qemu-ppc
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Qemu-ppc] [PATCH v9 6/6] migration: Include migration support for m


From: Aravinda Prasad
Subject: Re: [Qemu-ppc] [PATCH v9 6/6] migration: Include migration support for machine check handling
Date: Thu, 6 Jun 2019 16:55:18 +0530
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.6.0


On Thursday 06 June 2019 08:36 AM, David Gibson wrote:
> On Wed, May 29, 2019 at 11:10:57AM +0530, Aravinda Prasad wrote:
>> This patch includes migration support for machine check
>> handling. Especially this patch blocks VM migration
>> requests until the machine check error handling is
>> complete as (i) these errors are specific to the source
>> hardware and is irrelevant on the target hardware,
>> (ii) these errors cause data corruption and should
>> be handled before migration.
>>
>> Signed-off-by: Aravinda Prasad <address@hidden>
>> ---
>>  hw/ppc/spapr.c         |   20 ++++++++++++++++++++
>>  hw/ppc/spapr_events.c  |   17 +++++++++++++++++
>>  hw/ppc/spapr_rtas.c    |    4 ++++
>>  include/hw/ppc/spapr.h |    2 ++
>>  4 files changed, 43 insertions(+)
>>
>> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
>> index e8a77636..31c4850 100644
>> --- a/hw/ppc/spapr.c
>> +++ b/hw/ppc/spapr.c
>> @@ -2104,6 +2104,25 @@ static const VMStateDescription vmstate_spapr_dtb = {
>>      },
>>  };
>>  
>> +static bool spapr_fwnmi_needed(void *opaque)
>> +{
>> +    SpaprMachineState *spapr = (SpaprMachineState *)opaque;
>> +
>> +    return (spapr->guest_machine_check_addr == -1) ? 0 : 1;
> 
> Since we're introducing a PAPR capability to enable this, it would
> actually be better to check that here, rather than the runtime state.
> That leads to less cases and easier to understand semantics for the
> migration stream.

I am fine with this approach as well.

> 
>> +}
>> +
>> +static const VMStateDescription vmstate_spapr_machine_check = {
>> +    .name = "spapr_machine_check",
>> +    .version_id = 1,
>> +    .minimum_version_id = 1,
>> +    .needed = spapr_fwnmi_needed,
>> +    .fields = (VMStateField[]) {
>> +        VMSTATE_UINT64(guest_machine_check_addr, SpaprMachineState),
>> +        VMSTATE_INT32(mc_status, SpaprMachineState),
>> +        VMSTATE_END_OF_LIST()
>> +    },
>> +};
>> +
>>  static const VMStateDescription vmstate_spapr = {
>>      .name = "spapr",
>>      .version_id = 3,
>> @@ -2137,6 +2156,7 @@ static const VMStateDescription vmstate_spapr = {
>>          &vmstate_spapr_dtb,
>>          &vmstate_spapr_cap_large_decr,
>>          &vmstate_spapr_cap_ccf_assist,
>> +        &vmstate_spapr_machine_check,
>>          NULL
>>      }
>>  };
>> diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
>> index 573c0b7..35e21e4 100644
>> --- a/hw/ppc/spapr_events.c
>> +++ b/hw/ppc/spapr_events.c
>> @@ -41,6 +41,7 @@
>>  #include "qemu/bcd.h"
>>  #include "hw/ppc/spapr_ovec.h"
>>  #include <libfdt.h>
>> +#include "migration/blocker.h"
>>  
>>  #define RTAS_LOG_VERSION_MASK                   0xff000000
>>  #define   RTAS_LOG_VERSION_6                    0x06000000
>> @@ -855,6 +856,22 @@ static void spapr_mce_dispatch_elog(PowerPCCPU *cpu, 
>> bool recovered)
>>  void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)
>>  {
>>      SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
>> +    int ret;
>> +    Error *local_err = NULL;
>> +
>> +    error_setg(&spapr->fwnmi_migration_blocker,
>> +            "Live migration not supported during machine check handling");
>> +    ret = migrate_add_blocker(spapr->fwnmi_migration_blocker, &local_err);
>> +    if (ret < 0) {
>> +        /*
>> +         * We don't want to abort and let the migration to continue. In a
>> +         * rare case, the machine check handler will run on the target
>> +         * hardware. Though this is not preferable, it is better than 
>> aborting
>> +         * the migration or killing the VM.
>> +         */
>> +        error_free(spapr->fwnmi_migration_blocker);
> 
> You should set fwnmi_migration_blocker to NULL here as well.

ok.

> 
> As mentioned on an earlier iteration, the migration blocker is the
> same every time.  Couldn't you just create it once and free at final
> teardown, rather than recreating it for every NMI?

That means, we create the error string at the time when ibm,nmi-register
is invoked and tear it down during machine reset?

Regards,
Aravinda

> 
>> +        warn_report_err(local_err);
>> +    }
>>  
>>      while (spapr->mc_status != -1) {
>>          /*
>> diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c
>> index 91a7ab9..c849223 100644
>> --- a/hw/ppc/spapr_rtas.c
>> +++ b/hw/ppc/spapr_rtas.c
>> @@ -50,6 +50,7 @@
>>  #include "target/ppc/mmu-hash64.h"
>>  #include "target/ppc/mmu-book3s-v3.h"
>>  #include "kvm_ppc.h"
>> +#include "migration/blocker.h"
>>  
>>  static void rtas_display_character(PowerPCCPU *cpu, SpaprMachineState 
>> *spapr,
>>                                     uint32_t token, uint32_t nargs,
>> @@ -404,6 +405,9 @@ static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu,
>>          spapr->mc_status = -1;
>>          qemu_cond_signal(&spapr->mc_delivery_cond);
>>          rtas_st(rets, 0, RTAS_OUT_SUCCESS);
>> +        migrate_del_blocker(spapr->fwnmi_migration_blocker);
>> +        error_free(spapr->fwnmi_migration_blocker);
>> +        spapr->fwnmi_migration_blocker = NULL;
>>      }
>>  }
>>  
>> diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
>> index bd75d4b..6c0cfd8 100644
>> --- a/include/hw/ppc/spapr.h
>> +++ b/include/hw/ppc/spapr.h
>> @@ -214,6 +214,8 @@ struct SpaprMachineState {
>>      SpaprCapabilities def, eff, mig;
>>  
>>      unsigned gpu_numa_id;
>> +
>> +    Error *fwnmi_migration_blocker;
>>  };
>>  
>>  #define H_SUCCESS         0
>>
> 

-- 
Regards,
Aravinda




reply via email to

[Prev in Thread] Current Thread [Next in Thread]