Re: [PATCH] ib_core: Enable and expose force_mr module parameter

[Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>]

[-- Attachment #1: Type: text/plain, Size: 1137 bytes --]

On Wed, Jun 28, 2017 at 05:48:33PM +0300, Sagi Grimberg wrote:
>
> > > > I hope that we are done.
> > > > https://patchwork.kernel.org/patch/9808615/
> > >
> > > You have a bogus empty line change there.
> >
> > If I remember correctly, It was needed to silence checkpatch.
>
> So it should not be a part of the patch.
>
> Also, I think that the statement is _really_ unnecessary:
>
> "* Setting it to "true" will allow to mimic with IB devices,
>  * the slow memory registration of iWARP devices."
>
> And, its simply not true. Its designed to test the rw logic for
> sg patterns that would normally not be registered. The fact
> that iWARP registers memory for rdma reads is completely orthogonal.
>
> And this statement is not true either:
>
> "* This parameter is useful for new ULP bringup
>  * and/or conversion to this R/W API."
>
> Its designed to test the code itself, not for ULP
> bringup or conversion, although it is useful for that.
>
> And, I can't say that I 100% agree with not making it
> configurable, but since you insist so much, at least
> give a proper description.

No problem, I'll send updated version.

Thanks

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]