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
