcph; + int olen; if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, sizeof(iph_inner)) < 0) @@ -52,24 +69,33 @@ static int encap_ipv4(struct __sk_buff *skb) if (tcph.dest != __bpf_constant_htons(cfg_port)) return TC_ACT_OK; + olen = with_gre ? sizeof(h_outer) : sizeof(h_outer.ip); + /* add room between mac and network header */ - if (bpf_skb_adjust_room(skb, sizeof(iph_outer), BPF_ADJ_ROOM_NET, 0)) + if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_NET, 0)) return TC_ACT_SHOT; /* prepare new outer network header */ - iph_outer = iph_inner; - iph_outer.protocol = IPPROTO_IPIP; - iph_outer.tot_len = bpf_htons(sizeof(iph_outer) + - bpf_htons(iph_outer.tot_len)); - set_ipv4_csum(&iph_outer); + h_outer.ip = iph_inner; + h_outer.ip.tot_len = bpf_htons(olen + + bpf_htons(h_outer.ip.tot_len)); + if (with_gre) { + h_outer.ip.protocol = IPPROTO_GRE; + h_outer.protocol = bpf_htons(ETH_P_IP); + h_outer.flags = 0; + } else { + h_outer.ip.protocol = IPPROTO_IPIP; + } + + set_ipv4_csum((void *)&h_outer.ip); /* store new outer network header */ - if (bpf_skb_store_bytes(skb, ETH_HLEN, &iph_outer, sizeof(iph_outer), + if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, BPF_F_INVALIDATE_HASH) < 0) return TC_ACT_SHOT; /* bpf_skb_adjust_room has moved header to start of room: restore */ - if (bpf_skb_store_bytes(skb, ETH_HLEN + sizeof(iph_outer), + if (bpf_skb_store_bytes(skb, ETH_HLEN + olen, &iph_inner, sizeof(iph_inner), BPF_F_INVALIDATE_HASH) < 0) return TC_ACT_SHOT; @@ -77,10 +103,12 @@ static int encap_ipv4(struct __sk_buff *skb) return TC_ACT_OK; } -static int encap_ipv6(struct __sk_buff *skb) +static __always_inline int encap_ipv6(struct __sk_buff *skb, bool with_gre) { - struct ipv6hdr iph_outer, iph_inner; + struct ipv6hdr iph_inner; + struct grev6hdr h_outer; struct tcphdr tcph; + int olen; if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, sizeof(iph_inner)) < 0) @@ -94,23 +122,31 @@ static int encap_ipv6(struct __sk_buff *skb) if (tcph.dest != __bpf_constant_htons(cfg_port)) return TC_ACT_OK; + olen = with_gre ? sizeof(h_outer) : sizeof(h_outer.ip); + /* add room between mac and network header */ - if (bpf_skb_adjust_room(skb, sizeof(iph_outer), BPF_ADJ_ROOM_NET, 0)) + if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_NET, 0)) return TC_ACT_SHOT; /* prepare new outer network header */ - iph_outer = iph_inner; - iph_outer.nexthdr = IPPROTO_IPV6; - iph_outer.payload_len = bpf_htons(sizeof(iph_outer) + - bpf_ntohs(iph_outer.payload_len)); + h_outer.ip = iph_inner; + h_outer.ip.payload_len = bpf_htons(olen + + bpf_ntohs(h_outer.ip.payload_len)); + if (with_gre) { + h_outer.ip.nexthdr = IPPROTO_GRE; + h_outer.protocol = bpf_htons(ETH_P_IPV6); + h_outer.flags = 0; + } else { + h_outer.ip.nexthdr = IPPROTO_IPV6; + } /* store new outer network header */ - if (bpf_skb_store_bytes(skb, ETH_HLEN, &iph_outer, sizeof(iph_outer), + if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, BPF_F_INVALIDATE_HASH) < 0) return TC_ACT_SHOT; /* bpf_skb_adjust_room has moved header to start of room: restore */ - if (bpf_skb_store_bytes(skb, ETH_HLEN + sizeof(iph_outer), + if (bpf_skb_store_bytes(skb, ETH_HLEN + olen, &iph_inner, sizeof(iph_inner), BPF_F_INVALIDATE_HASH) < 0) return TC_ACT_SHOT; @@ -118,28 +154,63 @@ static int encap_ipv6(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap") -int encap_f(struct __sk_buff *skb) +SEC("encap_ipip") +int __encap_ipip(struct __sk_buff *skb) { - switch (skb->protocol) { - case __bpf_constant_htons(ETH_P_IP): - return encap_ipv4(skb); - case __bpf_constant_htons(ETH_P_IPV6): - return encap_ipv6(skb); - default: - /* does not match, ignore */ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, false); + else return TC_ACT_OK; - } } -static int decap_internal(struct __sk_buff *skb, int off, int len) +SEC("encap_gre") +int __encap_gre(struct __sk_buff *skb) { - char buf[sizeof(struct ipv6hdr)]; + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, true); + else + return TC_ACT_OK; +} - if (bpf_skb_load_bytes(skb, off + len, &buf, len) < 0) +SEC("encap_ip6tnl") +int __encap_ip6tnl(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, false); + else + return TC_ACT_OK; +} + +SEC("encap_ip6gre") +int __encap_ip6gre(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, true); + else return TC_ACT_OK; +} - if (bpf_skb_adjust_room(skb, -len, BPF_ADJ_ROOM_NET, 0)) +static int decap_internal(struct __sk_buff *skb, int off, int len, char proto) +{ + char buf[sizeof(struct grev6hdr)]; + int olen; + + switch (proto) { + case IPPROTO_IPIP: + case IPPROTO_IPV6: + olen = len; + break; + case IPPROTO_GRE: + olen = len + 4 /* gre hdr */; + break; + default: + return TC_ACT_OK; + } + + if (bpf_skb_load_bytes(skb, off + olen, &buf, olen) < 0) + return TC_ACT_OK; + + if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_NET, 0)) return TC_ACT_SHOT; /* bpf_skb_adjust_room has moved outer over inner header: restore */ @@ -157,10 +228,11 @@ static int decap_ipv4(struct __sk_buff *skb) sizeof(iph_outer)) < 0) return TC_ACT_OK; - if (iph_outer.ihl != 5 || iph_outer.protocol != IPPROTO_IPIP) + if (iph_outer.ihl != 5) return TC_ACT_OK; - return decap_internal(skb, ETH_HLEN, sizeof(iph_outer)); + return decap_internal(skb, ETH_HLEN, sizeof(iph_outer), + iph_outer.protocol); } static int decap_ipv6(struct __sk_buff *skb) @@ -171,10 +243,8 @@ static int decap_ipv6(struct __sk_buff *skb) sizeof(iph_outer)) < 0) return TC_ACT_OK; - if (iph_outer.nexthdr != IPPROTO_IPV6) - return TC_ACT_OK; - - return decap_internal(skb, ETH_HLEN, sizeof(iph_outer)); + return decap_internal(skb, ETH_HLEN, sizeof(iph_outer), + iph_outer.nexthdr); } SEC("decap") diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index 7b1758f3006b..c78922048610 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -54,30 +54,36 @@ set -e # no arguments: automated test, run all if [[ "$#" -eq "0" ]]; then echo "ipip" - $0 ipv4 + $0 ipv4 ipip echo "ip6ip6" - $0 ipv6 + $0 ipv6 ip6tnl + + echo "ip gre" + $0 ipv4 gre + + echo "ip6 gre" + $0 ipv6 ip6gre echo "OK. All tests passed" exit 0 fi -if [[ "$#" -ne "1" ]]; then +if [[ "$#" -ne "2" ]]; then echo "Usage: $0" - echo " or: $0 <ipv4|ipv6>" + echo " or: $0 <ipv4|ipv6> <tuntype>" exit 1 fi case "$1" in "ipv4") - readonly tuntype=ipip + readonly tuntype=$2 readonly addr1="${ns1_v4}" readonly addr2="${ns2_v4}" readonly netcat_opt=-4 ;; "ipv6") - readonly tuntype=ip6tnl + readonly tuntype=$2 readonly addr1="${ns1_v6}" readonly addr2="${ns2_v6}" readonly netcat_opt=-6 @@ -103,7 +109,8 @@ client_connect # client can no longer connect ip netns exec "${ns1}" tc qdisc add dev veth1 clsact ip netns exec "${ns1}" tc filter add dev veth1 egress \ - bpf direct-action object-file ./test_tc_tunnel.o section encap + bpf direct-action object-file ./test_tc_tunnel.o \ + section "encap_${tuntype}" echo "test bpf encap without decap (expect failure)" server_listen ! client_connect

[bpf-next,v2,05/13] selftests/bpf: extend bpf tunnel test with gre

Commit Message

Patch