Bug 9352

Summary:	2.6.24-rc1-gb4f5550 oops
Product:	Process Management	Reporter:	Rafael J. Wysocki (rjwysocki)
Component:	Scheduler	Assignee:	Ingo Molnar (mingo)
Status:	CLOSED CODE_FIX
Severity:	normal	CC:	mingo
Priority:	P1
Hardware:	All
OS:	Linux
Kernel Version:	2.6.24-rc1-gb4f5550	Subsystem:
Regression:	Yes	Bisected commit-id:
Bug Depends on:
Bug Blocks:	9243

Description Rafael J. Wysocki 2007-11-11 11:28:51 UTC

Subject         : 2.6.24-rc1-gb4f5550 oops
Submitter       : Grant Wilson <grant.wilson@zen.co.uk>
References      : http://lkml.org/lkml/2007/11/5/6
Handled-By      : "Rafael J. Wysocki" <rjw@sisk.pl>

Comment 1 Ingo Molnar 2007-11-17 18:31:44 UTC

Please check whether this occurs with 2.6.24-rc3 or later kernels - we fixed a particular SMP race that could explain this crash.

Comment 2 Ingo Molnar 2007-11-20 00:29:50 UTC

reports of this bug have disappeared for now - it should be fixed by this commit:

--------------------------->
commit ce96b5ac742801718ae86d2adf0500c5abef3782
Author: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Date:   Thu Nov 15 20:57:40 2007 +0100

    sched: fix __set_task_cpu() SMP race
    
    Grant Wilson has reported rare SCHED_FAIR_USER crashes on his quad-core
    system, which crashes can only be explained via runqueue corruption.
<--------------------------

please reopen the bug if it still triggers for you.