Re: [PATCH v2 00/14] perf, persistent: Kernel updates for perf tool integration

[Robert Richter <rric@kernel.org>]

On 26.06.13 10:24:08, Borislav Petkov wrote:
> On Wed, Jun 26, 2013 at 10:12:23AM +0200, Robert Richter wrote:
> > We get a new fd by opening the persistent event with the syscall.
> > There would be 2 new ioctls:
> > 
> >  ioctl(fd, PERF_EVENT_IOC_DETACH, 0);
> >  ioctl(fd, PERF_EVENT_IOC_ATTACH, 0);
> > 
> > This would be fine and reuses existing infrastructure.
> 
> Well, how are you going to say that you want to open an already existing
> persistent event or your want to create exactly the same persistent
> event? Are we even going to allow identical persistent events to
> coexist?

Here is the scenario:

Creating a persistent event from userspace:

 * A process opens a system-wide event with the syscall and gets a fd.
 * The process mmaps the buffer.
 * The process does an ioctl to detach the process which increases the
   events and buffers refcount. The event is listed as 'persistent' in
   sysfs with a unique id.
 * The process closes the fd. Event and buffer remain in the system
   since the refcounts are not zero.

Opening a persistent event:

 * A process scans sysfs for persistent events.
 * To open the event it sets up the event attr according to sysfs.
 * The persistent event is opened with the syscall, the process gets a
   new fd of the event.
 * The process attaches to the event buffer with mmap.

Releasing a persistent event:

 * A process opens a persistent event and gets a fd.
 * The process does an ioctl to attach the process which decreases the
   refcounts. The sysfs entry is removed.
 * The process closes the fd.
 * After all processes that are tied to the event closed their event's
   fds, the persistent event and its buffer is released.

Sounds like a plan?

-Robert