| Message ID | 20200610201345.13273-21-willy@infradead.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Large pages in the page cache | expand |
On Wed, Jun 10, 2020 at 01:13:14PM -0700, Matthew Wilcox wrote: > +static inline void bvec_thp_advance(const struct bio_vec *bvec, > + struct bvec_iter_all *iter_all) > +{ > + struct bio_vec *bv = &iter_all->bv; > + unsigned int page_size = thp_size(bvec->bv_page); > + > + if (iter_all->done) { > + bv->bv_page += thp_nr_pages(bv->bv_page); > + bv->bv_offset = 0; > + } else { > + BUG_ON(bvec->bv_offset >= page_size); > + bv->bv_page = bvec->bv_page; > + bv->bv_offset = bvec->bv_offset & (page_size - 1); > + } > + bv->bv_len = min(page_size - bv->bv_offset, > + bvec->bv_len - iter_all->done); > + iter_all->done += bv->bv_len; > + > + if (iter_all->done == bvec->bv_len) { > + iter_all->idx++; > + iter_all->done = 0; > + } > +} If, for example, we have an order-2 page followed by two order-0 pages (thanks, generic/127!) in the bvec, we'll end up skipping the third page because we calculate the size based on bvec->bv_page instead of bv->bv_page. +++ b/include/linux/bvec.h @@ -166,15 +166,19 @@ static inline void bvec_thp_advance(const struct bio_vec *bvec, struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; - unsigned int page_size = thp_size(bvec->bv_page); + unsigned int page_size; if (iter_all->done) { bv->bv_page += thp_nr_pages(bv->bv_page); + page_size = thp_size(bv->bv_page); bv->bv_offset = 0; } else { - BUG_ON(bvec->bv_offset >= page_size); - bv->bv_page = bvec->bv_page; - bv->bv_offset = bvec->bv_offset & (page_size - 1); + bv->bv_page = thp_head(bvec->bv_page + + (bvec->bv_offset >> PAGE_SHIFT)); + page_size = thp_size(bv->bv_page); + bv->bv_offset = bvec->bv_offset - + (bv->bv_page - bvec->bv_page) * PAGE_SIZE; + BUG_ON(bv->bv_offset >= page_size); } bv->bv_len = min(page_size - bv->bv_offset, bvec->bv_len - iter_all->done); The previous code also wasn't handling the case fixed in 6bedf00e55e5 where a split bio might end up splitting a bvec. That BUG_ON can probably come out after a few months of testing.
diff --git a/include/linux/bio.h b/include/linux/bio.h index 91676d4b2dfe..1489e196abf5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -131,12 +131,25 @@ static inline bool bio_next_segment(const struct bio *bio, return true; } +static inline bool bio_next_thp_segment(const struct bio *bio, + struct bvec_iter_all *iter) +{ + if (iter->idx >= bio->bi_vcnt) + return false; + + bvec_thp_advance(&bio->bi_io_vec[iter->idx], iter); + return true; +} + /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it */ #define bio_for_each_segment_all(bvl, bio, iter) \ for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); ) +#define bio_for_each_thp_segment_all(bvl, bio, iter) \ + for (bvl = bvec_init_iter_all(&iter); \ + bio_next_thp_segment((bio), &iter); ) static inline void bio_advance_iter(const struct bio *bio, struct bvec_iter *iter, unsigned int bytes) diff --git a/include/linux/bvec.h b/include/linux/bvec.h index ac0c7299d5b8..71b435e573e1 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -162,4 +162,27 @@ static inline void bvec_advance(const struct bio_vec *bvec, } } +static inline void bvec_thp_advance(const struct bio_vec *bvec, + struct bvec_iter_all *iter_all) +{ + struct bio_vec *bv = &iter_all->bv; + unsigned int page_size = thp_size(bvec->bv_page); + + if (iter_all->done) { + bv->bv_page += thp_nr_pages(bv->bv_page); + bv->bv_offset = 0; + } else { + BUG_ON(bvec->bv_offset >= page_size); + bv->bv_page = bvec->bv_page; + bv->bv_offset = bvec->bv_offset & (page_size - 1); + } + bv->bv_len = min(page_size - bv->bv_offset, + bvec->bv_len - iter_all->done); + iter_all->done += bv->bv_len; + + if (iter_all->done == bvec->bv_len) { + iter_all->idx++; + iter_all->done = 0; + } +} #endif /* __LINUX_BVEC_ITER_H */