[PATCH v4 08/12] block: Introduce new bio_split()

[Kent Overstreet]

The new bio_split() can split arbitrary bios - it's not restricted to
single page bios, like the old bio_split() (previously renamed to
bio_pair_split()). It also has different semantics - it doesn't allocate
a struct bio_pair, leaving it up to the caller to handle completions.

Signed-off-by: Kent Overstreet <koverstreet@xxxxxxxxxx>
---
 fs/bio.c |   99 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 99 insertions(+), 0 deletions(-)

diff --git a/fs/bio.c b/fs/bio.c
index 5d02aa5..a15e121 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1539,6 +1539,105 @@ struct bio_pair *bio_pair_split(struct bio *bi, int first_sectors)
 EXPORT_SYMBOL(bio_pair_split);
 
 /**
+ * bio_split - split a bio
+ * @bio:	bio to split
+ * @sectors:	number of sectors to split from the front of @bio
+ * @gfp:	gfp mask
+ * @bs:		bio set to allocate from
+ *
+ * Allocates and returns a new bio which represents @sectors from the start of
+ * @bio, and updates @bio to represent the remaining sectors.
+ *
+ * If bio_sectors(@bio) was less than or equal to @sectors, returns @bio
+ * unchanged.
+ *
+ * The newly allocated bio will point to @bio's bi_io_vec, if the split was on a
+ * bvec boundry; it is the caller's responsibility to ensure that @bio is not
+ * freed before the split.
+ *
+ * If bio_split() is running under generic_make_request(), it's not safe to
+ * allocate more than one bio from the same bio set. Therefore, if it is running
+ * under generic_make_request() it masks out __GFP_WAIT when doing the
+ * allocation. The caller must check for failure if there's any possibility of
+ * it being called from under generic_make_request(); it is then the caller's
+ * responsibility to retry from a safe context (by e.g. punting to workqueue).
+ */
+struct bio *bio_split(struct bio *bio, int sectors,
+		      gfp_t gfp, struct bio_set *bs)
+{
+	unsigned idx, vcnt = 0, nbytes = sectors << 9;
+	struct bio_vec *bv;
+	struct bio *ret = NULL;
+
+	BUG_ON(sectors <= 0);
+
+	/*
+	 * If we're being called from underneath generic_make_request() and we
+	 * already allocated any bios from this bio set, we risk deadlock if we
+	 * use the mempool. So instead, we possibly fail and let the caller punt
+	 * to workqueue or somesuch and retry in a safe context.
+	 */
+	if (current->bio_list)
+		gfp &= ~__GFP_WAIT;
+
+	if (sectors >= bio_sectors(bio))
+		return bio;
+
+	trace_block_split(bdev_get_queue(bio->bi_bdev), bio,
+			  bio->bi_sector + sectors);
+
+	bio_for_each_segment(bv, bio, idx) {
+		vcnt = idx - bio->bi_idx;
+
+		if (!nbytes) {
+			ret = bio_alloc_bioset(gfp, 0, bs);
+			if (!ret)
+				return NULL;
+
+			ret->bi_io_vec = bio_iovec(bio);
+			ret->bi_flags |= 1 << BIO_CLONED;
+			break;
+		} else if (nbytes < bv->bv_len) {
+			ret = bio_alloc_bioset(gfp, ++vcnt, bs);
+			if (!ret)
+				return NULL;
+
+			memcpy(ret->bi_io_vec, bio_iovec(bio),
+			       sizeof(struct bio_vec) * vcnt);
+
+			ret->bi_io_vec[vcnt - 1].bv_len = nbytes;
+			bv->bv_offset	+= nbytes;
+			bv->bv_len	-= nbytes;
+			break;
+		}
+
+		nbytes -= bv->bv_len;
+	}
+
+	ret->bi_bdev	= bio->bi_bdev;
+	ret->bi_sector	= bio->bi_sector;
+	ret->bi_size	= sectors << 9;
+	ret->bi_rw	= bio->bi_rw;
+	ret->bi_vcnt	= vcnt;
+	ret->bi_max_vecs = vcnt;
+	ret->bi_end_io	= bio->bi_end_io;
+	ret->bi_private	= bio->bi_private;
+
+	bio->bi_sector	+= sectors;
+	bio->bi_size	-= sectors << 9;
+	bio->bi_idx	 = idx;
+
+	if (bio_integrity(bio)) {
+		bio_integrity_clone(ret, bio, gfp, bs);
+		bio_integrity_trim(ret, 0, bio_sectors(ret));
+		bio_integrity_trim(bio, bio_sectors(ret), bio_sectors(bio));
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bio_split);
+
+/**
  *      bio_sector_offset - Find hardware sector offset in bio
  *      @bio:           bio to inspect
  *      @index:         bio_vec index
-- 
1.7.7.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/