block: add BIO_NO_PAGE_REF flag

commit 399254aaf4892113c806816f7e64cf40c804d46d upstream.

If bio_iov_iter_get_pages() is called on an iov_iter that is flagged
with NO_REF, then we don't need to add a page reference for the pages
that we add.

Add BIO_NO_PAGE_REF to track this in the bio, so IO completion knows
not to drop a reference to these pages.
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NJoseph Qi <joseph.qi@linux.alibaba.com>
Reviewed-by: NJeffle Xu <jefflexu@linux.alibaba.com>
Acked-by: NCaspar Zhang <caspar@linux.alibaba.com>

block/bio.c

@@ -841,20 +841,14 @@ 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) {
-		struct page *page;
-		int i;
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
+			struct page *page;
+			int i;
+
+			mp_bvec_for_each_page(page, bv, i)
+				get_page(page);
+		}
 
-		/*
-		 * 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;
 	}
@@ -918,10 +912,12 @@ 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
@@ -933,6 +929,13 @@ 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;
 
@@ -1686,7 +1689,8 @@ static void bio_dirty_fn(struct work_struct *work)
 		next = bio->bi_private;
 
 		bio_set_pages_dirty(bio);
-		bio_release_pages(bio);
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+			bio_release_pages(bio);
 		bio_put(bio);
 	}
 }
@@ -1702,7 +1706,8 @@ void bio_check_pages_dirty(struct bio *bio)
 			goto defer;
 	}
 
-	bio_release_pages(bio);
+	if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+		bio_release_pages(bio);
 	bio_put(bio);
 	return;
 defer:

fs/block_dev.c

@@ -334,11 +334,13 @@ static void blkdev_bio_end_io(struct bio *bio)
 	if (should_dirty) {
 		bio_check_pages_dirty(bio);
 	} else {
-		struct bio_vec *bvec;
-		int i;
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
+			struct bio_vec *bvec;
+			int i;
 
-		bio_for_each_segment_all(bvec, bio, i)
-			put_page(bvec->bv_page);
+			bio_for_each_segment_all(bvec, bio, i)
+				put_page(bvec->bv_page);
+		}
 		bio_put(bio);
 	}
 }

fs/iomap.c

@@ -1591,11 +1591,13 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 	if (should_dirty) {
 		bio_check_pages_dirty(bio);
 	} else {
-		struct bio_vec *bvec;
-		int i;
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
+			struct bio_vec *bvec;
+			int i;
 
-		bio_for_each_segment_all(bvec, bio, i)
-			put_page(bvec->bv_page);
+			bio_for_each_segment_all(bvec, bio, i)
+				put_page(bvec->bv_page);
+		}
 		bio_put(bio);
 	}
 }

include/linux/blk_types.h

@@ -230,6 +230,7 @@ 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 */