Re: [RFC PATCH 2/3] media: qcom: camss: Add CAMSS Offline Processing Engine driver

[Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>]

On 3/24/26 12:00 PM, Bryan O'Donoghue wrote:
> On 23/03/2026 15:31, Loic Poulain wrote:

[...]


>>> So - this is where the CDM should be used - so that you don't have to do
>>> all of these MMIO writes inside of your ISR.
>> Indeed, and that also the reason stripes are computed ahead of time,
>> so that they can be further 'queued' in a CDM.
>>
>>> Is that and additional step after the RFC ?
>> The current implementation (without CDM) already provides good results
>> and performance, so CDM can be viewed as a future enhancement.
> 
> That's true but then the number of MMIO writes per ISR is pretty small right now. You have about 50 writes here.
> 
>> As far as I understand, CDM could also be implemented in a generic way
>> within CAMSS, since other CAMSS blocks make use of CDM as well.
>> This is something we should discuss further.
> My concern is even conservatively if each module adds another 10 ? writes by the time we get to denoising, sharpening, lens shade correction, those writes could easily look more like 100.
> 
> What user-space should submit is well documented data-structures which then get translated into CDM buffers by the OPE and IFE for the various bits of the pipeline.

Would simply switching to a threaded irq handler resolve this?

Konrad