Merge tag 'folio-5.18f' of git://git.infradead.org/users/willy/pagecache

Pull folio fixes from Matthew Wilcox:
 "Two folio fixes for 5.18.

  Darrick and Brian have done amazing work debugging the race I created
  in the folio BIO iterator. The readahead problem was deterministic, so
  easy to fix.

   - Fix a race when we were calling folio_next() in the BIO folio iter
     without holding a reference, meaning the folio could be split or
     freed, and we'd jump to the next page instead of the intended next
     folio.

   - Fix readahead creating single-page folios instead of the intended
     large folios when doing reads that are not a power of two in size"

* tag 'folio-5.18f' of git://git.infradead.org/users/willy/pagecache:
  mm/readahead: Fix readahead with large folios
  block: Do not call folio_next() on an unreferenced folio

2 files changed, 13 insertions, 7 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 278cc81cc1e7..00450fd86bb4 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -269,6 +269,7 @@ struct folio_iter {
 	size_t offset;
 	size_t length;
 	/* private: for use by the iterator */
+	struct folio *_next;
 	size_t _seg_count;
 	int _i;
 };
@@ -283,6 +284,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio,
 			PAGE_SIZE * (bvec->bv_page - &fi->folio->page);
 	fi->_seg_count = bvec->bv_len;
 	fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count);
+	fi->_next = folio_next(fi->folio);
 	fi->_i = i;
 }
 
@@ -290,9 +292,10 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio)
 {
 	fi->_seg_count -= fi->length;
 	if (fi->_seg_count) {
-		fi->folio = folio_next(fi->folio);
+		fi->folio = fi->_next;
 		fi->offset = 0;
 		fi->length = min(folio_size(fi->folio), fi->_seg_count);
+		fi->_next = folio_next(fi->folio);
 	} else if (fi->_i + 1 < bio->bi_vcnt) {
 		bio_first_folio(fi, bio, fi->_i + 1);
 	} else {
diff --git a/mm/readahead.c b/mm/readahead.c
index 8e3775829513..4a60cdb64262 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -474,7 +474,8 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
 
 	if (!folio)
 		return -ENOMEM;
-	if (mark - index < (1UL << order))
+	mark = round_up(mark, 1UL << order);
+	if (index == mark)
 		folio_set_readahead(folio);
 	err = filemap_add_folio(ractl->mapping, folio, index, gfp);
 	if (err)
@@ -555,8 +556,9 @@ static void ondemand_readahead(struct readahead_control *ractl,
 	struct file_ra_state *ra = ractl->ra;
 	unsigned long max_pages = ra->ra_pages;
 	unsigned long add_pages;
-	unsigned long index = readahead_index(ractl);
-	pgoff_t prev_index;
+	pgoff_t index = readahead_index(ractl);
+	pgoff_t expected, prev_index;
+	unsigned int order = folio ? folio_order(folio) : 0;
 
 	/*
 	 * If the request exceeds the readahead window, allow the read to
@@ -575,8 +577,9 @@ static void ondemand_readahead(struct readahead_control *ractl,
 	 * It's the expected callback index, assume sequential access.
 	 * Ramp up sizes, and push forward the readahead window.
 	 */
-	if ((index == (ra->start + ra->size - ra->async_size) ||
-	     index == (ra->start + ra->size))) {
+	expected = round_up(ra->start + ra->size - ra->async_size,
+			1UL << order);
+	if (index == expected || index == (ra->start + ra->size)) {
 		ra->start += ra->size;
 		ra->size = get_next_ra_size(ra, max_pages);
 		ra->async_size = ra->size;
@@ -662,7 +665,7 @@ readit:
 	}
 
 	ractl->_index = ra->start;
-	page_cache_ra_order(ractl, ra, folio ? folio_order(folio) : 0);
+	page_cache_ra_order(ractl, ra, order);
 }
 
 void page_cache_sync_ra(struct readahead_control *ractl,