Re: [PATCH 1/6] perf_counter: move the event overflow output bitsto record_type

[Corey Ashford]

Peter Zijlstra wrote:
> On Thu, 2009-04-02 at 16:27 -0700, Corey Ashford wrote:
> > Whoops, nevermind.
> >
> > My misunderstanding on this one.  This enum is used for event type, not 
> > the record_type, and as such is makes sense for there to be exclusive 
> > mmap and munmap event records.
> >
> > Thinking about this a bit, I'm guessing that the idea is to track the 
> > loading and unloading of shared objects which uses mmap and munmap, so 
> > that that the ip can be related to a particular object that was mapped 
> > in at the time of the counter overflow interrupt.  Is that right?
>
> Indeed, whenever a mmap/munmap happens of a PROT_EXEC range we record
> that information so that we can relate the userspace IPs to some file
> and hence the actual userspace code.

Ah, I see, PROT_EXEC identifies the executable code sections in particular.

Thanks :-)

- Corey

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/