From: Jason Gunthorpe <jgg@nvidia.com>
To: Parav Pandit <parav@nvidia.com>
Cc: Edwin Peer <edwin.peer@broadcom.com>,
Saeed Mahameed <saeed@kernel.org>,
"David S. Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>, netdev <netdev@vger.kernel.org>,
"linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>,
Alexander Duyck <alexander.duyck@gmail.com>,
Sridhar Samudrala <sridhar.samudrala@intel.com>,
David Ahern <dsahern@kernel.org>,
Kiran Patil <kiran.patil@intel.com>,
Jacob Keller <jacob.e.keller@intel.com>,
"Ertman, David M" <david.m.ertman@intel.com>,
Dan Williams <dan.j.williams@intel.com>,
Saeed Mahameed <saeedm@nvidia.com>
Subject: Re: [pull request][net-next V10 00/14] Add mlx5 subfunction support
Date: Mon, 25 Jan 2021 09:22:10 -0400 [thread overview]
Message-ID: <20210125132210.GJ4147@nvidia.com> (raw)
In-Reply-To: <BY5PR12MB43229840037E730F884C3356DCBD9@BY5PR12MB4322.namprd12.prod.outlook.com>
On Mon, Jan 25, 2021 at 10:57:14AM +0000, Parav Pandit wrote:
> Hi Edwin,
>
> > From: Edwin Peer <edwin.peer@broadcom.com>
> > Sent: Monday, January 25, 2021 2:17 AM
> >
> > On Fri, Jan 22, 2021 at 11:37 AM Saeed Mahameed <saeed@kernel.org>
> > wrote:
> >
> > > For more detailed information about subfunctions please see detailed tag
> > > log below.
> >
> > Apologies for the tardy question out of left field, but I've been
> > thinking about this some more. If I recall, the primary motivation for
> > this was a means to effectively address more VFs? But, why can't the
> > device simply expose more bus numbers?
>
> Several weeks back, Jason already answered this VF scaling question
> from you at discussion [1].
To add a little more colour, the PCI spec design requires a CAM (ie
search) to figure out which function an incoming address is connected
to because there are no restrictions on how BAR's of each function
have to be layed out.
SRIOV and SF's require a simple linear lookup to learn the "function"
because the BAR space is required to be linear.
Scaling a CAM to high sizes is physicaly infeasible, so all approaches
to scaling PCI functions go this road of having a single large BAR
space.
Jason
next prev parent reply other threads:[~2021-01-25 13:25 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-22 19:36 [pull request][net-next V10 00/14] Add mlx5 subfunction support Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 01/14] devlink: Prepare code to fill multiple port function attributes Saeed Mahameed
2021-01-29 1:40 ` patchwork-bot+netdevbpf
2021-01-22 19:36 ` [net-next V10 02/14] devlink: Introduce PCI SF port flavour and port attribute Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 03/14] devlink: Support add and delete devlink port Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 04/14] devlink: Support get and set state of port function Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 05/14] net/mlx5: Introduce vhca state event notifier Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 06/14] net/mlx5: SF, Add auxiliary device support Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 07/14] net/mlx5: SF, Add auxiliary device driver Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 08/14] net/mlx5: E-switch, Prepare eswitch to handle SF vport Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 09/14] net/mlx5: E-switch, Add eswitch helpers for " Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 10/14] net/mlx5: SF, Add port add delete functionality Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 11/14] net/mlx5: SF, Port function state change support Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 12/14] devlink: Add devlink port documentation Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 13/14] devlink: Extend devlink port documentation for subfunctions Saeed Mahameed
2021-01-22 19:36 ` [net-next V10 14/14] net/mlx5: Add devlink subfunction port documentation Saeed Mahameed
2021-01-24 20:47 ` [pull request][net-next V10 00/14] Add mlx5 subfunction support Edwin Peer
2021-01-25 10:57 ` Parav Pandit
2021-01-25 13:22 ` Jason Gunthorpe [this message]
2021-01-25 19:23 ` Edwin Peer
2021-01-25 19:49 ` Jason Gunthorpe
2021-01-25 20:05 ` Edwin Peer
2021-01-25 20:22 ` Michael Chan
2021-01-25 20:26 ` Parav Pandit
2021-01-25 18:35 ` Edwin Peer
2021-01-25 19:34 ` Edwin Peer
2021-01-25 19:59 ` Jason Gunthorpe
2021-01-25 20:22 ` Edwin Peer
2021-01-25 20:41 ` Jason Gunthorpe
2021-01-25 21:23 ` Edwin Peer
2021-01-25 23:13 ` Jason Gunthorpe
2021-01-27 1:34 ` Jakub Kicinski
2021-01-29 0:03 ` Saeed Mahameed
2021-01-29 0:11 ` Jakub Kicinski
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=20210125132210.GJ4147@nvidia.com \
--to=jgg@nvidia.com \
--cc=alexander.duyck@gmail.com \
--cc=dan.j.williams@intel.com \
--cc=davem@davemloft.net \
--cc=david.m.ertman@intel.com \
--cc=dsahern@kernel.org \
--cc=edwin.peer@broadcom.com \
--cc=jacob.e.keller@intel.com \
--cc=kiran.patil@intel.com \
--cc=kuba@kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=parav@nvidia.com \
--cc=saeed@kernel.org \
--cc=saeedm@nvidia.com \
--cc=sridhar.samudrala@intel.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;
as well as URLs for NNTP newsgroup(s).