Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
From: Moshe Shemesh <moshe@nvidia.com>
To: Jakub Kicinski <kuba@kernel.org>
Cc: Tariq Toukan <tariqt@nvidia.com>,
	Eric Dumazet <edumazet@google.com>,
	Paolo Abeni <pabeni@redhat.com>,
	Andrew Lunn <andrew+netdev@lunn.ch>,
	"David S. Miller" <davem@davemloft.net>,
	Saeed Mahameed <saeedm@nvidia.com>,
	"Leon Romanovsky" <leon@kernel.org>,
	Mark Bloch <mbloch@nvidia.com>,
	"Akiva Goldberger" <agoldberger@nvidia.com>,
	<netdev@vger.kernel.org>, <linux-rdma@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>, Gal Pressman <gal@nvidia.com>,
	Dragos Tatulea <dtatulea@nvidia.com>
Subject: Re: [PATCH net-next 0/8] net/mlx5: Prepare eswitch infrastructure for satellite PF support
Date: Fri, 15 May 2026 12:36:50 +0300	[thread overview]
Message-ID: <e5e1ae53-a458-4248-87b9-aa1e1a241571@nvidia.com> (raw)
In-Reply-To: <20260514161649.7a59a547@kernel.org>



On 5/15/2026 2:16 AM, Jakub Kicinski wrote:
> On Thu, 14 May 2026 10:56:26 +0300 Moshe Shemesh wrote:
>> Satellite PF is another type of Physical Function, its role and
>> privileges are similar to the host PF, but unlike host PF the Satellite
>> PF is on the DPU and not on another host. So it's kind of "Satellite"
>> for the ECPF which is also on the DPU.
> 
> Do you genuinely think these 2 sentences explain anything?
> 
> Maybe it's just me. If anyone reading this thinks Moshe's explanation
> clarifies things - please speak up..

OK, let me explain the idea of this feature:
Currently in Smartnic configuration we have 2 Physical Functions : one 
is the ECPF on the DPU, and it is the eswitch manager and page manager, 
while the other is the host PF on the external host and it doesn't have 
privileges of eswitch manager or page manager.

Now we have a new Smartnic configuration that adds another physical 
function, on the DPU, that is not eswitch manager and not page manager. 
The new PF can have its own SFs and the customer can passthrough this 
Satellite PF to a VM on the DPU and give it to a user that should not 
have access to the ECPF privileged function.
As will be shown in the next patchset, the ECPF handles the Satellite PF 
and the Host PF in a similar way, using the same management framework.


      reply	other threads:[~2026-05-15  9:37 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-10  5:34 [PATCH net-next 0/8] net/mlx5: Prepare eswitch infrastructure for satellite PF support Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 1/8] net/mlx5: Use helper to parse host PF info Tariq Toukan
2026-05-14 19:19   ` Simon Horman
2026-05-10  5:34 ` [PATCH net-next 2/8] net/mlx5: Use v1 response layout for query_esw_functions Tariq Toukan
2026-05-14 19:18   ` Simon Horman
2026-05-15 11:59     ` Moshe Shemesh
2026-05-10  5:34 ` [PATCH net-next 3/8] net/mlx5: Use mlx5_eswitch_is_vf_vport() for IPsec VF checks Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 4/8] net/mlx5: Switch vport HCA cap helpers to kvzalloc Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 5/8] net/mlx5: Add mlx5_vport_set_other_func_general_cap macro Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 6/8] net/mlx5: Refactor mlx5_set_msix_vec_count() SET_HCA_CAP Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 7/8] net/mlx5: Use vport helper for IPsec eswitch set caps Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 8/8] net/mlx5: Generalize enable/disable HCA for any PF vport Tariq Toukan
2026-05-14  2:25 ` [PATCH net-next 0/8] net/mlx5: Prepare eswitch infrastructure for satellite PF support Jakub Kicinski
2026-05-14  7:56   ` Moshe Shemesh
2026-05-14  9:53     ` Paolo Abeni
2026-05-14  9:59       ` Paolo Abeni
2026-05-14 23:16     ` Jakub Kicinski
2026-05-15  9:36       ` Moshe Shemesh [this message]

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=e5e1ae53-a458-4248-87b9-aa1e1a241571@nvidia.com \
    --to=moshe@nvidia.com \
    --cc=agoldberger@nvidia.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=dtatulea@nvidia.com \
    --cc=edumazet@google.com \
    --cc=gal@nvidia.com \
    --cc=kuba@kernel.org \
    --cc=leon@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=mbloch@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=saeedm@nvidia.com \
    --cc=tariqt@nvidia.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