linux-kernel - [PATCH v2 8/9] mm/compaction: don't use higher order freepage than compaction aims at

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1440382773-16070-9-git-send-email-iamjoonsoo.kim@lge.com>
Date:	Mon, 24 Aug 2015 11:19:32 +0900
From:	Joonsoo Kim <js1304@...il.com>
To:	Andrew Morton <akpm@...ux-foundation.org>
Cc:	linux-kernel@...r.kernel.org, linux-mm@...ck.org,
	Vlastimil Babka <vbabka@...e.cz>, Mel Gorman <mgorman@...e.de>,
	Rik van Riel <riel@...hat.com>,
	David Rientjes <rientjes@...gle.com>,
	Minchan Kim <minchan@...nel.org>,
	Joonsoo Kim <iamjoonsoo.kim@....com>
Subject: [PATCH v2 8/9] mm/compaction: don't use higher order freepage than compaction aims at

Purpose of compaction is to make high order page. To achive this purpose,
it is the best strategy that compaction migrates contiguous used pages
to fragmented unused freepages. Currently, freepage scanner don't
distinguish whether freepage is fragmented or not and blindly use
any freepage for migration target regardless of freepage's order.

Using higher order freepage than compaction aims at is not good because
what we do here is breaking high order freepage at somewhere and migrating
used pages from elsewhere to this broken high order freepages in order to
make new high order freepage. That is just position change of high order
freepage.

This is useless effort and doesn't help to make more high order freepages
because we can't be sure that migrating used pages makes high order
freepage. So, this patch makes freepage scanner only uses the ordered
freepage lower than compaction order.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@....com>
---
 mm/compaction.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/mm/compaction.c b/mm/compaction.c
index ca4d6d1..e61ee77 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -455,6 +455,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	unsigned long flags = 0;
 	bool locked = false;
 	unsigned long blockpfn = *start_pfn;
+	unsigned long freepage_order;

 	cursor = pfn_to_page(blockpfn);

@@ -482,6 +483,20 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 		if (!PageBuddy(page))
 			goto isolate_fail;

+		if (!strict && cc->order != -1) {
+			freepage_order = page_order_unsafe(page);
+
+			if (freepage_order > 0 && freepage_order < MAX_ORDER) {
+				/*
+				 * Do not use high order freepage for migration
+				 * taret. It would not be beneficial for
+				 * compaction success rate.
+				 */
+				if (freepage_order >= cc->order)
+					goto isolate_fail;
+			}
+		}
+
 		/*
 		 * If we already hold the lock, we can skip some rechecking.
 		 * Note that if we hold the lock now, checked_pageblock was
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/