On 31/10/2019 11:26, Will Deacon wrote:

[+John Garry]

Hi Mark,

On Thu, Oct 24, 2019 at 10:42:03PM +0100, Mark Brown wrote:

quoted

This series adds support for E0PD. We enable E0PD unconditionally where
present on systems where all the CPUs in the system support E0PD and
change to not enabling KPTI by default on systems where we have enabled
E0PD. It also converts the runtime checks for use of non-global mappings
into a variable.

Although I welcome the simplification introduced by this patch set, I'm
worried that we might be removing a significant optimisation to KASLR
boot-time on machines with large memory. John reported issues with this
in the past, so I'm looping him in in case he has a chance to test this
(branch here [1]). Of course, I could just be missing something since
this code was really subtle to begin with.

I booted our D05 and D06 boards with that branch and did not experience 
the pauses which we reported some time ago.

John

On KASLR systems other than TX1, we should use nG mappings by default so
that we can avoid the time-consuming task of rewriting swapper during boot.
However, with your patches, I think we defer the decision to use nG mappings
to the cpufeature code which means we always end up rewriting swapper in
this scenario because of the global mappings installed early on.

Have I got that right?

Cheers,

Will

[1] https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git/log/?h=for-next/e0pd
.

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel