Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:1 as permitted sender) client-ip=2620:137:e000::3:1;
Feedback-ID: iccd040f4:Fastmail
From:   Zi Yan <zi.yan@sent.com>
To:     linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc:     Zi Yan <ziy@nvidia.com>, Ryan Roberts <ryan.roberts@arm.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        "Matthew Wilcox (Oracle)" <willy@infradead.org>,
        David Hildenbrand <david@redhat.com>,
        "Yin, Fengwei" <fengwei.yin@intel.com>,
        Yu Zhao <yuzhao@google.com>, Vlastimil Babka <vbabka@suse.cz>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Baolin Wang <baolin.wang@linux.alibaba.com>,
        Kemeng Shi <shikemeng@huaweicloud.com>,
        Mel Gorman <mgorman@techsingularity.net>,
        Rohan Puri <rohan.puri15@gmail.com>,
        Mcgrof Chamberlain <mcgrof@kernel.org>,
        Adam Manzanares <a.manzanares@samsung.com>,
        John Hubbard <jhubbard@nvidia.com>
Subject: [RFC PATCH 2/4] mm/compaction: optimize >0 order folio compaction with free page split.
Date:   Tue, 12 Sep 2023 12:28:13 -0400
Message-Id: <20230912162815.440749-3-zi.yan@sent.com>
In-Reply-To: <20230912162815.440749-1-zi.yan@sent.com>
References: <20230912162815.440749-1-zi.yan@sent.com>
Reply-To: Zi Yan <ziy@nvidia.com>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

From: Zi Yan <ziy@nvidia.com>

During migration in a memory compaction, free pages are placed in an array
of page lists based on their order. But the desired free page order (i.e.,
the order of a source page) might not be always present, thus leading to
migration failures. Split a high order free pages when source migration
page has a lower order to increase migration successful rate.

Note: merging free pages when a migration fails and a lower order free
page is returned via compaction_free() is possible, but there is too much
work. Since the free pages are not buddy pages, it is hard to identify
these free pages using existing PFN-based page merging algorithm.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/compaction.c | 40 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 39 insertions(+), 1 deletion(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 868e92e55d27..45747ab5f380 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1801,9 +1801,46 @@ static struct folio *compaction_alloc(struct folio *=
src, unsigned long data)
 	struct compact_control *cc =3D (struct compact_control *)data;
 	struct folio *dst;
 	int order =3D folio_order(src);
+	bool has_isolated_pages =3D false;
=20
+again:
 	if (!cc->freepages[order].nr_free) {
-		isolate_freepages(cc);
+		int i;
+
+		for (i =3D order + 1; i <=3D MAX_ORDER; i++) {
+			if (cc->freepages[i].nr_free) {
+				struct page *freepage =3D
+					list_first_entry(&cc->freepages[i].pages,
+							 struct page, lru);
+
+				int start_order =3D i;
+				unsigned long size =3D 1 << start_order;
+
+				list_del(&freepage->lru);
+				cc->freepages[i].nr_free--;
+
+				while (start_order > order) {
+					start_order--;
+					size >>=3D 1;
+
+					list_add(&freepage[size].lru,
+						&cc->freepages[start_order].pages);
+					cc->freepages[start_order].nr_free++;
+					set_page_private(&freepage[size], start_order);
+				}
+				post_alloc_hook(freepage, order, __GFP_MOVABLE);
+				if (order)
+					prep_compound_page(freepage, order);
+				dst =3D page_folio(freepage);
+				goto done;
+			}
+		}
+		if (!has_isolated_pages) {
+			isolate_freepages(cc);
+			has_isolated_pages =3D true;
+			goto again;
+		}
+
 		if (!cc->freepages[order].nr_free)
 			return NULL;
 	}
@@ -1814,6 +1851,7 @@ static struct folio *compaction_alloc(struct folio *s=
rc, unsigned long data)
 	post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
 	if (order)
 		prep_compound_page(&dst->page, order);
+done:
 	cc->nr_freepages -=3D 1 << order;
 	return dst;
 }
--=20
2.40.1