Re: [PATCH RFC 1/3] IB/core: Expose a device attribute for rdma_read access flags

[Sagi Grimberg <sagig-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>]

Hi Yann,

>
> Why were those hw providers not modified to
> enforce IB_ACCESS_REMOTE_WRITE when needed, instead of asking users to
> set it for them ?

Do you mean that ULPs will set IB_ACCESS_LOCAL_WRITE and
iWARP providers executing the memory registration will add
IB_ACCESS_REMOTE_WRITE? That's even better I think! Given that
changing the access rights under the user legs is something we'd want
to do. is it?

Given that for IB memory registration is not even needed for rdma_read,
I'd like to move away from code like:

if (rdma_protocol_iwarp())
	register memory for rdma_read
else
	go ahead with ib_sge for rdma_read

I've maid some initial experimentation on trying to abstract this
aspect from ULPs but it's far from being complete and needs more work.

Sagi.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html