@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Send TCP segments with fixed or incrementing IPv4 IDs, optionally in
+ * VXLAN, and report the IP IDs of TCP segments received on a device,
+ * also inside IPIP, GRE, VXLAN or ESP.
+ *
+ * tx: tcp_fixedid -T -i dev -M dmac -s saddr -d daddr [-f] [-n segs]
+ * [-b bursts] [-l len] [-V osaddr,odaddr -m inner_dmac [-F]]
+ * rx: tcp_fixedid -R -i dev [-f] [-c segs] [-w ms]
+ *
+ * The receiver prints "ready" once it is bound, then the number of
+ * segments, of segments with an outer IPv4 header, of distinct outer and
+ * inner IDs, and of inner IDs the sender did not use: other than the fixed
+ * ID with -f, outside the incrementing range of segs IDs without it.
+ */
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/if_packet.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <time.h>
+#include <unistd.h>
+
+#define TEST_PORT 9000
+#define VXLAN_PORT 4789
+#define FIXED_ID 0x1234
+#define INCR_ID 0x1000
+
+static const char *ifname;
+static bool fixed_id, fixed_outer;
+static int segs = 40, bursts = 10, len = 1000, wait_ms = 2000, stop;
+static struct in_addr saddr, daddr, osaddr, odaddr;
+static bool vxlan;
+static unsigned char dmac[ETH_ALEN], inner_dmac[ETH_ALEN];
+
+static void parse_mac(const char *s, unsigned char *mac)
+{
+ if (sscanf(s, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", &mac[0], &mac[1],
+ &mac[2], &mac[3], &mac[4], &mac[5]) != 6)
+ error(1, 0, "bad mac %s", s);
+}
+
+static void parse_addr(const char *s, struct in_addr *a)
+{
+ if (inet_pton(AF_INET, s, a) != 1)
+ error(1, 0, "bad address %s", s);
+}
+
+static uint32_t csum_add(uint32_t sum, const void *data, size_t n)
+{
+ const uint8_t *p = data;
+
+ while (n > 1) {
+ sum += (p[0] << 8) | p[1];
+ p += 2;
+ n -= 2;
+ }
+ if (n)
+ sum += p[0] << 8;
+ return sum;
+}
+
+static uint16_t csum_fold(uint32_t sum)
+{
+ while (sum >> 16)
+ sum = (sum & 0xffff) + (sum >> 16);
+ return htons(~sum & 0xffff);
+}
+
+static void build_ip(struct iphdr *iph, int proto, int payload, uint16_t id,
+ struct in_addr s, struct in_addr d)
+{
+ memset(iph, 0, sizeof(*iph));
+ iph->version = 4;
+ iph->ihl = 5;
+ iph->tot_len = htons(sizeof(*iph) + payload);
+ iph->id = htons(id);
+ iph->frag_off = htons(IP_DF);
+ iph->ttl = 64;
+ iph->protocol = proto;
+ iph->saddr = s.s_addr;
+ iph->daddr = d.s_addr;
+ iph->check = csum_fold(csum_add(0, iph, sizeof(*iph)));
+}
+
+/* Ethernet, IPv4 and TCP header plus payload for segment @i at @p */
+static int build_tcp(unsigned char *p, const unsigned char *mac, int i,
+ uint16_t id)
+{
+ struct ethhdr *eth = (struct ethhdr *)p;
+ struct iphdr *iph = (struct iphdr *)(eth + 1);
+ struct tcphdr *th = (struct tcphdr *)(iph + 1);
+ struct {
+ uint32_t s, d;
+ uint8_t zero, proto;
+ uint16_t len;
+ } ph; /* 12 bytes, no padding */
+ uint32_t sum;
+
+ memcpy(eth->h_dest, mac, ETH_ALEN);
+ memset(eth->h_source, 0, ETH_ALEN);
+ eth->h_source[0] = 0x02;
+ eth->h_source[5] = 0x01;
+ eth->h_proto = htons(ETH_P_IP);
+ build_ip(iph, IPPROTO_TCP, sizeof(*th) + len, id, saddr, daddr);
+
+ memset(th, 0, sizeof(*th));
+ th->source = htons(TEST_PORT + 1);
+ th->dest = htons(TEST_PORT);
+ th->seq = htonl(1 + i * len);
+ th->ack_seq = htonl(1);
+ th->doff = 5;
+ th->ack = 1;
+ th->window = htons(65535);
+ memset(th + 1, 'a' + i % 26, len);
+
+ ph.s = iph->saddr;
+ ph.d = iph->daddr;
+ ph.zero = 0;
+ ph.proto = IPPROTO_TCP;
+ ph.len = htons(sizeof(*th) + len);
+ sum = csum_add(0, &ph, sizeof(ph));
+ th->check = csum_fold(csum_add(sum, th, sizeof(*th) + len));
+
+ return sizeof(*eth) + sizeof(*iph) + sizeof(*th) + len;
+}
+
+static int do_tx(int fd, struct sockaddr_ll *sll)
+{
+ unsigned char buf[ETH_FRAME_LEN + 128];
+ int b, s, i = 0, n;
+
+ for (b = 0; b < bursts; b++) {
+ for (s = 0; s < segs; s++, i++) {
+ uint16_t id = fixed_id ? FIXED_ID : INCR_ID + i;
+ unsigned char *p = buf;
+
+ if (vxlan) {
+ struct ethhdr *eth = (struct ethhdr *)p;
+ struct iphdr *iph = (struct iphdr *)(eth + 1);
+ struct udphdr *uh = (struct udphdr *)(iph + 1);
+ uint32_t *vx = (uint32_t *)(uh + 1);
+ int inner;
+
+ inner = build_tcp((unsigned char *)(vx + 2),
+ inner_dmac, i, id);
+ memcpy(eth->h_dest, dmac, ETH_ALEN);
+ memset(eth->h_source, 0, ETH_ALEN);
+ eth->h_source[0] = 0x02;
+ eth->h_source[5] = 0x01;
+ eth->h_proto = htons(ETH_P_IP);
+ memset(uh, 0, sizeof(*uh));
+ uh->source = htons(VXLAN_PORT + 1);
+ uh->dest = htons(VXLAN_PORT);
+ uh->len = htons(sizeof(*uh) + 8 + inner);
+ vx[0] = htonl(0x08000000);
+ vx[1] = htonl(42 << 8);
+ build_ip(iph, IPPROTO_UDP,
+ sizeof(*uh) + 8 + inner,
+ fixed_outer ? FIXED_ID : 0x2000 + i,
+ osaddr, odaddr);
+ n = sizeof(*eth) + sizeof(*iph) + sizeof(*uh) +
+ 8 + inner;
+ } else {
+ n = build_tcp(p, dmac, i, id);
+ }
+
+ if (sendto(fd, buf, n, 0, (struct sockaddr *)sll,
+ sizeof(*sll)) != n)
+ error(1, errno, "sendto");
+ }
+ usleep(50000);
+ }
+ return 0;
+}
+
+/* Return the inner IPv4 header of a TCP segment to TEST_PORT, or NULL */
+static const struct iphdr *find_inner(const unsigned char *p, int n,
+ const struct iphdr **outer4)
+{
+ const struct ethhdr *eth = (const struct ethhdr *)p;
+ const unsigned char *end = p + n;
+ const unsigned char *l4;
+ int proto, depth;
+
+ *outer4 = NULL;
+ if (n < (int)sizeof(*eth))
+ return NULL;
+ p += sizeof(*eth);
+
+ for (depth = 0; depth < 2; depth++) {
+ uint16_t etype = depth ? htons(ETH_P_IP) : eth->h_proto;
+
+ if (etype == htons(ETH_P_IP)) {
+ const struct iphdr *iph = (const struct iphdr *)p;
+
+ if (p + sizeof(*iph) > end)
+ return NULL;
+ proto = iph->protocol;
+ l4 = p + iph->ihl * 4;
+ if (proto == IPPROTO_TCP) {
+ const struct tcphdr *th;
+
+ th = (const struct tcphdr *)l4;
+ if (l4 + sizeof(*th) > end ||
+ th->dest != htons(TEST_PORT))
+ return NULL;
+ return iph;
+ }
+ if (depth)
+ return NULL;
+ *outer4 = iph;
+ } else if (etype == htons(ETH_P_IPV6)) {
+ const struct ip6_hdr *ip6h = (const struct ip6_hdr *)p;
+
+ if (p + sizeof(*ip6h) > end)
+ return NULL;
+ proto = ip6h->ip6_nxt;
+ l4 = p + sizeof(*ip6h);
+ } else {
+ return NULL;
+ }
+
+ /* step over the tunnel header to the inner IPv4 header */
+ if (proto == IPPROTO_IPIP) {
+ p = l4;
+ } else if (proto == IPPROTO_GRE) {
+ uint16_t flags;
+
+ if (l4 + 4 > end)
+ return NULL;
+ flags = (l4[0] << 8) | l4[1];
+ if (((l4[2] << 8) | l4[3]) != ETH_P_IP)
+ return NULL;
+ p = l4 + 4 + 4 * (!!(flags & 0x8000) +
+ !!(flags & 0x2000) +
+ !!(flags & 0x1000));
+ } else if (proto == IPPROTO_UDP) {
+ const struct udphdr *uh = (const struct udphdr *)l4;
+
+ if (l4 + sizeof(*uh) + 8 + sizeof(*eth) > end ||
+ uh->dest != htons(VXLAN_PORT))
+ return NULL;
+ p = l4 + sizeof(*uh) + 8 + sizeof(*eth);
+ } else if (proto == IPPROTO_ESP) {
+ /* SPI, sequence number and the 8 byte IV of
+ * rfc4106(gcm(aes)); netdevsim does not encrypt
+ */
+ if (l4 + 16 > end)
+ return NULL;
+ p = l4 + 16;
+ } else {
+ return NULL;
+ }
+ }
+ return NULL;
+}
+
+static void count_id(uint8_t *map, unsigned int *distinct, uint16_t id)
+{
+ if (!(map[id / 8] & (1 << (id % 8)))) {
+ map[id / 8] |= 1 << (id % 8);
+ (*distinct)++;
+ }
+}
+
+static int do_rx(int fd)
+{
+ static uint8_t outer_map[8192], inner_map[8192];
+ unsigned int frames = 0, outer4 = 0, outer_ids = 0, inner_ids = 0;
+ unsigned int inner_bad = 0;
+ unsigned char buf[65536];
+ struct pollfd pfd = { .fd = fd, .events = POLLIN };
+
+ printf("ready\n");
+ fflush(stdout);
+
+ /* wait longer for the first segment than between segments */
+ while (poll(&pfd, 1, frames ? wait_ms : 10 * wait_ms) > 0) {
+ const struct iphdr *iph, *oiph;
+ struct sockaddr_ll from;
+ socklen_t fl = sizeof(from);
+ uint16_t id;
+ int n;
+
+ n = recvfrom(fd, buf, sizeof(buf), 0, (struct sockaddr *)&from,
+ &fl);
+ if (n < 0)
+ error(1, errno, "recvfrom");
+ if (from.sll_pkttype == PACKET_OUTGOING)
+ continue;
+ iph = find_inner(buf, n, &oiph);
+ if (!iph)
+ continue;
+ frames++;
+ id = ntohs(iph->id);
+ count_id(inner_map, &inner_ids, id);
+ if (fixed_id ? id != FIXED_ID : (uint16_t)(id - INCR_ID) >= stop)
+ inner_bad++;
+ if (oiph) {
+ outer4++;
+ count_id(outer_map, &outer_ids, ntohs(oiph->id));
+ }
+ if (stop && frames == (unsigned int)stop)
+ break;
+ }
+
+ printf("frames %u outer4 %u outer_ids %u inner_ids %u inner_bad %u\n",
+ frames, outer4, outer_ids, inner_ids, inner_bad);
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ struct sockaddr_ll sll = {};
+ bool tx = false, rx = false;
+ char *comma;
+ int c, fd;
+
+ while ((c = getopt(argc, argv, "TRi:M:s:d:fn:b:l:V:m:Fw:c:")) != -1) {
+ switch (c) {
+ case 'T':
+ tx = true;
+ break;
+ case 'R':
+ rx = true;
+ break;
+ case 'i':
+ ifname = optarg;
+ break;
+ case 'M':
+ parse_mac(optarg, dmac);
+ break;
+ case 's':
+ parse_addr(optarg, &saddr);
+ break;
+ case 'd':
+ parse_addr(optarg, &daddr);
+ break;
+ case 'f':
+ fixed_id = true;
+ break;
+ case 'n':
+ segs = atoi(optarg);
+ break;
+ case 'b':
+ bursts = atoi(optarg);
+ break;
+ case 'l':
+ len = atoi(optarg);
+ break;
+ case 'V':
+ comma = strchr(optarg, ',');
+ if (!comma)
+ error(1, 0, "-V needs outer saddr,daddr");
+ *comma = '\0';
+ parse_addr(optarg, &osaddr);
+ parse_addr(comma + 1, &odaddr);
+ vxlan = true;
+ break;
+ case 'm':
+ parse_mac(optarg, inner_dmac);
+ break;
+ case 'F':
+ fixed_outer = true;
+ break;
+ case 'w':
+ wait_ms = atoi(optarg);
+ break;
+ case 'c':
+ stop = atoi(optarg);
+ break;
+ default:
+ error(1, 0, "bad option");
+ }
+ }
+ if (tx == rx || !ifname || len < 1 || len > 1400 || segs < 1 ||
+ bursts < 1)
+ error(1, 0, "usage: see the comment at the top of %s",
+ __FILE__);
+
+ fd = socket(AF_PACKET, SOCK_RAW, htons(tx ? 0 : ETH_P_ALL));
+ if (fd < 0)
+ error(1, errno, "socket");
+ sll.sll_family = AF_PACKET;
+ sll.sll_protocol = htons(ETH_P_ALL);
+ sll.sll_ifindex = if_nametoindex(ifname);
+ if (!sll.sll_ifindex)
+ error(1, errno, "%s", ifname);
+ if (bind(fd, (struct sockaddr *)&sll, sizeof(sll)))
+ error(1, errno, "bind");
+ sll.sll_halen = ETH_ALEN;
+ memcpy(sll.sll_addr, dmac, ETH_ALEN);
+
+ c = tx ? do_tx(fd, &sll) : do_rx(fd);
+ close(fd);
+ return c;
+}@@ -0,0 +1,400 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Check the IPv4 IDs of a TCP stream that GRO merged and software
+# segmentation split again across a tunnel. A sender in NSRC writes
+# segments with fixed or incrementing IDs onto a veth with GRO on in
+# NRTR, which forwards the merged packets:
+#
+# encap: into an IPIP, GRE or VXLAN tunnel over IPv4 or IPv6,
+# segmented on the underlay towards NMID
+# decap: out of VXLAN, received from NSRC with one header fixed and
+# the other incrementing, into an IPIP tunnel towards NMID
+# encap+decap: into a tunnel that NMID ends without segmenting, and on
+# to NDST, segmented there
+# esp: into an ESP tunnel mode SA offloaded to netdevsim, which
+# segments the packet in software and does not encrypt it
+#
+# The inner IDs must come out as they went in, and the IDs of a new outer
+# IPv4 header must be unique, or for ESP, whose outer IDs start at 0 for
+# each packet with DF set, increment. A run in which GRO merged nothing is
+# skipped.
+
+source lib.sh
+
+NSRC=""
+NRTR=""
+NMID=""
+NDST=""
+
+SEGS=40
+BURSTS=10
+TOTAL=$((SEGS * BURSTS))
+INNER_SRC=10.1.0.1
+INNER_DST=10.9.0.2
+VX_MAC=02:00:00:00:00:42
+TUN_MAC=02:00:00:00:00:99
+MID_MAC=02:00:00:00:00:98
+TX=./tcp_fixedid
+
+NOSEG="tso gso tx-gre-segmentation tx-gre-csum-segmentation
+ tx-ipxip4-segmentation tx-ipxip6-segmentation
+ tx-udp_tnl-segmentation tx-udp_tnl-csum-segmentation"
+
+cleanup() {
+ cleanup_all_ns
+ rm -f "$RESULT"
+}
+
+trap cleanup EXIT
+
+# NSRC s0 - r0 NRTR r1 - m1 NMID m2 - d2 NDST
+setup() {
+ setup_ns NSRC NRTR NMID NDST || return "$ksft_skip"
+
+ ip link add s0 netns "$NSRC" type veth peer name r0 netns "$NRTR"
+ ip link add r1 netns "$NRTR" type veth peer name m1 netns "$NMID"
+ ip link add m2 netns "$NMID" type veth peer name d2 netns "$NDST"
+
+ ip -n "$NRTR" addr add 10.1.0.2/24 dev r0
+ ip -n "$NRTR" addr add 10.2.0.1/24 dev r1
+ ip -n "$NRTR" addr add fd02::1/64 dev r1 nodad
+ ip -n "$NMID" addr add 10.2.0.2/24 dev m1
+ ip -n "$NMID" addr add fd02::2/64 dev m1 nodad
+ ip -n "$NMID" addr add 10.4.0.1/24 dev m2
+ ip -n "$NDST" addr add 10.4.0.2/24 dev d2
+ ip -n "$NSRC" link set s0 up
+ ip -n "$NRTR" link set r0 up
+ ip -n "$NRTR" link set r1 up
+ ip -n "$NMID" link set m1 up
+ ip -n "$NMID" link set m2 up
+ ip -n "$NDST" link set d2 up
+
+ ip netns exec "$NRTR" sysctl -qw net.ipv4.ip_forward=1
+ ip netns exec "$NMID" sysctl -qw net.ipv4.ip_forward=1
+ for ns in "$NRTR" "$NMID"; do
+ ip netns exec "$ns" sysctl -qw net.ipv4.conf.all.rp_filter=0 \
+ net.ipv4.conf.default.rp_filter=0
+ done
+
+ # veth passes packets to GRO only if the sender does not do TSO
+ ip netns exec "$NRTR" ethtool -K r0 gro on >/dev/null ||
+ return "$ksft_skip"
+ ip netns exec "$NSRC" ethtool -K s0 tso off >/dev/null ||
+ return "$ksft_skip"
+ # release the sender's segments in bursts for GRO to merge
+ tc -n "$NSRC" qdisc add dev s0 root netem slot 20ms 20ms \
+ packets "$SEGS" || return "$ksft_skip"
+}
+
+# tunnel <ns> <name> <type> <family> <local> <remote>
+tunnel() {
+ local ns=$1 name=$2 type=$3 family=$4 local=$5 remote=$6
+
+ case "$type" in
+ ipip)
+ if [ "$family" = 4 ]; then
+ ip -n "$ns" link add "$name" type ipip \
+ local "$local" remote "$remote"
+ else
+ ip -n "$ns" link add "$name" type ip6tnl mode ipip6 \
+ local "$local" remote "$remote" encaplimit none
+ fi ;;
+ gre)
+ if [ "$family" = 4 ]; then
+ ip -n "$ns" link add "$name" type gre \
+ local "$local" remote "$remote"
+ else
+ ip -n "$ns" link add "$name" type ip6gre \
+ local "$local" remote "$remote" encaplimit none
+ fi ;;
+ vxlan)
+ ip -n "$ns" link add "$name" address "$TUN_MAC" type vxlan \
+ id 7 dstport 4789 local "$local" remote "$remote" \
+ nolearning ;;
+ esac || return 1
+ # no IPv6 link-local traffic in the tx_packets of the tunnel
+ ip netns exec "$ns" sysctl -qw "net.ipv6.conf.$name.disable_ipv6=1"
+ ip -n "$ns" link set "$name" up
+}
+
+# route_into <ns> <dev>: send INNER_DST into <dev>
+route_into() {
+ ip -n "$1" route add "$INNER_DST/32" dev "$2"
+ ip -n "$1" neigh add "$INNER_DST" lladdr "$TUN_MAC" dev "$2" \
+ 2>/dev/null
+ return 0
+}
+
+# noseg <ns> <dev>: segment everything in software before <dev>
+noseg() {
+ local f
+
+ for f in $NOSEG; do
+ ip netns exec "$1" ethtool -K "$2" "$f" off >/dev/null 2>&1
+ done
+}
+
+tx_packets() {
+ ip netns exec "$1" cat "/sys/class/net/$2/statistics/tx_packets"
+}
+
+# fwd_packets <ns>: packets forwarded, a GSO packet counting once
+fwd_packets() {
+ ip netns exec "$1" awk '/^Ip: [0-9]/ { print $7 }' /proc/net/snmp
+}
+
+# check <name> <result> <want: fixed|incr> <outer: 0|unique|incr> <merged>
+check() {
+ local name=$1 res=$2 want=$3 outer=$4 sent=$5
+ local frames outer_ids inner_ids inner_bad
+
+ read -r _ frames _ _ _ outer_ids _ inner_ids _ inner_bad <<< "$res"
+ RET=0
+ if [ -z "$inner_bad" ]; then
+ check_err 1 "no result from the receiver"
+ log_test "$name"
+ return
+ fi
+ check_err $((frames != TOTAL)) "$frames of $TOTAL segments received"
+ check_err "$inner_bad" "$inner_bad inner IDs not sent"
+ if [ "$want" = fixed ]; then
+ check_err $((inner_ids != 1)) "$inner_ids inner IDs, want 1"
+ else
+ check_err $((inner_ids != TOTAL)) \
+ "$inner_ids inner IDs, want $TOTAL"
+ fi
+ if [ "$outer" = unique ]; then
+ check_err $((outer_ids != frames)) \
+ "$outer_ids outer IDs for $frames segments"
+ elif [ "$outer" = incr ]; then
+ check_err $((outer_ids < 2)) "fixed outer IDs"
+ fi
+ if [ "$RET" -eq 0 ] && [ "$sent" -ge "$TOTAL" ]; then
+ ret_set_ksft_status "$ksft_skip" "GRO did not merge"
+ fi
+ log_test "$name"
+}
+
+# capture <ns> <dev> <want: fixed|incr>: start the receiver in the
+# background, pid in CAP_PID, and wait until it is bound
+capture() {
+ local f="" i
+
+ [ "$3" = fixed ] && f=-f
+ : > "$RESULT"
+ ip netns exec "$1" "$TX" -R -i "$2" -c "$TOTAL" -w 3000 $f > "$RESULT" &
+ CAP_PID=$!
+ for i in $(seq 100); do
+ grep -q ready "$RESULT" && return
+ sleep 0.1
+ done
+}
+
+run_encap() {
+ local type=$1 family=$2 want=$3
+ local r0mac t0 laddr=10.2.0.1 raddr=10.2.0.2
+ local f=""
+
+ setup || { log_test_skip "encap $type IPv$family"; return; }
+ if [ "$family" = 6 ]; then
+ laddr=fd02::1
+ raddr=fd02::2
+ fi
+ if ! tunnel "$NRTR" tun0 "$type" "$family" "$laddr" "$raddr"; then
+ log_test_skip "encap $type IPv$family"
+ cleanup_all_ns
+ return
+ fi
+ route_into "$NRTR" tun0
+ noseg "$NRTR" r1
+
+ r0mac=$(ip -n "$NRTR" -br link show r0 | awk '{ print $3 }')
+ capture "$NMID" m1 "$want"
+ t0=$(tx_packets "$NRTR" tun0)
+ [ "$want" = fixed ] && f=-f
+ ip netns exec "$NSRC" "$TX" -T -i s0 -M "$r0mac" -s "$INNER_SRC" \
+ -d "$INNER_DST" -n "$SEGS" -b "$BURSTS" $f
+ wait "$CAP_PID"
+ check "encap $type IPv$family, $want inner IDs" \
+ "$(tail -n 1 "$RESULT")" "$want" \
+ "$([ "$family" = 4 ] && echo unique || echo 0)" \
+ $(($(tx_packets "$NRTR" tun0) - t0))
+ cleanup_all_ns
+}
+
+# run_decap <fixed: inner|outer>: VXLAN from NSRC, decapsulated in NRTR
+run_decap() {
+ local fixed=$1 want=incr flags=-F
+ local r0mac t0
+
+ setup || { log_test_skip "decap"; return; }
+ ip -n "$NRTR" link add vx0 address "$VX_MAC" type vxlan id 42 \
+ dstport 4789 local 10.1.0.2 nolearning ||
+ { log_test_skip "decap"; cleanup_all_ns; return; }
+ ip -n "$NRTR" addr add 10.3.0.2/24 dev vx0
+ ip -n "$NRTR" link set vx0 up
+ if ! tunnel "$NRTR" tun0 ipip 4 10.2.0.1 10.2.0.2; then
+ log_test_skip "decap"
+ cleanup_all_ns
+ return
+ fi
+ route_into "$NRTR" tun0
+ noseg "$NRTR" r1
+
+ if [ "$fixed" = inner ]; then
+ want=fixed
+ flags=-f
+ fi
+ r0mac=$(ip -n "$NRTR" -br link show r0 | awk '{ print $3 }')
+ capture "$NMID" m1 "$want"
+ t0=$(tx_packets "$NRTR" tun0)
+ ip netns exec "$NSRC" "$TX" -T -i s0 -M "$r0mac" -s 10.3.0.1 \
+ -d "$INNER_DST" -n "$SEGS" -b "$BURSTS" \
+ -V 10.1.0.1,10.1.0.2 -m "$VX_MAC" $flags
+ wait "$CAP_PID"
+ check "decap VXLAN with fixed $fixed IDs, into IPIP" \
+ "$(tail -n 1 "$RESULT")" "$want" unique \
+ $(($(tx_packets "$NRTR" tun0) - t0))
+ cleanup_all_ns
+}
+
+# run_encap_decap <type>: NRTR encapsulates, NMID decapsulates the GSO
+# packet without segmenting it and forwards it to NDST
+run_encap_decap() {
+ local type=$1
+ local r0mac t0
+
+ setup || { log_test_skip "encap+decap $type"; return; }
+ if ! tunnel "$NRTR" tun0 "$type" 4 10.2.0.1 10.2.0.2 ||
+ ! tunnel "$NMID" tun0 "$type" 4 10.2.0.2 10.2.0.1; then
+ log_test_skip "encap+decap $type"
+ cleanup_all_ns
+ return
+ fi
+ route_into "$NRTR" tun0
+ # VXLAN drops frames from its own address as loops
+ if [ "$type" = vxlan ]; then
+ ip -n "$NMID" link set tun0 address "$MID_MAC"
+ ip -n "$NRTR" neigh replace "$INNER_DST" lladdr "$MID_MAC" \
+ dev tun0
+ fi
+ ip -n "$NMID" route add "$INNER_DST/32" via 10.4.0.2
+ ip -n "$NDST" addr add "$INNER_DST/32" dev d2
+ noseg "$NMID" m2
+
+ r0mac=$(ip -n "$NRTR" -br link show r0 | awk '{ print $3 }')
+ capture "$NDST" d2 fixed
+ t0=$(tx_packets "$NRTR" tun0)
+ ip netns exec "$NSRC" "$TX" -T -i s0 -M "$r0mac" -s "$INNER_SRC" \
+ -d "$INNER_DST" -n "$SEGS" -b "$BURSTS" -f
+ wait "$CAP_PID"
+ check "encap+decap $type, fixed inner IDs" "$(tail -n 1 "$RESULT")" \
+ fixed 0 $(($(tx_packets "$NRTR" tun0) - t0))
+ cleanup_all_ns
+}
+
+NSIM_ID=$((RANDOM % 1024 + 1024))
+NSIM_BUS=/sys/bus/netdevsim
+
+# nsim_add <id> <ns>: create a netdevsim port in <ns>, print its name
+nsim_add() {
+ local dev
+
+ echo "$1 1" > "$NSIM_BUS/new_device" || return 1
+ for dev in "$NSIM_BUS/devices/netdevsim$1/net/"*; do
+ dev=${dev##*/}
+ ip link set "$dev" netns "$2" || return 1
+ echo "$dev"
+ return 0
+ done
+ return 1
+}
+
+nsim_del() {
+ echo "$NSIM_ID" > "$NSIM_BUS/del_device" 2>/dev/null
+ echo $((NSIM_ID + 1)) > "$NSIM_BUS/del_device" 2>/dev/null
+}
+
+# run_esp: NRTR forwards into an ESP tunnel mode SA offloaded to a
+# netdevsim port with TSO off, linked to a netdevsim port in NMID
+run_esp() {
+ local key=0x3132333435363738393031323334353664636261
+ local r0mac rdev mdev rfd mfd t0
+
+ setup || { log_test_skip "esp"; return; }
+ if ! modprobe -q netdevsim 2>/dev/null && [ ! -w "$NSIM_BUS/new_device" ]; then
+ log_test_skip "esp: no netdevsim"
+ cleanup_all_ns
+ return
+ fi
+ if ! rdev=$(nsim_add "$NSIM_ID" "$NRTR") ||
+ ! mdev=$(nsim_add $((NSIM_ID + 1)) "$NMID"); then
+ log_test_skip "esp: netdevsim"
+ nsim_del
+ cleanup_all_ns
+ return
+ fi
+ exec {rfd}<"/run/netns/$NRTR" {mfd}<"/run/netns/$NMID"
+ echo "$rfd:$(ip netns exec "$NRTR" cat "/sys/class/net/$rdev/ifindex")" \
+ "$mfd:$(ip netns exec "$NMID" cat "/sys/class/net/$mdev/ifindex")" \
+ > "$NSIM_BUS/link_device"
+ exec {rfd}<&- {mfd}<&-
+
+ ip -n "$NRTR" addr add 10.5.0.1/24 dev "$rdev"
+ ip -n "$NMID" addr add 10.5.0.2/24 dev "$mdev"
+ ip -n "$NRTR" link set "$rdev" up
+ ip -n "$NMID" link set "$mdev" up
+ ip -n "$NRTR" neigh add 10.5.0.2 dev "$rdev" lladdr \
+ "$(ip -n "$NMID" -br link show "$mdev" | awk '{ print $3 }')"
+ ip -n "$NRTR" route add "$INNER_DST/32" via 10.5.0.2 dev "$rdev"
+ ip netns exec "$NRTR" ethtool -K "$rdev" tso off >/dev/null
+ if ! ip -n "$NRTR" xfrm state add src 10.5.0.1 dst 10.5.0.2 \
+ proto esp spi 0x100 reqid 1 mode tunnel \
+ aead 'rfc4106(gcm(aes))' "$key" 128 \
+ offload dev "$rdev" dir out ||
+ ! ip -n "$NRTR" xfrm policy add dir out \
+ src "$INNER_SRC/32" dst "$INNER_DST/32" \
+ tmpl src 10.5.0.1 dst 10.5.0.2 proto esp reqid 1 mode tunnel; then
+ log_test_skip "esp: no ESP offload"
+ nsim_del
+ cleanup_all_ns
+ return
+ fi
+
+ r0mac=$(ip -n "$NRTR" -br link show r0 | awk '{ print $3 }')
+ capture "$NMID" "$mdev" fixed
+ t0=$(fwd_packets "$NRTR")
+ ip netns exec "$NSRC" "$TX" -T -i s0 -M "$r0mac" -s "$INNER_SRC" \
+ -d "$INNER_DST" -n "$SEGS" -b "$BURSTS" -f
+ wait "$CAP_PID"
+ check "esp tunnel offload, fixed inner IDs" "$(tail -n 1 "$RESULT")" \
+ fixed incr $(($(fwd_packets "$NRTR") - t0))
+ cleanup_all_ns
+ nsim_del
+}
+
+require_command ethtool
+require_command tc
+
+if [ ! -x "$TX" ]; then
+ echo "SKIP: $TX not built"
+ exit "$ksft_skip"
+fi
+
+RESULT=$(mktemp)
+
+for type in ipip gre vxlan; do
+ for family in 4 6; do
+ run_encap "$type" "$family" fixed
+ run_encap "$type" "$family" incr
+ done
+done
+run_decap inner
+run_decap outer
+for type in ipip gre vxlan; do
+ run_encap_decap "$type"
+done
+run_esp
+
+exit "$EXIT_STATUS"