Re: [PATCH] remove fullflush and nofullflush in IOMMU genericoption

[Ingo Molnar]

* Joerg Roedel <joerg.roedel@xxxxxxx> wrote:

> On Tue, Sep 23, 2008 at 01:51:05AM +0900, FUJITA Tomonori wrote:
> > The patch that I sent doesn't make any changes for you. GART works as
> > before and AMD IOMMU takes a new parameter, fullflush, as you want. It
> > does the exact same thing that the first version of your patchset for
> > 2.6.28.
> > 
> > So please let me apply it then we can stop this discussion.
> 
> Ok, so it was not nice from me to let Ingo pull this patch without 
> your ack, I already admitted. To end this discussion and get to 
> productive discussions, Ingo, please apply this patch. I hope we will 
> work together on a final solution for the problem.

applied Fujita's patch below to tip/x86/iommu that reverts those 
options, thanks guys!

i'm wondering how we should proceed. For debug, iommu=off is certainly 
good enough - all kernels are supposed to work out of box on all hw, and 
every other result is a regression that must be fixed.

For performance tuning, it probably makes sense for developers to tune 
IOMMU details (so that the bootup defaults can be improved - this is not 
really something that should be done on a workload basis), but for that 
IMO a /debug interface is a lot more useful than rather intrusive (and 
inflexible) boot options.

What do you think about a debugfs based tuning of various IOMMU details? 
Maybe even the active driver could be changed - say from AMD-IOMMU to 
GART, or to off.

Flipping IOMMU state on a running system means a whole lot of new 
complexities, but it might be rather useful. It's useful for testing as 
well, obviously.

	Ingo

------------------->