Re: [RFC-next 0/1] Odroid C2: Enable DVFS for cpu

[Brad <bjharper@gmail.com>]

On 14/12/2019 12:24 am, Neil Armstrong wrote:
>
> This is the point, the Odroid-C2 is *not* stable at 2GHz,
> a large amount of board doesn't support 2GHz, this is why Amlogic
> dropped the freq > 1.536 GHz for the GXBB family.
>
> But HardKernel still delivers the SCPI table with > 1.536 GHz which breaks
> on most of the boards, but doesn't on 3.14 since they have a hack disabling
> higher freqs with a cmdline set in boot.ini.

Hi Neil,

Hardkernel did update there firmware to restrict frequency to 1.536 back 
in 2017 back in this commit 
https://github.com/hardkernel/u-boot/commit/205c7b3259559283161703a1a200b787c2c445a5 
Versions prior to this would runaway on boot up to 2Ghz and crash.

They also added a hidden function to the SCPI_CMD_GET_DVFS_INFO call 
which works by changing the domain number in the call to pull back 
different OPP tables.  Domain set to 0 will limit frequency to 1.536.  
They set the highest bit in the domain number to 1 which opens SCPI 
table to 2.016GHz.  This is done in via BL301 so it might be possible 
for mainline kernel to check this bit and open up the table after boot 
using a special driver.  Joy posted some details here 
https://forum.odroid.com/viewtopic.php?f=141&t=23044&start=350#p181017

Of course it would still cause problems for boards running an old 
version of the firmware but newer versions of the bootloader boot fine 
in mainline with DVFS enabled as its limited to 1.536 by default.

> The various tests gave very little perf enhancement by going > 1,536 GHz, seriously
> it's not worth the pain.
>
> Neil

My tests showed my board (they may vary) was very stable up to 
1.680Ghz,  at 1.752Ghz could get it to crash if I tried to burn all 4 
cores with heavy NEON stress test. At 1.896GHz I would get random 
freezes even with only 1 core enabled at boot.  I must say I never 
tested with Mali enabled so it may influence things.

I do agree though it might cause more pain that it is worth especially 
when old firmware is used.

- Brad

>> -Anand
>>
>
> _______________________________________________
> linux-amlogic mailing list
> linux-amlogic@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-amlogic

_______________________________________________
linux-amlogic mailing list
linux-amlogic@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-amlogic