From mboxrd@z Thu Jan  1 00:00:00 1970
From: james_p_freyensee@linux.intel.com (J Freyensee)
Date: Thu, 18 Aug 2016 08:56:50 -0700
Subject: [PATCH v4 1/4] nvmet-rdma: +1 to *queue_size from hsqsize/hrqsize
In-Reply-To: <7b7f2836-ad77-b508-ad53-2f49aec03612@grimberg.me>
References: <1471471228-15818-1-git-send-email-james_p_freyensee@linux.intel.com>
 <1471471228-15818-2-git-send-email-james_p_freyensee@linux.intel.com>
 <7b7f2836-ad77-b508-ad53-2f49aec03612@grimberg.me>
Message-ID: <1471535810.31578.8.camel@linux.intel.com>

On Thu, 2016-08-18@10:00 +0300, Sagi Grimberg wrote:
> 
> On 18/08/16 01:00, Jay Freyensee wrote:
> > 
> > The host will be sending sqsize 0-based values,
> > the target need to be adjusted as well.
> > 
> > Signed-off-by: Jay Freyensee <james_p_freyensee at linux.intel.com>
> > Reviewed-by: Sagi Grimberg <sagi at grimberg.me>
> > ---
> > ?drivers/nvme/target/rdma.c | 8 ++++----
> > ?1 file changed, 4 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/nvme/target/rdma.c
> > b/drivers/nvme/target/rdma.c
> > index e06d504..68b7b04 100644
> > --- a/drivers/nvme/target/rdma.c
> > +++ b/drivers/nvme/target/rdma.c
> > @@ -1004,11 +1004,11 @@ nvmet_rdma_parse_cm_connect_req(struct
> > rdma_conn_param *conn,
> > ?	queue->host_qid = le16_to_cpu(req->qid);
> > 
> > ?	/*
> > -	?* req->hsqsize corresponds to our recv queue size
> > -	?* req->hrqsize corresponds to our send queue size
> > +	?* req->hsqsize corresponds to our recv queue size plus 1
> > +	?* req->hrqsize corresponds to our send queue size plus 1
> > ?	?*/
> > -	queue->recv_queue_size = le16_to_cpu(req->hsqsize);
> > -	queue->send_queue_size = le16_to_cpu(req->hrqsize);
> > +	queue->recv_queue_size = le16_to_cpu(req->hsqsize) + 1;
> > +	queue->send_queue_size = le16_to_cpu(req->hrqsize) + 1;
> 
> hrqsize is sent as is (1's based) so no need to increment.
> I'll fix it...

The target's send and receive queue size will be still the same length
and I thought we wanted to make the queue associated with hrqsize 1
entry larger more than the queue associated with hsqsize.

Either case, I'm fine with the solution, when the specification
actually explains how to use this better, we can re-visit.