[ltt-dev] LTTng 2.0 on ARM

Mathieu Desnoyers compudj at krystal.dyndns.org
Wed Sep 21 10:06:43 EDT 2011


* Avik Sil (avik.sil at linaro.org) wrote:
> Hi Mathieu,
> 
> Now as the ARM patch is in, I'm able to generate trace and read the
> trace with babeltrace on Pandaboard. But while enabling the events, I
> get following output:
> 
> # lttng enable-event -a -k
> [ 4304.827819] BUG: spinlock bad magic on CPU#1, ltt-sessiond/1305
> [ 4304.841735]  lock: 81453c00, .magic: 00000000, .owner: <none>/-1,
> .owner_cpu: 0
> [ 4304.857421] [<800110ad>] (unwind_backtrace+0x1/0x90) from
> [<8022c847>] (do_raw_spin_lock+0x17/0xfc)
> [ 4304.875213] [<8022c847>] (do_raw_spin_lock+0x17/0xfc) from
> [<7f97c30f>] (channel_create+0xd6/0x158 [lib_ring_buffer])
> [ 4304.894866] [<7f97c30f>] (channel_create+0xd6/0x158
> [lib_ring_buffer]) from [<7f99856b>] (_channel_create+0x28/0x32
> [ltt_ring_buffer_client_discard])
> [ 4304.917755] [<7f99856b>] (_channel_create+0x28/0x32
> [ltt_ring_buffer_client_discard]) from [<7f98b507>]
> (ltt_channel_create+0x12a/0x190 [ltt_relay])
> [ 4304.940551] [<7f98b507>] (ltt_channel_create+0x12a/0x190 [ltt_relay])
> from [<7f98c34b>] (lttng_abi_create_channel+0xba/0x158 [ltt_relay])
> [ 4304.962341] [<7f98c34b>] (lttng_abi_create_channel+0xba/0x158
> [ltt_relay]) from [<7f98c43f>] (lttng_session_ioctl+0x56/0x64 [ltt_relay])
> [ 4304.984436] [<7f98c43f>] (lttng_session_ioctl+0x56/0x64 [ltt_relay])
> from [<800baa49>] (do_vfs_ioctl+0x1a5/0x1dc)
> [ 4305.004394] [<800baa49>] (do_vfs_ioctl+0x1a5/0x1dc) from [<800baab3>]
> (sys_ioctl+0x33/0x4c)
> [ 4305.022369] [<800baab3>] (sys_ioctl+0x33/0x4c) from [<8000c2c1>]
> (ret_fast_syscall+0x1/0x50)
> All kernel events are enabled in channel channel0
> 
> Can you please look into this issue?

Yes, it looks like I missed a spinlock initialization in there. Can you
try with the following commit applied ?

commit 6fb8de4b6c1e8dcc69ff6f67310c5cf29718101a
Author: Mathieu Desnoyers <mathieu.desnoyers at efficios.com>
Date:   Wed Sep 21 10:08:34 2011 -0400

    lib ring buffer frontend: add missing lock initialization

Thanks,

Mathieu

> 
> Regards,
> Avik
> 
> On Sunday 11 September 2011 01:19 AM, Mathieu Desnoyers wrote:
> > * Avik Sil (avik.sil at linaro.org) wrote:
> >> Hi,
> >>
> >> I'm trying to use LTTng 2.0 on a Pandaboard. After building the latest
> >> tools and modules I tried to run lttng and got following error:
> >>
> >> # lttng list -k
> [...]
> > 
> > Hi Avik,
> > 
> > Can I get your kernel .config ? Also, adding a printk in lttng-modules
> > wrapper/vmalloc.h, just after vmalloc_sync_all_sym = (void *)
> > kallsyms_lookup_name("vmalloc_sync_all");
> > 
> > printing the vmalloc_sync_all_sym pointer value would be clearly
> > helpful. I would think ARM does not implement vmalloc_sync_all, so the
> > dummy mm/vmalloc.c vmalloc_sync_all weak symbol should be used as a
> > valid empty function. Please grep for vmalloc_sync_all under your
> > arch/arm to see if your particular omap flavor is implementing a
> > vmalloc_sync_all.
> > 
> > Thanks!
> > 
> > Mathieu
> > 
> >>
> >> Regards,
> >> Avik
> >>
> >> _______________________________________________
> >> ltt-dev mailing list
> >> ltt-dev at lists.casi.polymtl.ca
> >> http://lists.casi.polymtl.ca/cgi-bin/mailman/listinfo/ltt-dev
> >>
> > 
> 

-- 
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com




More information about the lttng-dev mailing list