Re: [patch] mm, slab: initialize object alignment on cache creation

2014-09-24 Thread Christoph Lameter
On Tue, 23 Sep 2014, David Rientjes wrote:

> Previous to commit 4590685546a3 ("mm/sl[aou]b: Common alignment code")
> which introduced this issue.

Ah. Ok. I see and approve.

Acked-by: Christoph Lameter 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/


Re: [patch] mm, slab: initialize object alignment on cache creation

2014-09-23 Thread David Rientjes
On Tue, 23 Sep 2014, Christoph Lameter wrote:

> > The proper alignment defaults to BYTES_PER_WORD and can be overridden by
> > SLAB_RED_ZONE or the alignment specified by the caller.
> 
> Where does it default to BYTES_PER_WORD in __kmem_cache_create?
> 

Previous to commit 4590685546a3 ("mm/sl[aou]b: Common alignment code") 
which introduced this issue.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/


Re: [patch] mm, slab: initialize object alignment on cache creation

2014-09-23 Thread Christoph Lameter
On Tue, 23 Sep 2014, David Rientjes wrote:

> The proper alignment defaults to BYTES_PER_WORD and can be overridden by
> SLAB_RED_ZONE or the alignment specified by the caller.

Where does it default to BYTES_PER_WORD in __kmem_cache_create?
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/


[patch] mm, slab: initialize object alignment on cache creation

2014-09-23 Thread David Rientjes
Since 4590685546a3 ("mm/sl[aou]b: Common alignment code"), the "ralign" 
automatic variable in __kmem_cache_create() may be used as uninitialized.

The proper alignment defaults to BYTES_PER_WORD and can be overridden by 
SLAB_RED_ZONE or the alignment specified by the caller.

This fixes https://bugzilla.kernel.org/show_bug.cgi?id=85031

Reported-by: Andrei Elovikov 
Signed-off-by: David Rientjes 
---
 a.elovikov: If you respond to this email with your full name, Andrew can 
 give proper credit for reporting this issue.

 mm/slab.c | 11 ++-
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/mm/slab.c b/mm/slab.c
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2128,7 +2128,8 @@ static int __init_refok setup_cpu_cache(struct kmem_cache 
*cachep, gfp_t gfp)
 int
 __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 {
-   size_t left_over, freelist_size, ralign;
+   size_t left_over, freelist_size;
+   size_t ralign = BYTES_PER_WORD;
gfp_t gfp;
int err;
size_t size = cachep->size;
@@ -2161,14 +2162,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned 
long flags)
size &= ~(BYTES_PER_WORD - 1);
}
 
-   /*
-* Redzoning and user store require word alignment or possibly larger.
-* Note this will be overridden by architecture or caller mandated
-* alignment if either is greater than BYTES_PER_WORD.
-*/
-   if (flags & SLAB_STORE_USER)
-   ralign = BYTES_PER_WORD;
-
if (flags & SLAB_RED_ZONE) {
ralign = REDZONE_ALIGN;
/* If redzoning, ensure that the second redzone is suitably
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/