Re: [PATCH 1/2] tracing/function-return-tracer: Make the functionreturn tracer lockless

From: Steven Rostedt
Date: Thu Nov 13 2008 - 13:35:32 EST



On Thu, 13 Nov 2008, Andi Kleen wrote:

> On Thu, Nov 13, 2008 at 12:32:23PM -0500, Steven Rostedt wrote:
> >
> > On Thu, 13 Nov 2008, Andi Kleen wrote:
> >
> > > > So the answer to this is:
> > > >
> > > > i = index++;
> > > > barrier();
> > > > write to index i (not index);
> > >
> > > That was my first thought when I wrote the original email,
> > > but the disadvantage is that barrier() is a big hammer
> > > that flushes everything and can make the code much worse.
> > > That is why I suggested local_add_return() instead.
> >
> > barrier() is a compiler barrier, does nothing with the caches, and is
> > quite cheap. We only need a compiler barrier because we are only
>
> I did not refer to CPU caches, but the compiler's register allocation
> [ok if you want the registers are the "level 0 cache"]. A memory barrier
> all messes it up. That is why it is better to only clobber specific
> memory regions, which is what local_* does.
>


#define barrier() __asm__ __volatile__("": : :"memory")

static inline long local_add_return(long i, local_t *l)
{
long __i;
#ifdef CONFIG_M386
unsigned long flags;
if (unlikely(boot_cpu_data.x86 <= 3))
goto no_xadd;
#endif
/* Modern 486+ processor */
__i = i;
asm volatile(_ASM_XADD "%0, %1;"
: "+r" (i), "+m" (l->a.counter)
: : "memory");
return i + __i;

#ifdef CONFIG_M386
no_xadd: /* Legacy 386 processor */
local_irq_save(flags);
__i = local_read(l);
local_set(l, i + __i);
local_irq_restore(flags);
return i + __i;
#endif
}



Now tell me again how local_* is more efficient than barrier?

Not to mention, if this is ever used on other archs with load-linked and
store-conditional, it gets even worse.

-- 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/