From: Jiri Pirko <jiri@resnulli.us>
To: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Ido Schimmel <idosch@idosch.org>, netdev <netdev@vger.kernel.org>,
David Miller <davem@davemloft.net>,
David Ahern <dsahern@gmail.com>, Jiri Pirko <jiri@mellanox.com>,
Jakub Kicinski <jakub.kicinski@netronome.com>,
Saeed Mahameed <saeedm@mellanox.com>, mlxsw <mlxsw@mellanox.com>,
Ido Schimmel <idosch@mellanox.com>
Subject: Re: [RFC PATCH net-next 12/15] ipv4: Add "in hardware" indication to routes
Date: Wed, 2 Oct 2019 20:21:19 +0200 [thread overview]
Message-ID: <20191002182119.GF2279@nanopsycho> (raw)
In-Reply-To: <CAJieiUiEHyU1UbX_rJGb-Ggnwk6SA6paK_zXvxyuYJSrah+8vg@mail.gmail.com>
Wed, Oct 02, 2019 at 05:58:52PM CEST, roopa@cumulusnetworks.com wrote:
>On Wed, Oct 2, 2019 at 1:41 AM Ido Schimmel <idosch@idosch.org> wrote:
>>
>> From: Ido Schimmel <idosch@mellanox.com>
>>
>> When performing L3 offload, routes and nexthops are usually programmed
>> into two different tables in the underlying device. Therefore, the fact
>> that a nexthop resides in hardware does not necessarily mean that all
>> the associated routes also reside in hardware and vice-versa.
>>
*****
>> While the kernel can signal to user space the presence of a nexthop in
>> hardware (via 'RTNH_F_OFFLOAD'), it does not have a corresponding flag
>> for routes. In addition, the fact that a route resides in hardware does
>> not necessarily mean that the traffic is offloaded. For example,
>> unreachable routes (i.e., 'RTN_UNREACHABLE') are programmed to trap
>> packets to the CPU so that the kernel will be able to generate the
>> appropriate ICMP error packet.
*****
>>
>> This patch adds an "in hardware" indication to IPv4 routes, so that
>> users will have better visibility into the offload process. In the
>> future IPv6 will be extended with this indication as well.
>>
>> 'struct fib_alias' is extended with a new field that indicates if
>> the route resides in hardware or not. Note that the new field is added
>> in the 6 bytes hole and therefore the struct still fits in a single
>> cache line [1].
>>
>> Capable drivers are expected to invoke fib_alias_in_hw_{set,clear}()
>> with the route's key in order to set / clear the "in hardware
>> indication".
>>
>> The new indication is dumped to user space via a new flag (i.e.,
>> 'RTM_F_IN_HW') in the 'rtm_flags' field in the ancillary header.
>>
>
>nice series Ido. why not call this RTM_F_OFFLOAD to keep it consistent
>with the nexthop offload indication ?.
See the second paragraph of this description.
>But this again does not seem to be similar to the other request flags
>like: RTM_F_FIB_MATCH
>
>(so far i think all the RTNH_F_* flags are used on routes too IIRC
>(see iproute2: print_rt_flags)
>RTNH_F_DEAD seems to fall in this category)
next prev parent reply other threads:[~2019-10-02 18:21 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-02 8:40 [RFC PATCH net-next 00/15] Simplify IPv4 route offload API Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 01/15] ipv4: Add temporary events to the FIB notification chain Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 02/15] ipv4: Notify route after insertion to the routing table Ido Schimmel
2019-10-03 1:34 ` David Ahern
2019-10-03 5:16 ` Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 03/15] ipv4: Notify route if replacing currently offloaded one Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 04/15] ipv4: Notify newly added route if should be offloaded Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 05/15] ipv4: Handle route deletion notification Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 06/15] ipv4: Handle route deletion notification during flush Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 07/15] ipv4: Only Replay routes of interest to new listeners Ido Schimmel
2019-10-02 17:44 ` Jiri Pirko
2019-10-03 13:04 ` Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 08/15] mlxsw: spectrum_router: Start using new IPv4 route notifications Ido Schimmel
2019-10-02 17:52 ` Jiri Pirko
2019-10-02 18:01 ` Jiri Pirko
2019-10-03 15:10 ` Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 09/15] ipv4: Remove old route notifications and convert listeners Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 10/15] ipv4: Replace route in list before notifying Ido Schimmel
2019-10-02 8:40 ` [RFC PATCH net-next 11/15] ipv4: Encapsulate function arguments in a struct Ido Schimmel
2019-10-02 8:41 ` [RFC PATCH net-next 12/15] ipv4: Add "in hardware" indication to routes Ido Schimmel
2019-10-02 15:58 ` Roopa Prabhu
2019-10-02 18:21 ` Jiri Pirko [this message]
2019-10-03 2:34 ` David Ahern
2019-10-03 5:37 ` Ido Schimmel
2019-10-04 1:55 ` David Ahern
2019-10-04 14:43 ` Ido Schimmel
2019-10-04 16:38 ` David Ahern
2019-10-04 17:43 ` Roopa Prabhu
2019-10-04 23:20 ` David Ahern
2019-10-03 5:40 ` Jiri Pirko
2019-10-03 12:59 ` Ido Schimmel
2019-10-04 4:25 ` Roopa Prabhu
2019-10-02 8:41 ` [RFC PATCH net-next 13/15] mlxsw: spectrum_router: Mark routes as "in hardware" Ido Schimmel
2019-10-02 18:27 ` Jiri Pirko
2019-10-03 15:16 ` Ido Schimmel
2019-10-02 8:41 ` [RFC PATCH net-next 14/15] netdevsim: fib: " Ido Schimmel
2019-10-02 8:41 ` [RFC PATCH net-next 15/15] selftests: netdevsim: Add test for route offload API Ido Schimmel
2019-10-02 18:17 ` [RFC PATCH net-next 00/15] Simplify IPv4 " Jiri Pirko
2019-10-03 5:18 ` Ido Schimmel
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=20191002182119.GF2279@nanopsycho \
--to=jiri@resnulli.us \
--cc=davem@davemloft.net \
--cc=dsahern@gmail.com \
--cc=idosch@idosch.org \
--cc=idosch@mellanox.com \
--cc=jakub.kicinski@netronome.com \
--cc=jiri@mellanox.com \
--cc=mlxsw@mellanox.com \
--cc=netdev@vger.kernel.org \
--cc=roopa@cumulusnetworks.com \
--cc=saeedm@mellanox.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.