<br>On Mon, Jun 2, 2008 at 7:35 PM, Roland Dreier <<a href="mailto:rdreier@cisco.com">rdreier@cisco.com</a>> wrote:<br><div class="gmail_quote"><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div class="Ih2E3d"> > + IB_DEVICE_BLOCK_LOOPBACK = (1<<22),<br>
<br>
</div>This clashes with MEM_MGT_EXTENSIONS.</blockquote><div> </div><div>looking in the for-2.6.27 branch of your tree, <br>
IB_DEVICE_SEND_W_INV (21) was removed and IB_DEVICE_MEM_MGT_EXTENSIONS (21) was added instead.<br>
So it seems that the value of 22 is free for adding a cap bit, if we decide we go this way. <br><br></div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>
<br>
Do we really need to burn a capability bit for this? Would it cause any<br>
problems to make IB_QP_BLOCK_LOOPBACK a hint that the underlying HCA may<br>
or may not support?<br>
<div class="Ih2E3d"><br>
> enum ib_qp_create_flags {<br>
> IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0,<br>
> + IB_QP_BLOCK_LOOPBACK = 1 << 1,<br>
> };<br>
<br>
</div>The naming convention is that this should be IB_QP_CREATE_BLOCK_LOOPBACK.</blockquote><div><br>You are right, will be fixed. <br><br></div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>
<font color="#888888"><br>
- R.<br>
</font><div><div></div><div class="Wj3C7c">_______________________________________________<br>
general mailing list<br>
<a href="mailto:general@lists.openfabrics.org">general@lists.openfabrics.org</a><br>
<a href="http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general" target="_blank">http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general</a><br>
<br>
To unsubscribe, please visit <a href="http://openib.org/mailman/listinfo/openib-general" target="_blank">http://openib.org/mailman/listinfo/openib-general</a><br>
</div></div></blockquote></div><br>