Re: [PATCH for-4.12] arm/p2m: do not invalidate p2m root if it is shared with IOMMU

[Julien Grall <julien.grall@arm.com>]

Hi Andrii,

On 29/01/2019 16:00, Andrii Anisov wrote:
> 
> On 29.01.19 17:17, Julien Grall wrote:
>> They have been lucky to see this working even on baremetal.
>> Set/Way operations have been dropped from Linux for a long time, so I really 
>> can't see why a proprietary driver is still using them.
> I guess there were some performance concerns. And they are really lucky, so they 
> did not face related issues on baremetal.

I am not entirely convinced this is related to performance. You have to flush 
all the cache level one by one and may miss some caches (i.e system caches).

I suspect this is a relic from early version of Linux and no-one have seen the 
issue and/or "difficult" to fix. Set/Way is quite convenient to use over going 
over virtual address.

> 
>> I think the policy for Set/Way operations is correct in Xen. This works to 
>> avoid breaking basic case but the most complex one are going to break.
> Maybe it worth to get a notification from XEN, i.e. WARN_ONCE, saying that 
> Set/Way cache operations are undesirable in VM and will lead to the system 
> performance drop, or even instability in case of IOMMU sharing p2m with CPU.
> This might save days of debugging to XEN on ARM users.

I would be happy with a printk warning the user.

> 
>> You solution is only delaying the real fix
> I would not say it is delaying the fix, but allows us to have a functional 
> system until we get that fix.

By experience, if you workaround something in the code then you have less 
incentive to fix the real issue. So I am not willing to merge any patch that 
could delay a vendor to fix their software.

Cheers,

-- 
Julien Grall

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel