Re: r4k_dma_cache_inv_pc() does writeback

[Ralf Baechle <ralf@oss.sgi.com>]

On Mon, Oct 30, 2000 at 10:45:05AM -0800, Jun Sun wrote:

> It just occur to me that r4k_dma_cache_inv_pc() actually does a
> writeback before it invalidates the cache.  Is there story behind it? 
> Or just a plain bug?

No big story, I was simply to lazy to implement yet another function.
You could probably get some performance gains.

> If it is a bug, I don't find an easy way to invalidate the whole dcache
> other than writing a new function, perhaps in r4kcache.h.

  Ralf