On Thu, Dec 3, 2015 at 1:29 PM, Random Guy <[email protected]> wrote: > I have a device with a piece of RAM. That memory is accessible to CPU. > I write a driver for that device and it maps device memory directly to > userspace processes. This mapping is cacheable. So far so good.
Ok, I did some research and all drivers that I've found that map memory to userspace do it with caching disabled. After some more reading, especially http://events.linuxfoundation.org/sites/events/files/slides/20140429-dma.pdf I conclude that cacheable mapping of device memory to userspace is not supported in linux at all. Is that correct? TIA _______________________________________________ Kernelnewbies mailing list [email protected] http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
