Re: [RFC v1 07/11] net/mlx4: Cache irq_desc->affinity instead of irq_desc

[Amir Vadai <amirv@mellanox.com>]

On Mon, May 4, 2015 at 5:00 PM, Jiang Liu <jiang.liu@linux.intel.com> wrote:
> On 2015/5/4 20:10, Amir Vadai wrote:
>> On Mon, May 4, 2015 at 6:15 AM, Jiang Liu <jiang.liu@linux.intel.com> wrote:
>>> The field 'affinity' in irq_desc won't change once the irq_desc data
>>> structure is created. So cache irq_desc->affinity instead of irq_desc.
>>> This also helps to hide struct irq_desc from device drivers.
>>
>> Hi Jiang,
>>
>> I might not understand the new changes irq core, but up until now
>> affinity was changed when the user changed it through
>> /proc/irq/<IRQ>/smp_affinity.
>> This code is monitoring the affinity from the napi_poll context to
>> detect affinity changes, and prevent napi from keep running on the
>> wrong CPU.
>> Therefore, the affinity can't be cached at the beginning. Please
>> revert this caching.
> Hi Amir,
>         Thanks for review:) We want to hide irq_desc implementation
> details from device drivers, so made these changes.
>         Function irq_get_affinity_mask() returns 'struct cpumask *'
> and we cache the returned pointer. On the other hand, user may change
> IRQ affinity through /proc/irq/<IRQ>/smp_affinity, but that only
> changes the bitmap pointed to by the cached pointer and won't change
> the pointer itself. So it should always return the latest affinity
> setting by calling cpumask_test_cpu(cpu_curr, cq->irq_affinity).
> Or am I missing something here?
No - you are completely right - I missed it.

Anyway I tested it to make sure, and everything works as expected.

Acked-By: Amir Vadai <amirv@mellanox.com>

Thanks,
Amir


> Thanks!
> Gerry
>>
>> Thanks,
>> Amir
>>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html