bio segment constraints

[Christoph Hellwig]

On Mon, Apr 07, 2025 at 09:59:16AM -0400, Sean Anderson wrote:
> > drivers (case 1a), or generated by bio_split_to_limits (case 1b), which
> > is called for every blk-mq driver before calling into ->queue_rq(s) or
> > explicitly called by a few bio based driver.
> > 
> > The other is the bio-vec synthesized by bio_for_each_segment (case 2).
> 
> I'm referring to the bio_vecs you get from queue_mq. Which I think is the
> latter.

The bios hanging off the request have bio_vecs that are case 1b.

If you use bio_for_each_segment or an open coded variant of that on the
bio you get on-stack bio_vecs for case 2.

> > > - Is it possible to have a bio where the total length is a multiple of
> > >    logical_sector_size, but the data is split across several segments
> > >    where each segment is a multiple of SECTOR_SIZE?
> > 
> > Yes.
> 
> ...if this is the case, then for some of those segments wouldn't bv_len
> not be a multiple of logical_sector_size?

Maybe I'm misunderstanding the question.  But if you have e.g. a
transfer that is 2MiB, it could be perfectly fine that each bio_vec is
say 1kiB.

> > > - Can I somehow request to only get segments with bv_len aligned to
> > >    logical_sector_size?
> > 
> > For drivers that use bio_split_to_limits implicitly or explicitly you can
> > do that by setting the right seg_boundary_mask.
> 
> Is that the right knob? It operates on the physical address, so it looked
> more like something for broken DMA engines. For example (if I recall correctly)
> MMC SDMA can't cross a page boundary, so you could use seg_boundary_mask to
> enforce that.

seg_boundary_mask is indeed primarily about physical addresses.  That
being said if your seg_boundary_mask is logical_sector_size all bio_vecs
in cases 1a/b will be aligned to it for their base address, and thus
automatically their length too.

> > in the short run the best fix would be to synthesized a
> > bio_for_each_segment like bio_vec that stays inside a single page
> > using bio_iter_iovec) at the top of do_blktrans_request and use
> > that for all references to the data.
> > 
> 
> OK, but if you have to stay inside a single page couldn't you end up
> with a sector spanning a page boundary due to only being aligned to
> dma_alignment? Or maybe we set seg_boundary_mask to PAGE_MASK to enforce that?

bio_iter_iovec ensures that the synthetic request never crosses a
page boundary.  But as Keith pointed out that means if your
dma_alignment or seg_boundary_mask are smaller than the logical block
size you might actually get a non-aligned length.