Greetings,

Here is a pktgen error triggered by this debug check.

git://git.kernel.org/pub/scm/linux/kernel/git/peterz/queue.git sched/wait
commit 64c2181bc433b17f04da8fe8592aa83cceac9606
Author:     Peter Zijlstra <peterz@infradead.org>
AuthorDate: Mon Aug 4 11:14:16 2014 +0200
Commit:     Peter Zijlstra <a.p.zijlstra@chello.nl>
CommitDate: Mon Aug 4 13:29:59 2014 +0200

    sched: Debug nested sleeps
    
    Validate we call might_sleep() with TASK_RUNNING, which catches places
    where we nest blocking primitives, eg. mutex usage in a wait loop.
    
    Since all blocking is arranged through task_struct::state, nesting
    this is going to cause two distinct issues:
    
     - the inner primitive will set TASK_RUNNING and the outer will not
       block
    
     - the outer sets !TASK_RUNNING and the inner expects to be called
       with TASK_RUNNING and blocks forever (mutex_lock).
    
    Signed-off-by: Peter Zijlstra <peterz@infradead.org>
    Link: http://lkml.kernel.org/n/tip-0hge361rozfbng4z2t64t217(a)git.kernel.org

[    1.604869] gre: GRE over IPv4 demultiplexor driver
[    1.606178] ip_gre: GRE over IPv4 tunneling driver
[    1.608031] ------------[ cut here ]------------
[    1.609370] WARNING: CPU: 0 PID: 89 at kernel/sched/core.c:7094 __might_sleep+0x6f/0x1f8()
[    1.611875] do not call blocking ops when !TASK_RUNNING; state=1 set at [<ffffffff8153f80c>] pktgen_thread_worker.part.36+0x5/0x769
[    1.618496] tcp_probe: probe registered (port=0/fwmark=0) bufsize=4096
[    1.620291] Modules linked in:
[    1.621568] CPU: 0 PID: 89 Comm: kpktgend_0 Not tainted 3.16.0-00053-g64c2181 #1
[    1.624084] TCP: bic registered
[    1.625297] TCP: cubic registered
[    1.626488] TCP: westwood registered
[    1.627749] TCP: highspeed registered
[    1.629117] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[    1.630928]  0000000000000000 ffff880013b53d48 ffffffff8153cc4f ffff880013b53d80
[    1.633938]  ffffffff8105fa45 ffffffff810856f3 0000000000000001 0000000000000000
[    1.636942]  ffffffff81420801 00000000000000a9 ffff880013b53de0 ffffffff8105faaa

This script may reproduce the error.

----------------------------------------------------------------------------
#!/bin/bash

kernel=$1
initrd=quantal-core-x86_64.cgz

wget --no-clobber https://github.com/fengguang/reproduce-kernel-bug/raw/master/initrd/$initrd

kvm=(
	qemu-system-x86_64
	-enable-kvm
	-cpu Haswell,+smep,+smap
	-kernel $kernel
	-initrd $initrd
	-m 320
	-smp 2
	-net nic,vlan=1,model=e1000
	-net user,vlan=1
	-boot order=nc
	-no-reboot
	-watchdog i6300esb
	-rtc base=localtime
	-serial stdio
	-display none
	-monitor null 
)

append=(
	hung_task_panic=1
	earlyprintk=ttyS0,115200
	debug
	apic=debug
	sysrq_always_enabled
	rcupdate.rcu_cpu_stall_timeout=100
	panic=10
	softlockup_panic=1
	nmi_watchdog=panic
	prompt_ramdisk=0
	console=ttyS0,115200
	console=tty0
	vga=normal
	root=/dev/ram0
	rw
	drbd.minor_count=8
)

"${kvm[@]}" --append "${append[*]}"
----------------------------------------------------------------------------

Thanks,
Fengguang

_______________________________________________
LKP mailing list
LKP(a)linux.intel.com