diff options
| author | Daniel Borkmann <daniel@iogearbox.net> | 2020-10-11 01:40:02 +0200 |
|---|---|---|
| committer | Alexei Starovoitov <ast@kernel.org> | 2020-10-11 10:21:04 -0700 |
| commit | 9aa1206e8f48222f35a0c809f33b2f4aaa1e2661 (patch) | |
| tree | 5bdbd711c69e17ba9cab45c023eb2b90d258ac3f /include | |
| parent | dd2ce6a5373c6f5c830be54be10775458a8bd312 (diff) | |
bpf: Add redirect_peer helper
Add an efficient ingress to ingress netns switch that can be used out of tc BPF
programs in order to redirect traffic from host ns ingress into a container
veth device ingress without having to go via CPU backlog queue [0]. For local
containers this can also be utilized and path via CPU backlog queue only needs
to be taken once, not twice. On a high level this borrows from ipvlan which does
similar switch in __netif_receive_skb_core() and then iterates via another_round.
This helps to reduce latency for mentioned use cases.
Pod to remote pod with redirect(), TCP_RR [1]:
# percpu_netperf 10.217.1.33
RT_LATENCY: 122.450 (per CPU: 122.666 122.401 122.333 122.401 )
MEAN_LATENCY: 121.210 (per CPU: 121.100 121.260 121.320 121.160 )
STDDEV_LATENCY: 120.040 (per CPU: 119.420 119.910 125.460 115.370 )
MIN_LATENCY: 46.500 (per CPU: 47.000 47.000 47.000 45.000 )
P50_LATENCY: 118.500 (per CPU: 118.000 119.000 118.000 119.000 )
P90_LATENCY: 127.500 (per CPU: 127.000 128.000 127.000 128.000 )
P99_LATENCY: 130.750 (per CPU: 131.000 131.000 129.000 132.000 )
TRANSACTION_RATE: 32666.400 (per CPU: 8152.200 8169.842 8174.439 8169.897 )
Pod to remote pod with redirect_peer(), TCP_RR:
# percpu_netperf 10.217.1.33
RT_LATENCY: 44.449 (per CPU: 43.767 43.127 45.279 45.622 )
MEAN_LATENCY: 45.065 (per CPU: 44.030 45.530 45.190 45.510 )
STDDEV_LATENCY: 84.823 (per CPU: 66.770 97.290 84.380 90.850 )
MIN_LATENCY: 33.500 (per CPU: 33.000 33.000 34.000 34.000 )
P50_LATENCY: 43.250 (per CPU: 43.000 43.000 43.000 44.000 )
P90_LATENCY: 46.750 (per CPU: 46.000 47.000 47.000 47.000 )
P99_LATENCY: 52.750 (per CPU: 51.000 54.000 53.000 53.000 )
TRANSACTION_RATE: 90039.500 (per CPU: 22848.186 23187.089 22085.077 21919.130 )
[0] https://linuxplumbersconf.org/event/7/contributions/674/attachments/568/1002/plumbers_2020_cilium_load_balancer.pdf
[1] https://github.com/borkmann/netperf_scripts/blob/master/percpu_netperf
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201010234006.7075-3-daniel@iogearbox.net
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/netdevice.h | 4 | ||||
| -rw-r--r-- | include/uapi/linux/bpf.h | 17 |
2 files changed, 21 insertions, 0 deletions
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 28cfa53daf72..0533f86018dd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1277,6 +1277,9 @@ struct netdev_net_notifier { * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. + * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); + * If a device is paired with a peer device, return the peer instance. + * The caller must be under RCU read context. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1484,6 +1487,7 @@ struct net_device_ops { struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); + struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); }; /** diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4272cc53d478..b97bc5abb3b8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3719,6 +3719,22 @@ union bpf_attr { * never return NULL. * Return * A pointer pointing to the kernel percpu variable on this cpu. + * + * long bpf_redirect_peer(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_redirect**\ (), except + * that the redirection happens to the *ifindex*' peer device and + * the netns switch takes place from ingress to ingress without + * going through the CPU's backlog queue. + * + * The *flags* argument is reserved and must be 0. The helper is + * currently only supported for tc BPF program types at the ingress + * hook and for veth device types. The peer device must reside in a + * different network namespace. + * Return + * The helper returns **TC_ACT_REDIRECT** on success or + * **TC_ACT_SHOT** on error. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3876,6 +3892,7 @@ union bpf_attr { FN(redirect_neigh), \ FN(bpf_per_cpu_ptr), \ FN(bpf_this_cpu_ptr), \ + FN(redirect_peer), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper |