Re: [PATCH linux-next] perf/ring_buffer: Add EPOLLRDNORM flag for poll

[Namhyung Kim <namhyung@kernel.org>]

Hello,

On Thu, Mar 13, 2025 at 06:09:45PM +0100, Ingo Molnar wrote:
> 
> * Tao Chen <chen.dylane@linux.dev> wrote:
> 
> > 在 2025/3/13 18:05, Ingo Molnar 写道:
> > > 
> > > * Tao Chen <chen.dylane@linux.dev> wrote:
> > > 
> > > > The poll man page says POLLRDNORM is equivalent to POLLIN,
> > > > so add EPOLLRDNORM here.
> > > > 
> > > > Signed-off-by: Tao Chen <chen.dylane@linux.dev>
> > > > ---
> > > >   kernel/events/ring_buffer.c | 2 +-
> > > >   1 file changed, 1 insertion(+), 1 deletion(-)
> > > > 
> > > > diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
> > > > index 59a52b1a1..5130b119d 100644
> > > > --- a/kernel/events/ring_buffer.c
> > > > +++ b/kernel/events/ring_buffer.c
> > > > @@ -19,7 +19,7 @@
> > > >   static void perf_output_wakeup(struct perf_output_handle *handle)
> > > >   {
> > > > -	atomic_set(&handle->rb->poll, EPOLLIN);
> > > > +	atomic_set(&handle->rb->poll, EPOLLIN | EPOLLRDNORM);
> > > 
> > > So what does EPOLLRDNORM mean to begin with? There doesn't seem to be
> > > separate/specific handling of it anywhere in the kernel that I can
> > > see...
> > > 
> > 
> > It seems that if user set pollfd with POLLRDNORM, perf_poll will not return
> > until timeout even if perf_output_wakeup called, whereas POLLIN returns.
> 
> Mind adding this to the changelog, and explain that this patch fixes 
> this particular poll() functionality and semantics for userspace?

Off topic, but I think it should return something (either POLLHUP or
POLLERR) when the event goes to an error state like pinned events are
not scheduled.

Thanks,
Namhyung