Re: [RFC PATCH v6 6/9] media: tegra: Add Tegra210 Video input driver

[Sowjanya Komatineni]

On 4/10/20 11:47 AM, Dmitry Osipenko wrote:
> External email: Use caution opening links or attachments
>
>
> 09.04.2020 21:28, Sowjanya Komatineni ÐÐÑÐÑ:
> > On 4/9/20 7:50 AM, Dmitry Osipenko wrote:
> > > External email: Use caution opening links or attachments
> > >
> > >
> > > 09.04.2020 06:38, Sowjanya Komatineni ÐÐÑÐÑ:
> > > ...
> > > > Tested with 3 buffers and by checking outstanding buffers in process by
> > > > VI hw and holding to start capture till one outstanding buffer in
> > > > process by HW.
> > > > Also tested with 2 buffers without checking for outstanding buffers.
> > > >
> > > > In both cases, I see same %CPU for the kthreads and is < 1%
> > > I don't see where buffers queue max limit is set to 3 in the code, but
> > > should be okay if CPU isn't getting hogged. Looking forward to v7.
> > Sorry, correction I meant to say pre-queued buffers before streaming not
> > num_buffers.
> > vb2 queue min_buffers_needed was set to 3 as part of one of the issue
> > debug in earlier version which actually was irrelevant to that issue and
> > should have been removed. Will remove min_buffers_needed in v7.
> >
> > I added checking for outstanding requests by hardware just to be safer
> > although we may not hit this case of issuing more than 1 outstanding
> > frame capture to VI hardware as capture_frame() waits till it sees frame
> > start event through HW syncpt increment before proceeding for memory
> > write and issuing next frame capture.
> >
> > So issuing frame captures are synchronized with frame start and frame end.
> >
> > Will remove min_buffers_needed and also explicit check for outstanding
> > buffers in v7.
> It's still not clear to me how the "pre-queued buffers" will be limited.
> I'll take another look at the v7.

OK, but I don't understand what you mean by limit on pre-queued buffers.

I was saying vb2 queue has min_buffers_needed which was set to 3 where 
streaming will start only after 3 buffers got queued up.

Regarding outstanding condition check to make sure no more than 2 syncpt 
trigger requests are in FIFO I added it to be safe where mostly we may 
not hit and also I only see capture start thread holding for it during 
initial frame capture as it issues single shot for 1st 2 buffers capture 
and holds 3 buffers which is already queued till at least one of those 2 
issued capture is done to make sure of not triggering syncpt condition 
when fifo already has 2 pending.

In v7, will remove setting min_buffers_needed and also outstanding 
syncpt trigger check.