Currently, sk_lookup allows an ebpf program to run on the ingress socket lookup path, and accept traffic not only on a range of addresses, but also on a range of ports. At Cloudflare we use sk_lookup for two main cases: 1. Sharing a single port between multiple services - i.e. two services (or more) use disjoint IP ranges but share the same port; 2. Receiving traffic on all ports - i.e. a service which accepts traffic on specific IP ranges but any port [1]. However, one main challenge we face while using sk_lookup for these use cases is how to source return UDP traffic: - On point 1. above, sometimes this range of addresses are not local (i.e. there's no local routes for these in the server), which means we need IP_TRANSPARENT set to be able to egress traffic from addresses we've received traffic on (or simply IP_FREEBIND in the case of IPv6); - And on point 2. above, allowing traffic to a range of ports means a service could get traffic on multiple ports, but currently there's no way to set the source UDP port egress traffic should be sourced from - it's possible to receive the original destination port using the IP_ORIGDSTADDR ancilliary message in recvmsg, but not set it in sendmsg. Both of these limitations can be worked around, but in a sub-optimal way. Using IP_TRANSPARENT, for instance, requires special privileges. And while one could use UDP connected sockets to send return traffic, creating a connected socket for each different address a UDP traffic is received on does have performance implications. Given sk_lookup allows services to accept traffic on a range of addresses or ports, it seems sensible to also allow return traffic to proceed through as well, without needing extra configurations / set ups. This patch sets out to fix both of this issues by: 1. Allowing users to set the src address/port egress traffic should be sent from, when calling sendmsg(); 2. Validating that this egress traffic comes from a socket that matches an ingress socket in sk_lookup. - If it does, traffic is allowed to proceed; - Otherwise it falls back to the regular egress path. The downsides to this is that this runs on the egress hot path, although this work tries to minimise its impact by only performing the reverse socket lookup when necessary (i.e. only when the src address/port are modified). Further performance measurements are to be taken, but we're reaching out early for feedback to see what the technical concerns are and if we can address them. [1] https://blog.cloudflare.com/how-we-built-spectrum/ Suggested-by: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx> Signed-off-by: Tiago Lam <tiagolam@xxxxxxxxxxxxxx> --- Changes in v2: - Amended commit messages and cover letter to make the intent and implementation clearer (Willem de Bruijn); - Fixed socket comparison by not using socket cookies and comparing them directly (Eric Dumazet); - Fixed misspellings and checkpatch.pl warnings on line lengths (Simon Horman); - Fixed usage of start_server_addr() and gcc compilation (Philo Lu); - Link to v1: https://lore.kernel.org/r/20240913-reverse-sk-lookup-v1-0-e721ea003d4c@xxxxxxxxxxxxxx --- Tiago Lam (3): ipv4: Support setting src port in sendmsg(). ipv6: Support setting src port in sendmsg(). bpf: Add sk_lookup test to use ORIGDSTADDR cmsg. include/net/ip.h | 1 + net/ipv4/ip_sockglue.c | 11 +++ net/ipv4/udp.c | 35 +++++++++- net/ipv6/datagram.c | 79 ++++++++++++++++++++++ net/ipv6/udp.c | 8 ++- tools/testing/selftests/bpf/prog_tests/sk_lookup.c | 67 ++++++++++++------ 6 files changed, 176 insertions(+), 25 deletions(-) --- base-commit: 6562a89739bbefddb5495c09aaab67c1c3756f36 change-id: 20240909-reverse-sk-lookup-f7bf36292bc4 Best regards, -- Tiago Lam <tiagolam@xxxxxxxxxxxxxx>
