[ofa-general] [PATCH 2/3] RDMA/cxgb3: fix page shift calculation in build_phys_page_list()

Bryan S Rosenburg rosnbrg at us.ibm.com
Mon Feb 11 08:24:19 PST 2008


Steve Wise <swise at opengridcomputing.com> wrote on 02/11/2008 11:10:18 AM:
> Bryan S Rosenburg wrote:
> > 
> > Steve Wise <swise at opengridcomputing.com> wrote on 02/11/2008 10:39:38 
AM:
> >  > Bryan, I assume you sign-off on this patch?
> > 
> > Steve, yes, I "sign-off" on this patch, although I posted it just for 
> > discussion.  I haven't tested (or even compiled) it for cxgb3.  Let me 

> > know if you want me to do anything more formal.
> > 
> 
> Oh.  I thought you said it fixed a bug? :)  Any testing you can do would 

> be great.

Sorry if I've misled you.  :-(  I only have mthca cards to play with.  I 
verified the analogous bug in that driver and tested the fix, although at 
this point Roland Dreier has implemented a more general fix that takes the 
alignment of the virtual address into account.

- Bryan


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20080211/c619ef3c/attachment.html>


More information about the general mailing list