linux-kernel - [PATCH 3.10 155/268] mm: vmpressure: fix sending wrong events on underflow

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 for Android: free password hash cracker in your pocket

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

Date:   Mon, 19 Jun 2017 20:30:54 +0200
From:   Willy Tarreau <w@....eu>
To:     linux-kernel@...r.kernel.org, stable@...r.kernel.org,
        linux@...ck-us.net
Cc:     Vinayak Menon <vinmenon@...eaurora.org>,
        Johannes Weiner <hannes@...xchg.org>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Vlastimil Babka <vbabka@...e.cz>,
        Rik van Riel <riel@...hat.com>,
        Vladimir Davydov <vdavydov.dev@...il.com>,
        Anton Vorontsov <anton.vorontsov@...aro.org>,
        Shiraz Hashim <shashim@...eaurora.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Willy Tarreau <w@....eu>
Subject: [PATCH 3.10 155/268] mm: vmpressure: fix sending wrong events on underflow

From: Vinayak Menon <vinmenon@...eaurora.org>

commit e1587a4945408faa58d0485002c110eb2454740c upstream.

At the end of a window period, if the reclaimed pages is greater than
scanned, an unsigned underflow can result in a huge pressure value and
thus a critical event.  Reclaimed pages is found to go higher than
scanned because of the addition of reclaimed slab pages to reclaimed in
shrink_node without a corresponding increment to scanned pages.

Minchan Kim mentioned that this can also happen in the case of a THP
page where the scanned is 1 and reclaimed could be 512.

Link: http://lkml.kernel.org/r/1486641577-11685-1-git-send-email-vinmenon@codeaurora.org
Signed-off-by: Vinayak Menon <vinmenon@...eaurora.org>
Acked-by: Minchan Kim <minchan@...nel.org>
Acked-by: Michal Hocko <mhocko@...e.com>
Cc: Johannes Weiner <hannes@...xchg.org>
Cc: Mel Gorman <mgorman@...hsingularity.net>
Cc: Vlastimil Babka <vbabka@...e.cz>
Cc: Rik van Riel <riel@...hat.com>
Cc: Vladimir Davydov <vdavydov.dev@...il.com>
Cc: Anton Vorontsov <anton.vorontsov@...aro.org>
Cc: Shiraz Hashim <shashim@...eaurora.org>
Signed-off-by: Andrew Morton <akpm@...ux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@...ux-foundation.org>
Signed-off-by: Willy Tarreau <w@....eu>
---
 mm/vmpressure.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 736a601..e8955f9 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -116,9 +116,16 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
 						    unsigned long reclaimed)
 {
 	unsigned long scale = scanned + reclaimed;
-	unsigned long pressure;
+	unsigned long pressure = 0;
 
 	/*
+	 * reclaimed can be greater than scanned in cases
+	 * like THP, where the scanned is 1 and reclaimed
+	 * could be 512
+	 */
+	if (reclaimed >= scanned)
+		goto out;
+	/*
 	 * We calculate the ratio (in percents) of how many pages were
 	 * scanned vs. reclaimed in a given time frame (window). Note that
 	 * time is in VM reclaimer's "ticks", i.e. number of pages
@@ -128,6 +135,7 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
 	pressure = scale - (reclaimed * scale / scanned);
 	pressure = pressure * 100 / scale;
 
+out:
 	pr_debug("%s: %3lu  (s: %lu  r: %lu)\n", __func__, pressure,
 		 scanned, reclaimed);
 
-- 
2.8.0.rc2.1.gbe9624a