Re: [PATCH] svcrdma: delete double assignment

[Steve Wise]

On 7/29/2014 5:50 PM, David Miller wrote:
> From: Himangi Saraogi <himangi774@xxxxxxxxx>
> Date: Mon, 28 Jul 2014 20:59:38 +0530
>
> > Delete successive assignments to the same location.
> >
> > A simplified version of Coccinelle semantic match that finds this problem is as
> > follows:
> >
> > // <smpl>
> > @@
> > expression i;
> > @@
> >
> > *i = ...;
> >   i = ...;
> > // </smpl>
> >
> > Signed-off-by: Himangi Saraogi <himangi774@xxxxxxxxx>
> I am not so sure about this change either.
>
> > @@ -956,7 +956,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
> >   			dprintk("svcrdma: failed to create QP, ret=%d\n", ret);
> >   			goto errout;
> >   		}
> > -		newxprt->sc_max_sge = qp_attr.cap.max_send_sge;
> >   		newxprt->sc_max_sge = qp_attr.cap.max_recv_sge;
> >   		newxprt->sc_sq_depth = qp_attr.cap.max_send_wr;
> >   		newxprt->sc_max_requests = qp_attr.cap.max_recv_wr;
> ->sc_max_sge is used to limit the number of segments used during sends,
> currently in this code.  Grep for where it is used.
>
> Therefore, if anything, the correct thing to do would be to retain the
> first line rather than the second line.
>
> Someone who actually works on this code and understands it should
> really take a close look at this before anyone even thinks about
> applying this patch.

We should remove that whole block that tries to recover from a 
rdma_create_qp() failure.   I don't believe we would ever hit it. The 
value initially stored in sc_max_sge is from the device attribute 
max_sge returned from ib_query_device() just above the code we're 
talking about.  If rdma_create_qp() fails, it would not be because the 
max_send_sge and max_recv_sge values passed in exceed the device's max...

Like this:

diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c 
b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index e7323fb..282a43b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -942,23 +942,8 @@ static struct svc_xprt *svc_rdma_accept(struct 
svc_xprt *xprt)

        ret = rdma_create_qp(newxprt->sc_cm_id, newxprt->sc_pd, &qp_attr);
        if (ret) {
-               /*
-                * XXX: This is a hack. We need a xx_request_qp interface
-                * that will adjust the qp_attr's with a best-effort
-                * number
-                */
-               qp_attr.cap.max_send_sge -= 2;
-               qp_attr.cap.max_recv_sge -= 2;
-               ret = rdma_create_qp(newxprt->sc_cm_id, newxprt->sc_pd,
-                                    &qp_attr);
-               if (ret) {
-                       dprintk("svcrdma: failed to create QP, 
ret=%d\n", ret);
-                       goto errout;
-               }
-               newxprt->sc_max_sge = qp_attr.cap.max_send_sge;
-               newxprt->sc_max_sge = qp_attr.cap.max_recv_sge;
-               newxprt->sc_sq_depth = qp_attr.cap.max_send_wr;
-               newxprt->sc_max_requests = qp_attr.cap.max_recv_wr;
+               dprintk("svcrdma: failed to create QP, ret=%d\n", ret);
+               goto errout;
        }
        newxprt->sc_qp = newxprt->sc_cm_id->qp;


Steve.




--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/