On Tue, 2016-10-25 at 08:43 +0200, Stefan Roese wrote: > Hi Andy, > > On 24.10.2016 16:12, Andy Shevchenko wrote: > > On Mon, 2016-10-24 at 15:43 +0200, Stefan Roese wrote: > > > Hi Andy, > dmatest works just fine when using it on local memory as source > and destination. So, DMA engine works. > I've also hacked dmatest to use the PCI memory as destination address. And here is the problem. How memory is addressed? DMA there works with memory in system address space. Moreover it a) supports only 32-bit DMA mask, and b) does increment addresses after each burst size. Transfer width and alignment is calculated automatically from addresses and lengths parameters (when you call prep_memcpy()). Burst sizes IIRC hard coded to 16 items. All those at least what you have to think of. If your PCI memory space requires I/O operation, it will not work I assume. Basically you need to be sure that your memory is represented in the system in the same way as system memory (including virtual <-> physical mapping). > The test shows that with "noverify=1" no data is written at all to > this PCI memory. And w/o this parameter, only the data that is > written "manually" in dmatest_init_dsts() shows up in the PCI > memory space and dmatest reports the verify errors. So dmatest > shows the same results as my testing device driver using the DW DMA > driver to write data into this PCI memory space. Nothing seems to > be written to this PCI memory space at all. > > May I ask if you are really sure that the DMA controller on Bay > Trail is able to access data located on the PCI devices other than > the internal BayTrail PCI devices (like I2C, SPI, HSUART)? See above. > Is there some documentation about the DW DMA controller on BayTrail > and its relationship (hardwired request lines inside the SoC ?) > other that the "Intel Atom Processor E3800 Product Family Datasheet"? I'm afraid not publicly available, though I'm not sure. -- Andy Shevchenko <andriy.shevchenko@xxxxxxxxxxxxxxx> Intel Finland Oy -- To unsubscribe from this list: send the line "unsubscribe dmaengine" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
