I have asked TI FAE, they said TI will not revise the PCI master bug in the
future, and currently TI only provide slave mode driver under linux. :(

2008/6/19 Ryan Talbot <[EMAIL PROTECTED]>:

>  Hi,
>
>
>
> I'm looking to utilize the DM6467 as a PCI master and am wondering how well
> supported this functionality is in Linux.  Are there suitable drivers that
> would allow us to interface to existing PCI modules?  Has anybody played
> with this functionality at all?  I understand there are some hardware issues
> at the silicon level… has that been worked around?
>
>
>
> We were originally using a DM6446 for our application, but it needs DMA to
> a hard drive and some external interface to DM642s and an FPGA.  We were
> going to use VLYNQ to communicate with the other silicon (and dodge the
> EMIF/DMA ATA issue), but would rather slap everything on a PCI bus
> (upgrading the 642s to 648s).  We still need the DMA hard drive
> functionality, though, and seeing as how the pins for PCI and ATA are also
> multiplexed, we're not sure that we're gaining much going to PCI.  Although,
> if I'm not mistaken, the pin multiplexing problem with ATA DMA can be
> alleviated with some driver patches… any ground gained there?
>
>
>
> Thanks; any insight appreciated!
>
> _______________________________________________
> Davinci-linux-open-source mailing list
> [email protected]
> http://linux.davincidsp.com/mailman/listinfo/davinci-linux-open-source
>
>
_______________________________________________
Davinci-linux-open-source mailing list
[email protected]
http://linux.davincidsp.com/mailman/listinfo/davinci-linux-open-source

Reply via email to