[Cbe-oss-dev] [PATCH 0:3] spusched: assorted spu scheduler fixes

[Kazunori Asayama]

Gerhard Stenzel wrote:
> Kazunori Asayama <asayama at sm.sony.co.jp> wrote on 04/25/2008 05:02:15 PM:
> 
>> Gerhard Stenzel wrote:
> ...
>>> it seems like it is fixed:
>> Did you apply the patch following?
>>
>>   http://ozlabs.org/pipermail/cbe-oss-dev/2007-August/003139.html
> 
> No
> 
>> It looks like that, without this patch, the SPUFS can restore invalid
>> DMA queue if all outstanding DMAs are completed between save_mfc_cntl
>> and save_spu_status. Actually, without it, check-test_dma.elf on

Oops, it's my misunderstanding with the current implementation!
The case above can't occur since the DMA is suspended at save_mfc_cntl.
The problem with the current public SPUFS is that the MFC_CNTL[Q] is 
never saved.

>> PS3 failed with the current Geoff's ps3-linux tree.
>>
>> Or does Jeremy's experimental tree have any alternative fix?
> 
> Yes

Regarding opposite case to the above, it looks like that the case 
mentioned in http://ozlabs.org/pipermail/cbe-oss-dev/2007-August/003141.html
is difficult to reproduce, and the probability to reproduce the 
problem by test_mfc.elf seems to be low...

Anyway, I'm looking forward upcoming Jeremy's patch set.

Thanks,
-- 
(ASAYAMA Kazunori
  (asayama at sm.sony.co.jp))
t