[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <YQ041Djm5GzjU3WR@dhcp22.suse.cz>
Date: Fri, 6 Aug 2021 15:27:48 +0200
From: Michal Hocko <mhocko@...e.com>
To: Feng Tang <feng.tang@...el.com>
Cc: linux-mm@...ck.org, Andrew Morton <akpm@...ux-foundation.org>,
David Rientjes <rientjes@...gle.com>,
Dave Hansen <dave.hansen@...el.com>,
Ben Widawsky <ben.widawsky@...el.com>,
linux-kernel@...r.kernel.org, linux-api@...r.kernel.org,
Andrea Arcangeli <aarcange@...hat.com>,
Mel Gorman <mgorman@...hsingularity.net>,
Mike Kravetz <mike.kravetz@...cle.com>,
Randy Dunlap <rdunlap@...radead.org>,
Vlastimil Babka <vbabka@...e.cz>,
Andi Kleen <ak@...ux.intel.com>,
Dan Williams <dan.j.williams@...el.com>, ying.huang@...el.com,
Dave Hansen <dave.hansen@...ux.intel.com>
Subject: Re: [PATCH v7 1/5] mm/mempolicy: Add MPOL_PREFERRED_MANY for
multiple preferred nodes
On Tue 03-08-21 13:59:18, Feng Tang wrote:
[...]
> @@ -1936,7 +1969,9 @@ unsigned int mempolicy_slab_node(void)
> case MPOL_INTERLEAVE:
> return interleave_nodes(policy);
>
> - case MPOL_BIND: {
> + case MPOL_BIND:
> + case MPOL_PREFERRED_MANY:
> + {
> struct zoneref *z;
I guess this is ok for now but it would be great if slab maintainers
could have a look here. I suspect this will need some more changes. E.g.
I find it highly suspicious how fallback_alloc uses mempolicy_slab_node.
Let's say that the local node is not a part of the nodemask.
mempolicy_slab_node will switch to the first node in the order list
which is ok but fallback_alloc then iterates over the whole zonelist
without any policy node mask constrains. get_any_partial looks very
similar.
--
Michal Hocko
SUSE Labs
Powered by blists - more mailing lists