From 73318e2cafe53e8b7c8899d990cf8eaca32184d0 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Tue, 20 Feb 2024 13:32:20 -0500
Subject: [PATCH] mm/compaction: optimize >0 order folio compaction with free
 page split.

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 and premature compaction termination.  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.

Link: https://lkml.kernel.org/r/20240220183220.1451315-5-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Tested-by: Yu Zhao <yuzhao@google.com>
Cc: Adam Manzanares <a.manzanares@samsung.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/compaction.c | 35 ++++++++++++++++++++++++++++++-----
 1 file changed, 30 insertions(+), 5 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 61b2c731c9db..1faeffb28720 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1856,15 +1856,40 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
 	struct compact_control *cc = (struct compact_control *)data;
 	struct folio *dst;
 	int order = folio_order(src);
+	bool has_isolated_pages = false;
+	int start_order;
+	struct page *freepage;
+	unsigned long size;
 
-	if (list_empty(&cc->freepages[order])) {
-		isolate_freepages(cc);
-		if (list_empty(&cc->freepages[order]))
+again:
+	for (start_order = order; start_order < NR_PAGE_ORDERS; start_order++)
+		if (!list_empty(&cc->freepages[start_order]))
+			break;
+
+	/* no free pages in the list */
+	if (start_order == NR_PAGE_ORDERS) {
+		if (has_isolated_pages)
 			return NULL;
+		isolate_freepages(cc);
+		has_isolated_pages = true;
+		goto again;
 	}
 
-	dst = list_first_entry(&cc->freepages[order], struct folio, lru);
-	list_del(&dst->lru);
+	freepage = list_first_entry(&cc->freepages[start_order], struct page,
+				lru);
+	size = 1 << start_order;
+
+	list_del(&freepage->lru);
+
+	while (start_order > order) {
+		start_order--;
+		size >>= 1;
+
+		list_add(&freepage[size].lru, &cc->freepages[start_order]);
+		set_page_private(&freepage[size], start_order);
+	}
+	dst = (struct folio *)freepage;
+
 	post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
 	if (order)
 		prep_compound_page(&dst->page, order);