From: Kent Overstreet <kent.overstreet@xxxxxxxxx>
This is a helper that pins down a range from an iov_iter and adds it to
a bio without requiring a separate memory allocation for the page array.
It will be used for upcoming direct I/O implementations for block devices
and iomap based file systems.
Signed-off-by: Kent Overstreet <kent.overstreet@xxxxxxxxx>
[hch: ported to the iov_iter interface, renamed and added comments.
All blame should be directed to me and all fame should go to Kent
after this!]
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
block/bio.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
include/linux/bio.h | 1 +
2 files changed, 50 insertions(+)
diff --git a/block/bio.c b/block/bio.c
index db85c57..2cf6eba 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -847,6 +847,55 @@ int bio_add_page(struct bio *bio, struct page *page,
}
EXPORT_SYMBOL(bio_add_page);
+/**
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * @bio: bio to add pages to
+ * @iter: iov iterator describing the region to be mapped
+ *
+ * Pins as many pages from *iter and appends them to @bio's bvec array. The
+ * pages will have to be released using put_page() when done.
+ */
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+ unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+ struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
+ struct page **pages = (struct page **)bv;
+ size_t offset, diff;
+ ssize_t size;
+
+ size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
+ if (unlikely(size <= 0))
+ return size ? size : -EFAULT;
+ nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
+
+ /*
+ * Deep magic below: We need to walk the pinned pages backwards
+ * because we are abusing the space allocated for the bio_vecs
+ * for the page array. Because the bio_vecs are larger than the
+ * page pointers by definition this will always work. But it also
+ * means we can't use bio_add_page, so any changes to it's semantics
+ * need to be reflected here as well.
+ */
+ bio->bi_iter.bi_size += size;
+ bio->bi_vcnt += nr_pages;
+
+ diff = (nr_pages * PAGE_SIZE - offset) - size;
+ while (nr_pages--) {
+ bv[nr_pages].bv_page = pages[nr_pages];
+ bv[nr_pages].bv_len = PAGE_SIZE;
+ bv[nr_pages].bv_offset = 0;
+ }
+
+ bv[0].bv_offset += offset;
+ bv[0].bv_len -= offset;
+ if (diff)
+ bv[bio->bi_vcnt - 1].bv_len -= diff;
+
+ iov_iter_advance(iter, size);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
+
struct submit_bio_ret {
struct completion event;
int error;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 87ce64d..c39fa0b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -419,6 +419,7 @@ void bio_chain(struct bio *, struct bio *);
extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
unsigned int, unsigned int);
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
struct rq_map_data;
extern struct bio *bio_map_user_iov(struct request_queue *,
const struct iov_iter *, gfp_t);
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-block" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
