diff options
| -rw-r--r-- | include/linux/ipv6.h | 1 | ||||
| -rw-r--r-- | include/net/ip.h | 1 | ||||
| -rw-r--r-- | net/ipv4/ip_input.c | 3 | ||||
| -rw-r--r-- | net/ipv4/route.c | 1 | ||||
| -rw-r--r-- | net/ipv6/ip6_input.c | 3 | ||||
| -rw-r--r-- | net/ipv6/route.c | 3 | ||||
| -rwxr-xr-x | tools/testing/selftests/net/fib_tests.sh | 155 |
7 files changed, 164 insertions, 3 deletions
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 5883551b1ee8..af8a771a053c 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -147,6 +147,7 @@ struct inet6_skb_parm { #define IP6SKB_JUMBOGRAM 128 #define IP6SKB_SEG6 256 #define IP6SKB_FAKEJUMBO 512 +#define IP6SKB_MULTIPATH 1024 }; #if defined(CONFIG_NET_L3_MASTER_DEV) diff --git a/include/net/ip.h b/include/net/ip.h index 9276cea775cc..3489a1cca5e7 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -57,6 +57,7 @@ struct inet_skb_parm { #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) #define IPSKB_NOPOLICY BIT(8) +#define IPSKB_MULTIPATH BIT(9) u16 frag_max_size; }; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index fe9ead9ee863..5e9c8156656a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -584,7 +584,8 @@ static void ip_sublist_rcv_finish(struct list_head *head) static struct sk_buff *ip_extract_route_hint(const struct net *net, struct sk_buff *skb, int rt_type) { - if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST) + if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST || + IPCB(skb)->flags & IPSKB_MULTIPATH) return NULL; return skb; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a4e153dd615b..6a3f57a3fa41 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2144,6 +2144,7 @@ static int ip_mkroute_input(struct sk_buff *skb, int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); + IPCB(skb)->flags |= IPSKB_MULTIPATH; } #endif diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index d94041bb4287..b8378814532c 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -99,7 +99,8 @@ static bool ip6_can_use_hint(const struct sk_buff *skb, static struct sk_buff *ip6_extract_route_hint(const struct net *net, struct sk_buff *skb) { - if (fib6_routes_require_src(net) || fib6_has_custom_rules(net)) + if (fib6_routes_require_src(net) || fib6_has_custom_rules(net) || + IP6CB(skb)->flags & IP6SKB_MULTIPATH) return NULL; return skb; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 846aec8e0093..01d6d352850a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -423,6 +423,9 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, if (match->nh && have_oif_match && res->nh) return; + if (skb) + IP6CB(skb)->flags |= IP6SKB_MULTIPATH; + /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index d328af4a149c..e7d2a530618a 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -12,7 +12,8 @@ ksft_skip=4 TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \ ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \ ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \ - ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test" + ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \ + ipv4_mpath_list ipv6_mpath_list" VERBOSE=0 PAUSE_ON_FAIL=no @@ -2352,6 +2353,156 @@ ipv4_bcast_neigh_test() cleanup } +mpath_dep_check() +{ + if [ ! -x "$(command -v mausezahn)" ]; then + echo "mausezahn command not found. Skipping test" + return 1 + fi + + if [ ! -x "$(command -v jq)" ]; then + echo "jq command not found. Skipping test" + return 1 + fi + + if [ ! -x "$(command -v bc)" ]; then + echo "bc command not found. Skipping test" + return 1 + fi + + if [ ! -x "$(command -v perf)" ]; then + echo "perf command not found. Skipping test" + return 1 + fi + + perf list fib:* | grep -q fib_table_lookup + if [ $? -ne 0 ]; then + echo "IPv4 FIB tracepoint not found. Skipping test" + return 1 + fi + + perf list fib6:* | grep -q fib6_table_lookup + if [ $? -ne 0 ]; then + echo "IPv6 FIB tracepoint not found. Skipping test" + return 1 + fi + + return 0 +} + +link_stats_get() +{ + local ns=$1; shift + local dev=$1; shift + local dir=$1; shift + local stat=$1; shift + + ip -n $ns -j -s link show dev $dev \ + | jq '.[]["stats64"]["'$dir'"]["'$stat'"]' +} + +list_rcv_eval() +{ + local file=$1; shift + local expected=$1; shift + + local count=$(tail -n 1 $file | jq '.["counter-value"] | tonumber | floor') + local ratio=$(echo "scale=2; $count / $expected" | bc -l) + local res=$(echo "$ratio >= 0.95" | bc) + [[ $res -eq 1 ]] + log_test $? 0 "Multipath route hit ratio ($ratio)" +} + +ipv4_mpath_list_test() +{ + echo + echo "IPv4 multipath list receive tests" + + mpath_dep_check || return 1 + + route_setup + + set -e + run_cmd "ip netns exec ns1 ethtool -K veth1 tcp-segmentation-offload off" + + run_cmd "ip netns exec ns2 bash -c \"echo 20000 > /sys/class/net/veth2/gro_flush_timeout\"" + run_cmd "ip netns exec ns2 bash -c \"echo 1 > /sys/class/net/veth2/napi_defer_hard_irqs\"" + run_cmd "ip netns exec ns2 ethtool -K veth2 generic-receive-offload on" + run_cmd "ip -n ns2 link add name nh1 up type dummy" + run_cmd "ip -n ns2 link add name nh2 up type dummy" + run_cmd "ip -n ns2 address add 172.16.201.1/24 dev nh1" + run_cmd "ip -n ns2 address add 172.16.202.1/24 dev nh2" + run_cmd "ip -n ns2 neigh add 172.16.201.2 lladdr 00:11:22:33:44:55 nud perm dev nh1" + run_cmd "ip -n ns2 neigh add 172.16.202.2 lladdr 00:aa:bb:cc:dd:ee nud perm dev nh2" + run_cmd "ip -n ns2 route add 203.0.113.0/24 + nexthop via 172.16.201.2 nexthop via 172.16.202.2" + run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.fib_multipath_hash_policy=1" + set +e + + local dmac=$(ip -n ns2 -j link show dev veth2 | jq -r '.[]["address"]') + local tmp_file=$(mktemp) + local cmd="ip netns exec ns1 mausezahn veth1 -a own -b $dmac + -A 172.16.101.1 -B 203.0.113.1 -t udp 'sp=12345,dp=0-65535' -q" + + # Packets forwarded in a list using a multipath route must not reuse a + # cached result so that a flow always hits the same nexthop. In other + # words, the FIB lookup tracepoint needs to be triggered for every + # packet. + local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets) + run_cmd "perf stat -e fib:fib_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd" + local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets) + local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l) + list_rcv_eval $tmp_file $diff + + rm $tmp_file + route_cleanup +} + +ipv6_mpath_list_test() +{ + echo + echo "IPv6 multipath list receive tests" + + mpath_dep_check || return 1 + + route_setup + + set -e + run_cmd "ip netns exec ns1 ethtool -K veth1 tcp-segmentation-offload off" + + run_cmd "ip netns exec ns2 bash -c \"echo 20000 > /sys/class/net/veth2/gro_flush_timeout\"" + run_cmd "ip netns exec ns2 bash -c \"echo 1 > /sys/class/net/veth2/napi_defer_hard_irqs\"" + run_cmd "ip netns exec ns2 ethtool -K veth2 generic-receive-offload on" + run_cmd "ip -n ns2 link add name nh1 up type dummy" + run_cmd "ip -n ns2 link add name nh2 up type dummy" + run_cmd "ip -n ns2 -6 address add 2001:db8:201::1/64 dev nh1" + run_cmd "ip -n ns2 -6 address add 2001:db8:202::1/64 dev nh2" + run_cmd "ip -n ns2 -6 neigh add 2001:db8:201::2 lladdr 00:11:22:33:44:55 nud perm dev nh1" + run_cmd "ip -n ns2 -6 neigh add 2001:db8:202::2 lladdr 00:aa:bb:cc:dd:ee nud perm dev nh2" + run_cmd "ip -n ns2 -6 route add 2001:db8:301::/64 + nexthop via 2001:db8:201::2 nexthop via 2001:db8:202::2" + run_cmd "ip netns exec ns2 sysctl -qw net.ipv6.fib_multipath_hash_policy=1" + set +e + + local dmac=$(ip -n ns2 -j link show dev veth2 | jq -r '.[]["address"]') + local tmp_file=$(mktemp) + local cmd="ip netns exec ns1 mausezahn -6 veth1 -a own -b $dmac + -A 2001:db8:101::1 -B 2001:db8:301::1 -t udp 'sp=12345,dp=0-65535' -q" + + # Packets forwarded in a list using a multipath route must not reuse a + # cached result so that a flow always hits the same nexthop. In other + # words, the FIB lookup tracepoint needs to be triggered for every + # packet. + local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets) + run_cmd "perf stat -e fib6:fib6_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd" + local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets) + local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l) + list_rcv_eval $tmp_file $diff + + rm $tmp_file + route_cleanup +} + ################################################################################ # usage @@ -2433,6 +2584,8 @@ do ipv6_mangle) ipv6_mangle_test;; ipv4_bcast_neigh) ipv4_bcast_neigh_test;; fib6_gc_test|ipv6_gc) fib6_gc_test;; + ipv4_mpath_list) ipv4_mpath_list_test;; + ipv6_mpath_list) ipv6_mpath_list_test;; help) echo "Test names: $TESTS"; exit 0;; esac |