Messages in this thread | | | Date | Fri, 27 Aug 2010 21:19:39 +0800 | From | DDD <> | Subject | Re: [PATCH] perf: fix possible divide-by-zero in perf_swevent_overflow() |
| |
Peter Zijlstra wrote: > On Fri, 2010-08-27 at 20:21 +0800, DDD wrote: > >>>> Maybe the root cause was from kgdb/hw_breakpoint_layer, >>> Yeah, I think there's a bug in the hw_breakpoint stuff, does something >>> like the below fix it? > >> Thanks for your patch, but I still could reproduce the problem with your >> patch. > > Frederic, any clue as to what makes hw breakpoints go funny and have > last_period == 0?
Hi Peter,
Thanks for you take care of it, I have got the root cause of it now.
It is the kgdb using hw_breakpoint_layer's API problem, and I have a RFC patch for it.(maybe it is not correctly), I will contact with Jason to fix this problem.
Thank you very much, Dongdong
> >>> --- >>> kernel/hw_breakpoint.c | 13 ++++++++++++- >>> 1 files changed, 12 insertions(+), 1 deletions(-) >>> >>> diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c >>> index d71a987..f57ebee 100644 >>> --- a/kernel/hw_breakpoint.c >>> +++ b/kernel/hw_breakpoint.c >>> @@ -600,9 +600,20 @@ static int __init init_hw_breakpoint(void) >>> } >>> core_initcall(init_hw_breakpoint); >>> >>> +static int hw_breakpoint_enable(struct perf_event *event) >>> +{ >>> + struct hw_perf_event *hwc = &event->hw; >>> + >>> + if (hwc->sample_period) { >>> + hwc->last_period = hwc->sample_period; >>> + perf_swevent_set_period(event); >>> + } >>> + >>> + return arch_install_hw_breakpoint(event); >>> +} >>> >>> struct pmu perf_ops_bp = { >>> - .enable = arch_install_hw_breakpoint, >>> + .enable = hw_breakpoint_enable, >>> .disable = arch_uninstall_hw_breakpoint, >>> .read = hw_breakpoint_pmu_read, >>> }; >>> >>> >
| |