On 01/12/2020 13:32, Christoph Hellwig wrote:

On Tue, Dec 01, 2020 at 01:17:49PM +0000, Pavel Begunkov wrote:

quoted

I was thinking about memcpy bvec instead of iterating as a first step,
and then try to reuse passed in bvec.

A thing that doesn't play nice with that is setting BIO_WORKINGSET in
__bio_add_page(), which requires to iterate all pages anyway. I have no
clue what it is, so rather to ask if we can optimise it out somehow?
Apart from pre-computing for specific cases...

E.g. can pages of a single bvec segment be both in and out of a working
set? (i.e. PageWorkingset(page)).

Adding Johannes for the PageWorkingset logic, which keeps confusing me
everytime I look at it.  I think it is intended to deal with pages
being swapped out and in, and doesn't make much sense to look at in
any form for direct I/O, but as said I'm rather confused by this code.

If PageWorkingset is a non-issue we should be able to just point the
bio at the biovec array.  I think that be done by allocating the bio
with nr_iovecs == 0, and then just updating >bi_io_vec and ->bi_vcnt
using a little helper like this:

Yeah, that's the idea, but also wanted to verify that callers don't
free it while in use, or if that's not the case to make it conditional
by adding a flag in iov_iter.

Can anybody vow right off the bat that all callers behave well?

static inline void bio_assign_bvec(struct bio *bio, struct bio_vec *bvecs,
		unsigned short nr_bvecs)
{
	WARN_ON_ONCE(BVEC_POOL_IDX(bio) != 0);
	bio->bi_io_vec = bvecs;
	bio->bi_vcnt = nr_bvecs;
}

-- 
Pavel Begunkov