All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: netdev@vger.kernel.org, "(JC),
	Jayachandran" <j-rameshbabu@ti.com>,
	"David S. Miller" <davem@davemloft.net>,
	Andrew Lunn <andrew+netdev@lunn.ch>,
	Chintan Vankar <c-vankar@ti.com>,
	Danish Anwar <danishanwar@ti.com>, Daolin Qiu <d-qiu@ti.com>,
	Eric Dumazet <edumazet@google.com>,
	Felix Maurer <fmaurer@redhat.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Richard Cochran <richardcochran@gmail.com>,
	Simon Horman <horms@kernel.org>
Subject: Re: [PATCH RFC net-next v2 2/2] af_packet: Add port specific handling for HSR
Date: Tue, 24 Mar 2026 17:38:20 +0100	[thread overview]
Message-ID: <20260324163820.p9M2z27W@linutronix.de> (raw)
In-Reply-To: <willemdebruijn.kernel.8e323262df61@gmail.com>

On 2026-03-19 12:27:57 [-0400], Willem de Bruijn wrote:
> 
> Right, so this is simple without hardware offload. Does this HW
> offload exist, or is this aspirational. At least for infrequent PTP
> it does not sound important.

The snippet below was for the icssg driver as-is and it works with
updated firmware to ignore PTP packets while HW offloading is enabled.

The hardware offload in general forwards the packets without linux so if
a packet arrives on port A, the HW forwards it on port B and the linux
networking stack receives one copy and does not need to forward it
anymore.
This "cut-through" forwarding is beneficial because the packet is
forwarded instantly without getting delayed by the software stack.

For PTP packets I don't want any of this because the forwarding breaks
the timestamp information. So I need to tell the driver not do any of
the offloading while sending and the updated firmware does the same for
incoming packets.

There is no HW-offloading of PTP related packets.

With the skb_ext I had, the mechanism was mostly the same but it relied
only on the skb_ext data. Now it has to look at skb->mark.

Sebastian

  reply	other threads:[~2026-03-24 16:38 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-09 15:52 [PATCH RFC net-next v2 0/2] hsr: Add additional info to send/ receive skbs Sebastian Andrzej Siewior
2026-03-09 15:52 ` [PATCH RFC net-next v2 1/2] hsr: Allow to send a specific port and with HSR header Sebastian Andrzej Siewior
2026-03-12  4:09   ` kernel test robot
2026-03-12  4:48   ` kernel test robot
2026-03-09 15:52 ` [PATCH RFC net-next v2 2/2] af_packet: Add port specific handling for HSR Sebastian Andrzej Siewior
2026-03-10  1:38   ` Willem de Bruijn
2026-03-10 10:55     ` Sebastian Andrzej Siewior
2026-03-10 21:35       ` Willem de Bruijn
2026-03-12 15:42         ` Sebastian Andrzej Siewior
2026-03-12 21:43           ` Willem de Bruijn
2026-03-13  9:22             ` Sebastian Andrzej Siewior
2026-03-13 16:04               ` Sebastian Andrzej Siewior
2026-03-16 20:12                 ` Willem de Bruijn
2026-03-17 17:29                   ` Sebastian Andrzej Siewior
2026-03-19 13:29                     ` Willem de Bruijn
2026-03-19 14:26                       ` Sebastian Andrzej Siewior
2026-03-19 16:27                         ` Willem de Bruijn
2026-03-24 16:38                           ` Sebastian Andrzej Siewior [this message]
2026-04-02 16:32                             ` Sebastian Andrzej Siewior
2026-04-06 14:47                               ` Willem de Bruijn
2026-04-16 16:18                                 ` Sebastian Andrzej Siewior
2026-04-21  7:41                                   ` Willem de Bruijn
2026-04-22 13:27                                     ` Sebastian Andrzej Siewior

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=20260324163820.p9M2z27W@linutronix.de \
    --to=bigeasy@linutronix.de \
    --cc=andrew+netdev@lunn.ch \
    --cc=c-vankar@ti.com \
    --cc=d-qiu@ti.com \
    --cc=danishanwar@ti.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=fmaurer@redhat.com \
    --cc=horms@kernel.org \
    --cc=j-rameshbabu@ti.com \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=richardcochran@gmail.com \
    --cc=willemdebruijn.kernel@gmail.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.