Received-SPF: pass (google.com: domain of linux-kernel+bounces-71853-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Date: Mon, 19 Feb 2024 20:12:23 +0100
From: Michal Hocko <mhocko@suse.com>
To: Donet Tom <donettom@linux.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org,
	Aneesh Kumar <aneesh.kumar@kernel.org>,
	Huang Ying <ying.huang@intel.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Mel Gorman <mgorman@suse.de>, Ben Widawsky <ben.widawsky@intel.com>,
	Feng Tang <feng.tang@intel.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>, Rik van Riel <riel@surriel.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Matthew Wilcox <willy@infradead.org>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Vlastimil Babka <vbabka@suse.cz>,
	Dan Williams <dan.j.williams@intel.com>,
	Hugh Dickins <hughd@google.com>,
	Kefeng Wang <wangkefeng.wang@huawei.com>,
	Suren Baghdasaryan <surenb@google.com>
Subject: Re: [PATCH 3/3] mm/numa_balancing:Allow migrate on protnone
 reference with MPOL_PREFERRED_MANY policy
Message-ID: <ZdOoF_pMAa-FGN4m@tiehlicka>
References: <9c3f7b743477560d1c5b12b8c111a584a2cc92ee.1708097962.git.donettom@linux.ibm.com>
 <8d7737208bd24e754dc7a538a3f7f02de84f1f72.1708097962.git.donettom@linux.ibm.com>
 <ZdNjmOlkMqEOGci1@tiehlicka>
 <25b420aa-3fe6-40a4-8d60-a46ab61ee7b7@linux.ibm.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <25b420aa-3fe6-40a4-8d60-a46ab61ee7b7@linux.ibm.com>

On Mon 19-02-24 20:37:17, Donet Tom wrote:
> 
> On 2/19/24 19:50, Michal Hocko wrote:
> > On Sat 17-02-24 01:31:35, Donet Tom wrote:
> > [...]
> > > +static inline bool mpol_preferred_should_numa_migrate(int exec_node, int folio_node,
> > > +					    struct mempolicy *pol)
> > > +{
> > > +	/* if the executing node is in the policy node mask, migrate */
> > > +	if (node_isset(exec_node, pol->nodes))
> > > +		return true;
> > > +
> > > +	/* If the folio node is in policy node mask, don't migrate */
> > > +	if (node_isset(folio_node, pol->nodes))
> > > +		return false;
> > > +	/*
> > > +	 * both the folio node and executing node are outside the policy nodemask,
> > > +	 * migrate as normal numa fault migration.
> > > +	 */
> > > +	return true;
> > > +}
> > I have looked at this again and only now noticed that this doesn't
> > really work as one would expected.
> > 
> >          case MPOL_PREFERRED_MANY:
> >                  /*
> >                   * use current page if in policy nodemask,
> >                   * else select nearest allowed node, if any.
> >                   * If no allowed nodes, use current [!misplaced].
> >                   */
> >                  if (node_isset(curnid, pol->nodes))
> >                          goto out;
> >                  z = first_zones_zonelist(
> >                                  node_zonelist(numa_node_id(), GFP_HIGHUSER),
> >                                  gfp_zone(GFP_HIGHUSER),
> >                                  &pol->nodes);
> >                  polnid = zone_to_nid(z->zone);
> >                  break;
> > 
> > Will collapse the whole MPOL_PREFERRED_MANY nodemask into the first
> > notde into that mask. Is that really what we want here? Shouldn't we use
> > the full nodemask as the migration target?
> 
> With this patch it will take full nodemask and find out the correct migration target. It will not collapse into first node.

Correct me if I am wrong, but mpol_misplaced will return the first node
of the preffered node mask and then migrate_misplaced_folio would use
it as a target node for alloc_misplaced_dst_folio which performs
__GFP_THISNODE allocation so it won't fall back to a different node.
-- 
Michal Hocko
SUSE Labs