This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: BUG: [preempt-rt] scheduling while atomic: stapio
- From: Josh Stone <jistone at redhat dot com>
- To: Kiran <kiran at linux dot vnet dot ibm dot com>
- Cc: systemtap at sources dot redhat dot com, sripathi at in dot ibm dot com, dvhltc at us dot ibm dot com, jkenisto at us dot ibm dot com
- Date: Wed, 20 May 2009 12:21:58 -0700
- Subject: Re: BUG: [preempt-rt] scheduling while atomic: stapio
- References: <1242812648.13247.12.camel@kiran-laptop>
On 05/20/2009 02:44 AM, Kiran wrote:
> BUG: scheduling while atomic: stapio/0x00000001/26142, CPU#3
> [...]
> [<ffffffff812a2dea>] cpufreq_unregister_notifier+0x35/0x5c
> [<ffffffffa02e0a1f>] _stp_kill_time+0xb6/0xbd [stap_246f93f30a500769142af9987624737a_5072]
> [<ffffffffa02e1749>] probe_1391+0x3c/0xa8 [stap_246f93f30a500769142af9987624737a_5072]
> [<ffffffffa02e2621>] enter_end_probe+0x14a/0x1e3 [stap_246f93f30a500769142af9987624737a_5072]
enter_end_probe will call preempt_disable, and apparently the call path
from cpufreq_unregister_notifier can sleep. Is this true only of the RT
kernel?
I organized the init/kill_time calls this way to avoid running our time
code when it's not used. I'll see if I can tweak it to run in a
sleep-able context...
Josh