The tape drivers (and the sg driver in a special case that doesn't matter here) use the null_mapped flag to tell blk_rq_map_user to not copy around any data into or out of the bounce buffers. blk_rq_map_user_iov never got that treatment, which didn't matter until I refactored blk_rq_map_user to be implemented in terms of blk_rq_map_user_iov.
Signed-off-by: Christoph Hellwig <[email protected]> --- block/blk-map.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/block/blk-map.c b/block/blk-map.c index 0f22911..b8d2725 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -93,6 +93,9 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, if (IS_ERR(bio)) return PTR_ERR(bio); + if (map_data && map_data->null_mapped) + bio->bi_flags |= (1 << BIO_NULL_MAPPED); + if (bio->bi_iter.bi_size != iter->count) { /* * Grab an extra reference to this bio, as bio_unmap_user() -- 1.9.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
