[PATCH 12/12] accel/ivpu: Share NPU busy time in sysfs

[Jacek Lawrynowicz]

Hi,

On 13.05.2024 12:45, Tvrtko Ursulin wrote:
> 
> On 13/05/2024 11:22, Jacek Lawrynowicz wrote:
>> Hi,
>>
>> On 10.05.2024 18:55, Jeffrey Hugo wrote:
>>> On 5/8/2024 7:29 AM, Jacek Lawrynowicz wrote:
>>>> From: Tomasz Rusinowicz <tomasz.rusinowicz at intel.com>
>>>>
>>>> The driver tracks the time spent by NPU executing jobs
>>>> and shares it through sysfs `npu_busy_time_us` file.
>>>> It can be then used by user space applications to monitor device
>>>> utilization.
>>>>
>>>> NPU is considered 'busy' starting with a first job submitted
>>>> to firmware and ending when there is no more jobs pending/executing.
>>>>
>>>> Signed-off-by: Tomasz Rusinowicz <tomasz.rusinowicz at intel.com>
>>>> Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz at linux.intel.com>
>>>
>>> This feels like something that would normally be handled by perf. Why not use that mechanism?
>>
>> Yeah, probably but we had several request to provide easy to use interface for this metric that
>> could be integrated in various user space apps/tools that do not use ftrace.
> 
> Probably more Perf/PMU aka performance counters? Which would be scriptable via $kernel/tools/perf or directly via perf_event_open(2) and read(2).
> 
> Note it is not easy to get right and in the i915 implementation (see i915_pmu.c) we have a known issue with PCI hot unplug and use after free which needs input from perf core folks.

OK, we will consider using perf/pmu for NPU but for the moment I would like to keep this sysfs interface.
It so simple it can be used from bash and it always can be removed if obsoleted by something fancier.