XDP hardware hints discussion mail archive
 help / color / mirror / Atom feed
From: Jakub Kicinski <kuba@kernel.org>
To: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Stanislav Fomichev <sdf@google.com>,
	bpf@vger.kernel.org, ast@kernel.org, daniel@iogearbox.net,
	andrii@kernel.org, martin.lau@linux.dev, song@kernel.org,
	yhs@fb.com, john.fastabend@gmail.com, kpsingh@kernel.org,
	haoluo@google.com, jolsa@kernel.org, toke@kernel.org,
	willemb@google.com, dsahern@kernel.org,
	magnus.karlsson@intel.com, bjorn@kernel.org,
	maciej.fijalkowski@intel.com, hawk@kernel.org,
	netdev@vger.kernel.org, xdp-hints@xdp-project.net
Subject: [xdp-hints] Re: [RFC bpf-next v3 09/14] net/mlx5e: Implement devtx kfuncs
Date: Tue, 11 Jul 2023 17:32:26 -0700	[thread overview]
Message-ID: <20230711173226.7e9cca4a@kernel.org> (raw)
In-Reply-To: <20230711225657.kuvkil776fajonl5@MacBook-Pro-8.local>

On Tue, 11 Jul 2023 15:56:57 -0700 Alexei Starovoitov wrote:
> I think this proves my point: csum is not generalizable even across veth and mlx5.
> Above is a square peg that tries to fit csum_start/offset api (that makes sense from SW pov)
> into HW that has different ideas about csum-ing.
> 
> Here is what mlx5 does:
> mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
>                             struct mlx5e_accel_tx_state *accel,
>                             struct mlx5_wqe_eth_seg *eseg)
> {
>         if (unlikely(mlx5e_ipsec_txwqe_build_eseg_csum(sq, skb, eseg)))
>                 return;
> 
>         if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
>                 eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
>                 if (skb->encapsulation) {

This should be irrelevant today, as LCO exists?

>                         eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM |
>                                           MLX5_ETH_WQE_L4_INNER_CSUM;
>                         sq->stats->csum_partial_inner++;
>                 } else {
>                         eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
>                         sq->stats->csum_partial++;
>                 }
> 
> How would you generalize that into csum api that will work across NICs ?
> 
> My answer stands: you cannot.
> 
> My proposal again:
> add driver specifc kfuncs and hooks for things like csum.
> 
> Kuba,
> since you nacked driver specific stuff please suggest a way to unblock this stalemate.

I hope I'm not misremembering but I think I suggested at the beginning
to create a structure describing packet geometry and requested offloads,
and for the prog fill that in.

All operating systems I know end up doing that, we'll end up doing
that as well. The question is whether we're willing to learn from
experience or prefer to go on a wild ride first...

  parent reply	other threads:[~2023-07-12  0:32 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-07 19:29 [xdp-hints] [RFC bpf-next v3 00/14] bpf: Netdev TX metadata Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 01/14] bpf: Rename some xdp-metadata functions into dev-bound Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 02/14] bpf: Make it easier to add new metadata kfunc Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 03/14] xsk: Support XDP_TX_METADATA_LEN Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 04/14] bpf: Implement devtx hook points Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 05/14] bpf: Implement devtx timestamp kfunc Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 06/14] net: veth: Implement devtx timestamp kfuncs Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 07/14] bpf: Introduce tx checksum devtx kfuncs Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 08/14] net: veth: Implement devtx tx checksum Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 09/14] net/mlx5e: Implement devtx kfuncs Stanislav Fomichev
2023-07-11 22:56   ` [xdp-hints] " Alexei Starovoitov
2023-07-11 23:24     ` Stanislav Fomichev
2023-07-11 23:45       ` Alexei Starovoitov
2023-07-12  0:14         ` Stanislav Fomichev
2023-07-12  2:50           ` Alexei Starovoitov
2023-07-12  3:29             ` Stanislav Fomichev
2023-07-12  4:59               ` Alexei Starovoitov
2023-07-12  5:36                 ` Stanislav Fomichev
2023-07-12 15:16                   ` Willem de Bruijn
2023-07-12 16:28                     ` Willem de Bruijn
2023-07-12 19:03                     ` Alexei Starovoitov
2023-07-12 19:11                       ` Willem de Bruijn
2023-07-12 19:42                         ` Alexei Starovoitov
2023-07-12 20:09                           ` Jakub Kicinski
2023-07-12 20:53                             ` Stanislav Fomichev
2023-07-12  0:32     ` Jakub Kicinski [this message]
2023-07-12  2:37       ` Alexei Starovoitov
2023-07-12  3:07         ` Jakub Kicinski
2023-07-12  3:23           ` Alexei Starovoitov
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 10/14] selftests/xsk: Support XDP_TX_METADATA_LEN Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 11/14] selftests/bpf: Add helper to query current netns cookie Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 12/14] selftests/bpf: Add csum helpers Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 13/14] selftests/bpf: Extend xdp_metadata with devtx kfuncs Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 14/14] selftests/bpf: Extend xdp_hw_metadata " Stanislav Fomichev

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

  List information: https://lists.xdp-project.net/postorius/lists/xdp-hints.xdp-project.net/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230711173226.7e9cca4a@kernel.org \
    --to=kuba@kernel.org \
    --cc=alexei.starovoitov@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bjorn@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=dsahern@kernel.org \
    --cc=haoluo@google.com \
    --cc=hawk@kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=maciej.fijalkowski@intel.com \
    --cc=magnus.karlsson@intel.com \
    --cc=martin.lau@linux.dev \
    --cc=netdev@vger.kernel.org \
    --cc=sdf@google.com \
    --cc=song@kernel.org \
    --cc=toke@kernel.org \
    --cc=willemb@google.com \
    --cc=xdp-hints@xdp-project.net \
    --cc=yhs@fb.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox