[PATCH] arm64/fpsimd: Exit streaming mode when flushing tasks

[Anders Roxell]

On Wed, 7 Jun 2023 at 22:42, Mark Brown <broonie at kernel.org> wrote:
>
> Ensure there is no path where we might attempt to save SME state after we
> flush a task by updating the SVCR register state as well as updating our
> in memory state. I haven't seen a specific case where this is happening or
> seen a path where it might happen but for the cost of a single low overhead
> instruction it seems sensible to close the potential gap.
>
> Signed-off-by: Mark Brown <broonie at kernel.org>

Applied this onto todays next tag next-20230608 and ran
kselftest-arm64 on a FVP model.
I still see the "BUG: KFENCE: memory corruption in
fpsimd_release_task+0x1c/0x3c".

I'm trying to use the latest kselftest from today with older next tags
trying to find when
this issue started to happen.

Cheers,
Anders


> ---
>  arch/arm64/kernel/fpsimd.c | 1 +
>  1 file changed, 1 insertion(+)
>
> diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
> index 2fbafa5cc7ac..1627e0efe39a 100644
> --- a/arch/arm64/kernel/fpsimd.c
> +++ b/arch/arm64/kernel/fpsimd.c
> @@ -1649,6 +1649,7 @@ void fpsimd_flush_thread(void)
>
>                 fpsimd_flush_thread_vl(ARM64_VEC_SME);
>                 current->thread.svcr = 0;
> +               sme_smstop_sm();
>         }
>
>         current->thread.fp_type = FP_STATE_FPSIMD;
>
> ---
> base-commit: 44c026a73be8038f03dbdeef028b642880cf1511
> change-id: 20230607-arm64-flush-svcr-47cc76a8cbbc
>
> Best regards,
> --
> Mark Brown <broonie at kernel.org>
>