Re: [PATCH]: Re: qla1280.c broken on SGI visws, PCI coherency problem

[Michael Joosten <michael.joosten@c-lab.de>]

Jeremy Higdon wrote:

>On Thu, Dec 15, 2005 at 02:17:38AM +0100, Michael Joosten wrote:
>  
>
>>>Btw, the VisWS Linux port apparently uses non-coherent DMA.  Perhaps it
>>>should be switched to coherent DMA, as there could be bugs in that area
>>>with qla1280.
>>>      
>>>
>>Aha, so we are back at coherence, but it's not MP, but DMA one...
>>(I'm not sure what is meant with DMA coherence - make sure that before a 
>>DMA transfer is started at least the related CPU cache lines (in the DMA 
>>address range) are written back?)
>>    
>>
>
>For a start.  You need to invalidate before read into memory and write
>back before write to disk.  You also need to make sure that the memory
>stays out of the CPU cache during the DMA (so you need to make sure that
>when you DMA into memory that nothing is loading or storing to a cacheline
>that you're DMA'ing into.  On a speculative execution CPU, this is really
>hard.
>  
>
Aha. Thanks for the info, now I can figure what's going on.

>>in qla1280_32/64bit_start_scsi().
>>    
>>
>
>We're going to work on an API change to mmiowb() instead.
>
>  
>
OK. From my point, this has been settled and I'll stay tuned to test a 
patch. It's not urgent.

Thanks for the lively discussion and some insights, Michael