linux-kernel - Re: RCU stall

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: <56F44CE2.1060703@sandisk.com>
Date:	Thu, 24 Mar 2016 13:24:02 -0700
From:	Bart Van Assche <bart.vanassche@...disk.com>
To:	"paulmck@...ux.vnet.ibm.com" <paulmck@...ux.vnet.ibm.com>
CC:	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: RCU stall

On 03/22/2016 07:29 PM, Paul E. McKenney wrote:
> Note that a soft lockup triggered at 10509.568010, well before the RCU
> CPU stall warning..  And you have a second soft lockup at 10537.567212,
> with the same funtion scsi_request_fn() at the top of the stack in both
> stack traces.  That function has a nice big "for (;;)" loop that does
> not appear to have any iteration-limiting mechanism.

Hello Paul,

Your feedback is really appreciated. I have started with testing the 
four attached patches. With the tests I ran so far these patches were 
sufficient to avoid any soft lockup or RCU stall complaints. I will 
submit these patches to the appropriate maintainers once I have finished 
testing these patches.

Bart.

View attachment "0001-IB-cm-Fix-a-recently-introduced-locking-bug.patch" of type "text/x-patch" (3020 bytes)

View attachment "0002-kernel-kthread.c-Avoid-CPU-lockups.patch" of type "text/x-patch" (1765 bytes)

View attachment "0003-block-Limit-work-processed-in-softirq-context.patch" of type "text/x-patch" (2854 bytes)

View attachment "0004-Avoid-that-I-O-completion-processing-triggers-lockup.patch" of type "text/x-patch" (4863 bytes)