block: add BIO_NO_PAGE_REF flag (399254aa) · Commits · 戴 / test

block/bio.c

+24 −19

Original line number	Diff line number	Diff line
		@@ -849,20 +849,14 @@ static int __bio_iov_bvec_add_pages(struct bio bio, struct iov_iter iter)
		size = bio_add_page(bio, bv->bv_page, len,
		bv->bv_offset + iter->iov_offset);
		if (size == len) {
		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
		struct page *page;
		int i;

		/*
		* For the normal O_DIRECT case, we could skip grabbing this
		* reference and then not have to put them again when IO
		* completes. But this breaks some in-kernel users, like
		* splicing to/from a loop device, where we release the pipe
		* pages unconditionally. If we can fix that case, we can
		* get rid of the get here and the need to call
		* bio_release_pages() at IO completion time.
		*/
		mp_bvec_for_each_page(page, bv, i)
		get_page(page);
		}

		iov_iter_advance(iter, size);
		return 0;
		}
		@@ -925,10 +919,12 @@ static int __bio_iov_iter_get_pages(struct bio bio, struct iov_iter iter)
		* This takes either an iterator pointing to user memory, or one pointing to
		* kernel pages (BVEC iterator). If we're adding user pages, we pin them and
		* map them into the kernel. On IO completion, the caller should put those
		* pages. For now, when adding kernel pages, we still grab a reference to the
		* page. This isn't strictly needed for the common case, but some call paths
		* end up releasing pages from eg a pipe and we can't easily control these.
		* See comment in __bio_iov_bvec_add_pages().
		* pages. If we're adding kernel pages, and the caller told us it's safe to
		* do so, we just have to add the pages to the bio directly. We don't grab an
		* extra reference to those pages (the user should already have that), and we
		* don't put the page on IO completion. The caller needs to check if the bio is
		* flagged BIO_NO_PAGE_REF on IO completion. If it isn't, then pages should be
		* released.
		*
		* The function tries, but does not guarantee, to pin as many pages as
		* fit into the bio, or are requested in *iter, whatever is smaller. If
		@@ -940,6 +936,13 @@ int bio_iov_iter_get_pages(struct bio bio, struct iov_iter iter)
		const bool is_bvec = iov_iter_is_bvec(iter);
		unsigned short orig_vcnt = bio->bi_vcnt;

		/*
		* If this is a BVEC iter, then the pages are kernel pages. Don't
		* release them on IO completion, if the caller asked us to.
		*/
		if (is_bvec && iov_iter_bvec_no_ref(iter))
		bio_set_flag(bio, BIO_NO_PAGE_REF);

		do {
		int ret;

		@@ -1696,6 +1699,7 @@ static void bio_dirty_fn(struct work_struct *work)
		next = bio->bi_private;

		bio_set_pages_dirty(bio);
		if (!bio_flagged(bio, BIO_NO_PAGE_REF))
		bio_release_pages(bio);
		bio_put(bio);
		}
		@@ -1713,6 +1717,7 @@ void bio_check_pages_dirty(struct bio *bio)
		goto defer;
		}

		if (!bio_flagged(bio, BIO_NO_PAGE_REF))
		bio_release_pages(bio);
		bio_put(bio);
		return;

fs/block_dev.c

+7 −5

Original line number	Diff line number	Diff line
		@@ -336,12 +336,14 @@ static void blkdev_bio_end_io(struct bio *bio)
		if (should_dirty) {
		bio_check_pages_dirty(bio);
		} else {
		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
		struct bvec_iter_all iter_all;
		struct bio_vec *bvec;
		int i;
		struct bvec_iter_all iter_all;

		bio_for_each_segment_all(bvec, bio, i, iter_all)
		put_page(bvec->bv_page);
		}
		bio_put(bio);
		}
		}

fs/iomap.c

+7 −5

Original line number	Diff line number	Diff line
		@@ -1589,12 +1589,14 @@ static void iomap_dio_bio_end_io(struct bio *bio)
		if (should_dirty) {
		bio_check_pages_dirty(bio);
		} else {
		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
		struct bvec_iter_all iter_all;
		struct bio_vec *bvec;
		int i;
		struct bvec_iter_all iter_all;

		bio_for_each_segment_all(bvec, bio, i, iter_all)
		put_page(bvec->bv_page);
		}
		bio_put(bio);
		}
		}

include/linux/blk_types.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -215,6 +215,7 @@ struct bio {
		/*
		* bio flags
		*/
		#define BIO_NO_PAGE_REF 0 /* don't put release vec pages */
		#define BIO_SEG_VALID 1 /* bi_phys_segments valid */
		#define BIO_CLONED 2 /* doesn't own data */
		#define BIO_BOUNCED 3 /* bio is a bounce bio */

Admin message