block: Introduce REQ_OP_ZONE_APPEND

Define REQ_OP_ZONE_APPEND to append-write sectors to a zone of a zoned
block device. This is a no-merge write operation.

A zone append write BIO must:
* Target a zoned block device
* Have a sector position indicating the start sector of the target zone
* The target zone must be a sequential write zone
* The BIO must not cross a zone boundary
* The BIO size must not be split to ensure that a single range of LBAs
  is written with a single command.

Implement these checks in generic_make_request_checks() using the
helper function blk_check_zone_append(). To avoid write append BIO
splitting, introduce the new max_zone_append_sectors queue limit
attribute and ensure that a BIO size is always lower than this limit.
Export this new limit through sysfs and check these limits in bio_full().

Also when a LLDD can't dispatch a request to a specific zone, it
will return BLK_STS_ZONE_RESOURCE indicating this request needs to
be delayed, e.g.  because the zone it will be dispatched to is still
write-locked. If this happens set the request aside in a local list
to continue trying dispatching requests such as READ requests or a
WRITE/ZONE_APPEND requests targetting other zones. This way we can
still keep a high queue depth without starving other requests even if
one request can't be served due to zone write-locking.

Finally, make sure that the bio sector position indicates the actual
write position as indicated by the device on completion.

Signed-off-by: Keith Busch <kbusch@kernel.org>
[ jth: added zone-append specific add_page and merge_page helpers ]
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 58 insertions, 4 deletions

diff --git a/block/bio.c b/block/bio.c
index aad0a6dad4f9..3aa3c4ce2e5e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1025,6 +1025,50 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	return 0;
 }
 
+static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
+	struct request_queue *q = bio->bi_disk->queue;
+	unsigned int max_append_sectors = queue_max_zone_append_sectors(q);
+	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
+	struct page **pages = (struct page **)bv;
+	ssize_t size, left;
+	unsigned len, i;
+	size_t offset;
+
+	if (WARN_ON_ONCE(!max_append_sectors))
+		return 0;
+
+	/*
+	 * Move page array up in the allocated memory for the bio vecs as far as
+	 * possible so that we can start filling biovecs from the beginning
+	 * without overwriting the temporary page array.
+	 */
+	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
+	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
+
+	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
+	if (unlikely(size <= 0))
+		return size ? size : -EFAULT;
+
+	for (left = size, i = 0; left > 0; left -= len, i++) {
+		struct page *page = pages[i];
+		bool same_page = false;
+
+		len = min_t(size_t, PAGE_SIZE - offset, left);
+		if (bio_add_hw_page(q, bio, page, len, offset,
+				max_append_sectors, &same_page) != len)
+			return -EINVAL;
+		if (same_page)
+			put_page(page);
+		offset = 0;
+	}
+
+	iov_iter_advance(iter, size);
+	return 0;
+}
+
 /**
  * bio_iov_iter_get_pages - add user or kernel pages to a bio
  * @bio: bio to add pages to
@@ -1054,10 +1098,16 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 		return -EINVAL;
 
 	do {
-		if (is_bvec)
-			ret = __bio_iov_bvec_add_pages(bio, iter);
-		else
-			ret = __bio_iov_iter_get_pages(bio, iter);
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+			if (WARN_ON_ONCE(is_bvec))
+				return -EINVAL;
+			ret = __bio_iov_append_get_pages(bio, iter);
+		} else {
+			if (is_bvec)
+				ret = __bio_iov_bvec_add_pages(bio, iter);
+			else
+				ret = __bio_iov_iter_get_pages(bio, iter);
+		}
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
 
 	if (is_bvec)
@@ -1460,6 +1510,10 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	BUG_ON(sectors <= 0);
 	BUG_ON(sectors >= bio_sectors(bio));
 
+	/* Zone append commands cannot be split */
+	if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND))
+		return NULL;
+
 	split = bio_clone_fast(bio, gfp, bs);
 	if (!split)
 		return NULL;