Files
linux/include/net
Willem de Bruijn 65e9024643 ip: load balance tcp connections to single dst addr and port
Load balance new TCP connections across nexthops also when they
connect to the same service at a single remote address and port.

This affects only port-based multipath hashing:
fib_multipath_hash_policy 1 or 3.

Local connections must choose both a source address and port when
connecting to a remote service, in ip_route_connect. This
"chicken-and-egg problem" (commit 2d7192d6cb ("ipv4: Sanitize and
simplify ip_route_{connect,newports}()")) is resolved by first
selecting a source address, by looking up a route using the zero
wildcard source port and address.

As a result multiple connections to the same destination address and
port have no entropy in fib_multipath_hash.

This is not a problem when forwarding, as skb-based hashing has a
4-tuple. Nor when establishing UDP connections, as autobind there
selects a port before reaching ip_route_connect.

Load balance also TCP, by using a random port in fib_multipath_hash.
Port assignment in inet_hash_connect is not atomic with
ip_route_connect. Thus ports are unpredictable, effectively random.

Implementation details:

Do not actually pass a random fl4_sport, as that affects not only
hashing, but routing more broadly, and can match a source port based
policy route, which existing wildcard port 0 will not. Instead,
define a new wildcard flowi flag that is used only for hashing.

Selecting a random source is equivalent to just selecting a random
hash entirely. But for code clarity, follow the normal 4-tuple hash
process and only update this field.

fib_multipath_hash can be reached with zero sport from other code
paths, so explicitly pass this flowi flag, rather than trying to infer
this case in the function itself.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250424143549.669426-3-willemdebruijn.kernel@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2025-04-29 16:22:25 +02:00
..
2024-10-08 15:33:49 -07:00
2024-12-09 14:44:59 -08:00
2024-01-02 12:41:16 +00:00
2025-01-20 12:16:04 -08:00
2025-04-24 17:03:45 -07:00
2025-03-24 10:26:53 +00:00
2022-08-09 22:14:02 -07:00
2025-01-16 13:04:58 -08:00
2024-05-08 10:35:09 +01:00
2024-08-26 09:37:23 -07:00
2024-12-09 14:44:59 -08:00
2024-11-13 18:49:50 -08:00
2024-08-26 09:37:23 -07:00
2024-05-07 01:35:55 +02:00
2024-08-26 09:37:23 -07:00
2021-10-15 11:33:08 +01:00
2024-02-28 11:19:41 +00:00
2023-04-22 01:39:41 +02:00
2024-12-06 17:43:08 -08:00
2021-10-13 09:40:46 -07:00
2024-08-26 09:37:23 -07:00
2025-04-15 08:21:46 -07:00
2024-08-12 17:23:57 -07:00
2025-02-06 16:27:30 -08:00
2024-04-01 10:49:28 +01:00
2023-07-14 20:39:30 -07:00
2024-08-26 09:37:23 -07:00
2024-08-26 09:37:23 -07:00
2025-04-11 18:58:10 -07:00
2025-04-11 18:58:10 -07:00
2024-05-30 18:29:38 -07:00
2024-05-30 18:29:38 -07:00
2023-10-04 11:49:20 -07:00
2025-01-29 13:32:08 -08:00
2025-04-10 18:29:26 -07:00
2024-07-08 14:07:31 -07:00
2024-05-09 20:25:55 -07:00
2023-07-28 14:07:59 -07:00
2022-12-12 15:04:39 -08:00
2023-09-14 16:16:36 +02:00
2025-04-22 11:11:16 +02:00
2024-08-26 09:37:23 -07:00