Re: [PATCH] mtd: fix mtd_blkdevs problem with caches on some architectures (2.6.31)

[Ilya Loginov <isloginov@gmail.com>]

On Fri, 20 Nov 2009 16:37:51 -0800
Andrew Morton <akpm@linux-foundation.org> wrote:

> Your patch fixes bascially the same problem in MTD as we have in AOE. 
> And it introduces the same problem as well - pointless empty
> cache-thrashing loops on architectures for which flush_dcache_page() is
> a no-op.
> 
> What would be better here would be for block core to add a new
> rq_flush_dcache_pages() and bio_flush_dcache_pages() which the drivers
> can call.  Those functions would be a no-op on architectures which
> don't need them.

Do you mean something like this?

in include/linux/bio.h

#ifdef SOMETHING_LIKE_CONFIG_CPU_HAS_DCACHE_ALIAS
extern void bio_flush_dcache_pages(struct bio *bi);
#else
static inline void bio_flush_dcache_pages(struct bio *bi)
{
}
#endif /* SOMETHING_LIKE_CONFIG_CPU_HAS_DCACHE_ALIAS */

in fs/bio.c

void bio_flush_dcache_pages(struct bio *bi)
{
	int i;
	struct bio_vec* bvec;

	rq_for_each_segment(bvec, bio, i)
		flush_dcache_page(bvec->bv_page);
}

in include/linux/blkdev.h

#ifdef SOMETHING_LIKE_CONFIG_CPU_HAS_DCACHE_ALIAS
extern void rq_flush_dcache_pages(struct request *rq);
#else
static inline void rq_flush_dcache_pages(struct request *rq)
{
}
#endif

in block/blk-core.c

void rq_flush_dcache_pages(struct request *rq)
{
	struct req_iterator iter;
	struct bio_vec* bvec;

	rq_for_each_segment(bvec, bio, iter)
		flush_dcache_page(bvec->bv_page);
}

And SOMETHING_LIKE_CONFIG_CPU_HAS_DCACHE_ALIAS should be defined
in Kconfigs for each architecture that requires this fix. I think 
this is good solution and if you think the same I can create the
patch.

-- 
Ilya Loginov <isloginov@gmail.com>