On 5/8/24 16:51, Christoph Hellwig wrote:
On Wed, May 08, 2024 at 12:35:52PM +0100, Pavel Begunkov wrote:
all these, because e.g. ttm internally does have a page pool because depending upon allocator, that's indeed beneficial. Other drm drivers have more buffer-based concepts for opportunistically memory around, usually by marking buffers that are just kept as cache as purgeable (which is a concept that goes all the way to opengl/vulkan).
Because in this case it solves nothing and helps with nothing, quite the opposite. Just as well we can ask why NVMe doesn't wrap user pages into a dmabuf while doing IO.
You seem to confused totally unrelated things.
For short-term pins, that is pin_user_pages without FOLL_LONGTERM there would never be any point in using a dmabuf as the pin is transient. For long-term pin dmabufs in the block layer absolutely make sense, and I
Well, the example fell flat, but you don't use dmabuf when there are no upsides from using it. For instance, when you already have pinned pages, you're going to use pages, and there are no other refcounting concerns. Unless there is an advantage of dmabufs over FOLL_LONGTERM that I don't know about when used with normal user pages.
wish io_uring would have just implemented them from the start instead of the current fixed buffers that are not quite as useful by not pre-mapping DMA and not supporting P2P.
fdget(dmabuf) would be horrible, I assume that's not the suggestion. But then it's really about kernel internals, and theoretically can be patched to wrap user pages into a dmabuf and pass it in. The tricky part is how that "pass it in" should looks like. Keith tried to cover both pre-mapping and p2p by registering dmabuf and passing the mapped addresses in an iter IIRC.
Anyway, this discussion should better move from to block/fs lists, if there is any interest.