Re: [PATCH v2 1/7] ring-buffer: add NMI protection for spinlocks

[Steven Rostedt]

On Fri, 6 Feb 2009, Mathieu Desnoyers wrote:
> >  
> >  	commit_page = cpu_buffer->commit_page;
> >  	/* we just need to protect against interrupts */
> > @@ -995,7 +1026,19 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
> >  		struct buffer_page *next_page = tail_page;
> >  
> >  		local_irq_save(flags);
> > -		__raw_spin_lock(&cpu_buffer->lock);
> > +		/*
> > +		 * NMIs can happen after we take the lock.
> > +		 * If we are in an NMI, only take the lock
> > +		 * if it is not already taken. Otherwise
> > +		 * simply fail.
> > +		 */
> > +		if (unlikely(__get_cpu_var(rb_in_nmi))) {
> > +			if (!__raw_spin_trylock(&cpu_buffer->lock))
> > +				goto out_unlock;
> 
> Hi Steven,
> 
> You're not silently discarding an event, aren't you ? ;)
> 
> Please keep at least a count of "events_lost" so it can be reported
> later by a printk().

I could add a counter here, but it is not a silent discard. The tracer 
would receive a "NULL" pointer in this case. Then the tracer can do what 
it wants with this information. The ring buffer will never discard data 
(otherwise it is a bug) without letting the tracer know that it did so.

-- Steve

--
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/