From mboxrd@z Thu Jan 1 00:00:00 1970 From: hch@infradead.org (Christoph Hellwig) Date: Thu, 14 Sep 2017 10:01:39 -0700 Subject: [PATCH] nvmet: implement valid sqhd values in completions In-Reply-To: <20170907201836.25067-1-jsmart2021@gmail.com> References: <20170907201836.25067-1-jsmart2021@gmail.com> Message-ID: <20170914170139.GA25583@infradead.org> On Thu, Sep 07, 2017@01:18:36PM -0700, James Smart wrote: > To support sqhd, for initiators that are following the spec and > paying attention to sqhd vs their sqtail values: > - add sqhd to struct nvmet_sq > - initialize sqhd to 0 in nvmet_sq_setup > - rather than propagate the 0's-based qsize value from the connect message > which requires a +1 in every sqhd update, and as nothing else references > it, convert to 1's-based value in nvmt_sq/cq_setup() calls. > - validate connect message sqsize being non-zero per spec. > - updated assign sqhd for every completion that goes back. > > Signed-off-by: James Smart > --- > drivers/nvme/target/core.c | 9 +++++---- > drivers/nvme/target/fabrics-cmd.c | 9 +++++++-- > drivers/nvme/target/nvmet.h | 1 + > 3 files changed, 13 insertions(+), 6 deletions(-) > > diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c > index 7c23eaf8e563..434394ead4a2 100644 > --- a/drivers/nvme/target/core.c > +++ b/drivers/nvme/target/core.c > @@ -390,8 +390,8 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status) > if (status) > nvmet_set_status(req, status); > > - /* XXX: need to fill in something useful for sq_head */ > - req->rsp->sq_head = 0; > + req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size; > + req->rsp->sq_head = req->sq->sqhd; This is missing an endianes conversion: drivers/nvme/target/core.c:394:27: warning: incorrect type in assignment (different base types) drivers/nvme/target/core.c:394:27: expected restricted __le16 [usertype] sq_head drivers/nvme/target/core.c:394:27: got unsigned short [unsigned] [usertype] sqhd