On Wed, Aug 29, 2018 at 06:23:52PM -0500, Mike Christie wrote: > > Can you still hit the issue where t_prot_nents > BIO_MAX_PAGES so > bio_integrity_alloc fails or is t_prot_nents always going to be smaller. > Was wondering why you dropped that from the last patch. There was a vhost bug that was artificially inflating the size of the PI SGL by including both the protection and data in the PI SGL [1]. In testing with that patch applied, I haven't seen the PI SGL get anywhere close to BIO_MAX_PAGES. That said, you're right, we should probably retain that safety check. I'll add it back for a v3. Thanks for the feedback. Greg [1] https://lists.linuxfoundation.org/pipermail/virtualization/2018-August/039106.html