[PATCH tracing/kprobes 4/7] tracing/kprobes: Add event profiling support

[Frederic Weisbecker]

On Fri, Sep 11, 2009 at 12:22:16PM -0400, Masami Hiramatsu wrote:
> Frederic Weisbecker wrote:
>>> +static int probe_profile_enable(struct ftrace_event_call *call)
>>> +{
>>> +	struct trace_probe *tp = (struct trace_probe *)call->data;
>>> +
>>> +	if (atomic_inc_return(&call->profile_count))
>>> +		return 0;
>>> +
>>> +	if (probe_is_return(tp)) {
>>> +		tp->rp.handler = kretprobe_profile_func;
>>> +		return enable_kretprobe(&tp->rp);
>>> +	} else {
>>> +		tp->rp.kp.pre_handler = kprobe_profile_func;
>>> +		return enable_kprobe(&tp->rp.kp);
>>> +	}
>>> +}
>>
>>
>>
>> May be I misunderstood but it seems that concurrent uses of
>> ftrace and perf would really mess up the result, as one would
>> overwrite the handler of the other.
>>
>> Even though it's hard to imagine one using both at the same
>> time on the same probe, but still...
>
> Oops, it's my misunderstanding. I thought those are exclusively
> enabled each other.


It's automatically managed with events because ftrace and
and perf have their individual tracepoint probes, because
tracepoints support multiple probes.


>> Is it possible to have two kprobes having the exact same
>> properties? (pointing to the same address, having the same
>> probe handlers, etc...)
>>
>> Another solution would be to allow kprobes to have multiple
>> handlers.
>
> It could be to have multiple kprobes on same point, but I think
> it's waste of the memory and time in this case.


Yeah.


>
> I'd like to have a dispatcher function and flags internally :)


You mean kprobes that could support multiple probes?
That would be a nice solution IMHO...