On Tue, Nov 24, 2009 at 04:18:35PM +0200, Or Gerlitz wrote: > > I see this code in a patch whose commit log has the following "Date: Mon, 3 > Aug 2009 18:29:07 +0300" and "Subject: [PATCH 11/13] mlx4: Add support for > RDMAoE - address resolution" > > +struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr) > [...] > + /* TBD: need to handle the case when we get called > + in an atomic context and there we might sleep. We > + don't expect this currently since we're working with > + link local addresses which we can translate without > + going to sleep */ > + ret = create_rdmaoe_ah(pd, ah_attr, ah); > > are all the addresses which this code will run to serve are link local? Addresses (e.g. GIDs) may be either link local or mulitcast; in both cases the translation is immediate.
> also what patch set version is present in the ofed 1.5 rdmaoe branch? OFED rdmaoe is based on v6. It has a some fixes in it which I intend to send to the rdma list as distinct patches (on top of v6 rather then sending a v7 series). _______________________________________________ ewg mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
