On 29.01.20 17:43, Christopher Lameter wrote: > On Tue, 28 Jan 2020, Kees Cook wrote: > >>> On the other hand not marking the DMA caches still seems questionable. >> >> My understanding is that exposing DMA memory to userspace copies can >> lead to unexpected results, especially for misbehaving hardware, so I'm >> not convinced this is a generically bad hardening choice. > > "DMA" memory (and thus DMA caches) have nothing to do with DMA. Its a > legacy term. "DMA Memory" is memory limited to a certain > physical address boundary (old restrictions on certain devices only > supporting a limited number of address bits). > > DMA can be done to NORMAL memory as well. Exactly. I think iucv uses GFP_DMA because z/VM needs those buffers to reside below 2GB (which is ZONA_DMA for s390).