> -----Original Message-----
> From: Jiri Pirko <[email protected]>
> Sent: Thursday, June 20, 2019 7:08 PM
> To: Sudarsana Reddy Kalluru <[email protected]>
> Cc: Jakub Kicinski <[email protected]>; [email protected];
> [email protected]; Michal Kalderon <[email protected]>; Ariel
> Elior <[email protected]>
> Subject: Re: [EXT] Re: [PATCH net-next 4/4] qed: Add devlink support for
> configuration attributes.
>
> Thu, Jun 20, 2019 at 02:09:29PM CEST, [email protected] wrote:
> >> -----Original Message-----
> >> From: Jakub Kicinski <[email protected]>
> >> Sent: Tuesday, June 18, 2019 4:24 AM
> >> To: Sudarsana Reddy Kalluru <[email protected]>
> >> Cc: [email protected]; [email protected]; Michal Kalderon
> >> <[email protected]>; Ariel Elior <[email protected]>; Jiri Pirko
> >> <[email protected]>
> >> Subject: [EXT] Re: [PATCH net-next 4/4] qed: Add devlink support for
> >> configuration attributes.
> >>
> >> External Email
> >>
> >> ---------------------------------------------------------------------
> >> - On Mon, 17 Jun 2019 04:45:28 -0700, Sudarsana Reddy Kalluru wrote:
> >> > This patch adds implementation for devlink callbacks for reading/
> >> > configuring the device attributes.
> >> >
> >> > Signed-off-by: Sudarsana Reddy Kalluru <[email protected]>
> >> > Signed-off-by: Ariel Elior <[email protected]>
> >>
> >> You need to provide documentation for your parameters, plus some of
> >> them look like they should potentially be port params, not device params.
> >
> >Thanks a lot for your review. Will add the required documentation. In case
> of Marvell adapter, any of the device/adapter/port parameters can be
> read/configurable via any PF (ethdev) on the port. Hence adding the
> commands at device level. Hope this is fine.
>
> No it is not. Port param should be port param.
>
> Also please be careful not to add any generic param as driver specific.
>
> Thanks!
Apologies for bringing this topic again. From the driver(s) code paths/'devlink
man pages', I understood that devlink-port object is an entity on top of the
PCI bus device.
Some drivers say NFP represents vnics (on pci-dev) as a devlink-ports and, some
represents (virtual?) ports on the PF/device as devlink-ports.
In the case of Marvell NIC driver, we don't have [port] partitioning of the PCI
device. And the config attributes are specific to PCI-device (not the
vports/vnics of PF).
Hence I didn't see a need for creating devlink-port objects in the system for
Marvell NICs. And planning to add the config attributes to 'devlink-dev' object.
Please let me know if my understanding and the proposal is ok?
Code paths which use devlink-port:
mlx4_load_one(struct pci_dev *pdev): mlx4_init_port_info(1 ..
dev->caps.num_ports) -> devlink_port_register()
nfp_net_pf_init_vnics (1 .. pf->vnics) -> nfp_net_pf_init_vnic() ->
nfp_devlink_port_register()
nsim_dev_probe (1 .. nsim_bus_dev->port_count) -> __nsim_dev_port_add() ->
devlink_port_register ()
man page for 'devlink-port':
devlink port set - change devlink port attributes
DEV/PORT_INDEX - specifies the devlink port to operate on.
devlink port show pci/0000:01:00.0/1
Shows the state of specified devlink port.
