>>> On 02.03.15 at 18:12, <ian.campb...@citrix.com> wrote: > On Thu, 2015-02-26 at 13:53 +0000, Jan Beulich wrote: >> ... using struct domain as a container for passing the respective >> affinity mask: Quite a number of allocations are domain specific, yet >> not to be accounted for that domain. Introduce a flag suppressing the >> accounting altogether (i.e. going beyond MEMF_no_refcount) and use it >> right away in common code (x86 and IOMMU code will get adjusted >> subsequently). >> >> Signed-off-by: Jan Beulich <jbeul...@suse.com> > > Acked-by: Ian Campbell <ian.campb...@citrix.com>
Thanks. > Does this patch constitute all the "not just"(x86) from the initial > mail? I'll assume so unless I hear otherwise. No, this part of patch 1 "Note that this gives meaning to MEMF_exact_node specified alone (i.e. implicitly combined with NUMA_NO_NODE): In such a case any node inside the domain's node mask is acceptable, but no other node. This changed behavior is (implicitly) being exposed through the memop hypercalls." does too. (Patches 4 and 5 are only indirectly x86-specific, as the IOMMU code touched there is used on x86 only. But that's of no concern to you anyway.) Jan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel