From: "Saleem, Shiraz" <shiraz.saleem@intel.com>
To: Parav Pandit <parav@nvidia.com>,
"dledford@redhat.com" <dledford@redhat.com>,
Jason Gunthorpe <jgg@nvidia.com>,
"kuba@kernel.org" <kuba@kernel.org>,
"davem@davemloft.net" <davem@davemloft.net>
Cc: "linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
"Ertman, David M" <david.m.ertman@intel.com>,
"Nguyen, Anthony L" <anthony.l.nguyen@intel.com>
Subject: RE: [PATCH v2 05/23] ice: Add devlink params support
Date: Thu, 25 Mar 2021 20:10:13 +0000 [thread overview]
Message-ID: <9ae54c8e60fe4036bd3016cfa0798dac@intel.com> (raw)
In-Reply-To: <BY5PR12MB43228B823CA619460AAF2099DC639@BY5PR12MB4322.namprd12.prod.outlook.com>
> Subject: RE: [PATCH v2 05/23] ice: Add devlink params support
>
> Hi Shiraz,
>
> > From: Shiraz Saleem <shiraz.saleem@intel.com>
> > Sent: Wednesday, March 24, 2021 5:30 AM
> >
> > Add two new runtime RDMA related devlink parameters to ice driver.
> > 'rdma_resource_limits_sel' is driver-specific while 'rdma_protocol' is generic.
> > Configuration changes result in unplugging the auxiliary RDMA device
> > and re- plugging it with updated values for irdma auxiiary driver to
> > consume at
> > drv.probe()
> >
> > Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
> > ---
> > .../networking/devlink/devlink-params.rst | 6 +
> > Documentation/networking/devlink/ice.rst | 35 +++++
> > drivers/net/ethernet/intel/ice/ice_devlink.c | 146
> > ++++++++++++++++++++-
> > drivers/net/ethernet/intel/ice/ice_devlink.h | 6 +
> > drivers/net/ethernet/intel/ice/ice_main.c | 2 +
> > include/net/devlink.h | 4 +
> > net/core/devlink.c | 5 +
> > 7 files changed, 202 insertions(+), 2 deletions(-)
> >
>
> [..]
> > +.. list-table:: Driver-specific parameters implemented
> > + :widths: 5 5 5 85
> > +
> > + * - Name
> > + - Type
> > + - Mode
> > + - Description
> > + * - ``rdma_resource_limits_sel``
> > + - string
> > + - runtime
> > + - Selector to limit the RDMA resources configured for the
> > + device. The
> > range
> > + is between 0 and 7 with a default value equal to 3. Each
> > + selector
> > supports
> > + up to the value specified in the table.
> > + - 0: 128 QPs
> > + - 1: 1K QPs
> > + - 2: 2K QPs
> > + - 3: 4K QPs
> > + - 4: 16K QPs
> > + - 5: 64K QPs
> > + - 6: 128K QPs
> > + - 7: 256K QPs
>
> Resources are better represented as devlink resource.
> Such as,
>
> $ devlink resource set pci/0000:06:00.0 /rdma/max_qps 16384 $ devlink resource
> set pci/0000:06:00.0 /rdma/max_cqs 8192 $ devlink resource set pci/0000:06:00.0
> /rdma/max_mrs 16384
>
Hi Parav - Thank you for the feedback.
Maybe I am missing something but I see that a devlink hot reload is required to enforce the update?
There isn't really a de-init required of PCI driver entities in this case for this rdma param.
But only an unplug, plug of the auxdev with new value. Intuitively it feels more runtime-ish.
There is also a device powerof2 requirement on the maxqp which I don't see enforceable as it stands.
This is not super-critical for the initial submission but a nice to have. But I do want to brainstorm options..
Shiraz
next prev parent reply other threads:[~2021-03-25 20:11 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-23 23:59 [PATCH v2 00/23] Add Intel Ethernet Protocol Driver for RDMA (irdma) Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 01/23] iidc: Introduce iidc.h Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 02/23] ice: Initialize RDMA support Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 03/23] ice: Implement iidc operations Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 04/23] ice: Register auxiliary device to provide RDMA Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 05/23] ice: Add devlink params support Shiraz Saleem
2021-03-24 4:50 ` Parav Pandit
2021-03-25 20:10 ` Saleem, Shiraz [this message]
2021-03-26 5:42 ` Parav Pandit
2021-03-29 16:07 ` Jason Gunthorpe
2021-03-29 16:25 ` Saleem, Shiraz
2021-03-23 23:59 ` [PATCH v2 06/23] i40e: Prep i40e header for aux bus conversion Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 07/23] i40e: Register auxiliary devices to provide RDMA Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 08/23] RDMA/irdma: Register auxiliary driver and implement private channel OPs Shiraz Saleem
2021-03-24 13:47 ` Leon Romanovsky
2021-03-24 14:00 ` Jason Gunthorpe
2021-03-24 14:17 ` Leon Romanovsky
2021-03-24 14:35 ` Jason Gunthorpe
2021-03-24 23:46 ` Saleem, Shiraz
2021-03-25 8:45 ` Leon Romanovsky
2021-03-23 23:59 ` [PATCH v2 09/23] RDMA/irdma: Implement device initialization definitions Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 10/23] RDMA/irdma: Implement HW Admin Queue OPs Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 11/23] RDMA/irdma: Add HMC backing store setup functions Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 12/23] RDMA/irdma: Add privileged UDA queue implementation Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 13/23] RDMA/irdma: Add QoS definitions Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 14/23] RDMA/irdma: Add connection manager Shiraz Saleem
2021-03-23 23:59 ` [PATCH v2 15/23] RDMA/irdma: Add PBLE resource manager Shiraz Saleem
2021-03-24 0:00 ` [PATCH v2 16/23] RDMA/irdma: Implement device supported verb APIs Shiraz Saleem
2021-03-24 0:00 ` [PATCH v2 17/23] RDMA/irdma: Add RoCEv2 UD OP support Shiraz Saleem
2021-03-24 0:00 ` [PATCH v2 18/23] RDMA/irdma: Add user/kernel shared libraries Shiraz Saleem
2021-03-24 0:00 ` [PATCH v2 19/23] RDMA/irdma: Add miscellaneous utility definitions Shiraz Saleem
2021-03-24 0:00 ` [PATCH v2 20/23] RDMA/irdma: Add dynamic tracing for CM Shiraz Saleem
2021-03-24 0:00 ` [PATCH v2 21/23] RDMA/irdma: Add ABI definitions Shiraz Saleem
2021-03-24 0:00 ` [PATCH v2 22/23] RDMA/irdma: Add irdma Kconfig/Makefile and remove i40iw Shiraz Saleem
2021-03-24 18:54 ` Randy Dunlap
2021-03-24 23:47 ` Saleem, Shiraz
2021-03-24 0:00 ` [PATCH v2 23/23] RDMA/irdma: Update MAINTAINERS file Shiraz Saleem
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=9ae54c8e60fe4036bd3016cfa0798dac@intel.com \
--to=shiraz.saleem@intel.com \
--cc=anthony.l.nguyen@intel.com \
--cc=davem@davemloft.net \
--cc=david.m.ertman@intel.com \
--cc=dledford@redhat.com \
--cc=jgg@nvidia.com \
--cc=kuba@kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=parav@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;
as well as URLs for NNTP newsgroup(s).