[PATCH v2 19/28] iomap: Convert __iomap_zero_iter to use a folio
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: 2021-11-08 04:54:10
Also in:
linux-fsdevel, linux-xfs, lkml
Subsystem:
filesystems (vfs and infrastructure), filesystems [iomap], the rest · Maintainers:
Alexander Viro, Christian Brauner, Linus Torvalds
The zero iterator can work in folio-sized chunks instead of page-sized chunks. This will save a lot of page cache lookups if the file is cached in multi-page folios. Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> --- fs/iomap/buffered-io.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 64e54981b651..9c61d12028ca 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c@@ -881,17 +881,20 @@ EXPORT_SYMBOL_GPL(iomap_file_unshare); static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) { + struct folio *folio; struct page *page; int status; - unsigned offset = offset_in_page(pos); - unsigned bytes = min_t(u64, PAGE_SIZE - offset, length); + size_t offset, bytes; - status = iomap_write_begin(iter, pos, bytes, &page); + status = iomap_write_begin(iter, pos, length, &page); if (status) return status; + folio = page_folio(page); - zero_user(page, offset, bytes); - mark_page_accessed(page); + offset = offset_in_folio(folio, pos); + bytes = min_t(u64, folio_size(folio) - offset, length); + folio_zero_range(folio, offset, bytes); + folio_mark_accessed(folio); return iomap_write_end(iter, pos, bytes, bytes, page); }
--
2.33.0