Re: [PATCH 1/2] perf: Correctly align perf event tracing buffer

From: Peter Zijlstra <peterz@infradead.org>
To: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>, LKML <linux-kernel@vger.kernel.org>,
	Arnaldo Carvalho de Melo <acme@redhat.com>,
	Paul Mackerras <paulus@samba.org>,
	David Miller <davem@davemloft.net>,
	Steven Rostedt <rostedt@goodmis.org>
Subject: Re: [PATCH 1/2] perf: Correctly align perf event tracing buffer
Date: Mon, 29 Mar 2010 19:20:09 +0200	[thread overview]
Message-ID: <1269883209.12097.366.camel@laptop> (raw)
In-Reply-To: <20100329171615.GA5101@nowhere>

On Mon, 2010-03-29 at 19:16 +0200, Frederic Weisbecker wrote:
> On Mon, Mar 29, 2010 at 10:51:31AM +0200, Peter Zijlstra wrote:
> > On Sun, 2010-03-28 at 07:11 +0200, Frederic Weisbecker wrote:
> > >  kernel/trace/trace_event_perf.c |   11 +++++++++--
> > >  1 files changed, 9 insertions(+), 2 deletions(-)
> > > 
> > > diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
> > > index 0709e4f..69941f3 100644
> > > --- a/kernel/trace/trace_event_perf.c
> > > +++ b/kernel/trace/trace_event_perf.c
> > > @@ -15,7 +15,12 @@ EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs);
> > >  static char *perf_trace_buf;
> > >  static char *perf_trace_buf_nmi;
> > >  
> > > -typedef typeof(char [PERF_MAX_TRACE_SIZE]) perf_trace_t ;
> > > +/*
> > > + * Force it to be aligned to unsigned long to avoid misaligned accesses
> > > + * suprises
> > > + */
> > > +typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
> > > +	perf_trace_t;
> > >  
> > 
> > wouldn't __aligned(8) be simpler?
> 
> 
> David and Tejun seemed to prefer to create the alignment on the
> type level rather than using an align.
> 
> I'm personally fine either way.

Also, if you need u64 alignment, shouldn't you use u64 instead of
unsigned long, the alignment requirement on those two might differ on
32bit machines.