On Fri, Feb 03, 2017 at 08:54:15AM +0000, Al Viro wrote: > Hmm... Reuse part is really nasty ;-/ OTOH, it might make sense to have > a "fill bio_vec array" as separate primitive - having that sucker come > from bio looks like an artificial restriction. Or just the only usecase :) But yes, it could be generalized to take a bio_vec without too much effort. > OK, next question, seeing that you've dealt with O_DIRECT guts more than > I have. When we have iov_iter_get_pages() fail on do_direct_IO() write > with some blocks already allocated, we pick zero page as data source. > So far, so good, but: > * should we bother zeroing anything unless buffer_new() is true? I don't think so. > * why, in case of more than a page worth of pending allocated > blocks, do we bother with calling iov_iter_get_pages() again and again? > We *do* take care not to allocate anything else after that point, but > dio_get_page() will be calling iov_iter_get_pages() every time in that > case - there's only one page in queue. There shouldn't be a need for it. But take it with a grain of salt - fs/direct-io.c is a hairy mess, that's one of the reasons why I replaced it with the new iomap code instead of trying to gradually move it to iomap API.
