linux-kernel - Re: [bug] very high non-preempt latency in context_struct_compute

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]

Date:	Thu, 7 Jun 2007 21:51:51 +0200
From:	Ingo Molnar <mingo@...e.hu>
To:	Stephen Smalley <sds@...ho.nsa.gov>
Cc:	linux-kernel@...r.kernel.org,
	Andrew Morton <akpm@...ux-foundation.org>,
	James Carter <jwcart2@...ho.nsa.gov>,
	Paul Moore <paul.moore@...com>,
	James Morris <jmorris@...ei.org>
Subject: Re: [bug] very high non-preempt latency in
	context_struct_compute_av()


* Stephen Smalley <sds@...ho.nsa.gov> wrote:

> Can you try the patch below to see whether it helps?
> 
> In security_get_user_sids, move the transition permission checks 
> outside of the section holding the policy rdlock, and use the AVC to 
> perform the checks, calling cond_resched after each one.  These 
> changes should allow preemption between the individual checks and 
> enable caching of the results.  It may however increase the overall 
> time spent in the function in some cases, particularly in the cache 
> miss case.
> 
> The long term fix will be to take much of this logic to userspace by 
> exporting additional state via selinuxfs, and ultimately deprecating 
> and eliminating this interface from the kernel.
> 
> Signed-off-by: Stephen Smalley <sds@...ho.nsa.gov>

i have just tried your patch and it completely solves the issue! Without 
the patch, a simple script that keeps logging in on a box:

	while :; do ssh testbox true; done

would cause glxgears to get into a very jerky motion due to the 
latencies. With the patch it's 100%, totally smooth! Thanks!

Tested-by: Ingo Molnar <mingo@...e.hu>

	Ingo
-
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/