Re: [PATCH v2 4/4] ppc/spapr: Don't kill the guest if a recovered FWNMI machine check delivery fails

[David Gibson]

On Thu, Mar 26, 2020 at 12:29:06AM +1000, Nicholas Piggin wrote:
> Try to be tolerant of FWNMI delivery errors if the machine check had been
> recovered by the host.
> 
> Signed-off-by: Nicholas Piggin <address@hidden>

Applied to ppc-for-5.0.

> ---
>  hw/ppc/spapr_events.c | 27 ++++++++++++++++++++++-----
>  1 file changed, 22 insertions(+), 5 deletions(-)
> 
> diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
> index c8964eb25d..b90ecb8afe 100644
> --- a/hw/ppc/spapr_events.c
> +++ b/hw/ppc/spapr_events.c
> @@ -833,13 +833,25 @@ static void spapr_mce_dispatch_elog(PowerPCCPU *cpu, 
> bool recovered)
>      /* get rtas addr from fdt */
>      rtas_addr = spapr_get_rtas_addr();
>      if (!rtas_addr) {
> -        error_report(
> +        if (!recovered) {
> +            error_report(
>  "FWNMI: Unable to deliver machine check to guest: rtas_addr not found.");
> -        qemu_system_guest_panicked(NULL);
> +            qemu_system_guest_panicked(NULL);
> +        } else {
> +            warn_report(
> +"FWNMI: Unable to deliver machine check to guest: rtas_addr not found. "
> +"Machine check recovered.");
> +        }
>          g_free(ext_elog);
>          return;
>      }
>  
> +    /*
> +     * Must not set interlock if the MCE does not get delivered to the guest
> +     * in the error case above.
> +     */
> +    spapr->fwnmi_machine_check_interlock = cpu->vcpu_id;
> +
>      stq_be_phys(&address_space_memory, rtas_addr + RTAS_ERROR_LOG_OFFSET,
>                  env->gpr[3]);
>      cpu_physical_memory_write(rtas_addr + RTAS_ERROR_LOG_OFFSET +
> @@ -876,9 +888,15 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)
>           * that CPU called "ibm,nmi-interlock")
>           */
>          if (spapr->fwnmi_machine_check_interlock == cpu->vcpu_id) {
> -            error_report(
> +            if (!recovered) {
> +                error_report(
>  "FWNMI: Unable to deliver machine check to guest: nested machine check.");
> -            qemu_system_guest_panicked(NULL);
> +                qemu_system_guest_panicked(NULL);
> +            } else {
> +                warn_report(
> +"FWNMI: Unable to deliver machine check to guest: nested machine check. "
> +"Machine check recovered.");
> +            }
>              return;
>          }
>          qemu_cond_wait_iothread(&spapr->fwnmi_machine_check_interlock_cond);
> @@ -906,7 +924,6 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)
>          warn_report("Received a fwnmi while migration was in progress");
>      }
>  
> -    spapr->fwnmi_machine_check_interlock = cpu->vcpu_id;
>      spapr_mce_dispatch_elog(cpu, recovered);
>  }
>  

-- 
David Gibson                    | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au  | minimalist, thank you.  NOT _the_ _other_
                                | _way_ _around_!
http://www.ozlabs.org/~dgibson

signature.asc
Description: PGP signature