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
| ||
|
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
Powered by blists - more mailing lists