mirror of https://github.com/torvalds/linux.git
With legacy nexthops, when net.ipv4.fib_multipath_use_neigh is set,
fib_select_multipath() will never set res->nhc to a nexthop that is not
good (as per fib_good_nh()). OTOH, with nexthop objects,
nexthop_select_path_hthr() may return a nexthop that failed the
nexthop_is_good_nh() test even if there was one that passed. Refactor
nexthop_select_path_hthr() to follow a selection logic more similar to
fib_select_multipath().
The issue can be demonstrated with the following sequence of commands. The
first block shows that things work as expected with legacy nexthops. The
last sequence of `ip rou get` in the second block shows the problem case -
some routes still use the .2 nexthop.
sysctl net.ipv4.fib_multipath_use_neigh=1
ip link add dummy1 up type dummy
ip rou add 198.51.100.0/24 nexthop via 192.0.2.1 dev dummy1 onlink nexthop via 192.0.2.2 dev dummy1 onlink
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip neigh add 192.0.2.1 dev dummy1 nud failed
echo ".1 failed:" # results should not use .1
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip neigh del 192.0.2.1 dev dummy1
ip neigh add 192.0.2.2 dev dummy1 nud failed
echo ".2 failed:" # results should not use .2
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip link del dummy1
ip link add dummy1 up type dummy
ip nexthop add id 1 via 192.0.2.1 dev dummy1 onlink
ip nexthop add id 2 via 192.0.2.2 dev dummy1 onlink
ip nexthop add id 1001 group 1/2
ip rou add 198.51.100.0/24 nhid 1001
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip neigh add 192.0.2.1 dev dummy1 nud failed
echo ".1 failed:" # results should not use .1
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip neigh del 192.0.2.1 dev dummy1
ip neigh add 192.0.2.2 dev dummy1 nud failed
echo ".2 failed:" # results should not use .2
for i in {10..19}; do ip -o rou get 198.51.100.$i; done
ip link del dummy1
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230719-nh_select-v2-3-04383e89f868@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
||
|---|---|---|
| .. | ||
| bpfilter | ||
| netfilter | ||
| Kconfig | ||
| Makefile | ||
| af_inet.c | ||
| ah4.c | ||
| arp.c | ||
| bpf_tcp_ca.c | ||
| cipso_ipv4.c | ||
| datagram.c | ||
| devinet.c | ||
| esp4.c | ||
| esp4_offload.c | ||
| fib_frontend.c | ||
| fib_lookup.h | ||
| fib_notifier.c | ||
| fib_rules.c | ||
| fib_semantics.c | ||
| fib_trie.c | ||
| fou_bpf.c | ||
| fou_core.c | ||
| fou_nl.c | ||
| fou_nl.h | ||
| gre_demux.c | ||
| gre_offload.c | ||
| icmp.c | ||
| igmp.c | ||
| inet_connection_sock.c | ||
| inet_diag.c | ||
| inet_fragment.c | ||
| inet_hashtables.c | ||
| inet_timewait_sock.c | ||
| inetpeer.c | ||
| ip_forward.c | ||
| ip_fragment.c | ||
| ip_gre.c | ||
| ip_input.c | ||
| ip_options.c | ||
| ip_output.c | ||
| ip_sockglue.c | ||
| ip_tunnel.c | ||
| ip_tunnel_core.c | ||
| ip_vti.c | ||
| ipcomp.c | ||
| ipconfig.c | ||
| ipip.c | ||
| ipmr.c | ||
| ipmr_base.c | ||
| metrics.c | ||
| netfilter.c | ||
| netlink.c | ||
| nexthop.c | ||
| ping.c | ||
| proc.c | ||
| protocol.c | ||
| raw.c | ||
| raw_diag.c | ||
| route.c | ||
| syncookies.c | ||
| sysctl_net_ipv4.c | ||
| tcp.c | ||
| tcp_bbr.c | ||
| tcp_bic.c | ||
| tcp_bpf.c | ||
| tcp_cdg.c | ||
| tcp_cong.c | ||
| tcp_cubic.c | ||
| tcp_dctcp.c | ||
| tcp_dctcp.h | ||
| tcp_diag.c | ||
| tcp_fastopen.c | ||
| tcp_highspeed.c | ||
| tcp_htcp.c | ||
| tcp_hybla.c | ||
| tcp_illinois.c | ||
| tcp_input.c | ||
| tcp_ipv4.c | ||
| tcp_lp.c | ||
| tcp_metrics.c | ||
| tcp_minisocks.c | ||
| tcp_nv.c | ||
| tcp_offload.c | ||
| tcp_output.c | ||
| tcp_plb.c | ||
| tcp_rate.c | ||
| tcp_recovery.c | ||
| tcp_scalable.c | ||
| tcp_timer.c | ||
| tcp_ulp.c | ||
| tcp_vegas.c | ||
| tcp_vegas.h | ||
| tcp_veno.c | ||
| tcp_westwood.c | ||
| tcp_yeah.c | ||
| tunnel4.c | ||
| udp.c | ||
| udp_bpf.c | ||
| udp_diag.c | ||
| udp_impl.h | ||
| udp_offload.c | ||
| udp_tunnel_core.c | ||
| udp_tunnel_nic.c | ||
| udp_tunnel_stub.c | ||
| udplite.c | ||
| xfrm4_input.c | ||
| xfrm4_output.c | ||
| xfrm4_policy.c | ||
| xfrm4_protocol.c | ||
| xfrm4_state.c | ||
| xfrm4_tunnel.c | ||