NAS-129309 / None / Copy offload support for block devices

Documentation/ABI/stable/sysfs-block

@@ -218,6 +218,29 @@ Description:
 		last zone of the device which may be smaller.
 
 
+What:		/sys/block/<disk>/queue/copy_max_bytes
+Date:		May 2024
+Contact:	[email protected]
+Description:
+		[RW] This is the maximum number of bytes that the block layer
+		will allow for a copy request. This is always smaller or
+		equal to the maximum size allowed by the hardware, indicated by
+		'copy_max_hw_bytes'. An attempt to set a value higher than
+		'copy_max_hw_bytes' will truncate this to 'copy_max_hw_bytes'.
+		Writing '0' to this file will disable offloading copies for this
+		device, instead copy is done via emulation.
+
+
+What:		/sys/block/<disk>/queue/copy_max_hw_bytes
+Date:		May 2024
+Contact:	[email protected]
+Description:
+		[RO] This is the maximum number of bytes that the hardware
+		will allow for single data copy request.
+		A value of 0 means that the device does not support
+		copy offload.
+
+
 What:		/sys/block/<disk>/queue/crypto/
 Date:		February 2022
 Contact:	[email protected]

block/blk-core.c

@@ -108,6 +108,8 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(ZONE_FINISH),
 	REQ_OP_NAME(ZONE_APPEND),
 	REQ_OP_NAME(WRITE_ZEROES),
+	REQ_OP_NAME(COPY_SRC),
+	REQ_OP_NAME(COPY_DST),
 	REQ_OP_NAME(DRV_IN),
 	REQ_OP_NAME(DRV_OUT),
 };
@@ -852,6 +854,11 @@ void submit_bio_noacct(struct bio *bio)
 		if (!bdev_is_zoned(bio->bi_bdev))
 			goto not_supported;
 		break;
+	case REQ_OP_COPY_SRC:
+	case REQ_OP_COPY_DST:
+		if (!q->limits.max_copy_sectors)
+			goto not_supported;
+		break;
 	case REQ_OP_DRV_IN:
 	case REQ_OP_DRV_OUT:
 		/*

block/blk-lib.c

@@ -103,6 +103,231 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
 
+static inline ssize_t blkdev_copy_sanity_check(struct block_device *bdev_in,
+					       loff_t pos_in,
+					       struct block_device *bdev_out,
+					       loff_t pos_out, size_t len)
+{
+	unsigned int align = max(bdev_logical_block_size(bdev_out),
+				 bdev_logical_block_size(bdev_in)) - 1;
+
+	if ((pos_in & align) || (pos_out & align) || (len & align) || !len ||
+	    len >= BLK_COPY_MAX_BYTES)
+		return -EINVAL;
+
+	return 0;
+}
+
+static inline void blkdev_copy_endio(struct blkdev_copy_io *cio)
+{
+	if (cio->endio) {
+		cio->endio(cio->private, cio->status, cio->copied);
+		kfree(cio);
+	} else {
+		struct task_struct *waiter = cio->waiter;
+
+		WRITE_ONCE(cio->waiter, NULL);
+		blk_wake_io_task(waiter);
+	}
+}
+
+/*
+ * This must only be called once all bios have been issued so that the refcount
+ * can only decrease. This just waits for all bios to complete.
+ * Returns the length of bytes copied or error
+ */
+static ssize_t blkdev_copy_wait_for_completion_io(struct blkdev_copy_io *cio)
+{
+	ssize_t ret;
+
+	for (;;) {
+		__set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!READ_ONCE(cio->waiter))
+			break;
+		blk_io_schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+	ret = cio->copied;
+	kfree(cio);
+
+	return ret;
+}
+
+static void blkdev_copy_offload_src_endio(struct bio *bio)
+{
+	struct blkdev_copy_offload_io *offload_io = bio->bi_private;
+	struct blkdev_copy_io *cio = offload_io->cio;
+
+	if (bio->bi_status) {
+		cio->copied = min_t(ssize_t, offload_io->offset, cio->copied);
+		if (!cio->status)
+			cio->status = blk_status_to_errno(bio->bi_status);
+	}
+	bio_put(bio);
+	if (offload_io->dst_bio)
+		bio_put(offload_io->dst_bio);
+
+	kfree(offload_io);
+
+	if (atomic_dec_and_test(&cio->refcount))
+		blkdev_copy_endio(cio);
+}
+
+/*
+ * @bdev:	source block device
+ * @pos_in:	source offset
+ * @pos_out:	destination offset
+ * @len:	length in bytes to be copied
+ * @endio:	endio function to be called on completion of copy operation,
+ *		for synchronous operation this should be NULL
+ * @private:	endio function will be called with this private data,
+ *		for synchronous operation this should be NULL
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @bdev_out:	destination block device
+ *
+ * For synchronous operation returns the length of bytes copied or error
+ * For asynchronous operation returns -EIOCBQUEUED or error
+ *
+ * Description:
+ *	Copy source offset to destination offset within block device, using
+ *	device's native copy offload feature.
+ *	We perform copy operation using 2 bio's.
+ *	1. We take a plug and send a REQ_OP_COPY_DST bio along with destination
+ *	sector and length. Once this bio reaches request layer, we form a
+ *	request and wait for dst bio to arrive.
+ *	2. We issue REQ_OP_COPY_SRC bio along with source sector, length.
+ *	Once this bio reaches request layer and find a request with previously
+ *	sent destination info we merge the source bio and return.
+ *	3. Release the plug and request is sent to driver
+ *	This design works only for drivers with request queue.
+ */
+ssize_t blkdev_copy_offload(struct block_device *bdev, loff_t pos_in,
+			    loff_t pos_out, size_t len,
+			    void (*endio)(void *, int, ssize_t),
+			    void *private, gfp_t gfp, struct block_device *bdev_out)
+{
+	struct blkdev_copy_io *cio;
+	struct blkdev_copy_offload_io *offload_io;
+	struct bio *src_bio, *dst_bio;
+	size_t rem, chunk;
+	ssize_t ret;
+	struct blk_plug plug;
+	int is_mq = 0;
+	size_t max_copy_bytes = min(bdev_max_copy_sectors(bdev) << SECTOR_SHIFT,
+	    bdev_max_copy_sectors(bdev_out) << SECTOR_SHIFT);
+
+	if (!max_copy_bytes)
+		return -EOPNOTSUPP;
+
+	if (queue_is_mq(bdev->bd_queue)) {
+		if (bdev->bd_queue->mq_ops != bdev_out->bd_queue->mq_ops)
+			return -EOPNOTSUPP;
+		is_mq = 1;
+	} else if (!bdev->bd_disk->fops->submit_bio ||
+	    bdev->bd_disk->fops->submit_bio != bdev_out->bd_disk->fops->submit_bio) {
+			return -EOPNOTSUPP;
+	}
+
+	/*
+	 * Single queue only supported for zvols
+	 */
+	if (!is_mq && strncmp(bdev->bd_disk->disk_name, "zd", 2))
+		return -EOPNOTSUPP;
+
+	/*
+	 * Cross device copy only supported for zvols
+	 */
+	if (bdev != bdev_out && strncmp(bdev_out->bd_disk->disk_name, "zd", 2))
+		return -EOPNOTSUPP;
+
+	ret = blkdev_copy_sanity_check(bdev, pos_in, bdev_out, pos_out, len);
+
+	if (ret)
+		return ret;
+
+	cio = kzalloc(sizeof(*cio), gfp);
+	if (!cio)
+		return -ENOMEM;
+	atomic_set(&cio->refcount, 1);
+	cio->waiter = current;
+	cio->endio = endio;
+	cio->private = private;
+
+	/*
+	 * If there is a error, copied will be set to least successfully
+	 * completed copied length
+	 */
+	cio->copied = len;
+	for (rem = len; rem > 0; rem -= chunk) {
+		chunk = min(rem, max_copy_bytes);
+
+		offload_io = kzalloc(sizeof(*offload_io), gfp);
+		if (!offload_io)
+			goto err_free_cio;
+		offload_io->cio = cio;
+		/*
+		 * For partial completion, we use offload_io->offset to truncate
+		 * successful copy length
+		 */
+		offload_io->offset = len - rem;
+		offload_io->driver_private = bdev_out->bd_queue->queuedata;
+
+		dst_bio = bio_alloc(bdev, 0, REQ_OP_COPY_DST, gfp);
+		if (!dst_bio)
+			goto err_free_offload_io;
+		dst_bio->bi_iter.bi_size = chunk;
+		dst_bio->bi_iter.bi_sector = pos_out >> SECTOR_SHIFT;
+
+		if (is_mq) {
+			blk_start_plug(&plug);
+			src_bio = blk_next_bio(dst_bio, bdev, 0, REQ_OP_COPY_SRC, gfp);
+		} else {
+			src_bio = bio_alloc(bdev, 0, REQ_OP_COPY_SRC, gfp);
+		}
+		if (!src_bio)
+			goto err_free_dst_bio;
+		src_bio->bi_iter.bi_size = chunk;
+		src_bio->bi_iter.bi_sector = pos_in >> SECTOR_SHIFT;
+		src_bio->bi_end_io = blkdev_copy_offload_src_endio;
+		src_bio->bi_private = offload_io;
+		offload_io->dst_bio = (is_mq) ? NULL : dst_bio;
+
+		atomic_inc(&cio->refcount);
+		submit_bio(src_bio);
+		if (is_mq)
+			blk_finish_plug(&plug);
+		pos_in += chunk;
+		pos_out += chunk;
+	}
+
+	if (atomic_dec_and_test(&cio->refcount))
+		blkdev_copy_endio(cio);
+	if (endio)
+		return -EIOCBQUEUED;
+
+	return blkdev_copy_wait_for_completion_io(cio);
+
+err_free_dst_bio:
+	if (is_mq)
+		blk_finish_plug(&plug);
+	bio_put(dst_bio);
+err_free_offload_io:
+	kfree(offload_io);
+err_free_cio:
+	cio->copied = min_t(ssize_t, cio->copied, (len - rem));
+	cio->status = -ENOMEM;
+	if (rem == len) {
+		ret = cio->status;
+		kfree(cio);
+		return ret;
+	}
+	if (cio->endio)
+		return cio->status;
+
+	return blkdev_copy_wait_for_completion_io(cio);
+}
+EXPORT_SYMBOL_GPL(blkdev_copy_offload);
+
 static sector_t bio_write_zeroes_limit(struct block_device *bdev)
 {
 	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;

block/blk-merge.c

@@ -979,6 +979,9 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (!rq_mergeable(rq) || !bio_mergeable(bio))
 		return false;
 
+	if (blk_copy_offload_mergable(rq, bio))
+		return true;
+
 	if (req_op(rq) != bio_op(bio))
 		return false;
 
@@ -1015,6 +1018,8 @@ enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
 {
 	if (blk_discard_mergable(rq))
 		return ELEVATOR_DISCARD_MERGE;
+	else if (blk_copy_offload_mergable(rq, bio))
+		return ELEVATOR_COPY_OFFLOAD_MERGE;
 	else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
 		return ELEVATOR_BACK_MERGE;
 	else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
@@ -1122,6 +1127,20 @@ static enum bio_merge_status bio_attempt_discard_merge(struct request_queue *q,
 	return BIO_MERGE_FAILED;
 }
 
+static enum bio_merge_status bio_attempt_copy_offload_merge(struct request *req,
+							    struct bio *bio)
+{
+	if (req->__data_len != bio->bi_iter.bi_size)
+		return BIO_MERGE_FAILED;
+
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->nr_phys_segments++;
+	req->__data_len += bio->bi_iter.bi_size;
+
+	return BIO_MERGE_OK;
+}
+
 static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
 						   struct request *rq,
 						   struct bio *bio,
@@ -1142,6 +1161,8 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
 		break;
 	case ELEVATOR_DISCARD_MERGE:
 		return bio_attempt_discard_merge(q, rq, bio);
+	case ELEVATOR_COPY_OFFLOAD_MERGE:
+		return bio_attempt_copy_offload_merge(rq, bio);
 	default:
 		return BIO_MERGE_NONE;
 	}