On Fri, May 30, 2025 at 03:25:19PM -0300, Jason Gunthorpe wrote:

On Fri, May 30, 2025 at 11:23:02AM -0700, Nicolin Chen wrote:

quoted

On Fri, May 30, 2025 at 02:40:37PM -0300, Jason Gunthorpe wrote:

quoted

On Fri, May 30, 2025 at 10:38:24AM -0700, Nicolin Chen wrote:

quoted

On Fri, May 30, 2025 at 01:14:55PM -0300, Jason Gunthorpe wrote:

quoted

On Sat, May 17, 2025 at 08:21:31PM -0700, Nicolin Chen wrote:

quoted

+	offset =
+		cmd->nesting_parent_iova - PAGE_ALIGN(cmd->nesting_parent_iova);
+	max_npages = DIV_ROUND_UP(offset + cmd->length, PAGE_SIZE);

This should probably be capped to PAGE_SIZE/sizeof(void *), return
EINVAL if not

Hmm, mind elaborating where this PAGE_SIZE/sizeof comes from?

We can usually allocate up to a PAGE_SIZE without too much
trouble. Beyond that it gets more likely to fail.

If PAGE_SIZE=4096, the upper limit for max_npages is 512, i.e. the
max size of a guest queue is 2MB? It seems to be too small, as the
VMM can use a larger huge page size to back the guest queue?

May need to make a new API that returns a bio_vec or something else
more efficient then :\

Hmm, that sounds like a rabbit hole :-\

Let me leave a FIXME at this max_npages calculation instead..

Thanks
Nicolin