[SPDK] Re: Clarification regarding VFIO driver bind in the setup.sh

[SPDK] Re: Clarification regarding VFIO driver bind in the setup.sh

[Harris, James R]

[-- Attachment #1: Type: text/plain, Size: 1616 bytes --]

Hi,

For binding to vfio-pci (or uio_pci_generic), the first line is sufficient.

This same function is also used though for `setup.sh reset` to bind the devices back to their respective kernel mode drivers.  For that case, the bind is required (but not the new_id).

So both steps are there since the linux_bind_driver() function is used for both cases.  It could probably be optimized to check the $driver_name and only do the necessary sysfs writes.

Are these extra writes to /bind a problem in your use case, or was your question more out of curiosity?

Regards,

Jim


On 8/16/21, 3:36 PM, "chandanga(a)google.com" <chandanga(a)google.com> wrote:

    I needed a clarification regarding the VFIO setup script for SPDK (https://github.com/spdk/spdk/blob/master/scripts/setup.sh). 
    In the linux_bind_driver() method, we have the following lines:
    	echo "$ven_dev_id" > "/sys/bus/pci/drivers/$driver_name/new_id" 2> /dev/null || true
    	echo "$bdf" > "/sys/bus/pci/drivers/$driver_name/bind" 2> /dev/null || true

    I'm wondering if both steps are necessary? It looks like if we set the vendor_id, device_id into "/sys/bus/pci/drivers/vfio-pci/new_id", this will automatically assign all the VFs (which are not assigned to the NVMe driver) to the VFIO driver. Hence, the second line (echoing the $bdf to the bind file) becomes redundant. Is this correct? Any reason why both of these steps are required? Thanks.
    _______________________________________________
    SPDK mailing list -- spdk(a)lists.01.org
    To unsubscribe send an email to spdk-leave(a)lists.01.org