netdev - rhashtable concurrent writers issue, 4.2+

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>] [day] [month] [year] [list]

Date:	Fri, 11 Dec 2015 16:09:04 +0000
From:	Colin Ian King <colin.king@...onical.com>
To:	netdev@...r.kernel.org
Cc:	Thomas Graf <tgraf@...g.ch>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: rhashtable concurrent writers issue, 4.2+

Hi,

After testing with commit 7def0f952eccdd0edb3c504f4dab35ee0d3aba1f
("lib: fix data race in rhashtable_rehash_one") on the current 4.4-rc4
kernel, I believe I am still seeing race conditions that seem to bite
concurrent readers.

The reproducer is found in my stress-ng system stress tool:

git://kernel.ubuntu.com/cking/stress-ng.git

one needs libattr1-dev, libkeyutils-dev to build this.

run the concurrent procfs stressor on 2 CPUs:

./stress-ng --procfs 2

..sometimes this hangs w/o a kernel stack dump, but sometimes it oopses
and one can see that we get a concurrent reader failure.

Colin
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html