Re: [PATCH] arm64: Avoid eager DVMSync reclaim batches with C1-Pro SME erratum

[Will Deacon <will@kernel.org>]

On Mon, Jun 22, 2026 at 12:52:27PM +0000, Joshua Liu wrote:
> On Wed, Jun 10, 2026 at 11:37 AM Catalin Marinas <catalin.marinas@arm.com> wrote:
> > Introduce the sme_active_cpus mask tracking which CPUs run in user-space
> > with SME enabled and use it for batch flushing instead of accumulating
> > the mm_cpumask() of the unmapped pages.
> > [...]
> > The dsb() in arch_tlbbatch_add_pending() -> sme_dvmsync_add_pending()
> > did introduce a performance regression for kswapd. This patch restores
> > the original behaviour with the barrier only issued when the TLB batch
> > is flushed. The trade-off is that the IPIs are now sent to all CPUs
> > running with SME enabled at EL0 even if the reclaimed pages do not
> > belong to SME tasks. This is acceptable for current SME deployments.
> 
> Profiling shows this solution has robust performance for common
> workloads and is the best among a few approaches we tested with Catalin,
> so we are happy to go with this solution.
> 
> Some sidenotes: for certain edge cases we still observe performance
> regression, specifically when a workload pegs multiple cores with SME
> status threads.
>
> Tested-by: Joshua Liu <josliu@google.com>

Thanks, Joshua, I'll pick this up at -rc1.

Will