Re: [PATCH v4 4/5] slub: Only IPI CPUs that have per cpu obj to flush

From: Gilad Ben-Yossef
Date: Wed Nov 23 2011 - 02:52:48 EST


On Wed, Nov 23, 2011 at 8:57 AM, Pekka Enberg <penberg@xxxxxxxxxx> wrote:
> On Wed, Nov 23, 2011 at 8:23 AM, Pekka Enberg <penberg@xxxxxxxxxx> wrote:
>> On Tue, 22 Nov 2011, Gilad Ben-Yossef wrote:
>>>
>>> static void flush_all(struct kmem_cache *s)
>>> {
>>> -       on_each_cpu(flush_cpu_slab, s, 1);
>>> +       cpumask_var_t cpus;
>>> +       struct kmem_cache_cpu *c;
>>> +       int cpu;
>>> +
>>> +       if (likely(zalloc_cpumask_var(&cpus, GFP_ATOMIC))) {
>>
>> __GFP_NOWARN too maybe?
>>

Right, the allocation failure here is harmless. I should probably do
the same for the page_alloc.c case as well.

>>> +               for_each_online_cpu(cpu) {
>>> +                       c = per_cpu_ptr(s->cpu_slab, cpu);
>>> +                       if (c->page)
>>> +                               cpumask_set_cpu(cpu, cpus);
>>> +               }
>>> +               on_each_cpu_mask(cpus, flush_cpu_slab, s, 1);
>>> +               free_cpumask_var(cpus);
>>> +       } else
>>> +               on_each_cpu(flush_cpu_slab, s, 1);
>>> }
>>
>> Acked-by: Pekka Enberg <penberg@xxxxxxxxxx>
>>
>> I can't take the patch because it depends on a new API introduced in the
>> first patch.
>>
>> I'm CC'ing Andrew.

Thanks!

There's a git tree of these over at: git://github.com/gby/linux.git
branch ipi_noise_v4 in case that helps.

I will send v5 (and create a new git branch for it) with the above
changes and the Arm patch description update once I get an Ack from
Russel K.

Cheers,
Gilad

>



--
Gilad Ben-Yossef
Chief Coffee Drinker
gilad@xxxxxxxxxxxxx
Israel Cell: +972-52-8260388
US Cell: +1-973-8260388
http://benyossef.com

"Unfortunately, cache misses are an equal opportunity pain provider."
-- Mike Galbraith, LKML
--
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/