On Mon, Mar 25, 2019 at 11:52:31AM +0100, Christoph Hellwig wrote:
On Mon, Mar 25, 2019 at 06:07:07PM +0800, Ming Lei wrote:
There isn't sg iterator helper for building bvec, so invent one and fix the issue in nvmet_file_init_bvec().
The issue is that one sg may include multipge continuous pages, and only the 1st .bv_offset isn't zero, also the length for the last bvec has to consider the remained length.
The scatterlist in the nvme target is always allocated by the nvmet code itself an thus never contains multi-page sg list entries.
I am wondering if it is true.
Not look at other target code yet, however seems it isn't true for loop, see the following code in nvme_loop_queue_rq():
iod->req.sg = iod->sg_table.sgl; iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl); iod->req.transfer_len = blk_rq_payload_bytes(req);
And it has been triggered by nvme/011 in Yi's test.
Thanks, Ming