This patchset adds two kfunc helpers, bpf_xdp_get_xfrm_state() and bpf_xdp_xfrm_state_release() that wrap xfrm_state_lookup() and xfrm_state_put(). The intent is to support software RSS (via XDP) for the ongoing/upcoming ipsec pcpu work [0]. Recent experiments performed on (hopefully) reproducible AWS testbeds indicate that single tunnel pcpu ipsec can reach line rate on 100G ENA nics.
Note this patchset only tests/shows generic xfrm_state access. The "secret sauce" (if you can really even call it that) involves accessing a soon-to-be-upstreamed pcpu_num field in xfrm_state. Early example is available here [1].
[0]: https://datatracker.ietf.org/doc/draft-ietf-ipsecme-multi-sa-performance/03/ [1]: https://github.com/danobi/xdp-tools/blob/e89a1c617aba3b50d990f779357d6ce2863...
Changes from v1: * Move xfrm tunnel tests to test_progs * Fix writing to opts->error when opts is invalid * Use __bpf_kfunc_start_defs() * Remove unused vxlanhdr definition * Add and use BPF_CORE_WRITE_BITFIELD() macro * Make series bisect clean
Changes from RFCv2: * Rebased to ipsec-next * Fix netns leak
Changes from RFCv1: * Add Antony's commit tags * Add KF_ACQUIRE and KF_RELEASE semantics
Daniel Xu (6): bpf: xfrm: Add bpf_xdp_get_xfrm_state() kfunc bpf: xfrm: Add bpf_xdp_xfrm_state_release() kfunc libbpf: Add BPF_CORE_WRITE_BITFIELD() macro bpf: selftests: test_tunnel: Use vmlinux.h declarations bpf: selftests: Move xfrm tunnel test to test_progs bpf: xfrm: Add selftest for bpf_xdp_get_xfrm_state()
include/net/xfrm.h | 9 + net/xfrm/Makefile | 1 + net/xfrm/xfrm_policy.c | 2 + net/xfrm/xfrm_state_bpf.c | 128 +++++++++++++++ tools/lib/bpf/bpf_core_read.h | 36 ++++ .../selftests/bpf/prog_tests/test_tunnel.c | 155 ++++++++++++++++++ .../selftests/bpf/progs/bpf_tracing_net.h | 1 + .../selftests/bpf/progs/test_tunnel_kern.c | 138 +++++++++------- tools/testing/selftests/bpf/test_tunnel.sh | 92 ----------- 9 files changed, 412 insertions(+), 150 deletions(-) create mode 100644 net/xfrm/xfrm_state_bpf.c
vmlinux.h declarations are more ergnomic, especially when working with kfuncs. The uapi headers are often incomplete for kfunc definitions.
This commit also switches bitfield accesses to use CO-RE helpers. Switching to vmlinux.h definitions makes the verifier very unhappy with raw bitfield accesses. The error is:
; md.u.md2.dir = direction; 33: (69) r1 = *(u16 *)(r2 +11) misaligned stack access off (0x0; 0x0)+-64+11 size 2
Fix by using CO-RE-aware bitfield reads and writes.
Co-developed-by: Antony Antony antony.antony@secunet.com Signed-off-by: Antony Antony antony.antony@secunet.com Signed-off-by: Daniel Xu dxu@dxuuu.xyz --- .../selftests/bpf/progs/bpf_tracing_net.h | 1 + .../selftests/bpf/progs/test_tunnel_kern.c | 76 +++++-------------- 2 files changed, 22 insertions(+), 55 deletions(-)
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 0b793a102791..1bdc680b0e0e 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -26,6 +26,7 @@ #define IPV6_AUTOFLOWLABEL 70
#define TC_ACT_UNSPEC (-1) +#define TC_ACT_OK 0 #define TC_ACT_SHOT 2
#define SOL_TCP 6 diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index f66af753bbbb..b320fb7bb080 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -6,62 +6,26 @@ * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */ -#include <stddef.h> -#include <string.h> -#include <arpa/inet.h> -#include <linux/bpf.h> -#include <linux/if_ether.h> -#include <linux/if_packet.h> -#include <linux/if_tunnel.h> -#include <linux/ip.h> -#include <linux/ipv6.h> -#include <linux/icmp.h> -#include <linux/types.h> -#include <linux/socket.h> -#include <linux/pkt_cls.h> -#include <linux/erspan.h> -#include <linux/udp.h> +#include "vmlinux.h" +#include <bpf/bpf_core_read.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> +#include "bpf_kfuncs.h" +#include "bpf_tracing_net.h"
#define log_err(__ret) bpf_printk("ERROR line:%d ret:%d\n", __LINE__, __ret)
-#define VXLAN_UDP_PORT 4789 +#define VXLAN_UDP_PORT 4789 +#define ETH_P_IP 0x0800 +#define PACKET_HOST 0 +#define TUNNEL_CSUM bpf_htons(0x01) +#define TUNNEL_KEY bpf_htons(0x04)
/* Only IPv4 address assigned to veth1. * 172.16.1.200 */ #define ASSIGNED_ADDR_VETH1 0xac1001c8
-struct geneve_opt { - __be16 opt_class; - __u8 type; - __u8 length:5; - __u8 r3:1; - __u8 r2:1; - __u8 r1:1; - __u8 opt_data[8]; /* hard-coded to 8 byte */ -}; - -struct vxlanhdr { - __be32 vx_flags; - __be32 vx_vni; -} __attribute__((packed)); - -struct vxlan_metadata { - __u32 gbp; -}; - -struct bpf_fou_encap { - __be16 sport; - __be16 dport; -}; - -enum bpf_fou_encap_type { - FOU_BPF_ENCAP_FOU, - FOU_BPF_ENCAP_GUE, -}; - int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx, struct bpf_fou_encap *encap, int type) __ksym; int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx, @@ -205,9 +169,9 @@ int erspan_set_tunnel(struct __sk_buff *skb) __u8 hwid = 7;
md.version = 2; - md.u.md2.dir = direction; - md.u.md2.hwid = hwid & 0xf; - md.u.md2.hwid_upper = (hwid >> 4) & 0x3; + BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction); + BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf)); + BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3); #endif
ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); @@ -246,8 +210,9 @@ int erspan_get_tunnel(struct __sk_buff *skb) bpf_printk("\tindex %x\n", index); #else bpf_printk("\tdirection %d hwid %x timestamp %u\n", - md.u.md2.dir, - (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + BPF_CORE_READ_BITFIELD(&md.u.md2, dir), + (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) + + BPF_CORE_READ_BITFIELD(&md.u.md2, hwid), bpf_ntohl(md.u.md2.timestamp)); #endif
@@ -284,9 +249,9 @@ int ip4ip6erspan_set_tunnel(struct __sk_buff *skb) __u8 hwid = 17;
md.version = 2; - md.u.md2.dir = direction; - md.u.md2.hwid = hwid & 0xf; - md.u.md2.hwid_upper = (hwid >> 4) & 0x3; + BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction); + BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf)); + BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3); #endif
ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); @@ -326,8 +291,9 @@ int ip4ip6erspan_get_tunnel(struct __sk_buff *skb) bpf_printk("\tindex %x\n", index); #else bpf_printk("\tdirection %d hwid %x timestamp %u\n", - md.u.md2.dir, - (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + BPF_CORE_READ_BITFIELD(&md.u.md2, dir), + (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) + + BPF_CORE_READ_BITFIELD(&md.u.md2, hwid), bpf_ntohl(md.u.md2.timestamp)); #endif
test_progs is better than a shell script b/c C is a bit easier to maintain than shell. Also it's easier to use new infra like memory mapped global variables from C via bpf skeleton.
Co-developed-by: Antony Antony antony.antony@secunet.com Signed-off-by: Antony Antony antony.antony@secunet.com Signed-off-by: Daniel Xu dxu@dxuuu.xyz --- .../selftests/bpf/prog_tests/test_tunnel.c | 143 ++++++++++++++++++ .../selftests/bpf/progs/test_tunnel_kern.c | 11 +- tools/testing/selftests/bpf/test_tunnel.sh | 92 ----------- 3 files changed, 151 insertions(+), 95 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c index d149ab98798d..3bcb6f96b9b5 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c +++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c @@ -50,6 +50,7 @@ */
#include <arpa/inet.h> +#include <linux/if_link.h> #include <linux/if_tun.h> #include <linux/limits.h> #include <linux/sysctl.h> @@ -92,6 +93,11 @@ #define IPIP_TUNL_DEV0 "ipip00" #define IPIP_TUNL_DEV1 "ipip11"
+#define XFRM_AUTH "0x1111111111111111111111111111111111111111" +#define XFRM_ENC "0x22222222222222222222222222222222" +#define XFRM_SPI_IN_TO_OUT 0x1 +#define XFRM_SPI_OUT_TO_IN 0x2 + #define PING_ARGS "-i 0.01 -c 3 -w 10 -q"
static int config_device(void) @@ -264,6 +270,92 @@ static void delete_ipip_tunnel(void) SYS_NOFAIL("ip fou del port 5555 2> /dev/null"); }
+static int add_xfrm_tunnel(void) +{ + /* at_ns0 namespace + * at_ns0 -> root + */ + SYS(fail, + "ip netns exec at_ns0 " + "ip xfrm state add src %s dst %s proto esp " + "spi %d reqid 1 mode tunnel " + "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", + IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC); + SYS(fail, + "ip netns exec at_ns0 " + "ip xfrm policy add src %s/32 dst %s/32 dir out " + "tmpl src %s dst %s proto esp reqid 1 " + "mode tunnel", + IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1, IP4_ADDR_VETH0, IP4_ADDR1_VETH1); + + /* root -> at_ns0 */ + SYS(fail, + "ip netns exec at_ns0 " + "ip xfrm state add src %s dst %s proto esp " + "spi %d reqid 2 mode tunnel " + "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", + IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC); + SYS(fail, + "ip netns exec at_ns0 " + "ip xfrm policy add src %s/32 dst %s/32 dir in " + "tmpl src %s dst %s proto esp reqid 2 " + "mode tunnel", + IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0, IP4_ADDR1_VETH1, IP4_ADDR_VETH0); + + /* address & route */ + SYS(fail, "ip netns exec at_ns0 ip addr add dev veth0 %s/32", + IP4_ADDR_TUNL_DEV0); + SYS(fail, "ip netns exec at_ns0 ip route add %s dev veth0 via %s src %s", + IP4_ADDR_TUNL_DEV1, IP4_ADDR1_VETH1, IP4_ADDR_TUNL_DEV0); + + /* root namespace + * at_ns0 -> root + */ + SYS(fail, + "ip xfrm state add src %s dst %s proto esp " + "spi %d reqid 1 mode tunnel " + "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", + IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC); + SYS(fail, + "ip xfrm policy add src %s/32 dst %s/32 dir in " + "tmpl src %s dst %s proto esp reqid 1 " + "mode tunnel", + IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1, IP4_ADDR_VETH0, IP4_ADDR1_VETH1); + + /* root -> at_ns0 */ + SYS(fail, + "ip xfrm state add src %s dst %s proto esp " + "spi %d reqid 2 mode tunnel " + "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", + IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC); + SYS(fail, + "ip xfrm policy add src %s/32 dst %s/32 dir out " + "tmpl src %s dst %s proto esp reqid 2 " + "mode tunnel", + IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0, IP4_ADDR1_VETH1, IP4_ADDR_VETH0); + + /* address & route */ + SYS(fail, "ip addr add dev veth1 %s/32", IP4_ADDR_TUNL_DEV1); + SYS(fail, "ip route add %s dev veth1 via %s src %s", + IP4_ADDR_TUNL_DEV0, IP4_ADDR_VETH0, IP4_ADDR_TUNL_DEV1); + + return 0; +fail: + return -1; +} + +static void delete_xfrm_tunnel(void) +{ + SYS_NOFAIL("ip xfrm policy delete dir out src %s/32 dst %s/32 2> /dev/null", + IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0); + SYS_NOFAIL("ip xfrm policy delete dir in src %s/32 dst %s/32 2> /dev/null", + IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1); + SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d 2> /dev/null", + IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT); + SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d 2> /dev/null", + IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN); +} + static int test_ping(int family, const char *addr) { SYS(fail, "%s %s %s > /dev/null", ping_command(family), PING_ARGS, addr); @@ -532,6 +624,56 @@ static void test_ipip_tunnel(enum ipip_encap encap) test_tunnel_kern__destroy(skel); }
+static void test_xfrm_tunnel(void) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, + .attach_point = BPF_TC_INGRESS); + struct test_tunnel_kern *skel = NULL; + struct nstoken *nstoken; + int tc_prog_fd; + int ifindex; + int err; + + err = add_xfrm_tunnel(); + if (!ASSERT_OK(err, "add_xfrm_tunnel")) + return; + + skel = test_tunnel_kern__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) + goto done; + + ifindex = if_nametoindex("veth1"); + if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex")) + goto done; + + /* attach tc prog to tunnel dev */ + tc_hook.ifindex = ifindex; + tc_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state); + if (!ASSERT_GE(tc_prog_fd, 0, "bpf_program__fd")) + goto done; + if (attach_tc_prog(&tc_hook, tc_prog_fd, -1)) + goto done; + + /* ping from at_ns0 namespace test */ + nstoken = open_netns("at_ns0"); + err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1); + close_netns(nstoken); + if (!ASSERT_OK(err, "test_ping")) + goto done; + + if (!ASSERT_EQ(skel->bss->xfrm_reqid, 1, "req_id")) + goto done; + if (!ASSERT_EQ(skel->bss->xfrm_spi, XFRM_SPI_IN_TO_OUT, "spi")) + goto done; + if (!ASSERT_EQ(skel->bss->xfrm_remote_ip, 0xac100164, "remote_ip")) + goto done; + +done: + delete_xfrm_tunnel(); + if (skel) + test_tunnel_kern__destroy(skel); +} + #define RUN_TEST(name, ...) \ ({ \ if (test__start_subtest(#name)) { \ @@ -549,6 +691,7 @@ static void *test_tunnel_run_tests(void *arg) RUN_TEST(ipip_tunnel, NONE); RUN_TEST(ipip_tunnel, FOU); RUN_TEST(ipip_tunnel, GUE); + RUN_TEST(xfrm_tunnel);
cleanup();
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index b320fb7bb080..3a59eb9c34de 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -929,6 +929,10 @@ int ip6ip6_get_tunnel(struct __sk_buff *skb) return TC_ACT_OK; }
+volatile int xfrm_reqid = 0; +volatile int xfrm_spi = 0; +volatile int xfrm_remote_ip = 0; + SEC("tc") int xfrm_get_state(struct __sk_buff *skb) { @@ -939,9 +943,10 @@ int xfrm_get_state(struct __sk_buff *skb) if (ret < 0) return TC_ACT_OK;
- bpf_printk("reqid %d spi 0x%x remote ip 0x%x\n", - x.reqid, bpf_ntohl(x.spi), - bpf_ntohl(x.remote_ipv4)); + xfrm_reqid = x.reqid; + xfrm_spi = bpf_ntohl(x.spi); + xfrm_remote_ip = bpf_ntohl(x.remote_ipv4); + return TC_ACT_OK; }
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index 2dec7dbf29a2..d9661b9988ba 100755 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -517,90 +517,6 @@ test_ip6ip6() echo -e ${GREEN}"PASS: ip6$TYPE"${NC} }
-setup_xfrm_tunnel() -{ - auth=0x$(printf '1%.0s' {1..40}) - enc=0x$(printf '2%.0s' {1..32}) - spi_in_to_out=0x1 - spi_out_to_in=0x2 - # at_ns0 namespace - # at_ns0 -> root - ip netns exec at_ns0 \ - ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ - spi $spi_in_to_out reqid 1 mode tunnel \ - auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc - ip netns exec at_ns0 \ - ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \ - tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ - mode tunnel - # root -> at_ns0 - ip netns exec at_ns0 \ - ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ - spi $spi_out_to_in reqid 2 mode tunnel \ - auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc - ip netns exec at_ns0 \ - ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \ - tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ - mode tunnel - # address & route - ip netns exec at_ns0 \ - ip addr add dev veth0 10.1.1.100/32 - ip netns exec at_ns0 \ - ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \ - src 10.1.1.100 - - # root namespace - # at_ns0 -> root - ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ - spi $spi_in_to_out reqid 1 mode tunnel \ - auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc - ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \ - tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ - mode tunnel - # root -> at_ns0 - ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ - spi $spi_out_to_in reqid 2 mode tunnel \ - auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc - ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \ - tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ - mode tunnel - # address & route - ip addr add dev veth1 10.1.1.200/32 - ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200 -} - -test_xfrm_tunnel() -{ - if [[ -e /sys/kernel/tracing/trace ]]; then - TRACE=/sys/kernel/tracing/trace - else - TRACE=/sys/kernel/debug/tracing/trace - fi - config_device - > ${TRACE} - setup_xfrm_tunnel - mkdir -p ${BPF_PIN_TUNNEL_DIR} - bpftool prog loadall ${BPF_FILE} ${BPF_PIN_TUNNEL_DIR} - tc qdisc add dev veth1 clsact - tc filter add dev veth1 proto ip ingress bpf da object-pinned \ - ${BPF_PIN_TUNNEL_DIR}/xfrm_get_state - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - sleep 1 - grep "reqid 1" ${TRACE} - check_err $? - grep "spi 0x1" ${TRACE} - check_err $? - grep "remote ip 0xac100164" ${TRACE} - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: xfrm tunnel"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: xfrm tunnel"${NC} -} - attach_bpf() { DEV=$1 @@ -630,10 +546,6 @@ cleanup() ip link del ip6geneve11 2> /dev/null ip link del erspan11 2> /dev/null ip link del ip6erspan11 2> /dev/null - ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null - ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null - ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null - ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null }
cleanup_exit() @@ -716,10 +628,6 @@ bpf_tunnel_test() test_ip6ip6 errors=$(( $errors + $? ))
- echo "Testing IPSec tunnel..." - test_xfrm_tunnel - errors=$(( $errors + $? )) - return $errors }
This commit extends test_tunnel selftest to test the new XDP xfrm state lookup kfunc.
Co-developed-by: Antony Antony antony.antony@secunet.com Signed-off-by: Antony Antony antony.antony@secunet.com Signed-off-by: Daniel Xu dxu@dxuuu.xyz --- .../selftests/bpf/prog_tests/test_tunnel.c | 20 ++++++-- .../selftests/bpf/progs/test_tunnel_kern.c | 51 +++++++++++++++++++ 2 files changed, 67 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c index 3bcb6f96b9b5..54308afb3cdc 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c +++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c @@ -278,7 +278,7 @@ static int add_xfrm_tunnel(void) SYS(fail, "ip netns exec at_ns0 " "ip xfrm state add src %s dst %s proto esp " - "spi %d reqid 1 mode tunnel " + "spi %d reqid 1 mode tunnel replay-window 42 " "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC); SYS(fail, @@ -292,7 +292,7 @@ static int add_xfrm_tunnel(void) SYS(fail, "ip netns exec at_ns0 " "ip xfrm state add src %s dst %s proto esp " - "spi %d reqid 2 mode tunnel " + "spi %d reqid 2 mode tunnel replay-window 42 " "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC); SYS(fail, @@ -313,7 +313,7 @@ static int add_xfrm_tunnel(void) */ SYS(fail, "ip xfrm state add src %s dst %s proto esp " - "spi %d reqid 1 mode tunnel " + "spi %d reqid 1 mode tunnel replay-window 42 " "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC); SYS(fail, @@ -325,7 +325,7 @@ static int add_xfrm_tunnel(void) /* root -> at_ns0 */ SYS(fail, "ip xfrm state add src %s dst %s proto esp " - "spi %d reqid 2 mode tunnel " + "spi %d reqid 2 mode tunnel replay-window 42 " "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC); SYS(fail, @@ -628,8 +628,10 @@ static void test_xfrm_tunnel(void) { DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); + LIBBPF_OPTS(bpf_xdp_attach_opts, opts); struct test_tunnel_kern *skel = NULL; struct nstoken *nstoken; + int xdp_prog_fd; int tc_prog_fd; int ifindex; int err; @@ -654,6 +656,14 @@ static void test_xfrm_tunnel(void) if (attach_tc_prog(&tc_hook, tc_prog_fd, -1)) goto done;
+ /* attach xdp prog to tunnel dev */ + xdp_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state_xdp); + if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__fd")) + goto done; + err = bpf_xdp_attach(ifindex, xdp_prog_fd, XDP_FLAGS_REPLACE, &opts); + if (!ASSERT_OK(err, "bpf_xdp_attach")) + goto done; + /* ping from at_ns0 namespace test */ nstoken = open_netns("at_ns0"); err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1); @@ -667,6 +677,8 @@ static void test_xfrm_tunnel(void) goto done; if (!ASSERT_EQ(skel->bss->xfrm_remote_ip, 0xac100164, "remote_ip")) goto done; + if (!ASSERT_EQ(skel->bss->xfrm_replay_window, 42, "replay_window")) + goto done;
done: delete_xfrm_tunnel(); diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 3a59eb9c34de..c0dd38616562 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -30,6 +30,10 @@ int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx, struct bpf_fou_encap *encap, int type) __ksym; int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx, struct bpf_fou_encap *encap) __ksym; +struct xfrm_state * +bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts, + u32 opts__sz) __ksym; +void bpf_xdp_xfrm_state_release(struct xfrm_state *x) __ksym;
struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -950,4 +954,51 @@ int xfrm_get_state(struct __sk_buff *skb) return TC_ACT_OK; }
+volatile int xfrm_replay_window = 0; + +SEC("xdp") +int xfrm_get_state_xdp(struct xdp_md *xdp) +{ + struct bpf_xfrm_state_opts opts = {}; + struct xfrm_state *x = NULL; + struct ip_esp_hdr *esph; + struct bpf_dynptr ptr; + u8 esph_buf[8] = {}; + u8 iph_buf[20] = {}; + struct iphdr *iph; + u32 off; + + if (bpf_dynptr_from_xdp(xdp, 0, &ptr)) + goto out; + + off = sizeof(struct ethhdr); + iph = bpf_dynptr_slice(&ptr, off, iph_buf, sizeof(iph_buf)); + if (!iph || iph->protocol != IPPROTO_ESP) + goto out; + + off += sizeof(struct iphdr); + esph = bpf_dynptr_slice(&ptr, off, esph_buf, sizeof(esph_buf)); + if (!esph) + goto out; + + opts.netns_id = BPF_F_CURRENT_NETNS; + opts.daddr.a4 = iph->daddr; + opts.spi = esph->spi; + opts.proto = IPPROTO_ESP; + opts.family = AF_INET; + + x = bpf_xdp_get_xfrm_state(xdp, &opts, sizeof(opts)); + if (!x || opts.error) + goto out; + + if (!x->replay_esn) + goto out; + + xfrm_replay_window = x->replay_esn->replay_window; +out: + if (x) + bpf_xdp_xfrm_state_release(x); + return XDP_PASS; +} + char _license[] SEC("license") = "GPL";
linux-kselftest-mirror@lists.linaro.org
-
Daniel Xu