Messages in this thread | | | Date | Tue, 18 Nov 2008 13:37:48 +0100 | From | Michal Hocko <> | Subject | Re: BUG: using smp_processor_id() in preemptible [00000000] code: latencytop/5621 |
| |
On Sun 16-11-08 00:28:12, Rafael J. Wysocki wrote: > On Friday, 14 of November 2008, Michal Hocko wrote: > > Hi Ingo, > > I am experiencing %subj whenever I run latencytop with the rc4 kernel. I > > have bisected down to the patch 7cbaef9c83e58bbd4bdd534b09052b6c5ec457d5 > > I am not sure whether this is the same problem as the one reported by > > Maciej Rutecki (http://lkml.org/lkml/2008/11/12/266), but I have tried > > your patch (http://lkml.org/lkml/2008/11/12/295) and the problem is > > still there: > > BUG: using smp_processor_id() in preemptible [00000000] code: > > latencytop/5621 > > caller is native_sched_clock+0x47/0x65 > > Pid: 5621, comm: latencytop Not tainted 2.6.28-rc4 #13 > > Call Trace: > > [<c03f17c0>] ? printk+0xf/0x11 > > [<c022ad36>] debug_smp_processor_id+0xa2/0xb8 > > [<c01080d4>] native_sched_clock+0x47/0x65 > > [<c01259a9>] proc_sched_show_task+0xd72/0xdd0 > > [<c01a73c4>] sched_show+0x39/0x55 > > [<c018cc43>] seq_read+0xee/0x29a > > [<c018cb55>] ? seq_read+0x0/0x29a > > [<c017a04c>] vfs_read+0x87/0x12b > > [<c017a189>] sys_read+0x3b/0x60 > > [<c0103a59>] sysenter_do_call+0x12/0x25 > > [<c03f0000>] ? cpu_callback+0x238/0x25b > > > > I receive flood if this messages immediately after latencytop starts. > > Reverting 7cbaef9c83e58bbd4bdd534b09052b6c5ec457d5 solves the problem. > > Config is attached. > > > > Let me know if you need some more testing (however I will afk until > > Tuesday). > > Please retest with 2.6.28-rc5.
Still problem with rc5 (4e14e833ac3b97a4aa8803eea49f899adc5bb5f4). Ingo's patch from http://lkml.org/lkml/2008/11/16/26 fixes this problem
> > Thanks, > Rafael
-- Michal Hocko L3 team SUSE LINUX s.r.o. Lihovarska 1060/12 190 00 Praha 9 Czech Republic
| |