lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <77c88717-618f-b366-2b6a-f8b4abaa66cc@nvidia.com>
Date:   Thu, 9 Apr 2020 11:28:15 -0700
From:   Sowjanya Komatineni <skomatineni@...dia.com>
To:     Dmitry Osipenko <digetx@...il.com>, <thierry.reding@...il.com>,
        <jonathanh@...dia.com>, <frankc@...dia.com>, <hverkuil@...all.nl>,
        <sakari.ailus@....fi>, <helen.koike@...labora.com>
CC:     <sboyd@...nel.org>, <linux-media@...r.kernel.org>,
        <devicetree@...r.kernel.org>, <linux-clk@...r.kernel.org>,
        <linux-tegra@...r.kernel.org>, <linux-kernel@...r.kernel.org>
Subject: Re: [RFC PATCH v6 6/9] media: tegra: Add Tegra210 Video input driver


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 пишет:
> ...
>> 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.


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ