On Fri, Jan 12, 2018 at 12:11 PM, Benjamin Beckmeyer <beckmeyer.b@xxxxxxxxx> wrote: > sorry to say that but in my case the kernel doesn't boot anymore. > Again, after I "patched out" the bounce buffer it's running fine. > Here is the kernel output.. Something is corrupting the data apparently :/ Well since dma_alloc_coherent() is know to work, I will make a v5 that uses that and still caps the buffer to 64K, and bail out to single segments if we can't allocate a bounce buffer. Yours, Linus Walleij