Re: [PATCH RESEND iproute2-next] devlink: Add optional controller user input

On 2021/6/7 19:12, Parav Pandit wrote:

quoted

From: Yunsheng Lin <redacted>
Sent: Monday, June 7, 2021 4:27 PM

[..]

quoted

quoted

quoted

2. each PF's devlink instance has three types of port, which is
   FLAVOUR_PHYSICAL, FLAVOUR_PCI_PF and

FLAVOUR_PCI_VF(supposing I

quoted

quoted

understand
   port flavour correctly).

FLAVOUR_PCI_{PF,VF,SF} belongs to eswitch (representor) side on

switchdev device.

If devlink instance or eswitch is in DEVLINK_ESWITCH_MODE_LEGACY mode,
the FLAVOUR_PCI_{PF,VF,SF} port instance does not need to created?

No. in eswitch legacy, there are no representor netdevice or devlink ports.

It seems each devlink port instance corresponds to a netdevice.
More specificly, the devlink instance is created in the
struct pci_driver' probe function of a pci function, a devlink
port instance is created and registered to that devlink instance
when a netdev of that pci function is created?

As in diagram [1], the devlink port instance(flavour FLAVOUR_PHYSICAL)
for ctrl-0-pf0 is created when the netdev of ctrl-0-pf0 is created in
the host of smartNIC, the devlink port instance(flavour FLAVOUR_VIRTUAL)
for ctrl-0-pf0vfN is created when the netdev of ctrl-0-pf0vfN is created
in the host of smartNIC, right?

When eswitch mode is set to DEVLINK_ESWITCH_MODE_SWITCHDEV, the representor
netdev for PF/VF in "controller_num=1" is created in the host of smartNIC,
so is the devlink port instance(FLAVOUR_PCI_{PF,VF,SF}) corresponding to that
representor netdev just created in the host of smartNIC? More specificly,
devlink port instance(flavour FLAVOUR_PCI_PF) for ctrl-1-pf0 and devlink port
instance (flavour FLAVOUR_PCI_VF)for ctrl-1-pf0vfN?

When "controller_num=1" is plugged to a server, the server host creates
devlink instance and devlink port instance in the host of server as
similar as the ctrl-0-pf0 and ctrl-0-pf0vfN in the host of smartNIC?

quoted

quoted

quoted

If I understand above correctly, all ports in the same devlink
instance should have the same controller id, right? If yes, why not
put the controller id in the devlink instance?

Need not be. All PCI_{PF,VF,SF} can have controller id different for

different controllers.

The point is that two VF from different PF may be in the different host, all VF
of a specific PF need to be in the same host, right?
otherwise it may break PCI enumeration process?

Sure. VFs belong to PF, PF belong to controller, controller is plugged into a host root complex.

quoted

If yes, as PCI_{PF,VF,SF} belongs to eswitch (representor) side on switchdev
device(which means PCI_{PF,VF,SF} port instance is in the same host, as the
host corresponding to "controller_num=0" in diagram [1]), so it seems all the
PCI_{PF,VF,SF} of a specific PF should have the same controller id, 

Yes.

quoted

and using
a controller id of the devlink instance in "controller_num=0" in diagram [1]
seems enough?

Yes.

quoted

quoted

Usually each multi-host is a different controller.
Refer to this diagram [1] and detailed description.

devlink instance does not exist in the host corresponding to
"controller_num=1" in diagram [1]?

Devlink instance do exist for controller=1 related PCI PF,VF,SF devices when those functions are plugged in the host.

quoted

Or devlink instance does exist in the host corresponding to
"controller_num=1", but the mode of that devlink instance is
DEVLINK_ESWITCH_MODE_LEGACY in diagram [1]?

As you can see that eswitch is located only on controller=0.
This eswitch is serving PF, VF, SFs of controller=1 + controlloler=0 as well.

How do we decide where eswitch is located? through some fw/hw
configuration?

It seems if the eswitch is enabled on "controller=1", that is
a nested eswitch too, which you mentioned below?

quoted

Also, eswitch mode can only be set on the devlink instance corresponding to
PF, but not for VF/SF(supposing that VF/SF could have it's own devlink
instance too), right?

Yes. Eswitch can be located on the VF too. Mlx5 driver doesn't have it yet on VF.
This may be some nested eswitch in future. I do not know when.

quoted

by the network/sysadmin.

quoted

While devlink instance of a given PF,VF,SF is managed by the user of such

function itself.

'devlink port function' means "struct devlink_port", right?

'function' is the object managing the function connected on the otherside of this port.
This includes its hw_addr, rate, state, operational state.

Does "other side of this port" means the pci function that is most
likely have been passed through to a VM?

"devlink port" without the "function" represents the representor
netdev on the host where eswitch is located?

quoted

It seems 'devlink port function' in the host is representing a VF when devlink
instance of that VF is in the VM?

Right.

quoted

quoted

For example when a VF is mapped to a VM, devlink instance of this VF

resides in the VM managed by the guest VM.

Does the user in VM really care about devlink info or configuration when
network/sysadmin has configured the VF through 'devlink port function'
in the host?

Yes. devlink instance offers many knobs in uniform way on PF, VF, SF.
They are in use in mlx5 for devlink params, reload, net ns.

"net ns" refer to "net namespace", right?
I am not sure how devlink instance related to net namespace yet.
I thought devlink is not limited to networking, it can be used in
other pcie device other than ethernet device?

quoted

which devlink info or configuration does user need to query or configure in a
VM?

Usually not much.
Few examples that mlx5 users do with devlink instance of VF in a VM are, devlink params, devlink reload, board info. Health reporters, health recovery to name few.