On Mon, 24 Oct 2016 17:56:13 +0200 Arnd Bergmann <a...@arndb.de> wrote:

> The slub allocator gives us some incorrect warnings when
> CONFIG_PROFILE_ANNOTATED_BRANCHES is set, as the unlikely()
> macro prevents it from seeing that the return code matches
> what it was before:
> 
> mm/slub.c: In function ‘kmem_cache_free_bulk’:
> mm/slub.c:262:23: error: ‘df.s’ may be used uninitialized in this function 
> [-Werror=maybe-uninitialized]
> mm/slub.c:2943:3: error: ‘df.cnt’ may be used uninitialized in this function 
> [-Werror=maybe-uninitialized]
> mm/slub.c:2933:4470: error: ‘df.freelist’ may be used uninitialized in this 
> function [-Werror=maybe-uninitialized]
> mm/slub.c:2943:3: error: ‘df.tail’ may be used uninitialized in this function 
> [-Werror=maybe-uninitialized]
> 
> I have not been able to come up with a perfect way for dealing with
> this, the three options I see are:
> 
> - add a bogus initialization, which would increase the runtime overhead
> - replace unlikely() with unlikely_notrace()
> - remove the unlikely() annotation completely
> 
> I checked the object code for a typical x86 configuration and the
> last two cases produce the same result, so I went for the last
> one, which is the simplest.

If the object code is the same, then I've fine with this solution, as
the performance should then also be the same.

I do have micro-benchmark module there to verify the performance:
 
https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c

Acked-by: Jesper Dangaard Brouer <bro...@redhat.com>


> Signed-off-by: Arnd Bergmann <a...@arndb.de>
> ---
>  mm/slub.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/mm/slub.c b/mm/slub.c
> index 2b3e740609e9..68b84f93d38d 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -3076,7 +3076,7 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t 
> size, void **p)
>               struct detached_freelist df;
>  
>               size = build_detached_freelist(s, size, p, &df);
> -             if (unlikely(!df.page))
> +             if (!df.page)
>                       continue;
>  
>               slab_free(df.s, df.page, df.freelist, df.tail, df.cnt,_RET_IP_);



-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  Author of http://www.iptv-analyzer.org
  LinkedIn: http://www.linkedin.com/in/brouer

Reply via email to