> And mm/slab.c changes semantics when CONFIG_SLAB_DEBUG
> is set: it ignores SLAB_HWCACHE_ALIGN. That seems more like
> the root cause of the problem to me!
>
HWCACHE_ALIGN does not guarantee a certain byte alignment. And
additionally it's not even guaranteed that kmalloc() uses that
HWCACHE_ALIGN.
Uhci is broken, not my slab code ;-)
> I think that the pci_alloc_consistent patch that Johannes sent
>by for "uhci.c" would be a better approach. Though I'd like
>to see that be more general ... say, making mm/slab.c know
>about such things. Add a simple abstraction, and that should
>be it -- right? :-)
I looked at it, and there are 2 problems that make it virtually
impossible to integrate kmem_cache_alloc() with pci memory alloc without
a major redesign:
* pci_alloc_consistent returns 2 values, kmem_cache_alloc() only one.
This one would be possible to work around.
* the slab allocator heavily relies on the 'struct page' structure, but
it's not guaranteed that it exists for pci_alloced memory.
I'd switch to pci_alloc_consistent with some optimizations to avoid
wasting a complete page for each DMA header. (I haven't seen Johannes
patch, but we discussed the problem 6 weeks ago and that proposal was
the end of the thread)
--Manfred
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Wed Mar 07 2001 - 21:00:18 EST