Yes, you are right, I misunderstood it, corrected now thanks for replying. On Sun, Aug 3, 2008 at 2:26 PM, Dotan Barak <[EMAIL PROTECTED]> wrote:
> On Sat, Aug 2, 2008 at 1:02 PM, Devesh Sharma <[EMAIL PROTECTED]> wrote: > > Thanks for replying, > > Can you explain me in a bit more detail, because if QP dose not have a > > IB_ACCESS_LOCAL_WRITE permission, according to IB spec, HCA should > generate > > Local Protection Error while processing the WRs. Is it assumed that mthca > > driver (or some other provider driver) will set IB_ACCESS_LOCAL_WRITE by > > itself, even if its not requested? > The protection flag in the QP attributes is only specify which > incoming remote operations are supported (Read/Write/Atomic). > > The IB_ACCESS_LOCAL_WRITE is enabled (or not) in the Memory Region. > > Dotan > > > > > On Fri, Aug 1, 2008 at 10:07 PM, Sean Hefty <[EMAIL PROTECTED]> > wrote: > >> > >> > while creating QP using rdma_create_qp(), I am not seeing any where > >> > it is setting IB_ACCESS_LOCAL_WRITE flag other then for IW QPs. Is > >> > it for some specific reason its just a mistake? > >> > >> Commit 1ca8d15619f725e223c19137350b0336b9196193 (dated July 22nd) > removed > >> this > >> for iWarp QPs. The qp_access_flags is only used to set remote > >> permissions, so > >> it should not be being set. > >> > >> - Sean > >> > > > > > > _______________________________________________ > > general mailing list > > [email protected] > > http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general > > > > To unsubscribe, please visit > > http://openib.org/mailman/listinfo/openib-general > > >
_______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
