Re: [PATCH v8 0/2] arm64/sve: Performance improvements with SVE state saving

[Mark Brown <broonie@kernel.org>]

[-- Attachment #1: Type: text/plain, Size: 1464 bytes --]

On Tue, May 12, 2026 at 03:10:36PM +0100, Will Deacon wrote:
> On Fri, Mar 20, 2026 at 03:44:13PM +0000, Mark Brown wrote:

> > The two patches here move to using a time based heuristic to decide when
> > to reenable the SVE access trap, doing so after a second.  This means
> > that tasks actively using SVE which block in syscalls should see reduced
> > or similar numbers of access traps, while CPU bound tasks that rarely
> > use SVE will see the SVE syscall overhead removed after running for
> > approximately a second, confirmed via fp-pidbench.

> Have you looked at all at applying this heuristic to SME? I wonder if it
> would help with the recent DVMSync erratum workaround, where tasks that
> use SME once/infrequently end up causing IPIs for TLB invalidation every
> time they run on an effected core.

I have not done so myself, though I did discuss this with Catalin while
he was working on those workarounds.  IIRC he wanted to get a better
picture of the system level costs with actual usage before deciding if
it was a good tradeoff, either to do this at all or to see if we can
skip the timeout based approach or could just reenable SME traps
whenever we see SME is not in use.

With SME it's easier because you can directly tell if the task currently
has SME enabled so I'd expect the checks on state load are enough and we
don't need to put anything into the syscall path, it's likely that the
tradeoffs for doing that don't work out so well.

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]