[Skiboot] [PATCH 1/3] npu2-hw-procedures: Don't set iovalid for opencapi devices

[Andrew Donnellan]

On 16/3/19 3:44 am, Frederic Barrat wrote:
> set_iovalid() is called on the PHY reset path. The hw logic it touches
> is meaningless for opencapi. It's not hurting as long as all the links
> under the NPU are in opencapi mode, but in case of mixing opencapi and
> nvlink, we'll be in troubles: the code finds which bit to modify based
> on the brick index, which varies depending on the mode. So calling
> that function on an opencapi device may modify a nvlink brick! For
> example, for brick index 3.
> 
> So we simply avoid doing anything when calling set_iovalid() for an
> opencapi device.
> 
> Signed-off-by: Frederic Barrat <fbarrat at linux.ibm.com>

Makes sense.

Reviewed-by: Andrew Donnellan <andrew.donnellan at au1.ibm.com>

> ---
>   hw/npu2-hw-procedures.c | 3 +++
>   1 file changed, 3 insertions(+)
> 
> diff --git a/hw/npu2-hw-procedures.c b/hw/npu2-hw-procedures.c
> index a10ccb7c..3ee646cd 100644
> --- a/hw/npu2-hw-procedures.c
> +++ b/hw/npu2-hw-procedures.c
> @@ -218,6 +218,9 @@ static void set_iovalid(struct npu2_dev *ndev, bool raise)
>   	uint64_t addr, val, mask;
>   	int rc;
>   
> +	if (ndev->type == NPU2_DEV_TYPE_OPENCAPI)
> +		return;
> +
>   	addr = (ndev->pl_xscom_base & 0x3F000000) | 0x9;
>   	mask = PPC_BIT(6 + obus_brick_index(ndev));
>   	val = raise ? mask : 0;
> 

-- 
Andrew Donnellan              OzLabs, ADL Canberra
andrew.donnellan at au1.ibm.com  IBM Australia Limited