[v3,net-next,0/2] udp_tunnel: GRO optimizations

Message

Paolo Abeni March 10, 2025, 7:09 p.m. UTC

The UDP tunnel GRO stage is source of measurable overhead for workload
based on UDP-encapsulated traffic: each incoming packets requires a full
UDP socket lookup and an indirect call.

In the most common setups a single UDP tunnel device is used. In such
case we can optimize both the lookup and the indirect call.

Patch 1 tracks per netns the active UDP tunnels and replaces the socket
lookup with a single destination port comparison when possible.

Patch 2 tracks the different types of UDP tunnels and replaces the
indirect call with a static one when there is a single UDP tunnel type
active.

I measure ~5% performance improvement in TCP over UDP tunnel stream
tests on top of this series.
---
v2 -> v3:
 - avoid unneeded checks in udp_tunnel_update_gro_rcv()
 - use RCU_INIT_POINTER() when possible
 - drop 'inline' from c file
 v2: https://lore.kernel.org/netdev/[e-mail]/

v1 -> v2:
 - fixed a couple of typos
 - fixed UDP_TUNNEL=n build
 - clarified design choices 
 (see the individual patches changelog for more details)
 v1: https://lore.kernel.org/netdev/[e-mail]/

Paolo Abeni (2):
  udp_tunnel: create a fastpath GRO lookup.
  udp_tunnel: use static call for GRO hooks when possible

 include/linux/udp.h        |  16 ++++
 include/net/netns/ipv4.h   |  11 +++
 include/net/udp.h          |   1 +
 include/net/udp_tunnel.h   |  22 +++++
 net/ipv4/udp.c             |  13 ++-
 net/ipv4/udp_offload.c     | 174 ++++++++++++++++++++++++++++++++++++-
 net/ipv4/udp_tunnel_core.c |  14 +++
 net/ipv6/udp.c             |   2 +
 net/ipv6/udp_offload.c     |   5 ++
 9 files changed, 256 insertions(+), 2 deletions(-)