From: David Miller <davem@davemloft.net>
To: tom@quantonium.net
Cc: netdev@vger.kernel.org, pablo@netfilter.org,
laforge@gnumonks.org, rohit@quantonium.net
Subject: Re: [PATCH net-next 03/14] gtp: Call common functions to get tunnel routes and add dst_cache
Date: Mon, 18 Sep 2017 21:17:51 -0700 (PDT) [thread overview]
Message-ID: <20170918.211751.1871429944584121281.davem@davemloft.net> (raw)
In-Reply-To: <20170919003904.5124-4-tom@quantonium.net>
From: Tom Herbert <tom@quantonium.net>
Date: Mon, 18 Sep 2017 17:38:53 -0700
> Call ip_tunnel_get_route and dst_cache to pdp context which should
> improve performance by obviating the need to perform a route lookup
> on every packet.
>
> Signed-off-by: Tom Herbert <tom@quantonium.net>
Not caused by your changes, but something to think about:
> -static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4,
> - const struct sock *sk,
> - __be32 daddr)
> -{
> - memset(fl4, 0, sizeof(*fl4));
> - fl4->flowi4_oif = sk->sk_bound_dev_if;
> - fl4->daddr = daddr;
> - fl4->saddr = inet_sk(sk)->inet_saddr;
> - fl4->flowi4_tos = RT_CONN_FLAGS(sk);
> - fl4->flowi4_proto = sk->sk_protocol;
> -
> - return ip_route_output_key(sock_net(sk), fl4);
> -}
This and the new dst caching code ignores any source address selection
done by ip_route_output_key() or the new tunnel route lookup helpers.
Either source address selection should be respected, or if saddr will
never be modified by a route lookup for some specific reason here,
that should be documented.
next prev parent reply other threads:[~2017-09-19 4:17 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-19 0:38 [PATCH net-next 00/14] gtp: Additional feature support Tom Herbert
2017-09-19 0:38 ` [PATCH net-next 01/14] iptunnel: Add common functions to get a tunnel route Tom Herbert
2017-09-19 7:30 ` kbuild test robot
2017-09-19 0:38 ` [PATCH net-next 02/14] vxlan: Call common functions to get tunnel routes Tom Herbert
2017-09-19 0:38 ` [PATCH net-next 03/14] gtp: Call common functions to get tunnel routes and add dst_cache Tom Herbert
2017-09-19 4:17 ` David Miller [this message]
2017-09-19 12:09 ` Harald Welte
2017-09-19 17:44 ` David Miller
2017-09-20 15:37 ` Andreas Schultz
2017-09-24 1:33 ` Harald Welte
2017-09-19 16:05 ` Tom Herbert
2017-09-19 0:38 ` [PATCH net-next 04/14] gtp: udp recv clean up Tom Herbert
2017-09-19 7:44 ` kbuild test robot
2017-09-19 11:32 ` Harald Welte
2017-09-19 0:38 ` [PATCH net-next 05/14] gtp: Remove special mtu handling Tom Herbert
2017-09-19 11:42 ` Harald Welte
2017-09-19 18:12 ` Tom Herbert
2017-09-19 0:38 ` [PATCH net-next 06/14] gtp: Eliminate pktinfo and add port configuration Tom Herbert
2017-09-19 0:38 ` [PATCH net-next 07/14] gtp: Support encapsulation of IPv6 packets Tom Herbert
2017-09-19 4:19 ` David Miller
2017-09-19 12:12 ` Harald Welte
2017-09-19 17:42 ` David Miller
2017-09-20 0:11 ` Tom Herbert
2017-09-19 11:53 ` Harald Welte
2017-09-19 0:38 ` [PATCH net-next 08/14] gtp: Support encpasulating over IPv6 Tom Herbert
2017-09-19 4:19 ` David Miller
2017-09-20 18:03 ` Tom Herbert
2017-09-20 19:45 ` David Miller
2017-09-20 20:40 ` Tom Herbert
2017-09-21 0:04 ` Harald Welte
2017-09-21 0:16 ` Tom Herbert
2017-09-19 11:59 ` Harald Welte
2017-09-19 0:38 ` [PATCH net-next 09/14] gtp: Allow configuring GTP interface as standalone Tom Herbert
2017-09-20 15:27 ` Andreas Schultz
2017-09-20 15:57 ` Tom Herbert
2017-09-20 16:07 ` Andreas Schultz
2017-09-20 16:24 ` Tom Herbert
2017-09-21 0:13 ` Harald Welte
2017-09-21 0:55 ` Tom Herbert
2017-09-21 15:12 ` Harald Welte
2017-09-21 16:43 ` Tom Herbert
2017-09-24 2:16 ` Harald Welte
2017-09-24 15:55 ` Tom Herbert
2017-09-24 16:25 ` Harald Welte
2017-09-24 17:18 ` Tom Herbert
2017-09-19 0:39 ` [PATCH net-next 10/14] gtp: Add support for devnet Tom Herbert
2017-09-19 0:39 ` [PATCH net-next 11/14] net: Add a facility to support application defined GSO Tom Herbert
2017-09-19 4:21 ` David Miller
2017-09-19 0:39 ` [PATCH net-next 12/14] gtp: Configuration for zero UDP checksum Tom Herbert
2017-09-19 4:24 ` David Miller
2017-09-20 18:09 ` Tom Herbert
2017-09-21 1:55 ` Harald Welte
2017-09-21 22:41 ` Tom Herbert
2017-09-19 0:39 ` [PATCH net-next 13/14] gtp: Support for GRO Tom Herbert
2017-09-19 11:57 ` kbuild test robot
2017-09-19 12:03 ` Harald Welte
2017-09-19 0:39 ` [PATCH net-next 14/14] gtp: GSO support Tom Herbert
2017-09-19 12:43 ` [PATCH net-next 00/14] gtp: Additional feature support Harald Welte
2017-09-19 15:59 ` Tom Herbert
2017-09-19 23:19 ` Harald Welte
2017-09-19 23:47 ` Tom Herbert
2017-09-21 15:38 ` Harald Welte
2017-09-20 15:34 ` Andreas Schultz
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170918.211751.1871429944584121281.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=laforge@gnumonks.org \
--cc=netdev@vger.kernel.org \
--cc=pablo@netfilter.org \
--cc=rohit@quantonium.net \
--cc=tom@quantonium.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).