Re: Oops in a driver while using SLUB as a SLAB allocator

[Christoph Lameter]

On Fri, 22 Jun 2007, Linus Torvalds wrote:

> > Looks like it would indeed address the immediate issue on ARM -
> > IF they've no particular reason to be using kmalloc there.
> 
> I think the right thing to do is do both of these things. I already 
> applied Hugh's patch - it seemed like a total nobrainer to do at this 
> stage in the 2.6.22 -rc series. But that doesn't mean that we should not 
> _also_ look at "flush_dcache_page()" users.

Hugh's patch not address the complete issue. It only works right now 
because the size of the allocation is page size and fits right into a slab 
page. If debugging is enabled then the slab size will increase and the 
"pages" will be misaligned which will lead to other sorts of funky 
behavior. kmalloc allocations are only guaranteed to be aligned to 
ARCH_KMALLOC_MINALIGN which is 4 to 8 bytes. If one must have a 
page aligned entity out of a slab allocator then a custom slab needs to be 
created.
-
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/